Copy from v0.0.1 to v0.0.2

charts/rancher-monitoring/v0.0.2/.helmignore

+# Patterns to ignore when building packages.
+# This supports shell glob matching, relative path matching, and
+# negation (prefixed with !). Only one pattern per line.
+.DS_Store
+# Common VCS dirs
+.git/
+.gitignore
+.bzr/
+.bzrignore
+.hg/
+.hgignore
+.svn/
+# Common backup files
+*.swp
+*.bak
+*.tmp
+*~
+# Various IDEs
+.project
+.idea/
+*.tmproj

charts/rancher-monitoring/v0.0.2/Chart.yaml

+apiVersion: v1
+description: Provides monitoring for Kubernetes which maintaining by Rancher 2.
+engine: gotpl
+maintainers:
+- name: thxCode
+  email: frank@rancher.com
+name: rancher-monitoring
+sources:
+- https://github.com/coreos/prometheus-operator
+version: 0.0.1
+appVersion: "0.23.2"
+home: https://github.com/coreos/prometheus-operator
+keywords:
+- operator
+- prometheus
+icon: https://coreos.com/sites/default/files/inline-images/Overview-prometheus_0.png

charts/rancher-monitoring/v0.0.2/README.md

+# rancher-monitoring
+
+Installs [prometheus-operator](https://github.com/coreos/prometheus-operator) to create/configure/manage Prometheus clusters atop Kubernetes.
+
+> **Tip**: Only use for Rancher Monitoring!!!
+
+## Introduction
+
+This chart bootstraps a [prometheus-operator](https://github.com/coreos/prometheus-operator) deployment on a [Kubernetes](http://kubernetes.io) cluster using the [Helm](https://helm.sh) package manager.
+
+### Security
+
+Alertmanager, Node exporter, Kube-state exporter, Grafana and Prometheus in same [Namespace](https://kubernetes.io/docs/concepts/overview/working-with-objects/namespaces/) will use the same [ServiceAccount](https://kubernetes.io/docs/reference/access-authn-authz/service-accounts-admin/) as Prometheus, which named like `prometheus-{{ .Release.Name }}`. Operator uses another one.
+
+## Prerequisites
+  - Rancher 2.1+

charts/rancher-monitoring/v0.0.2/charts/alertmanager/Chart.yaml

+apiVersion: v1
+description: Creates Alertmanager CRD instance for Kubernetes which maintaining by Rancher 2.
+engine: gotpl
+maintainers:
+- name: thxCode
+  email: frank@rancher.com
+name: alertmanager
+version: 0.0.1

charts/rancher-monitoring/v0.0.2/charts/alertmanager/templates/alertmanager.yaml

+apiVersion: {{ template "operator_api_version" . }}
+kind: Alertmanager
+metadata:
+  labels:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+{{- if .Values.labels }}
+{{ toYaml .Values.labels | indent 4 }}
+{{- end }}
+  name: {{ .Release.Name }}
+spec:
+  podMetadata:
+    labels:
+{{- if .Values.labels }}
+{{ toYaml .Values.labels | indent 6 }}
+{{- else }}
+      app: {{ template "app.name" . }}
+      chart: {{ template "app.version" . }}
+      release: {{ .Release.Name }}
+{{- end }}
+  baseImage: "{{ .Values.image.repository }}"
+{{- if .Values.externalUrl }}
+  externalUrl: "{{ .Values.externalUrl }}"
+{{- end }}
+{{- if .Values.nodeSelector }}
+  nodeSelector:
+{{ toYaml .Values.nodeSelector | indent 4 }}
+{{- end }}
+  paused: {{ .Values.paused }}
+  replicas: {{ .Values.replicaCount }}
+  logLevel:  {{ .Values.logLevel }}
+  resources:
+{{ toYaml .Values.resources | indent 4 }}
+  retention: "{{ .Values.retention }}"
+{{- if .Values.routePrefix }}
+  routePrefix: "{{ .Values.routePrefix }}"
+{{- end }}
+{{- if .Values.secrets }}
+  secrets:
+{{ toYaml .Values.secrets | indent 4 }}
+{{- end }}
+{{- if .Values.enabledRBAC }}
+  serviceAccountName: {{ .Values.serviceAccountName }}
+{{- end }}
+{{- if or .Values.storageSpec .Values.persistence.enabled }}
+  storage:
+    volumeClaimTemplate:
+      spec:
+{{- if .Values.storageSpec }}
+{{ toYaml .Values.storageSpec | indent 8 }}
+{{- else }}
+        {{ if and .Values.persistence.storageClass (ne "default" .Values.persistence.storageClass) }}
+        storageClassName: {{ .Values.persistence.storageClass }}
+        {{ end }}
+        accessModes: 
+          - {{ default "ReadWriteOnce" .Values.persistence.accessMode }}
+        resources:
+          requests:
+            storage: {{ .Values.persistence.size | quote }}
+{{- end }}
+{{- end }}
+  version: "{{ .Values.image.tag }}"
+  affinity:
+    podAntiAffinity:
+      preferredDuringSchedulingIgnoredDuringExecution:
+      - weight: 100
+        podAffinityTerm:
+          topologyKey: kubernetes.io/hostname
+          labelSelector:
+            matchLabels:
+              app: {{ template "app.name" . }}
+              alertmanager: {{ .Release.Name }}
+{{- if .Values.tolerations }}
+  tolerations:
+{{ toYaml .Values.tolerations | indent 4 }}
+{{- end }}
+  imagePullSecrets:
+{{ toYaml .Values.image.pullSecrets | indent 4 }}
+{{- if .Values.sidecarsSpec }}
+  containers:
+{{ toYaml .Values.sidecarsSpec | indent 4 }}
+{{- end }}

charts/rancher-monitoring/v0.0.2/charts/alertmanager/templates/metrics-service.yaml

+apiVersion: v1
+kind: Service
+metadata:
+  name: expose-alertmanager-metrics
+  labels:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+    monitoring.cattle.io: "true"
+spec:
+  type: ClusterIP
+  selector:
+{{- if .Values.labels }}
+{{ toYaml .Values.labels | indent 4 }}
+{{- else }}
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    release: {{ .Release.Name }}
+{{- end }}
+  ports:
+    - name: http
+      port: 9093
+      targetPort: web
\ No newline at end of file

charts/rancher-monitoring/v0.0.2/charts/alertmanager/templates/nginx-configmap.yaml

+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: {{ template "app.nginx.fullname" . }}
+  labels:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+    component: nginx
+data:
+  nginx.conf: |-
+    user  nginx;
+    worker_processes  auto;
+    error_log  /dev/null warn;
+    pid        /var/run/nginx.pid;
+    
+    events {
+       worker_connections  1024;
+    }
+
+    http {
+      include /etc/nginx/mime.types;
+
+      log_format  main  '[$time_local - $status] $remote_addr - $remote_user $request ($http_referer)';
+
+      server {
+        listen 80;
+
+        access_log off;
+
+        gzip on;
+        gzip_min_length 1k;
+        gzip_comp_level 2;
+        gzip_types text/plain application/javascript application/x-javascript text/css application/xml text/javascript image/jpeg image/gif image/png;
+        gzip_vary on;
+        gzip_disable "MSIE [1-6]\.";
+
+        proxy_set_header Host $host;
+        proxy_set_header X-Real-IP $remote_addr;
+        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
+        proxy_set_header X-Forwarded-Proto $scheme;
+
+        location / {
+          proxy_pass     http://alertmanager-operated:9093/;
+        }
+
+      }
+
+    }
\ No newline at end of file

charts/rancher-monitoring/v0.0.2/charts/alertmanager/templates/nginx-deployment.yaml

+apiVersion: {{ template "deployment_api_version" . }}
+kind: Deployment
+metadata:
+  name: {{ template "app.nginx.fullname" . }}
+  labels:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+    component: nginx
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: {{ template "app.name" . }}
+      chart: {{ template "app.version" . }}
+      release: {{ .Release.Name }}
+      component: nginx
+  template:
+    metadata:
+      labels:
+        app: {{ template "app.name" . }}
+        chart: {{ template "app.version" . }}
+        release: {{ .Release.Name }}
+        component: nginx
+    spec:
+      containers:
+      - name: nginx
+        image: nginx:1.15.2
+        args:
+        - nginx
+        - -g
+        - daemon off;
+        - -c
+        - /nginx/nginx.conf
+        volumeMounts:
+        - mountPath: /nginx/
+          name: alertmanager-nginx
+        ports:
+        - name: http
+          containerPort: 80
+          protocol: TCP
+      volumes:
+      - name: alertmanager-nginx
+        configMap:
+          defaultMode: 438
+          items:
+          - key: nginx.conf
+            mode: 438
+            path: nginx.conf
+          name: {{ template "app.nginx.fullname" . }}
\ No newline at end of file

charts/rancher-monitoring/v0.0.2/charts/alertmanager/templates/secret.yaml

+{{- if not .Values.configFromSecret }}
+apiVersion: v1
+kind: Secret
+metadata:
+  labels:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+  name: {{ template "app.fullname" . }}
+data:
+  alertmanager.yaml: {{ toYaml .Values.config | b64enc | quote }}
+{{- range $key, $val := .Values.templates }}
+  {{ $key }}: {{ $val | b64enc | quote }}
+{{- end }}
+{{- end }}

charts/rancher-monitoring/v0.0.2/charts/alertmanager/templates/service.yaml

+apiVersion: v1
+kind: Service
+metadata:
+  name: access-alertmanager
+  labels:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+    kubernetes.io/cluster-service: "true"
+spec:
+  type: ClusterIP
+  selector:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    release: {{ .Release.Name }}
+    component: nginx
+  ports:
+    - name: http
+      port: 80
+      targetPort: http

charts/rancher-monitoring/v0.0.2/charts/alertmanager/templates/servicemonitor.yaml

+apiVersion: {{ template "operator_api_version" . }}
+kind: ServiceMonitor
+metadata:
+  labels:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+    source: rancher-monitoring
+    {{- if .Values.serviceMonitor.labels }}
+{{ toYaml .Values.serviceMonitor.labels | indent 4 }}
+    {{- end }}
+  name: {{ template "app.fullname" . }}
+spec:
+  jobLabel: altermanager
+  selector:
+    matchLabels:
+      app: {{ template "app.name" . }}
+      chart: {{ template "app.version" . }}
+      release: {{ .Release.Name }}
+      monitoring.cattle.io: "true"
+  namespaceSelector:
+    matchNames:
+      - {{ .Release.Namespace | quote }}
+  endpoints:
+  - port: http
+    interval: 30s

charts/rancher-monitoring/v0.0.2/charts/alertmanager/values.yaml

+enabledRBAC: true
+
+## Already exist ServiceAccount
+##
+serviceAccountName: ""
+
+## CRD apiGroup
+##
+apiGroup: "monitoring.coreos.com"
+
+## The name of a secret in the same kubernetes namespace which contains the Alertmanager config
+## If defined this will be used instead of the `config` block values.
+## The name of the secret must be alertmanager-{{ .Release.Name }} and its data must contain, at least, a key called `alertmanager.yaml`
+## that contains the configuration as value.
+##
+configFromSecret: ""
+
+## Alertmanager configuration directives
+## Ref: https://prometheus.io/docs/alerting/configuration/
+##
+config: {}
+#
+# An example config:
+#   global:
+#     resolve_timeout: 5m
+#   route:
+#     group_by: ['job']
+#     group_wait: 30s
+#     group_interval: 5m
+#     repeat_interval: 12h
+#     receiver: 'null'
+#     routes:
+#     - match:
+#         alertname: DeadMansSwitch
+#       receiver: 'null'
+#   receivers:
+#   - name: 'null'
+
+## Alertmanager template files to include
+#
+templates: {}
+#
+# An example template:
+#   template_1.tmpl: |-
+#       {{ define "cluster" }}{{ .ExternalURL | reReplaceAll ".*alertmanager\\.(.*)" "$1" }}{{ end }}
+#
+#       {{ define "slack.myorg.text" }}
+#       {{- $root := . -}}
+#       {{ range .Alerts }}
+#         *Alert:* {{ .Annotations.summary }} - `{{ .Labels.severity }}`
+#         *Cluster:*  {{ template "cluster" $root }}
+#         *Description:* {{ .Annotations.description }}
+#         *Graph:* <{{ .GeneratorURL }}|:chart_with_upwards_trend:>
+#         *Runbook:* <{{ .Annotations.runbook }}|:spiral_note_pad:>
+#         *Details:*
+#           {{ range .Labels.SortedPairs }} • *{{ .Name }}:* `{{ .Value }}`
+#           {{ end }}
+
+## External URL at which Alertmanager will be reachable
+##
+externalUrl: ""
+
+serviceMonitor:
+  ## Custom Labels to be added to ServiceMonitor
+  ##
+  labels: {}
+
+## Alertmanager container image
+##
+image:
+  repository: quay.io/prometheus/alertmanager
+  tag: v0.15.2
+
+## Labels to be added to the Alertmanager
+##
+# labels: {}
+
+## Node labels for Alertmanager pod assignment
+## Ref: https://kubernetes.io/docs/user-guide/node-selection/
+##
+nodeSelector: {}
+
+## Tolerations for use with node taints
+## Ref: https://kubernetes.io/docs/concepts/configuration/taint-and-toleration/
+##
+tolerations: {}
+  #  - key: "key"
+  #    operator: "Equal"
+  #    value: "value"
+  #    effect: "NoSchedule"
+
+## If true, the Operator won't process any Alertmanager configuration changes
+##
+paused: false
+
+## Number of Alertmanager replicas desired
+##
+replicaCount: 1
+
+## Resource limits & requests
+## Ref: https://kubernetes.io/docs/user-guide/compute-resources/
+##
+resources: {}
+  # requests:
+  #   memory: 400Mi
+
+## How long to retain metrics
+##
+retention: 24h
+
+## Prefix used to register routes, overriding externalUrl route.
+## Useful for proxies that rewrite URLs.
+##
+routePrefix: ""
+
+## List of Secrets in the same namespace as the Alertmanager
+## object, which shall be mounted into the Alertmanager Pods.
+## Ref: https://github.com/coreos/prometheus-operator/blob/master/Documentation/api.md#prometheusspec
+##
+secrets: []
+
+service:
+  ## Maintains session affinity.  Should be set to ClientIP for HA setup
+  ## Only options are ClientIP and None.  Do not leave blank.
+  sessionAffinity: None
+
+  ## Annotations to be added to the Service
+  ##
+  annotations: {}
+
+  ## Cluster-internal IP address for Alertmanager Service
+  ##
+  clusterIP: ""
+
+  ## List of external IP addresses at which the Alertmanager Service will be available
+  ##
+  externalIPs: []
+
+  ## Labels to be added to the Service
+  ##
+  labels: {}
+
+  ## External IP address to assign to Alertmanager Service
+  ## Only used if service.type is 'LoadBalancer' and supported by cloud provider
+  ##
+  loadBalancerIP: ""
+
+  ## List of client IPs allowed to access Alertmanager Service
+  ## Only used if service.type is 'LoadBalancer' and supported by cloud provider
+  ##
+  loadBalancerSourceRanges: []
+
+  ## Port to expose on each node
+  ## Only used if service.type is 'NodePort'
+  ##
+  # nodePort: 30903
+
+  ## Service type
+  ##
+  type: ClusterIP
+
+logLevel: "info"
+
+## Alertmanager StorageSpec for persistent data
+## Ref: https://github.com/coreos/prometheus-operator/blob/master/Documentation/user-guides/storage.md
+##
+storageSpec: {}
+#  storageClassName: gluster
+#  accessModes: ["ReadWriteOnce"]
+#  resources:
+#    requests:
+#       storage: 50Gi
+#  selector: {}
+
+## Easy way to create persistent data
+##
+persistence: {}
+#  enabled: true
+#  storageClass: gluster
+#  accessMode: "ReadWriteOnce"
+#  size: 50Gi
+
+sidecarsSpec: []
+# - name: sidecar
+#   image: registry/name:tag

charts/rancher-monitoring/v0.0.2/charts/exporter-coredns/Chart.yaml

+apiVersion: v1
+description: Creates ServiceMonitor CRD of coredns for Kubernetes which maintaining by Rancher 2.
+engine: gotpl
+maintainers:
+- name: thxCode
+  email: frank@rancher.com
+name: exporter-coredns
+version: 0.0.1
+

charts/rancher-monitoring/v0.0.2/charts/exporter-coredns/templates/endpoints.yaml

+{{- if .Values.endpoints }}
+apiVersion: v1
+kind: Service
+metadata:
+  labels:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+    k8s-app: coredns
+  name: {{ template "app.dnsname" . }}
+spec:
+  type: ClusterIP
+  clusterIP: None
+  ports:
+    - name: metrics
+      port: {{ .Values.ports.metrics.port }}
+      protocol: TCP
+      targetPort: {{ .Values.ports.metrics.port }}
+---
+
+apiVersion: v1
+kind: Endpoints
+metadata:
+  labels:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+  name: {{ template "app.dnsname" . }}
+subsets:
+  - addresses:
+      {{- range .Values.endpoints }}
+      - ip: {{ . }}
+      {{- end }}
+    ports:
+      - name: metrics
+        port: {{ .Values.ports.metrics.port }}
+        protocol: TCP
+{{- end }}
+

charts/rancher-monitoring/v0.0.2/charts/exporter-coredns/templates/servicemonitor.yaml

+apiVersion: {{ template "operator_api_version" . }}
+kind: ServiceMonitor
+metadata:
+  labels:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+    source: rancher-monitoring
+    {{- if .Values.serviceMonitor.labels }}
+{{ toYaml .Values.serviceMonitor.labels | indent 4 }}
+    {{- end }}  
+  name: {{ template "app.fullname" . }}
+spec:
+  jobLabel: coredns
+  selector:
+    matchLabels:
+      k8s-app: coredns
+  namespaceSelector:
+    any: true
+    matchNames:
+      - "kube-system"
+      - {{ .Release.Namespace | quote }}
+  endpoints:
+  - port: metrics
+    interval: 15s
+    bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token

charts/rancher-monitoring/v0.0.2/charts/exporter-coredns/values.yaml

+## CRD apiGroup
+##
+apiGroup: "monitoring.coreos.com"
+
+## Custom endpoints
+##
+endpoints: []
+
+ports: 
+  metrics:
+    port: 9153
+
+serviceMonitor:
+  ## Custom Labels to be added to ServiceMonitor
+  ##
+  labels: {}

charts/rancher-monitoring/v0.0.2/charts/exporter-fluentd/Chart.yaml

+apiVersion: v1
+description: Creates Fluentd Metrics Exporter instance for Kubernetes which maintaining by Rancher 2.
+engine: gotpl
+maintainers:
+- name: aiwantaozi
+  email: michelia.feng@gmail.com
+name: exporter-fluentd
+version: 0.0.1

charts/rancher-monitoring/v0.0.2/charts/exporter-fluentd/templates/servicemonitor.yaml

+apiVersion: {{ template "operator_api_version" . }}
+kind: ServiceMonitor
+metadata:
+  labels:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+    source: rancher-monitoring
+    {{- if .Values.serviceMonitor.labels }}
+{{ toYaml .Values.serviceMonitor.labels | indent 4 }}
+    {{- end }}
+  name: {{ template "app.fullname" . }}
+spec:
+  jobLabel: fluentd
+  selector:
+    matchLabels:
+      k8s-app: fluentd
+  namespaceSelector:
+    matchNames:
+      - cattle-logging
+  endpoints:
+  - port: metrics
+    interval: 15s
+    honorLabels: true

charts/rancher-monitoring/v0.0.2/charts/exporter-fluentd/values.yaml

+## CRD apiGroup
+##
+apiGroup: "monitoring.coreos.com"
+
+## Skip verification until we have resolved why the certificate validation
+## for the kubelet on API server nodes fail.
+##
+serviceMonitor:
+  ## Custom Labels to be added to ServiceMonitor
+  ##
+  labels: {}

charts/rancher-monitoring/v0.0.2/charts/exporter-kube-controller-manager/Chart.yaml

+apiVersion: v1
+description: Creates ServiceMonitor CRD of controller manager for Kubernetes which maintaining by Rancher 2.
+engine: gotpl
+maintainers:
+- name: thxCode
+  email: frank@rancher.com
+name: exporter-kube-controller-manager
+version: 0.0.1
+

charts/rancher-monitoring/v0.0.2/charts/exporter-kube-controller-manager/templates/endpoints.yaml

+{{- if .Values.endpoints }}
+apiVersion: v1
+kind: Service
+metadata:
+  labels:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+    k8s-app: kube-controller-manager
+  name: {{ template "app.dnsname" . }}
+spec:
+  type: ClusterIP
+  clusterIP: None
+  ports:
+    - name: metrics
+      port: {{ .Values.ports.metrics.port }}
+      protocol: TCP
+      targetPort: {{ .Values.ports.metrics.port }}
+---
+
+apiVersion: v1
+kind: Endpoints
+metadata:
+  labels:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+  name: {{ template "app.dnsname" . }}
+subsets:
+  - addresses:
+      {{- range .Values.endpoints }}
+      - ip: {{ . }}
+      {{- end }}
+    ports:
+      - name: metrics
+        port: {{ .Values.ports.metrics.port }}
+        protocol: TCP
+{{- end }}

charts/rancher-monitoring/v0.0.2/charts/exporter-kube-controller-manager/templates/servicemonitor.yaml

+apiVersion: {{ template "operator_api_version" . }}
+kind: ServiceMonitor
+metadata:
+  labels:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+    source: rancher-monitoring
+    {{- if .Values.serviceMonitor.labels }}
+{{ toYaml .Values.serviceMonitor.labels | indent 4 }}
+    {{- end }}  
+  name: {{ template "app.fullname" . }}
+spec:
+  jobLabel: kube-controller-manager
+  selector:
+    matchLabels:
+      k8s-app: kube-controller-manager
+  namespaceSelector:
+    any: true
+    matchNames:
+      - "kube-system"
+      - {{ .Release.Namespace | quote }}
+  endpoints:
+  - port: metrics
+    interval: 15s
+    bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
+    tlsConfig:
+      caFile: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
+      {{- if .Values.insecureSkipVerify }}
+      insecureSkipVerify: true
+      {{- end }}

charts/rancher-monitoring/v0.0.2/charts/exporter-kube-controller-manager/values.yaml

+## CRD apiGroup
+##
+apiGroup: "monitoring.coreos.com"
+
+## Skip verification until we have resolved why the certificate validation
+## for the kubelet on API server nodes fail.
+##
+insecureSkipVerify: true
+
+## Custom endpoints
+##
+endpoints: []
+
+ports: 
+  metrics:
+    port: 10252
+
+serviceMonitor:
+  ## Custom Labels to be added to ServiceMonitor
+  ##
+  labels: {}

charts/rancher-monitoring/v0.0.2/charts/exporter-kube-dns/Chart.yaml

+apiVersion: v1
+description: Creates ServiceMonitor CRD of kube-dns for Kubernetes which maintaining by Rancher 2.
+engine: gotpl
+maintainers:
+- name: thxCode
+  email: frank@rancher.com
+name: exporter-kube-dns
+version: 0.0.1
+

charts/rancher-monitoring/v0.0.2/charts/exporter-kube-dns/templates/endpoints.yaml

+{{- if .Values.endpoints }}
+apiVersion: v1
+kind: Service
+metadata:
+  labels:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+    k8s-app: coredns
+  name: {{ template "app.dnsname" . }}
+spec:
+  type: ClusterIP
+  clusterIP: None
+  ports:
+    - name: dnsmasq-metrics
+      port: {{ .Values.ports.metrics.dnsmasq.port }}
+      protocol: TCP
+      targetPort: {{ .Values.ports.metrics.dnsmasq.port }}
+    - name: skydns-metrics
+      port: {{ .Values.ports.metrics.skydns.port }}
+      protocol: TCP
+      targetPort: {{ .Values.ports.metrics.skydns.port }}
+---
+
+apiVersion: v1
+kind: Endpoints
+metadata:
+  labels:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+  name: {{ template "app.dnsname" . }}
+subsets:
+  - addresses:
+      {{- range .Values.endpoints }}
+      - ip: {{ . }}
+      {{- end }}
+    ports:
+      - name: dnsmasq-metrics
+        port: {{ .Values.ports.metrics.dnsmasq.port }}
+        protocol: TCP
+      - name: skydns-metrics
+        port: {{ .Values.ports.metrics.skydns.port }}
+        protocol: TCP
+{{- end }}

charts/rancher-monitoring/v0.0.2/charts/exporter-kube-dns/templates/servicemonitor.yaml

+apiVersion: {{ template "operator_api_version" . }}
+kind: ServiceMonitor
+metadata:
+  labels:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+    source: rancher-monitoring
+    {{- if .Values.serviceMonitor.labels }}
+{{ toYaml .Values.serviceMonitor.labels | indent 4 }}
+    {{- end }}  
+  name: {{ template "app.fullname" . }}
+spec:
+  jobLabel: kube-dns
+  selector:
+    matchLabels:
+      k8s-app: coredns
+  namespaceSelector:
+    any: true
+    matchNames:
+      - "kube-system"
+      - {{ .Release.Namespace | quote }}
+  endpoints:
+  - port: dnsmasq-metrics
+    interval: 15s
+    bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
+  - port: skydns-metrics
+    interval: 15s
+    bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token

charts/rancher-monitoring/v0.0.2/charts/exporter-kube-dns/values.yaml

+## CRD apiGroup
+##
+apiGroup: "monitoring.coreos.com"
+
+## Custom endpoints
+##
+endpoints: []
+
+ports: 
+  metrics:
+    dnsmasq:
+      port: 10054
+    skydns: 
+      port: 10055
+
+serviceMonitor:
+  ## Custom Labels to be added to ServiceMonitor
+  ##
+  labels: {}

charts/rancher-monitoring/v0.0.2/charts/exporter-kube-etcd/Chart.yaml

+apiVersion: v1
+description: Creates ServiceMonitor CRD of etcd for Kubernetes which maintaining by Rancher 2.
+engine: gotpl
+maintainers:
+- name: thxCode
+  email: frank@rancher.com
+name: exporter-kube-etcd
+version: 0.0.1
+

charts/rancher-monitoring/v0.0.2/charts/exporter-kube-etcd/templates/endpoints.yaml

+{{- if .Values.endpoints }}
+apiVersion: v1
+kind: Service
+metadata:
+  labels:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+    k8s-app: etcd-server
+  name: {{ template "app.dnsname" . }}
+spec:
+  type: ClusterIP
+  clusterIP: None
+  ports:
+    - name: metrics
+      port: {{ .Values.ports.metrics.port }}
+      protocol: TCP
+      targetPort: {{ .Values.ports.metrics.port }}
+---
+
+apiVersion: v1
+kind: Endpoints
+metadata:
+  labels:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+  name: {{ template "app.dnsname" . }}
+subsets:
+  - addresses:
+      {{- range .Values.endpoints }}
+      - ip: {{ . }}
+      {{- end }}
+    ports:
+      - name: metrics
+        port: {{ .Values.ports.metrics.port }}
+        protocol: TCP
+{{- end }}

charts/rancher-monitoring/v0.0.2/charts/exporter-kube-etcd/templates/servicemonitor.yaml

+apiVersion: {{ template "operator_api_version" . }}
+kind: ServiceMonitor
+metadata:
+  labels:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+    source: rancher-monitoring
+    {{- if .Values.serviceMonitor.labels }}
+{{ toYaml .Values.serviceMonitor.labels | indent 4 }}
+    {{- end }}  
+  name: {{ template "app.fullname" . }}
+spec:
+  jobLabel: kube-etcd
+  selector:
+    matchLabels:
+      k8s-app: etcd-server
+  namespaceSelector:
+    any: true
+    matchNames:
+      - "kube-system"
+      - {{ .Release.Namespace | quote }}
+  endpoints:
+  - port: metrics
+    interval: 15s
+    bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
+    {{- if eq .Values.ports.metrics.scheme "https" }}
+    scheme: https
+    tlsConfig:
+      caFile: {{ .Values.caFile }}
+      {{- if  .Values.certFile }}
+      certFile: {{ .Values.certFile }}
+      {{- end }}
+      {{- if .Values.keyFile }}
+      keyFile: {{ .Values.keyFile }}
+      {{- end}}
+      {{- if .Values.insecureSkipVerify }}
+      insecureSkipVerify: true
+      {{- end }}
+    {{- end }}

charts/rancher-monitoring/v0.0.2/charts/exporter-kube-etcd/values.yaml

+## CRD apiGroup
+##
+apiGroup: "monitoring.coreos.com"
+
+## Skip verification until we have resolved why the certificate validation
+## for the kubelet on API server nodes fail.
+##
+insecureSkipVerify: true
+
+## TLS Cofiguration for the service monitor, default to none, but append cert and keyfile if passed
+##
+caFile: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
+certFile: ""
+keyFile: ""
+
+## Custom endpoints
+##
+endpoints: []
+
+ports: 
+  metrics:
+    scheme: "https"
+    port: 4001
+
+serviceMonitor:
+  ## Custom Labels to be added to ServiceMonitor
+  ##
+  labels: {}

charts/rancher-monitoring/v0.0.2/charts/exporter-kube-scheduler/Chart.yaml

+apiVersion: v1
+description: Creates ServiceMonitor CRD of scheduler for Kubernetes which maintaining by Rancher 2.
+engine: gotpl
+maintainers:
+- name: thxCode
+  email: frank@rancher.com
+name: exporter-kube-scheduler
+version: 0.0.1
+

charts/rancher-monitoring/v0.0.2/charts/exporter-kube-scheduler/templates/endpoints.yaml

+{{- if .Values.endpoints }}
+apiVersion: v1
+kind: Service
+metadata:
+  labels:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+    k8s-app: kube-scheduler
+  name: {{ template "app.dnsname" . }}
+spec:
+  type: ClusterIP
+  clusterIP: None
+  ports:
+    - name: metrics
+      port: {{ .Values.ports.metrics.port }}
+      protocol: TCP
+      targetPort: {{ .Values.ports.metrics.port }}
+---
+
+apiVersion: v1
+kind: Endpoints
+metadata:
+  labels:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+  name: {{ template "app.dnsname" . }}
+subsets:
+  - addresses:
+      {{- range .Values.endpoints }}
+      - ip: {{ . }}
+      {{- end }}
+    ports:
+      - name: metrics
+        port: {{ .Values.ports.metrics.port }}
+        protocol: TCP
+{{- end }}
\ No newline at end of file

charts/rancher-monitoring/v0.0.2/charts/exporter-kube-scheduler/templates/prometheusrule.yaml

+apiVersion: {{ template "operator_api_version" . }}
+kind: PrometheusRule
+metadata:
+  labels:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+    source: rancher-monitoring
+    {{- if .Values.prometheusRule.labels }}
+{{ toYaml .Values.prometheusRule.labels | indent 4 }}
+    {{- end }}   
+  name: {{ template "app.fullname" . }}
+spec:
+  groups:
+  - name: kube-scheduler.rules
+    rules:
+    - record: cluster:scheduler_e2e_scheduling_latency_seconds:quantile
+      expr: histogram_quantile(0.99, sum(scheduler_e2e_scheduling_latency_microseconds_bucket)
+        BY (le, cluster)) / 1e+06
+      labels:
+        quantile: "0.99"
+    - record: cluster:scheduler_e2e_scheduling_latency_seconds:quantile
+      expr: histogram_quantile(0.9, sum(scheduler_e2e_scheduling_latency_microseconds_bucket)
+        BY (le, cluster)) / 1e+06
+      labels:
+        quantile: "0.9"
+    - record: cluster:scheduler_e2e_scheduling_latency_seconds:quantile
+      expr: histogram_quantile(0.5, sum(scheduler_e2e_scheduling_latency_microseconds_bucket)
+        BY (le, cluster)) / 1e+06
+      labels:
+        quantile: "0.5"
+    - record: cluster:scheduler_scheduling_algorithm_latency_seconds:quantile
+      expr: histogram_quantile(0.99, sum(scheduler_scheduling_algorithm_latency_microseconds_bucket)
+        BY (le, cluster)) / 1e+06
+      labels:
+        quantile: "0.99"
+    - record: cluster:scheduler_scheduling_algorithm_latency_seconds:quantile
+      expr: histogram_quantile(0.9, sum(scheduler_scheduling_algorithm_latency_microseconds_bucket)
+        BY (le, cluster)) / 1e+06
+      labels:
+        quantile: "0.9"
+    - record: cluster:scheduler_scheduling_algorithm_latency_seconds:quantile
+      expr: histogram_quantile(0.5, sum(scheduler_scheduling_algorithm_latency_microseconds_bucket)
+        BY (le, cluster)) / 1e+06
+      labels:
+        quantile: "0.5"
+    - record: cluster:scheduler_binding_latency_seconds:quantile
+      expr: histogram_quantile(0.99, sum(scheduler_binding_latency_microseconds_bucket)
+        BY (le, cluster)) / 1e+06
+      labels:
+        quantile: "0.99"
+    - record: cluster:scheduler_binding_latency_seconds:quantile
+      expr: histogram_quantile(0.9, sum(scheduler_binding_latency_microseconds_bucket)
+        BY (le, cluster)) / 1e+06
+      labels:
+        quantile: "0.9"
+    - record: cluster:scheduler_binding_latency_seconds:quantile
+      expr: histogram_quantile(0.5, sum(scheduler_binding_latency_microseconds_bucket)
+        BY (le, cluster)) / 1e+06
+      labels:
+        quantile: "0.5"

charts/rancher-monitoring/v0.0.2/charts/exporter-kube-scheduler/templates/servicemonitor.yaml

+apiVersion: {{ template "operator_api_version" . }}
+kind: ServiceMonitor
+metadata:
+  labels:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+    source: rancher-monitoring
+    {{- if .Values.serviceMonitor.labels }}
+{{ toYaml .Values.serviceMonitor.labels | indent 4 }}
+    {{- end }}  
+  name: {{ template "app.fullname" . }}
+spec:
+  jobLabel: kube-scheduler
+  selector:
+    matchLabels:
+      k8s-app: kube-scheduler
+  namespaceSelector:
+    any: true
+    matchNames:
+      - "kube-system"
+      - {{ .Release.Namespace | quote }}
+  endpoints:
+  - port: metrics
+    interval: 15s
+    bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token

charts/rancher-monitoring/v0.0.2/charts/exporter-kube-scheduler/values.yaml

+## CRD apiGroup
+##
+apiGroup: "monitoring.coreos.com"
+
+## Custom endpoints
+##
+endpoints: []
+
+ports: 
+  metrics:
+    port: 10251
+
+serviceMonitor:
+  ## Custom Labels to be added to ServiceMonitor
+  ##
+  labels: {}
+
+prometheusRule:
+  ## Custom Labels to be added to PrometheusRule
+  ##
+  labels: {}

charts/rancher-monitoring/v0.0.2/charts/exporter-kube-state/Chart.yaml

+apiVersion: v1
+description: Creates Kube-state Exporter instance for Kubernetes which maintaining by Rancher 2.
+engine: gotpl
+maintainers:
+- name: thxCode
+  email: frank@rancher.com
+name: exporter-kube-state
+version: 0.0.1

charts/rancher-monitoring/v0.0.2/charts/exporter-kube-state/templates/deployment.yaml

+apiVersion: {{ template "deployment_api_version" . }}
+kind: Deployment
+metadata:
+  name: {{ template "app.fullname" . }}
+  labels:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+spec:
+  replicas: {{ .Values.replicaCount }}
+  selector:
+    matchLabels:
+      app: {{ template "app.name" . }}
+      chart: {{ template "app.version" . }}
+      release: {{ .Release.Name }}
+  template:
+    metadata:
+      labels:
+        app: {{ template "app.name" . }}
+        chart: {{ template "app.version" . }}
+        release: {{ .Release.Name }}
+    spec:
+      {{- if .Values.nodeSelector }}
+      nodeSelector:
+{{ toYaml .Values.nodeSelector | indent 8 }}
+    {{- end }}
+      containers:
+      - name: kube-state
+        image: "{{ .Values.image.repository }}:{{ .Values.image.tag }}"
+        ports:
+        - name: http
+          containerPort: 8080
+          protocol: TCP
+        livenessProbe:
+          httpGet:
+            path: /
+            port: 8080
+          initialDelaySeconds: 30
+          timeoutSeconds: 30
+        readinessProbe:
+          httpGet:
+            path: /
+            port: 8080
+          initialDelaySeconds: 30
+          timeoutSeconds: 5
+        resources:
+          limits:
+            cpu: 100m
+            memory: 200Mi
+          requests:
+            cpu: 100m
+            memory: 130Mi
+    {{- if .Values.enabledRBAC }}
+      serviceAccountName: {{ .Values.serviceAccountName }}
+    {{- end }}
+{{- if .Values.tolerations }}
+      tolerations:
+{{ toYaml .Values.tolerations | indent 8 }}
+    {{- end }}

charts/rancher-monitoring/v0.0.2/charts/exporter-kube-state/templates/service.yaml

+apiVersion: v1
+kind: Service
+metadata:
+  name: expose-kubernetes-metrics
+  labels:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+    monitoring.cattle.io: "true"
+spec:
+  type: ClusterIP
+  selector:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    release: {{ .Release.Name }}
+  ports:
+  - name: metrics
+    port: {{ .Values.ports.metrics.port }}
+    targetPort: 8080
+    protocol: TCP

charts/rancher-monitoring/v0.0.2/charts/exporter-kube-state/templates/servicemonitor.yaml

+apiVersion: {{ template "operator_api_version" . }}
+kind: ServiceMonitor
+metadata:
+  labels:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+    source: rancher-monitoring
+    {{- if .Values.serviceMonitor.labels }}
+{{ toYaml .Values.serviceMonitor.labels | indent 4 }}
+    {{- end }}
+  name: {{ template "app.fullname" . }}
+spec:
+  jobLabel: kube-state
+  selector:
+    matchLabels:
+      app: {{ template "app.name" . }}
+      chart: {{ template "app.version" . }}
+      release: {{ .Release.Name }}
+      monitoring.cattle.io: "true"
+  namespaceSelector:
+    matchNames:
+      - {{ .Release.Namespace | quote }}
+  endpoints:
+  - port: metrics
+    interval: 15s
+    honorLabels: true

charts/rancher-monitoring/v0.0.2/charts/exporter-kube-state/values.yaml

+enabledRBAC: true
+
+## Already exist ServiceAccount
+##
+serviceAccountName: ""
+
+## CRD apiGroup
+##
+apiGroup: "monitoring.coreos.com"
+
+## Expertor listens on where and exports on host
+##
+ports: 
+  metrics:
+    port: 8080
+
+# Default values for kube-state-metrics.
+# This is a YAML-formatted file.
+# Declare variables to be passed into your templates.
+replicaCount: 1
+
+image:
+  repository: quay.io/coreos/kube-state-metrics
+  tag: v1.4.0
+
+## Node Selector to constrain pods to run on particular nodes
+## Ref: https://kubernetes.io/docs/concepts/configuration/assign-pod-node/
+##
+nodeSelector: {}
+
+## Tolerations for use with node taints
+## Ref: https://kubernetes.io/docs/concepts/configuration/taint-and-toleration/
+##
+tolerations: {}
+  #  - key: "key"
+  #    operator: "Equal"
+  #    value: "value"
+  #    effect: "NoSchedule"
+
+serviceMonitor:
+  ## Custom Labels to be added to ServiceMonitor
+  ##
+  labels: {}

charts/rancher-monitoring/v0.0.2/charts/exporter-kubelets/Chart.yaml

+apiVersion: v1
+description: Creates ServiceMonitor CRD of kublets for Kubernetes which maintaining by Rancher 2.
+engine: gotpl
+maintainers:
+- name: thxCode
+  email: frank@rancher.com
+name: exporter-kubelets
+version: 0.0.1
+

charts/rancher-monitoring/v0.0.2/charts/exporter-kubelets/templates/servicemonitor.yaml

+apiVersion: {{ template "operator_api_version" . }}
+kind: ServiceMonitor
+metadata:
+  labels:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+    source: rancher-monitoring
+    {{- if .Values.serviceMonitor.labels }}
+{{ toYaml .Values.serviceMonitor.labels | indent 4 }}
+    {{- end }}  
+  name: {{ template "charts.exporter-kubelets.fullname" . }}
+spec:
+  jobLabel: kubelet
+  selector:
+    matchLabels:
+      k8s-app: kubelet
+  namespaceSelector:
+    any: true
+    matchNames:
+      - "kube-system"
+      - {{ .Release.Namespace | quote }}
+  endpoints:
+  - port: https-metrics
+    scheme: https
+    interval: 15s
+    tlsConfig:
+      caFile: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
+      {{- if .Values.insecureSkipVerify }}
+      insecureSkipVerify: true
+      {{- end }}
+    bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
+  - port: https-metrics
+    scheme: https
+    path: /metrics/cadvisor
+    interval: 30s
+    honorLabels: true
+    tlsConfig:
+      caFile: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
+      {{- if .Values.insecureSkipVerify }}
+      insecureSkipVerify: true
+      {{- end }}
+    bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
+  - port: http-metrics
+    interval: 15s
+  - port: cadvisor
+    interval: 30s
+    honorLabels: true

charts/rancher-monitoring/v0.0.2/charts/exporter-kubelets/values.yaml

+## CRD apiGroup
+##
+apiGroup: "monitoring.coreos.com"
+
+## Skip verification until we have resolved why the certificate validation
+## for the kubelet on API server nodes fail.
+##
+insecureSkipVerify: true
+
+serviceMonitor:
+  ## Custom Labels to be added to ServiceMonitor
+  ##
+  labels: {}

charts/rancher-monitoring/v0.0.2/charts/exporter-kubernetes/Chart.yaml

+apiVersion: v1
+description: Creates ServiceMonitor CRD of apiserver for Kubernetes which maintaining by Rancher 2.
+engine: gotpl
+maintainers:
+- name: thxCode
+  email: frank@rancher.com
+name: exporter-kubernetes
+version: 0.0.1

charts/rancher-monitoring/v0.0.2/charts/exporter-kubernetes/templates/prometheusrule.yaml

+apiVersion: {{ template "operator_api_version" . }}
+kind: PrometheusRule
+metadata:
+  labels:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+    source: rancher-monitoring
+    {{- if .Values.prometheusRule.labels }}
+{{ toYaml .Values.prometheusRule.labels | indent 4 }}
+    {{- end }}
+  name: {{ template "app.fullname" . }}
+spec:
+  groups:
+  - name: kubernetes.rules
+    rules:
+    - record: pod_name:container_memory_usage_bytes:sum
+      expr: sum(container_memory_usage_bytes{container_name!="POD",pod_name!=""}) BY
+        (pod_name)
+    - record: pod_name:container_spec_cpu_shares:sum
+      expr: sum(container_spec_cpu_shares{container_name!="POD",pod_name!=""}) BY (pod_name)
+    - record: pod_name:container_cpu_usage:sum
+      expr: sum(rate(container_cpu_usage_seconds_total{container_name!="POD",pod_name!=""}[5m]))
+        BY (pod_name)
+    - record: pod_name:container_fs_usage_bytes:sum
+      expr: sum(container_fs_usage_bytes{container_name!="POD",pod_name!=""}) BY (pod_name)
+    - record: namespace:container_memory_usage_bytes:sum
+      expr: sum(container_memory_usage_bytes{container_name!=""}) BY (namespace)
+    - record: namespace:container_spec_cpu_shares:sum
+      expr: sum(container_spec_cpu_shares{container_name!=""}) BY (namespace)
+    - record: namespace:container_cpu_usage:sum
+      expr: sum(rate(container_cpu_usage_seconds_total{container_name!="POD"}[5m]))
+        BY (namespace)
+    - record: cluster:memory_usage:ratio
+      expr: sum(container_memory_usage_bytes{container_name!="POD",pod_name!=""}) BY
+        (cluster) / sum(machine_memory_bytes) BY (cluster)
+    - record: cluster:container_spec_cpu_shares:ratio
+      expr: sum(container_spec_cpu_shares{container_name!="POD",pod_name!=""}) / 1000
+        / sum(machine_cpu_cores)
+    - record: cluster:container_cpu_usage:ratio
+      expr: sum(rate(container_cpu_usage_seconds_total{container_name!="POD",pod_name!=""}[5m]))
+        / sum(machine_cpu_cores)
+    - record: apiserver_latency_seconds:quantile
+      expr: histogram_quantile(0.99, rate(apiserver_request_latencies_bucket[5m])) /
+        1e+06
+      labels:
+        quantile: "0.99"
+    - record: apiserver_latency:quantile_seconds
+      expr: histogram_quantile(0.9, rate(apiserver_request_latencies_bucket[5m])) /
+        1e+06
+      labels:
+        quantile: "0.9"
+    - record: apiserver_latency_seconds:quantile
+      expr: histogram_quantile(0.5, rate(apiserver_request_latencies_bucket[5m])) /
+        1e+06
+      labels:
+        quantile: "0.5"

charts/rancher-monitoring/v0.0.2/charts/exporter-kubernetes/templates/servicemonitor.yaml

+apiVersion: {{ template "operator_api_version" . }}
+kind: ServiceMonitor
+metadata:
+  labels:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+    source: rancher-monitoring
+    {{- if .Values.serviceMonitor.labels }}
+{{ toYaml .Values.serviceMonitor.labels | indent 4 }}
+    {{- end }}   
+  name: {{ template "app.fullname" . }}
+spec:
+  jobLabel: kubernetes
+  selector:
+    matchLabels:
+      component: apiserver
+      provider: kubernetes
+  namespaceSelector:
+    matchNames:
+      - "default"
+  endpoints:
+  - port: https
+    interval: 15s
+    scheme: https
+    tlsConfig:
+      caFile: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
+      {{- if .Values.insecureSkipVerify }}
+      insecureSkipVerify: true
+      {{- end }}
+    bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token

charts/rancher-monitoring/v0.0.2/charts/exporter-kubernetes/values.yaml

+## CRD apiGroup
+##
+apiGroup: "monitoring.coreos.com"
+
+## Skip verification until we have resolved why the certificate validation
+## for the kubelet on API server nodes fail.
+##
+insecureSkipVerify: true
+
+serviceMonitor:
+  ## Custom Labels to be added to ServiceMonitor
+  ##
+  labels: {}
+
+prometheusRule:
+  ## Custom Labels to be added to PrometheusRule
+  ##
+  labels: {}
\ No newline at end of file

charts/rancher-monitoring/v0.0.2/charts/exporter-node/Chart.yaml

+apiVersion: v1
+description: Creates Node Exporter instance for Kubernetes which maintaining by Rancher 2.
+engine: gotpl
+maintainers:
+- name: thxCode
+  email: frank@rancher.com
+name: exporter-node
+version: 0.0.1
\ No newline at end of file

charts/rancher-monitoring/v0.0.2/charts/exporter-node/templates/daemonset.yaml

+apiVersion: {{ template "daemonset_api_version" . }}
+kind: DaemonSet
+metadata:
+  labels:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+  name: {{ template "app.fullname" . }}
+spec:
+  selector:
+    matchLabels:
+      app: {{ template "app.name" . }}
+      chart: {{ template "app.version" . }}
+      release: {{ .Release.Name }}
+  template:
+    metadata:
+      labels:
+        app: {{ template "app.name" . }}
+        chart: {{ template "app.version" . }}
+        release: {{ .Release.Name }}
+    spec:
+      tolerations:
+      - operator: "Exists"
+      - key: "node-role.kubernetes.io/master"
+        operator: "Exists"
+      - key: "node-role.kubernetes.io/etcd"
+        operator: "Exists"
+      - key: "node-role.kubernetes.io/controlplane"
+        operator: "Exists"
+      containers:
+        - name: exporter-node
+          image: "{{ .Values.image.repository }}:{{ .Values.image.tag }}"
+          args:
+          - --web.listen-address=0.0.0.0:{{ .Values.ports.metrics.port }}
+          {{- if and .Values.container .Values.container.args }}
+{{ toYaml .Values.container.args | indent 10 }}
+          {{- end }}
+          ports:
+            - name: http
+              containerPort: {{ .Values.ports.metrics.port }}
+              hostPort: {{ .Values.ports.metrics.port }}
+          resources:
+{{ toYaml .Values.resources | indent 12 }}
+          {{- if and .Values.container .Values.container.volumeMounts }}
+          volumeMounts:
+{{ toYaml .Values.container.volumeMounts | indent 10 }}
+          {{- end }}
+    {{- if .Values.enabledRBAC }}
+      serviceAccountName: {{ .Values.serviceAccountName }}
+    {{- end }}
+    {{- if .Values.tolerations }}
+      tolerations:
+{{ toYaml .Values.tolerations | indent 8 }}
+    {{- end }}
+    {{- if .Values.nodeSelector }}
+      nodeSelector:
+{{ toYaml .Values.nodeSelector | indent 8 }}
+    {{- end }}
+      hostNetwork: true
+      hostPID: true
+      {{- if and .Values.container .Values.container.volumes }}
+      volumes:
+{{ toYaml .Values.container.volumes | indent 6 }}
+      {{- end}}

charts/rancher-monitoring/v0.0.2/charts/exporter-node/templates/prometheusrule.yaml

+apiVersion: {{ template "operator_api_version" . }}
+kind: PrometheusRule
+metadata:
+  labels:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+    source: rancher-monitoring
+    {{- if .Values.prometheusRule.labels }}
+{{ toYaml .Values.prometheusRule.labels | indent 4 }}
+    {{- end }}   
+  name: {{ template "app.fullname" . }}
+spec:
+  groups:
+  - name: node.rules
+    rules:
+    - record: instance:node_cpu:rate:sum
+      expr: sum(rate(node_cpu{mode!="idle",mode!="iowait"}[3m]))
+        BY (instance)
+    - record: instance:node_filesystem_usage:sum
+      expr: sum((node_filesystem_size{mountpoint="/"} - node_filesystem_free{mountpoint="/"}))
+        BY (instance)
+    - record: instance:node_network_receive_bytes:rate:sum
+      expr: sum(rate(node_network_receive_bytes[3m])) BY (instance)
+    - record: instance:node_network_transmit_bytes:rate:sum
+      expr: sum(rate(node_network_transmit_bytes[3m])) BY (instance)
+    - record: instance:node_cpu:ratio
+      expr: sum(rate(node_cpu{mode!="idle",mode!="iowait"}[5m])) WITHOUT (cpu, mode) / ON(instance)
+        GROUP_LEFT() count(sum(node_cpu) BY (instance, cpu)) BY (instance)
+    - record: cluster:node_cpu:sum_rate5m
+      expr: sum(rate(node_cpu{mode!="idle",mode!="iowait"}[5m]))
+    - record: cluster:node_cpu:ratio
+      expr: cluster:node_cpu:rate5m / count(sum(node_cpu) BY (instance, cpu))

charts/rancher-monitoring/v0.0.2/charts/exporter-node/templates/service.yaml

+apiVersion: v1
+kind: Service
+metadata:
+  name:   expose-node-metrics
+  labels:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+    monitoring.cattle.io: "true"
+spec:
+  type: ClusterIP
+  selector:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    release: {{ .Release.Name }}
+  ports:
+  - name: metrics
+    port: {{ .Values.ports.metrics.port }}
+    targetPort: {{ .Values.ports.metrics.port }}
+    protocol: TCP

charts/rancher-monitoring/v0.0.2/charts/exporter-node/templates/servicemonitor.yaml

+apiVersion: {{ template "operator_api_version" . }}
+kind: ServiceMonitor
+metadata:
+  labels:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+    source: rancher-monitoring
+    {{- if .Values.serviceMonitor.labels }}
+{{ toYaml .Values.serviceMonitor.labels | indent 4 }}
+    {{- end }}    
+  name: {{ template "app.fullname" . }}
+spec:
+  jobLabel: node
+  selector:
+    matchLabels:
+      app: {{ template "app.name" . }}
+      chart: {{ template "app.version" . }}
+      release: {{ .Release.Name }}
+      monitoring.cattle.io: "true"
+  namespaceSelector:
+    matchNames:
+      - {{ .Release.Namespace | quote }}
+  endpoints:
+  - port: metrics
+    interval: 15s

charts/rancher-monitoring/v0.0.2/charts/exporter-node/values.yaml

+enabledRBAC: true
+
+## Already exist ServiceAccount
+##
+serviceAccountName: ""
+
+## CRD apiGroup
+##
+apiGroup: "monitoring.coreos.com"
+
+## Expertor listens on where and exports on host
+##
+ports: 
+  metrics:
+    port: 9100
+
+# This is a YAML-formatted file.
+# Declare variables to be passed into your templates.
+replicaCount: 1
+
+image:
+  repository: quay.io/prometheus/node-exporter
+  tag: v0.16.0
+
+resources:
+  limits:
+    cpu: 200m
+    memory: 50Mi
+  requests:
+    cpu: 100m
+    memory: 30Mi
+
+container:
+  args:
+  - --path.procfs=/host/proc
+  - --path.sysfs=/host/sys
+
+  volumes:
+  - name: proc
+    hostPath:
+      path: /proc
+  - name: sys
+    hostPath:
+      path: /sys
+
+  volumeMounts:
+  - name: proc
+    mountPath: /host/proc
+    readOnly:  true
+  - name: sys
+    mountPath: /host/sys
+    readOnly: true
+
+## Tolerations for use with node taints
+## Ref: https://kubernetes.io/docs/concepts/configuration/taint-and-toleration/
+##
+tolerations:
+- effect: NoSchedule
+  operator: Exists
+
+## Node Selector to constrain pods to run on particular nodes
+## Ref: https://kubernetes.io/docs/concepts/configuration/assign-pod-node/
+##
+nodeSelector: {}
+
+serviceMonitor:
+  ## Custom Labels to be added to ServiceMonitor
+  ##
+  labels: {}
+
+prometheusRule:
+  ## Custom Labels to be added to PrometheusRule
+  ##
+  labels: {}
+

charts/rancher-monitoring/v0.0.2/charts/grafana/Chart.yaml

+apiVersion: v1
+description: Creates Grafana instance for Kubernetes which maintaining by Rancher 2.
+engine: gotpl
+maintainers:
+- name: thxCode
+  email: frank@rancher.com
+name: grafana
+version: 0.0.1

charts/rancher-monitoring/v0.0.2/charts/grafana/dashboards/c_cluster-dashboard.json

+{"dashboard":{"__inputs":[{"name":"DS_PROMETHEUS","label":"Rancher-Monitoring","description":"","type":"datasource","pluginId":"prometheus","pluginName":"Prometheus"}],"__requires":[{"type":"grafana","id":"grafana","name":"Grafana","version":"5.3.0"},{"type":"panel","id":"graph","name":"Graph","version":"5.0.0"},{"type":"datasource","id":"prometheus","name":"Prometheus","version":"5.0.0"},{"type":"panel","id":"singlestat","name":"Singlestat","version":"5.0.0"},{"type":"panel","id":"table","name":"Table","version":"5.0.0"}],"annotations":{"list":[{"builtIn":1,"datasource":"-- Grafana --","enable":true,"hide":true,"iconColor":"rgba(0, 211, 255, 1)","name":"Annotations & Alerts","type":"dashboard"}]},"description":"Monitors Kubernetes cluster using Prometheus. Shows overall cluster CPU / Memory / Filesystem usage as well as individual pod, containers, systemd services statistics. Uses cAdvisor metrics only.","editable":true,"gnetId":1621,"graphTooltip":0,"id":null,"iteration":1543396027075,"links":[],"panels":[{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":0},"id":34,"panels":[],"title":"Total usage","type":"row"},{"cacheTimeout":null,"colorBackground":false,"colorValue":true,"colors":["rgba(50, 172, 45, 0.97)","rgba(237, 129, 40, 0.89)","rgba(245, 54, 54, 0.9)"],"datasource":"${DS_PROMETHEUS}","decimals":2,"editable":true,"error":false,"format":"percent","gauge":{"maxValue":100,"minValue":0,"show":true,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{"h":5,"w":8,"x":0,"y":1},"height":"180px","id":6,"interval":null,"isNew":true,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":false},"tableColumn":"","targets":[{"expr":"sum (rate (container_cpu_usage_seconds_total{id=\"/\",kubernetes_io_hostname=~\"^$Node$\"}[2m])) / sum (machine_cpu_cores{kubernetes_io_hostname=~\"^$Node$\"}) * 100","format":"time_series","interval":"10s","intervalFactor":1,"refId":"A","step":10}],"thresholds":"65, 90","title":"Cluster CPU usage (2m avg)","type":"singlestat","valueFontSize":"80%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"current"},{"cacheTimeout":null,"colorBackground":false,"colorValue":true,"colors":["rgba(50, 172, 45, 0.97)","rgba(237, 129, 40, 0.89)","rgba(245, 54, 54, 0.9)"],"datasource":"${DS_PROMETHEUS}","editable":true,"error":false,"format":"percent","gauge":{"maxValue":100,"minValue":0,"show":true,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{"h":5,"w":8,"x":8,"y":1},"height":"180px","id":4,"interval":null,"isNew":true,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":false},"tableColumn":"","targets":[{"expr":"sum (container_memory_working_set_bytes{id=\"/\",kubernetes_io_hostname=~\"^$Node$\"}) / sum (machine_memory_bytes{kubernetes_io_hostname=~\"^$Node$\"}) * 100","format":"time_series","interval":"10s","intervalFactor":1,"refId":"A","step":10}],"thresholds":"65, 90","title":"Cluster memory usage","transparent":false,"type":"singlestat","valueFontSize":"80%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"current"},{"cacheTimeout":null,"colorBackground":false,"colorValue":true,"colors":["rgba(50, 172, 45, 0.97)","rgba(237, 129, 40, 0.89)","rgba(245, 54, 54, 0.9)"],"datasource":"${DS_PROMETHEUS}","decimals":2,"editable":true,"error":false,"format":"percent","gauge":{"maxValue":100,"minValue":0,"show":true,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{"h":5,"w":8,"x":16,"y":1},"height":"180px","id":7,"interval":null,"isNew":true,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":false},"tableColumn":"","targets":[{"expr":"sum (container_fs_usage_bytes{device=~\"^/dev/.*$\",id=\"/\",kubernetes_io_hostname=~\"^$Node$\"}) / sum (container_fs_limit_bytes{device=~\"^/dev/.*$\",id=\"/\",kubernetes_io_hostname=~\"^$Node$\"}) * 100","format":"time_series","interval":"10s","intervalFactor":1,"legendFormat":"","metric":"","refId":"A","step":10}],"thresholds":"65, 90","title":"Cluster filesystem usage","type":"singlestat","valueFontSize":"80%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"current"},{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["rgba(50, 172, 45, 0.97)","rgba(237, 129, 40, 0.89)","rgba(245, 54, 54, 0.9)"],"datasource":"${DS_PROMETHEUS}","decimals":2,"editable":true,"error":false,"format":"none","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{"h":3,"w":4,"x":0,"y":6},"height":"1px","id":11,"interval":null,"isNew":true,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":" cores","postfixFontSize":"30%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":false},"tableColumn":"","targets":[{"expr":"sum (rate (container_cpu_usage_seconds_total{id=\"/\",kubernetes_io_hostname=~\"^$Node$\"}[2m]))","interval":"10s","intervalFactor":1,"refId":"A","step":10}],"thresholds":"","title":"Used","type":"singlestat","valueFontSize":"50%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"current"},{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["rgba(50, 172, 45, 0.97)","rgba(237, 129, 40, 0.89)","rgba(245, 54, 54, 0.9)"],"datasource":"${DS_PROMETHEUS}","decimals":2,"editable":true,"error":false,"format":"none","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{"h":3,"w":4,"x":4,"y":6},"height":"1px","id":12,"interval":null,"isNew":true,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":" cores","postfixFontSize":"30%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":false},"tableColumn":"","targets":[{"expr":"sum (machine_cpu_cores{kubernetes_io_hostname=~\"^$Node$\"})","interval":"10s","intervalFactor":1,"refId":"A","step":10}],"thresholds":"","title":"Total","type":"singlestat","valueFontSize":"50%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"current"},{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["rgba(50, 172, 45, 0.97)","rgba(237, 129, 40, 0.89)","rgba(245, 54, 54, 0.9)"],"datasource":"${DS_PROMETHEUS}","decimals":2,"editable":true,"error":false,"format":"bytes","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{"h":3,"w":4,"x":8,"y":6},"height":"1px","id":9,"interval":null,"isNew":true,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"20%","prefix":"","prefixFontSize":"20%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":false},"tableColumn":"","targets":[{"expr":"sum (container_memory_working_set_bytes{id=\"/\",kubernetes_io_hostname=~\"^$Node$\"})","interval":"10s","intervalFactor":1,"refId":"A","step":10}],"thresholds":"","title":"Used","type":"singlestat","valueFontSize":"50%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"current"},{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["rgba(50, 172, 45, 0.97)","rgba(237, 129, 40, 0.89)","rgba(245, 54, 54, 0.9)"],"datasource":"${DS_PROMETHEUS}","decimals":2,"editable":true,"error":false,"format":"bytes","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{"h":3,"w":4,"x":12,"y":6},"height":"1px","id":10,"interval":null,"isNew":true,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":false},"tableColumn":"","targets":[{"expr":"sum (machine_memory_bytes{kubernetes_io_hostname=~\"^$Node$\"})","interval":"10s","intervalFactor":1,"refId":"A","step":10}],"thresholds":"","title":"Total","type":"singlestat","valueFontSize":"50%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"current"},{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["rgba(50, 172, 45, 0.97)","rgba(237, 129, 40, 0.89)","rgba(245, 54, 54, 0.9)"],"datasource":"${DS_PROMETHEUS}","decimals":2,"editable":true,"error":false,"format":"bytes","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{"h":3,"w":4,"x":16,"y":6},"height":"1px","id":13,"interval":null,"isNew":true,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":false},"tableColumn":"","targets":[{"expr":"sum (container_fs_usage_bytes{device=~\"^/dev/.*$\",id=\"/\",kubernetes_io_hostname=~\"^$Node$\"})","interval":"10s","intervalFactor":1,"refId":"A","step":10}],"thresholds":"","title":"Used","type":"singlestat","valueFontSize":"50%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"current"},{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["rgba(50, 172, 45, 0.97)","rgba(237, 129, 40, 0.89)","rgba(245, 54, 54, 0.9)"],"datasource":"${DS_PROMETHEUS}","decimals":2,"editable":true,"error":false,"format":"bytes","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{"h":3,"w":4,"x":20,"y":6},"height":"1px","id":14,"interval":null,"isNew":true,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":false},"tableColumn":"","targets":[{"expr":"sum (container_fs_limit_bytes{device=~\"^/dev/.*$\",id=\"/\",kubernetes_io_hostname=~\"^$Node$\"})","interval":"10s","intervalFactor":1,"refId":"A","step":10}],"thresholds":"","title":"Total","type":"singlestat","valueFontSize":"50%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"current"},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"${DS_PROMETHEUS}","fill":1,"gridPos":{"h":6,"w":8,"x":0,"y":9},"id":2051,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum (rate (container_cpu_usage_seconds_total{id=\"/\",kubernetes_io_hostname=~\"^$Node$\"}[2m])) / sum (machine_cpu_cores{kubernetes_io_hostname=~\"^$Node$\"}) * 100","format":"time_series","hide":false,"instant":false,"intervalFactor":1,"legendFormat":"Cluster","refId":"A"},{"expr":"sum (rate (container_cpu_usage_seconds_total{id=\"/\"}[2m])) by (kubernetes_io_hostname) / sum (machine_cpu_cores) by (kubernetes_io_hostname) * 100","format":"time_series","hide":false,"intervalFactor":1,"legendFormat":"{{kubernetes_io_hostname}}","refId":"B"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Cluster CPU usage (2m avg)","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"percent","label":"","logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":"","logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"${DS_PROMETHEUS}","fill":1,"gridPos":{"h":6,"w":8,"x":8,"y":9},"id":2052,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum (container_memory_working_set_bytes{id=\"/\",kubernetes_io_hostname=~\"^$Node$\"}) / sum (machine_memory_bytes{kubernetes_io_hostname=~\"^$Node$\"}) * 100","format":"time_series","hide":false,"instant":false,"intervalFactor":1,"legendFormat":"Cluster","refId":"A"},{"expr":"sum (container_memory_working_set_bytes{id=\"/\"}) by (kubernetes_io_hostname) / sum (machine_memory_bytes) by (kubernetes_io_hostname) * 100","format":"time_series","hide":false,"intervalFactor":1,"legendFormat":"{{kubernetes_io_hostname}}","refId":"B"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Cluster memory usage","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"percent","label":"","logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":"","logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"${DS_PROMETHEUS}","fill":1,"gridPos":{"h":6,"w":8,"x":16,"y":9},"id":2053,"legend":{"alignAsTable":false,"avg":false,"current":false,"max":false,"min":false,"rightSide":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum (container_fs_usage_bytes{device=~\"^/dev/.*$\",id=\"/\",kubernetes_io_hostname=~\"^$Node$\"}) / sum (container_fs_limit_bytes{device=~\"^/dev/.*$\",id=\"/\",kubernetes_io_hostname=~\"^$Node$\"}) * 100","format":"time_series","hide":false,"instant":false,"intervalFactor":1,"legendFormat":"Cluster","refId":"A"},{"expr":"sum (container_fs_usage_bytes{device=~\"^/dev/.*$\",id=\"/\"}) by (kubernetes_io_hostname) / sum (container_fs_limit_bytes{device=~\"^/dev/.*$\",id=\"/\"}) by (kubernetes_io_hostname) * 100","format":"time_series","hide":false,"intervalFactor":1,"legendFormat":"{{kubernetes_io_hostname}}","refId":"B"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Cluster filesystem usage","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"decimals":null,"format":"percent","label":"","logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":"","logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":15},"id":2022,"panels":[],"title":"Node","type":"row"},{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["#299c46","rgba(237, 129, 40, 0.89)","#d44a3a"],"datasource":"${DS_PROMETHEUS}","format":"none","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{"h":3,"w":8,"x":0,"y":16},"id":2024,"interval":null,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":false},"tableColumn":"","targets":[{"expr":"sum(kube_node_info{node=~\"$Node\"})","format":"time_series","intervalFactor":1,"refId":"A"}],"thresholds":"","title":"Number Of Nodes","type":"singlestat","valueFontSize":"80%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"avg"},{"cacheTimeout":null,"colorBackground":true,"colorValue":false,"colors":["#299c46","rgba(237, 129, 40, 0.89)","#d44a3a"],"datasource":"${DS_PROMETHEUS}","format":"none","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{"h":3,"w":8,"x":8,"y":16},"id":2025,"interval":null,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":false},"tableColumn":"","targets":[{"expr":"sum(kube_node_status_condition{condition=\"OutOfDisk\", node=~\"$Node\", status=\"true\"})","format":"time_series","intervalFactor":1,"refId":"A"}],"thresholds":"1","title":"Nodes Out of Disk","type":"singlestat","valueFontSize":"80%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"current"},{"cacheTimeout":null,"colorBackground":true,"colorValue":false,"colors":["#299c46","rgba(237, 129, 40, 0.89)","#d44a3a"],"datasource":"${DS_PROMETHEUS}","format":"none","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{"h":3,"w":8,"x":16,"y":16},"id":2026,"interval":null,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":false},"tableColumn":"","targets":[{"expr":"sum(kube_node_spec_unschedulable{node=~\"$Node\"})","format":"time_series","intervalFactor":1,"refId":"A"}],"thresholds":"1","title":"Nodes Unavailable","type":"singlestat","valueFontSize":"80%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"current"},{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":19},"id":2014,"panels":[],"title":"Deployments","type":"row"},{"columns":[{"text":"Current","value":"current"}],"datasource":"${DS_PROMETHEUS}","fontSize":"100%","gridPos":{"h":5,"w":6,"x":0,"y":20},"id":2016,"links":[],"pageSize":null,"scroll":true,"showHeader":true,"sort":{"col":1,"desc":true},"styles":[{"alias":"Time","dateFormat":"YYYY-MM-DD HH:mm:ss","pattern":"Time","type":"date"},{"alias":"","colorMode":"row","colors":["rgba(245, 54, 54, 0.9)","rgba(237, 129, 40, 0.89)","rgba(50, 172, 45, 0.97)"],"decimals":0,"pattern":"Metric","thresholds":["0","0",".9"],"type":"string","unit":"none"},{"alias":"","colorMode":"row","colors":["rgba(245, 54, 54, 0.9)","rgba(237, 129, 40, 0.89)","rgba(50, 172, 45, 0.97)"],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":0,"link":false,"pattern":"Value","thresholds":["0","1"],"type":"number","unit":"none"}],"targets":[{"expr":"kube_deployment_status_replicas{namespace=~\".*\"}","format":"time_series","instant":true,"interval":"","intervalFactor":1,"legendFormat":"{{ deployment }}","refId":"A"}],"title":"Deployment Replicas - Up To Date","transform":"timeseries_to_rows","type":"table"},{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["#299c46","rgba(237, 129, 40, 0.89)","#d44a3a"],"datasource":"${DS_PROMETHEUS}","format":"none","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{"h":5,"w":6,"x":6,"y":20},"id":2018,"interval":null,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":false},"tableColumn":"","targets":[{"expr":"sum(kube_deployment_status_replicas{namespace=~\".*\"})","format":"time_series","intervalFactor":1,"refId":"A"}],"thresholds":"","title":"Deployment Replicas","type":"singlestat","valueFontSize":"80%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"avg"},{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["#299c46","rgba(237, 129, 40, 0.89)","#d44a3a"],"datasource":"${DS_PROMETHEUS}","format":"none","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{"h":5,"w":6,"x":12,"y":20},"id":2019,"interval":null,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":false},"tableColumn":"","targets":[{"expr":"sum(kube_deployment_status_replicas_updated{namespace=~\".*\"})","format":"time_series","intervalFactor":1,"refId":"A"}],"thresholds":"","title":"Deployment Replicas - Updated","type":"singlestat","valueFontSize":"80%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"avg"},{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["#299c46","rgba(237, 129, 40, 0.89)","#d44a3a"],"datasource":"${DS_PROMETHEUS}","format":"none","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{"h":5,"w":6,"x":18,"y":20},"id":2020,"interval":null,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":false},"tableColumn":"","targets":[{"expr":"sum(kube_deployment_status_replicas_unavailable{namespace=~\".*\"})","format":"time_series","intervalFactor":1,"refId":"A"}],"thresholds":"","title":"Deployment Replicas - Unavailable","type":"singlestat","valueFontSize":"80%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"avg"},{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":25},"id":2045,"panels":[],"title":"Jobs","type":"row"},{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["#299c46","rgba(237, 129, 40, 0.89)","#d44a3a"],"datasource":"${DS_PROMETHEUS}","format":"none","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{"h":3,"w":8,"x":0,"y":26},"id":2047,"interval":null,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":true},"tableColumn":"","targets":[{"expr":"sum(kube_job_status_succeeded{namespace=~\".*\"})","format":"time_series","intervalFactor":1,"refId":"A"}],"thresholds":"","title":"Jobs Succeeded","type":"singlestat","valueFontSize":"80%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"current"},{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["#299c46","rgba(237, 129, 40, 0.89)","#d44a3a"],"datasource":"${DS_PROMETHEUS}","format":"none","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{"h":3,"w":8,"x":8,"y":26},"id":2048,"interval":null,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":true},"tableColumn":"","targets":[{"expr":"sum(kube_job_status_active{namespace=~\".*\"})","format":"time_series","intervalFactor":1,"refId":"A"}],"thresholds":"","title":"Jobs Succeeded","type":"singlestat","valueFontSize":"80%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"current"},{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["#299c46","rgba(237, 129, 40, 0.89)","#d44a3a"],"datasource":"${DS_PROMETHEUS}","format":"none","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{"h":3,"w":8,"x":16,"y":26},"id":2049,"interval":null,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":true},"tableColumn":"","targets":[{"expr":"sum(kube_job_status_failed{namespace=~\".*\"})","format":"time_series","intervalFactor":1,"refId":"A"}],"thresholds":"","title":"Jobs Failed","type":"singlestat","valueFontSize":"80%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"current"},{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":29},"id":2028,"panels":[],"title":"Pods","type":"row"},{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["#299c46","rgba(237, 129, 40, 0.89)","#d44a3a"],"datasource":"${DS_PROMETHEUS}","format":"none","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{"h":3,"w":12,"x":0,"y":30},"id":2030,"interval":null,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(78, 203, 42, 0.28)","full":false,"lineColor":"#629e51","show":true},"tableColumn":"","targets":[{"expr":"sum(kube_pod_status_phase{namespace=~\".*\", phase=\"Running\"})","format":"time_series","interval":"","intervalFactor":1,"refId":"A"}],"thresholds":"","title":"Pods Running","type":"singlestat","valueFontSize":"80%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"current"},{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["#299c46","rgba(237, 129, 40, 0.89)","#d44a3a"],"datasource":"${DS_PROMETHEUS}","format":"none","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{"h":3,"w":12,"x":12,"y":30},"id":2031,"interval":null,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(78, 203, 42, 0.28)","full":false,"lineColor":"#629e51","show":true},"tableColumn":"","targets":[{"expr":"sum(kube_pod_status_phase{namespace=~\".*\", phase=\"Pending\"})","format":"time_series","interval":"","intervalFactor":1,"refId":"A"}],"thresholds":"","title":"Pods Pending","type":"singlestat","valueFontSize":"80%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"current"},{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["#299c46","rgba(237, 129, 40, 0.89)","#d44a3a"],"datasource":"${DS_PROMETHEUS}","format":"none","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{"h":3,"w":8,"x":0,"y":33},"id":2032,"interval":null,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(78, 203, 42, 0.28)","full":false,"lineColor":"#629e51","show":true},"tableColumn":"","targets":[{"expr":"sum(kube_pod_status_phase{namespace=~\".*\", phase=\"Failed\"})","format":"time_series","interval":"","intervalFactor":1,"refId":"A"}],"thresholds":"","title":"Pods Failed","type":"singlestat","valueFontSize":"80%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"current"},{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["#299c46","rgba(237, 129, 40, 0.89)","#d44a3a"],"datasource":"${DS_PROMETHEUS}","format":"none","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{"h":3,"w":8,"x":8,"y":33},"id":2033,"interval":null,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(78, 203, 42, 0.28)","full":false,"lineColor":"#629e51","show":true},"tableColumn":"","targets":[{"expr":"sum(kube_pod_status_phase{namespace=~\".*\", phase=\"Succeeded\"})","format":"time_series","interval":"","intervalFactor":1,"refId":"A"}],"thresholds":"","title":"Pods Succeeded","type":"singlestat","valueFontSize":"80%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"current"},{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["#299c46","rgba(237, 129, 40, 0.89)","#d44a3a"],"datasource":"${DS_PROMETHEUS}","format":"none","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{"h":3,"w":8,"x":16,"y":33},"id":2034,"interval":null,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(78, 203, 42, 0.28)","full":false,"lineColor":"#629e51","show":true},"tableColumn":"","targets":[{"expr":"sum(kube_pod_status_phase{namespace=~\".*\", phase=\"Unknown\"})","format":"time_series","interval":"","intervalFactor":1,"refId":"A"}],"thresholds":"","title":"Pods Unknown","type":"singlestat","valueFontSize":"80%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"current"},{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":36},"id":2036,"panels":[],"title":"Containers","type":"row"},{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["#299c46","rgba(237, 129, 40, 0.89)","#d44a3a"],"datasource":"${DS_PROMETHEUS}","format":"none","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{"h":3,"w":6,"x":0,"y":37},"id":2038,"interval":null,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":true},"tableColumn":"","targets":[{"expr":"sum(kube_pod_container_status_running{namespace=~\".*\"})","format":"time_series","intervalFactor":1,"refId":"A"}],"thresholds":"","title":"Containers Running","type":"singlestat","valueFontSize":"80%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"current"},{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["#299c46","rgba(237, 129, 40, 0.89)","#d44a3a"],"datasource":"${DS_PROMETHEUS}","format":"none","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{"h":3,"w":6,"x":6,"y":37},"id":2039,"interval":null,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":true},"tableColumn":"","targets":[{"expr":"sum(kube_pod_container_status_waiting{namespace=~\".*\"})","format":"time_series","intervalFactor":1,"refId":"A"}],"thresholds":"","title":"Containers Waiting","type":"singlestat","valueFontSize":"80%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"current"},{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["#299c46","rgba(237, 129, 40, 0.89)","#d44a3a"],"datasource":"${DS_PROMETHEUS}","format":"none","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{"h":3,"w":6,"x":12,"y":37},"id":2040,"interval":null,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":true},"tableColumn":"","targets":[{"expr":"sum(kube_pod_container_status_terminated{namespace=~\".*\"})","format":"time_series","intervalFactor":1,"refId":"A"}],"thresholds":"","title":"Containers Terminated","type":"singlestat","valueFontSize":"80%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"current"},{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["#299c46","rgba(237, 129, 40, 0.89)","#d44a3a"],"datasource":"${DS_PROMETHEUS}","format":"none","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{"h":3,"w":6,"x":18,"y":37},"id":2041,"interval":null,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":true},"tableColumn":"","targets":[{"expr":"sum(delta(kube_pod_container_status_restarts{namespace=\"kube-system\"}[30m]))","format":"time_series","intervalFactor":1,"refId":"A"}],"thresholds":"","title":"Containers Restarts (Last 30 Minutes)","type":"singlestat","valueFontSize":"80%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"current"},{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["#299c46","rgba(237, 129, 40, 0.89)","#d44a3a"],"datasource":"${DS_PROMETHEUS}","format":"none","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{"h":3,"w":12,"x":0,"y":40},"id":2043,"interval":null,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":true},"tableColumn":"","targets":[{"expr":"sum(kube_pod_container_resource_requests_cpu_cores{namespace=~\".*\", node=~\"$Node\"})","format":"time_series","intervalFactor":1,"refId":"A"}],"thresholds":"","title":"CPU Cores Requested by Containers","type":"singlestat","valueFontSize":"80%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"current"},{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["#299c46","rgba(237, 129, 40, 0.89)","#d44a3a"],"datasource":"${DS_PROMETHEUS}","format":"decbytes","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{"h":3,"w":12,"x":12,"y":40},"id":2042,"interval":null,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":true},"tableColumn":"","targets":[{"expr":"sum(kube_pod_container_resource_requests_memory_bytes{namespace=~\".*\", node=~\"$Node\"})","format":"time_series","intervalFactor":1,"refId":"A"}],"thresholds":"","title":"Memory Requested By Containers","type":"singlestat","valueFontSize":"80%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"current"},{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":43},"id":33,"panels":[],"title":"Network I/O pressure","type":"row"},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"${DS_PROMETHEUS}","decimals":2,"editable":true,"error":false,"fill":1,"grid":{},"gridPos":{"h":5,"w":24,"x":0,"y":44},"height":"200px","id":32,"isNew":true,"legend":{"alignAsTable":false,"avg":true,"current":true,"max":false,"min":false,"rightSide":false,"show":false,"sideWidth":200,"sort":"current","sortDesc":true,"total":false,"values":true},"lines":true,"linewidth":2,"links":[],"nullPointMode":"connected","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum (rate (container_network_receive_bytes_total{kubernetes_io_hostname=~\"^$Node$\"}[2m]))","format":"time_series","interval":"10s","intervalFactor":1,"legendFormat":"Received","metric":"network","refId":"A","step":10},{"expr":"- sum (rate (container_network_transmit_bytes_total{kubernetes_io_hostname=~\"^$Node$\"}[2m]))","format":"time_series","interval":"10s","intervalFactor":1,"legendFormat":"Sent","metric":"network","refId":"B","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Network I/O pressure","tooltip":{"msResolution":false,"shared":true,"sort":0,"value_type":"cumulative"},"transparent":false,"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"Bps","label":null,"logBase":1,"max":null,"min":null,"show":false}],"yaxis":{"align":false,"alignLevel":null}},{"collapsed":true,"gridPos":{"h":1,"w":24,"x":0,"y":49},"id":35,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"${DS_PROMETHEUS}","decimals":3,"editable":true,"error":false,"fill":0,"grid":{},"gridPos":{"h":7,"w":24,"x":0,"y":44},"height":"","id":17,"isNew":true,"legend":{"alignAsTable":true,"avg":true,"current":true,"max":false,"min":false,"rightSide":true,"show":true,"sort":"current","sortDesc":true,"total":false,"values":true},"lines":true,"linewidth":2,"links":[],"nullPointMode":"connected","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":true,"targets":[{"expr":"sum (rate (container_cpu_usage_seconds_total{image!=\"\",name=~\"^k8s_.*\",kubernetes_io_hostname=~\"^$Node$\"}[2m])) by (pod_name)","interval":"10s","intervalFactor":1,"legendFormat":"{{ pod_name }}","metric":"container_cpu","refId":"A","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Pods CPU usage (2m avg)","tooltip":{"msResolution":true,"shared":true,"sort":2,"value_type":"cumulative"},"transparent":false,"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"none","label":"cores","logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"title":"Pods CPU usage","type":"row"},{"collapsed":true,"gridPos":{"h":1,"w":24,"x":0,"y":50},"id":36,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"${DS_PROMETHEUS}","decimals":3,"editable":true,"error":false,"fill":0,"grid":{},"gridPos":{"h":7,"w":24,"x":0,"y":45},"height":"","id":23,"isNew":true,"legend":{"alignAsTable":true,"avg":true,"current":true,"max":false,"min":false,"rightSide":true,"show":true,"sort":"current","sortDesc":true,"total":false,"values":true},"lines":true,"linewidth":2,"links":[],"nullPointMode":"connected","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":true,"targets":[{"expr":"sum (rate (container_cpu_usage_seconds_total{systemd_service_name!=\"\",kubernetes_io_hostname=~\"^$Node$\"}[2m])) by (systemd_service_name)","hide":false,"interval":"10s","intervalFactor":1,"legendFormat":"{{ systemd_service_name }}","metric":"container_cpu","refId":"A","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"System services CPU usage (2m avg)","tooltip":{"msResolution":true,"shared":true,"sort":2,"value_type":"cumulative"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"none","label":"cores","logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"title":"System services CPU usage","type":"row"},{"collapsed":true,"gridPos":{"h":1,"w":24,"x":0,"y":51},"id":37,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"${DS_PROMETHEUS}","decimals":3,"editable":true,"error":false,"fill":0,"grid":{},"gridPos":{"h":7,"w":24,"x":0,"y":10},"height":"","id":24,"isNew":true,"legend":{"alignAsTable":true,"avg":true,"current":true,"hideEmpty":false,"hideZero":false,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"sort":"current","sortDesc":true,"total":false,"values":true},"lines":true,"linewidth":2,"links":[],"nullPointMode":"connected","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":true,"targets":[{"expr":"sum (rate (container_cpu_usage_seconds_total{image!=\"\",name=~\"^k8s_.*\",container_name!=\"POD\",kubernetes_io_hostname=~\"^$Node$\"}[2m])) by (container_name, pod_name)","hide":false,"interval":"10s","intervalFactor":1,"legendFormat":"pod: {{ pod_name }} | {{ container_name }}","metric":"container_cpu","refId":"A","step":10},{"expr":"sum (rate (container_cpu_usage_seconds_total{image!=\"\",name!~\"^k8s_.*\",kubernetes_io_hostname=~\"^$Node$\"}[2m])) by (kubernetes_io_hostname, name, image)","hide":false,"interval":"10s","intervalFactor":1,"legendFormat":"docker: {{ kubernetes_io_hostname }} | {{ image }} ({{ name }})","metric":"container_cpu","refId":"B","step":10},{"expr":"sum (rate (container_cpu_usage_seconds_total{rkt_container_name!=\"\",kubernetes_io_hostname=~\"^$Node$\"}[2m])) by (kubernetes_io_hostname, rkt_container_name)","interval":"10s","intervalFactor":1,"legendFormat":"rkt: {{ kubernetes_io_hostname }} | {{ rkt_container_name }}","metric":"container_cpu","refId":"C","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Containers CPU usage (2m avg)","tooltip":{"msResolution":true,"shared":true,"sort":2,"value_type":"cumulative"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"none","label":"cores","logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"title":"Containers CPU usage","type":"row"},{"collapsed":true,"gridPos":{"h":1,"w":24,"x":0,"y":52},"id":38,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"${DS_PROMETHEUS}","decimals":3,"editable":true,"error":false,"fill":0,"grid":{},"gridPos":{"h":13,"w":24,"x":0,"y":11},"id":20,"isNew":true,"legend":{"alignAsTable":true,"avg":true,"current":true,"max":false,"min":false,"rightSide":false,"show":true,"sort":"current","sortDesc":true,"total":false,"values":true},"lines":true,"linewidth":2,"links":[],"nullPointMode":"connected","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":true,"targets":[{"expr":"sum (rate (container_cpu_usage_seconds_total{id!=\"/\",kubernetes_io_hostname=~\"^$Node$\"}[2m])) by (id)","hide":false,"interval":"10s","intervalFactor":1,"legendFormat":"{{ id }}","metric":"container_cpu","refId":"A","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"All processes CPU usage (2m avg)","tooltip":{"msResolution":true,"shared":true,"sort":2,"value_type":"cumulative"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"none","label":"cores","logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"title":"All processes CPU usage","type":"row"},{"collapsed":true,"gridPos":{"h":1,"w":24,"x":0,"y":53},"id":39,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"${DS_PROMETHEUS}","decimals":2,"editable":true,"error":false,"fill":0,"grid":{},"gridPos":{"h":7,"w":24,"x":0,"y":15},"id":25,"isNew":true,"legend":{"alignAsTable":true,"avg":true,"current":true,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":200,"sort":"current","sortDesc":true,"total":false,"values":true},"lines":true,"linewidth":2,"links":[],"nullPointMode":"connected","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":true,"targets":[{"expr":"sum (container_memory_working_set_bytes{image!=\"\",name=~\"^k8s_.*\",kubernetes_io_hostname=~\"^$Node$\"}) by (pod_name)","interval":"10s","intervalFactor":1,"legendFormat":"{{ pod_name }}","metric":"container_memory_usage:sort_desc","refId":"A","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Pods memory usage","tooltip":{"msResolution":false,"shared":true,"sort":2,"value_type":"cumulative"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"bytes","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"title":"Pods memory usage","type":"row"},{"collapsed":true,"gridPos":{"h":1,"w":24,"x":0,"y":54},"id":40,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"${DS_PROMETHEUS}","decimals":2,"editable":true,"error":false,"fill":0,"grid":{},"gridPos":{"h":7,"w":24,"x":0,"y":13},"id":26,"isNew":true,"legend":{"alignAsTable":true,"avg":true,"current":true,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":200,"sort":"current","sortDesc":true,"total":false,"values":true},"lines":true,"linewidth":2,"links":[],"nullPointMode":"connected","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":true,"targets":[{"expr":"sum (container_memory_working_set_bytes{systemd_service_name!=\"\",kubernetes_io_hostname=~\"^$Node$\"}) by (systemd_service_name)","interval":"10s","intervalFactor":1,"legendFormat":"{{ systemd_service_name }}","metric":"container_memory_usage:sort_desc","refId":"A","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"System services memory usage","tooltip":{"msResolution":false,"shared":true,"sort":2,"value_type":"cumulative"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"bytes","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"title":"System services memory usage","type":"row"},{"collapsed":true,"gridPos":{"h":1,"w":24,"x":0,"y":55},"id":41,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"${DS_PROMETHEUS}","decimals":2,"editable":true,"error":false,"fill":0,"grid":{},"gridPos":{"h":7,"w":24,"x":0,"y":14},"id":27,"isNew":true,"legend":{"alignAsTable":true,"avg":true,"current":true,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":200,"sort":"current","sortDesc":true,"total":false,"values":true},"lines":true,"linewidth":2,"links":[],"nullPointMode":"connected","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":true,"targets":[{"expr":"sum (container_memory_working_set_bytes{image!=\"\",name=~\"^k8s_.*\",container_name!=\"POD\",kubernetes_io_hostname=~\"^$Node$\"}) by (container_name, pod_name)","interval":"10s","intervalFactor":1,"legendFormat":"pod: {{ pod_name }} | {{ container_name }}","metric":"container_memory_usage:sort_desc","refId":"A","step":10},{"expr":"sum (container_memory_working_set_bytes{image!=\"\",name!~\"^k8s_.*\",kubernetes_io_hostname=~\"^$Node$\"}) by (kubernetes_io_hostname, name, image)","interval":"10s","intervalFactor":1,"legendFormat":"docker: {{ kubernetes_io_hostname }} | {{ image }} ({{ name }})","metric":"container_memory_usage:sort_desc","refId":"B","step":10},{"expr":"sum (container_memory_working_set_bytes{rkt_container_name!=\"\",kubernetes_io_hostname=~\"^$Node$\"}) by (kubernetes_io_hostname, rkt_container_name)","interval":"10s","intervalFactor":1,"legendFormat":"rkt: {{ kubernetes_io_hostname }} | {{ rkt_container_name }}","metric":"container_memory_usage:sort_desc","refId":"C","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Containers memory usage","tooltip":{"msResolution":false,"shared":true,"sort":2,"value_type":"cumulative"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"bytes","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"title":"Containers memory usage","type":"row"},{"collapsed":true,"gridPos":{"h":1,"w":24,"x":0,"y":56},"id":42,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"${DS_PROMETHEUS}","decimals":2,"editable":true,"error":false,"fill":0,"grid":{},"gridPos":{"h":13,"w":24,"x":0,"y":15},"id":28,"isNew":true,"legend":{"alignAsTable":true,"avg":true,"current":true,"max":false,"min":false,"rightSide":false,"show":true,"sideWidth":200,"sort":"current","sortDesc":true,"total":false,"values":true},"lines":true,"linewidth":2,"links":[],"nullPointMode":"connected","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":true,"targets":[{"expr":"sum (container_memory_working_set_bytes{id!=\"/\",kubernetes_io_hostname=~\"^$Node$\"}) by (id)","interval":"10s","intervalFactor":1,"legendFormat":"{{ id }}","metric":"container_memory_usage:sort_desc","refId":"A","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"All processes memory usage","tooltip":{"msResolution":false,"shared":true,"sort":2,"value_type":"cumulative"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"bytes","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"title":"All processes memory usage","type":"row"},{"collapsed":true,"gridPos":{"h":1,"w":24,"x":0,"y":57},"id":43,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"${DS_PROMETHEUS}","decimals":2,"editable":true,"error":false,"fill":1,"grid":{},"gridPos":{"h":7,"w":24,"x":0,"y":16},"id":16,"isNew":true,"legend":{"alignAsTable":true,"avg":true,"current":true,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":200,"sort":"current","sortDesc":true,"total":false,"values":true},"lines":true,"linewidth":2,"links":[],"nullPointMode":"connected","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum (rate (container_network_receive_bytes_total{image!=\"\",name=~\"^k8s_.*\",kubernetes_io_hostname=~\"^$Node$\"}[2m])) by (pod_name)","interval":"10s","intervalFactor":1,"legendFormat":"-> {{ pod_name }}","metric":"network","refId":"A","step":10},{"expr":"- sum (rate (container_network_transmit_bytes_total{image!=\"\",name=~\"^k8s_.*\",kubernetes_io_hostname=~\"^$Node$\"}[2m])) by (pod_name)","interval":"10s","intervalFactor":1,"legendFormat":"<- {{ pod_name }}","metric":"network","refId":"B","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Pods network I/O (2m avg)","tooltip":{"msResolution":false,"shared":true,"sort":2,"value_type":"cumulative"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"title":"Pods network I/O","type":"row"},{"collapsed":true,"gridPos":{"h":1,"w":24,"x":0,"y":58},"id":44,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"${DS_PROMETHEUS}","decimals":2,"editable":true,"error":false,"fill":1,"grid":{},"gridPos":{"h":7,"w":24,"x":0,"y":17},"id":30,"isNew":true,"legend":{"alignAsTable":true,"avg":true,"current":true,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":200,"sort":"current","sortDesc":true,"total":false,"values":true},"lines":true,"linewidth":2,"links":[],"nullPointMode":"connected","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum (rate (container_network_receive_bytes_total{image!=\"\",name=~\"^k8s_.*\",kubernetes_io_hostname=~\"^$Node$\"}[2m])) by (container_name, pod_name)","hide":false,"interval":"10s","intervalFactor":1,"legendFormat":"-> pod: {{ pod_name }} | {{ container_name }}","metric":"network","refId":"B","step":10},{"expr":"- sum (rate (container_network_transmit_bytes_total{image!=\"\",name=~\"^k8s_.*\",kubernetes_io_hostname=~\"^$Node$\"}[2m])) by (container_name, pod_name)","hide":false,"interval":"10s","intervalFactor":1,"legendFormat":"<- pod: {{ pod_name }} | {{ container_name }}","metric":"network","refId":"D","step":10},{"expr":"sum (rate (container_network_receive_bytes_total{image!=\"\",name!~\"^k8s_.*\",kubernetes_io_hostname=~\"^$Node$\"}[2m])) by (kubernetes_io_hostname, name, image)","hide":false,"interval":"10s","intervalFactor":1,"legendFormat":"-> docker: {{ kubernetes_io_hostname }} | {{ image }} ({{ name }})","metric":"network","refId":"A","step":10},{"expr":"- sum (rate (container_network_transmit_bytes_total{image!=\"\",name!~\"^k8s_.*\",kubernetes_io_hostname=~\"^$Node$\"}[2m])) by (kubernetes_io_hostname, name, image)","hide":false,"interval":"10s","intervalFactor":1,"legendFormat":"<- docker: {{ kubernetes_io_hostname }} | {{ image }} ({{ name }})","metric":"network","refId":"C","step":10},{"expr":"sum (rate (container_network_transmit_bytes_total{rkt_container_name!=\"\",kubernetes_io_hostname=~\"^$Node$\"}[2m])) by (kubernetes_io_hostname, rkt_container_name)","hide":false,"interval":"10s","intervalFactor":1,"legendFormat":"-> rkt: {{ kubernetes_io_hostname }} | {{ rkt_container_name }}","metric":"network","refId":"E","step":10},{"expr":"- sum (rate (container_network_transmit_bytes_total{rkt_container_name!=\"\",kubernetes_io_hostname=~\"^$Node$\"}[2m])) by (kubernetes_io_hostname, rkt_container_name)","hide":false,"interval":"10s","intervalFactor":1,"legendFormat":"<- rkt: {{ kubernetes_io_hostname }} | {{ rkt_container_name }}","metric":"network","refId":"F","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Containers network I/O (2m avg)","tooltip":{"msResolution":false,"shared":true,"sort":2,"value_type":"cumulative"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"title":"Containers network I/O","type":"row"},{"collapsed":true,"gridPos":{"h":1,"w":24,"x":0,"y":59},"id":45,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"${DS_PROMETHEUS}","decimals":2,"editable":true,"error":false,"fill":1,"grid":{},"gridPos":{"h":13,"w":24,"x":0,"y":18},"id":29,"isNew":true,"legend":{"alignAsTable":true,"avg":true,"current":true,"max":false,"min":false,"rightSide":false,"show":true,"sideWidth":200,"sort":"current","sortDesc":true,"total":false,"values":true},"lines":true,"linewidth":2,"links":[],"nullPointMode":"connected","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum (rate (container_network_receive_bytes_total{id!=\"/\",kubernetes_io_hostname=~\"^$Node$\"}[2m])) by (id)","interval":"10s","intervalFactor":1,"legendFormat":"-> {{ id }}","metric":"network","refId":"A","step":10},{"expr":"- sum (rate (container_network_transmit_bytes_total{id!=\"/\",kubernetes_io_hostname=~\"^$Node$\"}[2m])) by (id)","interval":"10s","intervalFactor":1,"legendFormat":"<- {{ id }}","metric":"network","refId":"B","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"All processes network I/O (2m avg)","tooltip":{"msResolution":false,"shared":true,"sort":2,"value_type":"cumulative"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"title":"All processes network I/O","type":"row"}],"refresh":"1m","schemaVersion":16,"style":"dark","tags":[],"templating":{"list":[{"allValue":".*","current":{},"datasource":"${DS_PROMETHEUS}","hide":0,"includeAll":true,"label":null,"multi":false,"name":"Node","options":[],"query":"label_values(kubernetes_io_hostname)","refresh":1,"regex":"","skipUrlSync":false,"sort":0,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false}]},"time":{"from":"now-30m","to":"now"},"timepicker":{"refresh_intervals":["5s","10s","30s","1m","5m","15m","30m","1h","2h","1d"],"time_options":["5m","15m","1h","6h","12h","24h","2d","7d","30d"]},"timezone":"browser","title":"Cluster","uid":"icjpCppik","version":1},"inputs":[{"name":"DS_PROMETHEUS","pluginId":"prometheus","type":"datasource","value":"Rancher-Monitoring"}],"overwrite":false}
\ No newline at end of file

charts/rancher-monitoring/v0.0.2/charts/grafana/dashboards/c_etcd-dashboard.json

+{"dashboard":{"__inputs":[{"name":"DS_PROMETHEUS","label":"Rancher-Monitoring","description":"","type":"datasource","pluginId":"prometheus","pluginName":"Prometheus"}],"__requires":[{"type":"grafana","id":"grafana","name":"Grafana","version":"5.3.0"},{"type":"panel","id":"graph","name":"Graph","version":"5.0.0"},{"type":"datasource","id":"prometheus","name":"Prometheus","version":"5.0.0"},{"type":"panel","id":"singlestat","name":"Singlestat","version":"5.0.0"}],"annotations":{"list":[{"builtIn":1,"datasource":"-- Grafana --","enable":true,"hide":true,"iconColor":"rgba(0, 211, 255, 1)","name":"Annotations & Alerts","type":"dashboard"}]},"description":"Etcd Dashboard for Prometheus metrics scraper","editable":true,"gnetId":3070,"graphTooltip":0,"id":null,"links":[],"panels":[{"cacheTimeout":null,"colorBackground":false,"colorValue":true,"colors":["rgba(245, 54, 54, 0.9)","rgba(237, 129, 40, 0.89)","rgba(50, 172, 45, 0.97)"],"datasource":"${DS_PROMETHEUS}","format":"none","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{"h":7,"w":8,"x":0,"y":0},"id":44,"interval":null,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":false},"tableColumn":"","targets":[{"expr":"max(etcd_server_has_leader)","format":"time_series","intervalFactor":2,"refId":"A","step":600}],"thresholds":"0,1","title":"Etcd has a leader?","type":"singlestat","valueFontSize":"80%","valueMaps":[{"op":"=","text":"YES","value":"1"},{"op":"=","text":"NO","value":"0"}],"valueName":"avg"},{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["rgba(245, 54, 54, 0.9)","rgba(237, 129, 40, 0.89)","rgba(50, 172, 45, 0.97)"],"datasource":"${DS_PROMETHEUS}","format":"none","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{"h":7,"w":8,"x":8,"y":0},"id":42,"interval":null,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":false},"tableColumn":"","targets":[{"expr":"max(etcd_server_leader_changes_seen_total)","format":"time_series","intervalFactor":2,"refId":"A","step":600}],"thresholds":"","title":"The number of leader changes seen","type":"singlestat","valueFontSize":"80%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"avg"},{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["rgba(245, 54, 54, 0.9)","rgba(237, 129, 40, 0.89)","rgba(50, 172, 45, 0.97)"],"datasource":"${DS_PROMETHEUS}","format":"none","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{"h":7,"w":8,"x":16,"y":0},"id":43,"interval":null,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":false},"tableColumn":"","targets":[{"expr":"max(etcd_server_leader_changes_seen_total)","format":"time_series","intervalFactor":2,"refId":"A","step":600}],"thresholds":"","title":"The total number of failed proposals seen","type":"singlestat","valueFontSize":"80%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"avg"},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"${DS_PROMETHEUS}","editable":true,"error":false,"fill":0,"gridPos":{"h":7,"w":12,"x":0,"y":7},"id":23,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":false,"total":false,"values":false},"lines":true,"linewidth":2,"links":[],"nullPointMode":"connected","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(grpc_server_started_total{grpc_type=\"unary\"}[5m]))","format":"time_series","intervalFactor":2,"legendFormat":"RPC Rate","metric":"grpc_server_started_total","refId":"A","step":60},{"expr":"sum(rate(grpc_server_handled_total{grpc_type=\"unary\",grpc_code!=\"OK\"}[5m]))","format":"time_series","intervalFactor":2,"legendFormat":"RPC Failed Rate","metric":"grpc_server_handled_total","refId":"B","step":60}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"RPC Rate","tooltip":{"msResolution":false,"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"ops","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"${DS_PROMETHEUS}","editable":true,"error":false,"fill":0,"gridPos":{"h":7,"w":12,"x":12,"y":7},"id":41,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":false,"total":false,"values":false},"lines":true,"linewidth":2,"links":[],"nullPointMode":"connected","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":true,"steppedLine":false,"targets":[{"expr":"sum(grpc_server_started_total{grpc_service=\"etcdserverpb.Watch\",grpc_type=\"bidi_stream\"}) - sum(grpc_server_handled_total{grpc_service=\"etcdserverpb.Watch\",grpc_type=\"bidi_stream\"})","format":"time_series","intervalFactor":2,"legendFormat":"Watch Streams","metric":"grpc_server_handled_total","refId":"A","step":60},{"expr":"sum(grpc_server_started_total{grpc_service=\"etcdserverpb.Lease\",grpc_type=\"bidi_stream\"}) - sum(grpc_server_handled_total{grpc_service=\"etcdserverpb.Lease\",grpc_type=\"bidi_stream\"})","format":"time_series","intervalFactor":2,"legendFormat":"Lease Streams","metric":"grpc_server_handled_total","refId":"B","step":60}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Active Streams","tooltip":{"msResolution":false,"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":"","logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"${DS_PROMETHEUS}","decimals":null,"editable":true,"error":false,"fill":0,"grid":{},"gridPos":{"h":7,"w":8,"x":0,"y":14},"id":1,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":false,"total":false,"values":false},"lines":true,"linewidth":2,"links":[],"nullPointMode":"connected","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"etcd_debugging_mvcc_db_total_size_in_bytes","format":"time_series","hide":false,"interval":"","intervalFactor":2,"legendFormat":"{{instance}} DB Size","metric":"","refId":"A","step":120}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"DB Size","tooltip":{"msResolution":false,"shared":true,"sort":0,"value_type":"cumulative"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"bytes","logBase":1,"max":null,"min":null,"show":true},{"format":"short","logBase":1,"max":null,"min":null,"show":false}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"${DS_PROMETHEUS}","editable":true,"error":false,"fill":0,"grid":{},"gridPos":{"h":7,"w":8,"x":8,"y":14},"id":3,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":false,"total":false,"values":false},"lines":true,"linewidth":2,"links":[],"nullPointMode":"connected","percentage":false,"pointradius":1,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":true,"targets":[{"expr":"histogram_quantile(0.99, sum(rate(etcd_disk_wal_fsync_duration_seconds_bucket[5m])) by (instance, le))","format":"time_series","hide":false,"intervalFactor":2,"legendFormat":"{{instance}} WAL fsync","metric":"etcd_disk_wal_fsync_duration_seconds_bucket","refId":"A","step":120},{"expr":"histogram_quantile(0.99, sum(rate(etcd_disk_backend_commit_duration_seconds_bucket[5m])) by (instance, le))","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}} DB fsync","metric":"etcd_disk_backend_commit_duration_seconds_bucket","refId":"B","step":120}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Disk Sync Duration","tooltip":{"msResolution":false,"shared":true,"sort":0,"value_type":"cumulative"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"s","logBase":1,"max":null,"min":null,"show":true},{"format":"short","logBase":1,"max":null,"min":null,"show":false}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"${DS_PROMETHEUS}","editable":true,"error":false,"fill":0,"gridPos":{"h":7,"w":8,"x":16,"y":14},"id":29,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":false,"total":false,"values":false},"lines":true,"linewidth":2,"links":[],"nullPointMode":"connected","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"process_resident_memory_bytes","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}} Resident Memory","metric":"process_resident_memory_bytes","refId":"A","step":120}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Memory","tooltip":{"msResolution":false,"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"bytes","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"${DS_PROMETHEUS}","editable":true,"error":false,"fill":5,"gridPos":{"h":7,"w":6,"x":0,"y":21},"id":22,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":false,"total":false,"values":false},"lines":true,"linewidth":2,"links":[],"nullPointMode":"connected","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":true,"steppedLine":false,"targets":[{"expr":"rate(etcd_network_client_grpc_received_bytes_total[5m])","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}} Client Traffic In","metric":"etcd_network_client_grpc_received_bytes_total","refId":"A","step":120}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Client Traffic In","tooltip":{"msResolution":false,"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"${DS_PROMETHEUS}","editable":true,"error":false,"fill":5,"gridPos":{"h":7,"w":6,"x":6,"y":21},"id":21,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":false,"total":false,"values":false},"lines":true,"linewidth":2,"links":[],"nullPointMode":"connected","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":true,"steppedLine":false,"targets":[{"expr":"rate(etcd_network_client_grpc_sent_bytes_total[5m])","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}} Client Traffic Out","metric":"etcd_network_client_grpc_sent_bytes_total","refId":"A","step":120}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Client Traffic Out","tooltip":{"msResolution":false,"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"${DS_PROMETHEUS}","editable":true,"error":false,"fill":0,"gridPos":{"h":7,"w":6,"x":12,"y":21},"id":20,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":false,"total":false,"values":false},"lines":true,"linewidth":2,"links":[],"nullPointMode":"connected","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(etcd_network_peer_received_bytes_total[5m])) by (instance)","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}} Peer Traffic In","metric":"etcd_network_peer_received_bytes_total","refId":"A","step":120}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Peer Traffic In","tooltip":{"msResolution":false,"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"${DS_PROMETHEUS}","decimals":null,"editable":true,"error":false,"fill":0,"grid":{},"gridPos":{"h":7,"w":6,"x":18,"y":21},"id":16,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":false,"total":false,"values":false},"lines":true,"linewidth":2,"links":[],"nullPointMode":"connected","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(etcd_network_peer_sent_bytes_total[5m])) by (instance)","format":"time_series","hide":false,"interval":"","intervalFactor":2,"legendFormat":"{{instance}} Peer Traffic Out","metric":"etcd_network_peer_sent_bytes_total","refId":"A","step":120}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Peer Traffic Out","tooltip":{"msResolution":false,"shared":true,"sort":0,"value_type":"cumulative"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"Bps","logBase":1,"max":null,"min":null,"show":true},{"format":"short","logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"${DS_PROMETHEUS}","editable":true,"error":false,"fill":0,"gridPos":{"h":7,"w":12,"x":0,"y":28},"id":40,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":false,"total":false,"values":false},"lines":true,"linewidth":2,"links":[],"nullPointMode":"connected","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(etcd_server_proposals_failed_total[5m]))","format":"time_series","intervalFactor":2,"legendFormat":"Proposal Failure Rate","metric":"etcd_server_proposals_failed_total","refId":"A","step":60},{"expr":"sum(etcd_server_proposals_pending)","format":"time_series","intervalFactor":2,"legendFormat":"Proposal Pending Total","metric":"etcd_server_proposals_pending","refId":"B","step":60},{"expr":"sum(rate(etcd_server_proposals_committed_total[5m]))","format":"time_series","intervalFactor":2,"legendFormat":"Proposal Commit Rate","metric":"etcd_server_proposals_committed_total","refId":"C","step":60},{"expr":"sum(rate(etcd_server_proposals_applied_total[5m]))","format":"time_series","intervalFactor":2,"legendFormat":"Proposal Apply Rate","refId":"D","step":60}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Raft Proposals","tooltip":{"msResolution":false,"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":"","logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"${DS_PROMETHEUS}","decimals":0,"editable":true,"error":false,"fill":0,"gridPos":{"h":7,"w":12,"x":12,"y":28},"id":19,"legend":{"alignAsTable":false,"avg":false,"current":false,"max":false,"min":false,"rightSide":false,"show":false,"total":false,"values":false},"lines":true,"linewidth":2,"links":[],"nullPointMode":"connected","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"changes(etcd_server_leader_changes_seen_total[1d])","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}} Total Leader Elections Per Day","metric":"etcd_server_leader_changes_seen_total","refId":"A","step":60}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Total Leader Elections Per Day","tooltip":{"msResolution":false,"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"${DS_PROMETHEUS}","description":"proposals_committed_total records the total number of consensus proposals committed. This gauge should increase over time if the cluster is healthy. Several healthy members of an etcd cluster may have different total committed proposals at once. This discrepancy may be due to recovering from peers after starting, lagging behind the leader, or being the leader and therefore having the most commits. It is important to monitor this metric across all the members in the cluster; a consistently large lag between a single member and its leader indicates that member is slow or unhealthy.\n\nproposals_applied_total records the total number of consensus proposals applied. The etcd server applies every committed proposal asynchronously. The difference between proposals_committed_total and proposals_applied_total should usually be small (within a few thousands even under high load). If the difference between them continues to rise, it indicates that the etcd server is overloaded. This might happen when applying expensive queries like heavy range queries or large txn operations.","fill":1,"gridPos":{"h":7,"w":12,"x":0,"y":35},"id":2,"legend":{"alignAsTable":true,"avg":true,"current":true,"max":true,"min":false,"rightSide":false,"show":true,"total":false,"values":true},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(etcd_server_proposals_committed_total[5m]))","format":"time_series","intervalFactor":2,"legendFormat":"total number of consensus proposals committed","metric":"","refId":"A","step":60},{"expr":"sum(rate(etcd_server_proposals_applied_total[5m]))","format":"time_series","intervalFactor":2,"legendFormat":"total number of consensus proposals applied","metric":"","refId":"B","step":60}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"The total number of consensus proposals committed","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":"","logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"${DS_PROMETHEUS}","description":"indicates how many proposals are queued to commit. Rising pending proposals suggests there is a high client load or the member cannot commit proposals.","fill":1,"gridPos":{"h":7,"w":12,"x":12,"y":35},"id":5,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(etcd_server_proposals_pending)","format":"time_series","intervalFactor":2,"legendFormat":"Proposals pending","refId":"A","step":60}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Proposals pending","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"${DS_PROMETHEUS}","fill":1,"gridPos":{"h":7,"w":24,"x":0,"y":42},"id":7,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(etcd_disk_wal_fsync_duration_seconds_sum[1m]))","format":"time_series","intervalFactor":2,"legendFormat":" The latency distributions of fsync called by wal","refId":"A","step":30},{"expr":"sum(rate(etcd_disk_backend_commit_duration_seconds_sum[1m]))","format":"time_series","intervalFactor":2,"legendFormat":"The latency distributions of commit called by backend","refId":"B","step":30}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Disks operations","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"${DS_PROMETHEUS}","fill":1,"gridPos":{"h":7,"w":24,"x":0,"y":49},"id":8,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(etcd_network_client_grpc_received_bytes_total[1m]))","format":"time_series","intervalFactor":2,"legendFormat":"The total number of bytes received by grpc clients","refId":"A","step":30},{"expr":"sum(rate(etcd_network_client_grpc_sent_bytes_total[1m]))","format":"time_series","intervalFactor":2,"legendFormat":"The total number of bytes sent to grpc clients","refId":"B","step":30}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Network","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"${DS_PROMETHEUS}","description":"Abnormally high snapshot duration (snapshot_save_total_duration_seconds) indicates disk issues and might cause the cluster to be unstable.","fill":1,"gridPos":{"h":7,"w":24,"x":0,"y":56},"id":9,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(etcd_debugging_snap_save_total_duration_seconds_sum[1m]))","format":"time_series","intervalFactor":2,"legendFormat":"The total latency distributions of save called by snapshot","refId":"A","step":30}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Snapshot duration","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}}],"schemaVersion":16,"style":"dark","tags":[],"templating":{"list":[]},"time":{"from":"now-6h","to":"now"},"timepicker":{"refresh_intervals":["5s","10s","30s","1m","5m","15m","30m","1h","2h","1d"],"time_options":["5m","15m","1h","6h","12h","24h","2d","7d","30d"]},"timezone":"browser","title":"Etcd","uid":"8naNKoYik","version":1},"inputs":[{"name":"DS_PROMETHEUS","pluginId":"prometheus","type":"datasource","value":"Rancher-Monitoring"}],"overwrite":false}
\ No newline at end of file

charts/rancher-monitoring/v0.0.2/charts/grafana/dashboards/c_kubernetes-components-dashboard.json

+{"dashboard":{"__inputs":[{"name":"DS_PROMETHEUS","label":"Rancher-Monitoring","description":"","type":"datasource","pluginId":"prometheus","pluginName":"Prometheus"}],"__requires":[{"type":"grafana","id":"grafana","name":"Grafana","version":"5.3.0"},{"type":"panel","id":"graph","name":"Graph","version":"5.0.0"},{"type":"datasource","id":"prometheus","name":"Prometheus","version":"5.0.0"}],"annotations":{"list":[{"builtIn":1,"datasource":"-- Grafana --","enable":true,"hide":true,"iconColor":"rgba(0, 211, 255, 1)","name":"Annotations & Alerts","type":"dashboard"}]},"description":"-","editable":true,"gnetId":5508,"graphTooltip":0,"id":null,"links":[],"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"${DS_PROMETHEUS}","editable":true,"error":false,"fill":1,"grid":{"threshold1Color":"rgba(216, 200, 27, 0.27)","threshold2Color":"rgba(234, 112, 112, 0.22)"},"gridPos":{"h":7,"w":12,"x":0,"y":0},"id":6,"isNew":false,"legend":{"alignAsTable":false,"avg":false,"current":false,"hideEmpty":false,"hideZero":false,"max":false,"min":false,"rightSide":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum by(instance) (rate(apiserver_request_count{code!~\"2..\"}[5m]))","format":"time_series","intervalFactor":2,"legendFormat":"Error Rate","refId":"A","step":60},{"expr":"sum by(instance) (rate(apiserver_request_count[5m]))","format":"time_series","intervalFactor":2,"legendFormat":"Request Rate","refId":"B","step":60}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"API Server Request Rates","tooltip":{"msResolution":false,"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","logBase":1,"show":true},{"format":"short","logBase":1,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"${DS_PROMETHEUS}","editable":true,"error":false,"fill":1,"grid":{"threshold1Color":"rgba(216, 200, 27, 0.27)","threshold2Color":"rgba(234, 112, 112, 0.22)"},"gridPos":{"h":7,"w":12,"x":12,"y":0},"id":7,"isNew":false,"legend":{"alignAsTable":false,"avg":false,"current":false,"hideEmpty":false,"hideZero":false,"max":false,"min":false,"rightSide":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum by(verb) (rate(apiserver_latency_seconds:quantile[5m]) >= 0)","format":"time_series","intervalFactor":2,"legendFormat":"","refId":"A","step":30}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"API Server Request Latency","tooltip":{"msResolution":false,"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","logBase":1,"show":true},{"format":"short","logBase":1,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"${DS_PROMETHEUS}","fill":1,"gridPos":{"h":9,"w":12,"x":0,"y":7},"id":11,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"rate(nginx_requests_total[1m])","format":"time_series","intervalFactor":1,"legendFormat":"Request Rate","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Nginx Ingress Request Rate","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"${DS_PROMETHEUS}","fill":1,"gridPos":{"h":9,"w":12,"x":12,"y":7},"id":9,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"service_depth","format":"time_series","intervalFactor":1,"legendFormat":"Service Depth","refId":"A"},{"expr":"volumes_depth","format":"time_series","intervalFactor":1,"legendFormat":"Volumes Depth","refId":"B"},{"expr":"replicationmanager_depth","format":"time_series","intervalFactor":1,"legendFormat":"Replication Manager Depth","refId":"C"},{"expr":"statefulset_depth","format":"time_series","intervalFactor":1,"legendFormat":"StatefulSet Depth","refId":"D"},{"expr":"serviceaccount_depth","format":"time_series","intervalFactor":1,"legendFormat":"Service Account Depth","refId":"E"},{"expr":"endpoint_depth","format":"time_series","intervalFactor":1,"legendFormat":"Endpoint Depth","refId":"F"},{"expr":"deployment_depth","format":"time_series","intervalFactor":1,"legendFormat":"Deployment Depth","refId":"G"},{"expr":"daemonset_depth","format":"time_series","intervalFactor":1,"legendFormat":"DaemonSet Depth","refId":"H"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Controller Manager Queue Depth","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}}],"refresh":false,"schemaVersion":16,"style":"dark","tags":[],"templating":{"list":[]},"time":{"from":"now-6h","to":"now"},"timepicker":{"refresh_intervals":["5s","10s","30s","1m","5m","15m","30m","1h","2h","1d"],"time_options":["5m","15m","1h","6h","12h","24h","2d","7d","30d"]},"timezone":"browser","title":"Kubernetes Components","uid":"Ld4acTYmz","version":1},"inputs":[{"name":"DS_PROMETHEUS","pluginId":"prometheus","type":"datasource","value":"Rancher-Monitoring"}],"overwrite":false}
\ No newline at end of file

charts/rancher-monitoring/v0.0.2/charts/grafana/dashboards/c_kubernetes-resource-requests-dashboard.json

+{"dashboard":{"__inputs":[{"name":"DS_PROMETHEUS","label":"Rancher-Monitoring","description":"","type":"datasource","pluginId":"prometheus","pluginName":"Prometheus"}],"__requires":[{"type":"grafana","id":"grafana","name":"Grafana","version":"5.3.0"},{"type":"panel","id":"graph","name":"Graph","version":"5.0.0"},{"type":"datasource","id":"prometheus","name":"Prometheus","version":"5.0.0"},{"type":"panel","id":"singlestat","name":"Singlestat","version":"5.0.0"}],"annotations":{"list":[{"builtIn":1,"datasource":"-- Grafana --","enable":true,"hide":true,"iconColor":"rgba(0, 211, 255, 1)","name":"Annotations & Alerts","type":"dashboard"}]},"editable":true,"gnetId":null,"graphTooltip":0,"id":null,"links":[],"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"${DS_PROMETHEUS}","description":"This represents the total [CPU resource requests](https://kubernetes.io/docs/concepts/configuration/manage-compute-resources-container/#meaning-of-cpu) in the cluster.\nFor comparison the total [allocatable CPU cores](https://github.com/kubernetes/community/blob/master/contributors/design-proposals/node-allocatable.md) is also shown.","editable":true,"error":false,"fill":1,"grid":{"threshold1Color":"rgba(216, 200, 27, 0.27)","threshold2Color":"rgba(234, 112, 112, 0.22)"},"gridPos":{"h":8,"w":18,"x":0,"y":0},"id":1,"isNew":false,"legend":{"alignAsTable":false,"avg":false,"current":false,"hideEmpty":false,"hideZero":false,"max":false,"min":false,"rightSide":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"min(sum(kube_node_status_allocatable_cpu_cores) by (instance))","hide":false,"intervalFactor":2,"legendFormat":"Allocatable CPU Cores","refId":"A","step":20},{"expr":"max(sum(kube_pod_container_resource_requests_cpu_cores) by (instance))","hide":false,"intervalFactor":2,"legendFormat":"Requested CPU Cores","refId":"B","step":20}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"CPU Cores","tooltip":{"msResolution":false,"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":"CPU Cores","logBase":1,"show":true},{"format":"short","logBase":1,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["rgba(50, 172, 45, 0.97)","rgba(237, 129, 40, 0.89)","rgba(245, 54, 54, 0.9)"],"datasource":"${DS_PROMETHEUS}","editable":true,"format":"percent","gauge":{"maxValue":100,"minValue":0,"show":true,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{"h":8,"w":6,"x":18,"y":0},"hideTimeOverride":false,"id":2,"interval":null,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":true},"tableColumn":"","targets":[{"expr":"max(sum(kube_pod_container_resource_requests_cpu_cores) by (instance)) / min(sum(kube_node_status_allocatable_cpu_cores) by (instance)) * 100","intervalFactor":2,"legendFormat":"","refId":"A","step":240}],"thresholds":"80, 90","title":"CPU Cores","transparent":false,"type":"singlestat","valueFontSize":"110%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"avg"},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"${DS_PROMETHEUS}","description":"This represents the total [memory resource requests](https://kubernetes.io/docs/concepts/configuration/manage-compute-resources-container/#meaning-of-memory) in the cluster.\nFor comparison the total [allocatable memory](https://github.com/kubernetes/community/blob/master/contributors/design-proposals/node-allocatable.md) is also shown.","editable":true,"error":false,"fill":1,"grid":{"threshold1Color":"rgba(216, 200, 27, 0.27)","threshold2Color":"rgba(234, 112, 112, 0.22)"},"gridPos":{"h":8,"w":18,"x":0,"y":8},"id":3,"isNew":false,"legend":{"alignAsTable":false,"avg":false,"current":false,"hideEmpty":false,"hideZero":false,"max":false,"min":false,"rightSide":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"min(sum(kube_node_status_allocatable_memory_bytes) by (instance))","hide":false,"intervalFactor":2,"legendFormat":"Allocatable Memory","refId":"A","step":20},{"expr":"max(sum(kube_pod_container_resource_requests_memory_bytes) by (instance))","hide":false,"intervalFactor":2,"legendFormat":"Requested Memory","refId":"B","step":20}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Memory","tooltip":{"msResolution":false,"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"bytes","label":"Memory","logBase":1,"show":true},{"format":"short","logBase":1,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["rgba(50, 172, 45, 0.97)","rgba(237, 129, 40, 0.89)","rgba(245, 54, 54, 0.9)"],"datasource":"${DS_PROMETHEUS}","editable":true,"format":"percent","gauge":{"maxValue":100,"minValue":0,"show":true,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{"h":8,"w":6,"x":18,"y":8},"hideTimeOverride":false,"id":4,"interval":null,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":true},"tableColumn":"","targets":[{"expr":"max(sum(kube_pod_container_resource_requests_memory_bytes) by (instance)) / min(sum(kube_node_status_allocatable_memory_bytes) by (instance)) * 100","intervalFactor":2,"legendFormat":"","refId":"A","step":240}],"thresholds":"80, 90","title":"Memory","transparent":false,"type":"singlestat","valueFontSize":"110%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"avg"}],"refresh":false,"schemaVersion":16,"style":"dark","tags":[],"templating":{"list":[]},"time":{"from":"now-3h","to":"now"},"timepicker":{"refresh_intervals":["5s","10s","30s","1m","5m","15m","30m","1h","2h","1d"],"time_options":["5m","15m","1h","6h","12h","24h","2d","7d","30d"]},"timezone":"browser","title":"Kubernetes Resource Requests","uid":"0MdTILxik","version":1},"inputs":[{"name":"DS_PROMETHEUS","pluginId":"prometheus","type":"datasource","value":"Rancher-Monitoring"}],"overwrite":false}
\ No newline at end of file

charts/rancher-monitoring/v0.0.2/charts/grafana/dashboards/c_rancher-components-dashboard.json

+{"dashboard":{"__inputs":[{"name":"DS_PROMETHEUS","label":"Rancher-Monitoring","description":"","type":"datasource","pluginId":"prometheus","pluginName":"Prometheus"}],"__requires":[{"type":"grafana","id":"grafana","name":"Grafana","version":"5.3.0"},{"type":"panel","id":"graph","name":"Graph","version":"5.0.0"},{"type":"datasource","id":"prometheus","name":"Prometheus","version":"5.0.0"},{"type":"panel","id":"singlestat","name":"Singlestat","version":"5.0.0"}],"annotations":{"list":[{"builtIn":1,"datasource":"-- Grafana --","enable":true,"hide":true,"iconColor":"rgba(0, 211, 255, 1)","name":"Annotations & Alerts","type":"dashboard"}]},"description":"This is a simple dashboard for: https://github.com/banzaicloud/logging-operator utilising Fluent-bit and Fluentd","editable":true,"gnetId":7668,"graphTooltip":0,"id":null,"links":[],"panels":[{"cacheTimeout":null,"colorBackground":false,"colorValue":true,"colors":["#d44a3a","rgba(237, 129, 40, 0.89)","#299c46"],"datasource":"${DS_PROMETHEUS}","format":"none","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{"h":5,"w":3,"x":0,"y":0},"id":4,"interval":null,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":true},"tableColumn":"","targets":[{"expr":"sum(kube_node_status_condition{condition=\"Ready\"})","format":"time_series","intervalFactor":1,"legendFormat":"","refId":"A"}],"thresholds":"0,1","title":"Active Nodes","type":"singlestat","valueFontSize":"100%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"current"},{"cacheTimeout":null,"colorBackground":false,"colorValue":true,"colors":["#d44a3a","rgba(237, 129, 40, 0.89)","#299c46"],"datasource":"${DS_PROMETHEUS}","format":"none","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{"h":5,"w":3,"x":3,"y":0},"id":8,"interval":null,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":true},"tableColumn":"","targets":[{"expr":"sum(kube_pod_info{pod=~\"fluentd.*\"})","format":"time_series","instant":false,"intervalFactor":1,"refId":"A"}],"thresholds":"0,1","title":"Fluentd","type":"singlestat","valueFontSize":"100%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"current"},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"${DS_PROMETHEUS}","fill":1,"gridPos":{"h":5,"w":9,"x":6,"y":0},"id":2,"legend":{"alignAsTable":true,"avg":false,"current":true,"max":false,"min":false,"rightSide":true,"show":true,"sort":"current","sortDesc":true,"total":false,"values":true},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(fluentd_input_status_num_records_total[1m]))by (instance)","format":"time_series","hide":false,"intervalFactor":1,"legendFormat":"{{ instance }}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Fluent input records","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"bytes","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"${DS_PROMETHEUS}","fill":1,"gridPos":{"h":5,"w":9,"x":15,"y":0},"id":9,"legend":{"alignAsTable":true,"avg":false,"current":true,"max":false,"min":false,"rightSide":true,"show":true,"sort":"current","sortDesc":true,"total":false,"values":true},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"rate(fluentd_output_status_buffer_queue_length[1m])","format":"time_series","hide":false,"intervalFactor":1,"legendFormat":"{{ type }}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Fluentd output buffer queue length","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"bytes","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"${DS_PROMETHEUS}","fill":1,"gridPos":{"h":5,"w":8,"x":0,"y":5},"id":10,"legend":{"alignAsTable":true,"avg":false,"current":true,"max":false,"min":false,"rightSide":true,"show":true,"sort":"current","sortDesc":true,"total":false,"values":true},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"rate(fluentd_output_status_num_errors[1m])","format":"time_series","hide":false,"intervalFactor":1,"legendFormat":"{{ type }}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Fluentd output error/s","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"bytes","label":null,"logBase":1,"max":null,"min":"0","show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"${DS_PROMETHEUS}","fill":1,"gridPos":{"h":5,"w":8,"x":8,"y":5},"id":12,"legend":{"alignAsTable":true,"avg":false,"current":true,"max":false,"min":false,"rightSide":true,"show":true,"sort":"current","sortDesc":true,"total":false,"values":true},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"rate(fluentd_output_status_emit_count[1m])","format":"time_series","hide":false,"intervalFactor":1,"legendFormat":"{{ type }}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Fluentd output emit/s by Plugin","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"ops","label":null,"logBase":1,"max":null,"min":"0","show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"${DS_PROMETHEUS}","fill":1,"gridPos":{"h":5,"w":8,"x":16,"y":5},"id":15,"legend":{"alignAsTable":true,"avg":false,"current":true,"max":false,"min":false,"rightSide":true,"show":true,"sort":"current","sortDesc":true,"total":false,"values":true},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"fluentd_output_status_buffer_queue_length","format":"time_series","hide":false,"intervalFactor":1,"legendFormat":"{{ type }}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Fluentd output buffer queue","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":"0","show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"${DS_PROMETHEUS}","fill":1,"gridPos":{"h":6,"w":8,"x":0,"y":10},"id":11,"legend":{"alignAsTable":true,"avg":false,"current":true,"max":false,"min":false,"rightSide":true,"show":true,"sort":"current","sortDesc":true,"total":false,"values":true},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"rate(fluentd_output_status_retry_count[1m])","format":"time_series","hide":false,"intervalFactor":1,"legendFormat":"Retries {{ type }}","refId":"A"},{"expr":"rate(fluentd_output_status_rollback_count[1m])","format":"time_series","intervalFactor":1,"legendFormat":"Rollback {{ type }}","refId":"B"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Fluentd retries/rollback","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"decimals":null,"format":"short","label":"","logBase":1,"max":null,"min":"0","show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":"0","show":false}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"${DS_PROMETHEUS}","fill":1,"gridPos":{"h":6,"w":8,"x":8,"y":10},"id":14,"legend":{"alignAsTable":false,"avg":false,"current":true,"max":true,"min":true,"rightSide":false,"show":true,"sort":"current","sortDesc":true,"total":false,"values":true},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(fluentd_output_status_retry_count[1m]))","format":"time_series","hide":false,"intervalFactor":1,"legendFormat":"Retry rate","refId":"A"},{"expr":"sum(rate(fluentd_output_status_num_errors[1m]))","format":"time_series","intervalFactor":1,"legendFormat":"Error rate","refId":"C"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Fluentd output error/retry rate","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"ops","label":null,"logBase":1,"max":null,"min":"0","show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"${DS_PROMETHEUS}","fill":1,"gridPos":{"h":6,"w":8,"x":16,"y":10},"id":13,"legend":{"alignAsTable":false,"avg":false,"current":true,"max":true,"min":true,"rightSide":false,"show":true,"sort":"current","sortDesc":true,"total":false,"values":true},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"fluentd_output_status_buffer_total_bytes","format":"time_series","hide":false,"intervalFactor":1,"legendFormat":"{{ type }}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Fluentd output buffer size","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"bytes","label":null,"logBase":1,"max":null,"min":"0","show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}}],"refresh":"30s","schemaVersion":16,"style":"dark","tags":[],"templating":{"list":[]},"time":{"from":"now-15m","to":"now"},"timepicker":{"refresh_intervals":["5s","10s","30s","1m","5m","15m","30m","1h","2h","1d"],"time_options":["5m","15m","1h","6h","12h","24h","2d","7d","30d"]},"timezone":"","title":"Rancher Components","uid":"bNn5LUtiz","version":1},"inputs":[{"name":"DS_PROMETHEUS","pluginId":"prometheus","type":"datasource","value":"Rancher-Monitoring"}],"overwrite":false}
\ No newline at end of file

charts/rancher-monitoring/v0.0.2/charts/grafana/dashboards/w_daemonset-dashboard.json

+{"dashboard":{"__inputs":[{"name":"DS_PROMETHEUS","label":"Rancher-Monitoring","description":"","type":"datasource","pluginId":"prometheus","pluginName":"Prometheus"}],"__requires":[{"type":"grafana","id":"grafana","name":"Grafana","version":"5.3.0"},{"type":"panel","id":"graph","name":"Graph","version":"5.0.0"},{"type":"datasource","id":"prometheus","name":"Prometheus","version":"5.0.0"},{"type":"panel","id":"singlestat","name":"Singlestat","version":"5.0.0"}],"annotations":{"list":[{"builtIn":1,"datasource":"-- Grafana --","enable":true,"hide":true,"iconColor":"rgba(0, 211, 255, 1)","name":"Annotations & Alerts","type":"dashboard"}]},"description":"Kubernetes DaemonSet Overview","editable":true,"gnetId":6615,"graphTooltip":1,"id":null,"iteration":1543396055929,"links":[],"panels":[{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["rgba(245, 54, 54, 0.9)","rgba(237, 129, 40, 0.89)","rgba(50, 172, 45, 0.97)"],"datasource":"${DS_PROMETHEUS}","decimals":null,"editable":true,"format":"none","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":false},"gridPos":{"h":3,"w":8,"x":0,"y":0},"id":5,"interval":null,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":false},"tableColumn":"","targets":[{"expr":"max(kube_daemonset_status_desired_number_scheduled{daemonset=\"$daemonset_name\",namespace=\"$daemonset_namespace\"}) without (instance, pod)","format":"time_series","instant":false,"interval":"","intervalFactor":2,"legendFormat":"","refId":"A","step":600}],"thresholds":"","title":"Desired Replicas","transparent":false,"type":"singlestat","valueFontSize":"80%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"avg"},{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["rgba(245, 54, 54, 0.9)","rgba(237, 129, 40, 0.89)","rgba(50, 172, 45, 0.97)"],"datasource":"${DS_PROMETHEUS}","editable":true,"format":"none","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{"h":3,"w":8,"x":8,"y":0},"id":6,"interval":null,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":false},"tableColumn":"","targets":[{"expr":"min(kube_daemonset_status_number_available{daemonset=\"$daemonset_name\",namespace=\"$daemonset_namespace\"}) without (instance, pod)","format":"time_series","intervalFactor":2,"refId":"A","step":600}],"thresholds":"","title":"Available Replicas","type":"singlestat","valueFontSize":"80%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"avg"},{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["rgba(245, 54, 54, 0.9)","rgba(237, 129, 40, 0.89)","rgba(50, 172, 45, 0.97)"],"datasource":"${DS_PROMETHEUS}","editable":true,"format":"none","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{"h":3,"w":8,"x":16,"y":0},"id":2,"interval":null,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":false},"tableColumn":"","targets":[{"expr":"max(kube_daemonset_metadata_generation{daemonset=\"$daemonset_name\",namespace=\"$daemonset_namespace\"}) without (instance, pod)","format":"time_series","intervalFactor":2,"refId":"A","step":600}],"thresholds":"","title":"Metadata Generation","type":"singlestat","valueFontSize":"80%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"avg"},{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["#299c46","rgba(237, 129, 40, 0.89)","#d44a3a"],"datasource":"${DS_PROMETHEUS}","decimals":2,"format":"s","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{"h":6,"w":3,"x":0,"y":3},"id":11,"interval":null,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":false},"tableColumn":"","targets":[{"expr":"time() - max(kube_daemonset_created{daemonset=~\"$daemonset_name\"})","format":"time_series","intervalFactor":1,"refId":"A"}],"thresholds":"","title":"DaemonSet Create Time","type":"singlestat","valueFontSize":"80%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"current"},{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["rgba(245, 54, 54, 0.9)","rgba(237, 129, 40, 0.89)","rgba(50, 172, 45, 0.97)"],"datasource":"${DS_PROMETHEUS}","editable":true,"format":"none","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{"h":6,"w":7,"x":3,"y":3},"id":8,"interval":null,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"cores","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":true},"tableColumn":"","targets":[{"expr":"sum(rate(container_cpu_usage_seconds_total{namespace=\"$daemonset_namespace\",pod_name=~\"$daemonset_name.*\"}[2m]))","format":"time_series","intervalFactor":2,"refId":"A","step":600}],"thresholds":"","title":"Total CPU","type":"singlestat","valueFontSize":"110%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"current"},{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["rgba(245, 54, 54, 0.9)","rgba(237, 129, 40, 0.89)","rgba(50, 172, 45, 0.97)"],"datasource":"${DS_PROMETHEUS}","editable":true,"format":"bytes","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{"h":6,"w":7,"x":10,"y":3},"id":9,"interval":null,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"80%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":true},"tableColumn":"","targets":[{"expr":"sum(container_memory_working_set_bytes{namespace=\"$daemonset_namespace\",pod_name=~\"$daemonset_name.*\", container_name!=\"POD\"})","format":"time_series","intervalFactor":2,"refId":"A","step":600}],"thresholds":"","title":"Total Memory","type":"singlestat","valueFontSize":"110%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"current"},{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["rgba(245, 54, 54, 0.9)","rgba(237, 129, 40, 0.89)","rgba(50, 172, 45, 0.97)"],"datasource":"${DS_PROMETHEUS}","editable":true,"format":"Bps","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":false},"gridPos":{"h":6,"w":7,"x":17,"y":3},"id":7,"interval":null,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":true},"tableColumn":"","targets":[{"expr":"sum(rate(container_network_transmit_bytes_total{namespace=\"$daemonset_namespace\",pod_name=~\"$daemonset_name.*\"}[2m])) + sum(rate(container_network_receive_bytes_total{namespace=\"$daemonset_namespace\",pod_name=~\"$daemonset_name.*\"}[2m]))","format":"time_series","intervalFactor":2,"refId":"A","step":600}],"thresholds":"","title":"Total Network","type":"singlestat","valueFontSize":"80%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"current"},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"${DS_PROMETHEUS}","editable":true,"error":false,"fill":1,"grid":{"threshold1Color":"rgba(216, 200, 27, 0.27)","threshold2Color":"rgba(234, 112, 112, 0.22)"},"gridPos":{"h":7,"w":12,"x":0,"y":9},"id":13,"isNew":false,"legend":{"alignAsTable":false,"avg":false,"current":true,"hideEmpty":false,"hideZero":false,"max":false,"min":false,"rightSide":false,"show":false,"total":false,"values":true},"lines":true,"linewidth":2,"links":[],"nullPointMode":"connected","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum by (pod_name) (rate(container_cpu_usage_seconds_total{namespace=\"$daemonset_namespace\",pod_name=~\"$daemonset_name.*\"}[2m]))","format":"time_series","intervalFactor":2,"legendFormat":"{{pod_name}}","refId":"A","step":30}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"CPU Usage","tooltip":{"msResolution":true,"shared":true,"sort":0,"value_type":"cumulative"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"decimals":null,"format":"short","label":"","logBase":1,"min":"0","show":true},{"format":"short","logBase":1,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"${DS_PROMETHEUS}","editable":true,"error":false,"fill":1,"grid":{"threshold1Color":"rgba(216, 200, 27, 0.27)","threshold2Color":"rgba(234, 112, 112, 0.22)"},"gridPos":{"h":7,"w":12,"x":12,"y":9},"id":15,"isNew":false,"legend":{"alignAsTable":false,"avg":false,"current":false,"hideEmpty":false,"hideZero":false,"max":false,"min":false,"rightSide":false,"show":false,"total":false,"values":false},"lines":true,"linewidth":2,"links":[],"nullPointMode":"connected","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum by (pod_name) (container_memory_working_set_bytes{namespace=\"$daemonset_namespace\",pod_name=~\"$daemonset_name.*\", container_name!=\"POD\"})","format":"time_series","interval":"10s","intervalFactor":1,"legendFormat":"{{ pod_name }}","refId":"A","step":15}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Memory Usage","tooltip":{"msResolution":true,"shared":true,"sort":0,"value_type":"cumulative"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"bytes","logBase":1,"max":null,"min":"0","show":true},{"format":"short","logBase":1,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"${DS_PROMETHEUS}","decimals":0,"editable":true,"error":false,"fill":1,"grid":{"threshold1Color":"rgba(216, 200, 27, 0.27)","threshold2Color":"rgba(234, 112, 112, 0.22)"},"gridPos":{"h":9,"w":24,"x":0,"y":16},"id":1,"isNew":true,"legend":{"alignAsTable":true,"avg":false,"current":true,"hideEmpty":false,"hideZero":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":true},"lines":true,"linewidth":2,"links":[],"nullPointMode":"connected","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"avg(kube_daemonset_status_number_ready{daemonset=\"$daemonset_name\",namespace=\"$daemonset_namespace\"}) without (instance, pod)","format":"time_series","intervalFactor":1,"legendFormat":"Ready","refId":"A"},{"expr":"avg(kube_daemonset_status_number_available{daemonset=\"$daemonset_name\",namespace=\"$daemonset_namespace\"}) without (instance, pod)","format":"time_series","hide":false,"intervalFactor":1,"legendFormat":"Available","refId":"C"},{"expr":"avg(kube_daemonset_status_number_unavailable{daemonset=\"$daemonset_name\",namespace=\"$daemonset_namespace\"}) without (instance, pod)","format":"time_series","hide":false,"intervalFactor":1,"legendFormat":"Unavailable","refId":"B"},{"expr":"avg(kube_daemonset_status_number_misscheduled{daemonset=\"$daemonset_name\",namespace=\"$daemonset_namespace\"}) without (instance, pod)","format":"time_series","hide":false,"intervalFactor":1,"legendFormat":"Misscheduled","refId":"D"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Replicas Status","tooltip":{"msResolution":true,"shared":true,"sort":0,"value_type":"cumulative"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"decimals":0,"format":"none","label":"","logBase":1,"show":true},{"format":"short","label":"","logBase":1,"show":false}],"yaxis":{"align":false,"alignLevel":null}}],"refresh":"30s","schemaVersion":16,"style":"dark","tags":[],"templating":{"list":[{"allValue":".*","current":{},"datasource":"${DS_PROMETHEUS}","hide":0,"includeAll":false,"label":"Namespace","multi":false,"name":"daemonset_namespace","options":[],"query":"label_values(kube_daemonset_metadata_generation, namespace)","refresh":1,"regex":"","skipUrlSync":false,"sort":0,"tagValuesQuery":null,"tags":[],"tagsQuery":"","type":"query","useTags":false},{"allValue":null,"current":{},"datasource":"${DS_PROMETHEUS}","hide":0,"includeAll":false,"label":"DaemonSet","multi":false,"name":"daemonset_name","options":[],"query":"label_values(kube_daemonset_metadata_generation{namespace=\"$daemonset_namespace\"}, daemonset)","refresh":1,"regex":"","skipUrlSync":false,"sort":0,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false}]},"time":{"from":"now-30m","to":"now"},"timepicker":{"hidden":false,"refresh_intervals":["5s","10s","30s","1m","5m","15m","30m","1h","2h","1d"],"time_options":["5m","15m","1h","6h","12h","24h","2d","7d","30d"]},"timezone":"browser","title":"DaemonSet","uid":"gekRLzHiz","version":1},"inputs":[{"name":"DS_PROMETHEUS","pluginId":"prometheus","type":"datasource","value":"Rancher-Monitoring"}],"overwrite":false}
\ No newline at end of file

charts/rancher-monitoring/v0.0.2/charts/grafana/dashboards/w_deployment-dashboard.json

+{"dashboard":{"__inputs":[{"name":"DS_PROMETHEUS","label":"Rancher-Monitoring","description":"","type":"datasource","pluginId":"prometheus","pluginName":"Prometheus"}],"__requires":[{"type":"grafana","id":"grafana","name":"Grafana","version":"5.3.0"},{"type":"panel","id":"graph","name":"Graph","version":"5.0.0"},{"type":"datasource","id":"prometheus","name":"Prometheus","version":"5.0.0"},{"type":"panel","id":"singlestat","name":"Singlestat","version":"5.0.0"}],"annotations":{"list":[{"builtIn":1,"datasource":"-- Grafana --","enable":true,"hide":true,"iconColor":"rgba(0, 211, 255, 1)","name":"Annotations & Alerts","type":"dashboard"}]},"editable":true,"gnetId":null,"graphTooltip":1,"id":null,"iteration":1543396071820,"links":[],"panels":[{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["rgba(245, 54, 54, 0.9)","rgba(237, 129, 40, 0.89)","rgba(50, 172, 45, 0.97)"],"datasource":"${DS_PROMETHEUS}","editable":true,"format":"none","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{"h":5,"w":8,"x":0,"y":0},"id":8,"interval":null,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"cores","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":true},"tableColumn":"","targets":[{"expr":"sum(rate(container_cpu_usage_seconds_total{namespace=\"$deployment_namespace\",pod_name=~\"$deployment_name.*\"}[3m]))","intervalFactor":2,"refId":"A","step":600}],"thresholds":"","title":"CPU","type":"singlestat","valueFontSize":"110%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"avg"},{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["rgba(245, 54, 54, 0.9)","rgba(237, 129, 40, 0.89)","rgba(50, 172, 45, 0.97)"],"datasource":"${DS_PROMETHEUS}","editable":true,"format":"none","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{"h":5,"w":8,"x":8,"y":0},"id":9,"interval":null,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"GB","postfixFontSize":"50%","prefix":"","prefixFontSize":"80%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":true},"tableColumn":"","targets":[{"expr":"sum(container_memory_usage_bytes{namespace=\"$deployment_namespace\",pod_name=~\"$deployment_name.*\"}) / 1024^3","intervalFactor":2,"refId":"A","step":600}],"thresholds":"","title":"Memory","type":"singlestat","valueFontSize":"110%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"avg"},{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["rgba(245, 54, 54, 0.9)","rgba(237, 129, 40, 0.89)","rgba(50, 172, 45, 0.97)"],"datasource":"${DS_PROMETHEUS}","editable":true,"format":"Bps","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":false},"gridPos":{"h":5,"w":8,"x":16,"y":0},"id":7,"interval":null,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":true},"tableColumn":"","targets":[{"expr":"sum(rate(container_network_transmit_bytes_total{namespace=\"$deployment_namespace\",pod_name=~\"$deployment_name.*\"}[3m])) + sum(rate(container_network_receive_bytes_total{namespace=\"$deployment_namespace\",pod_name=~\"$deployment_name.*\"}[3m]))","intervalFactor":2,"refId":"A","step":600}],"thresholds":"","title":"Network","type":"singlestat","valueFontSize":"80%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"avg"},{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["rgba(245, 54, 54, 0.9)","rgba(237, 129, 40, 0.89)","rgba(50, 172, 45, 0.97)"],"datasource":"${DS_PROMETHEUS}","editable":true,"format":"none","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":false},"gridPos":{"h":3,"w":6,"x":0,"y":5},"id":5,"interval":null,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":false},"tableColumn":"","targets":[{"expr":"max(kube_deployment_spec_replicas{deployment=\"$deployment_name\",namespace=\"$deployment_namespace\"}) without (instance, pod)","intervalFactor":2,"metric":"kube_deployment_spec_replicas","refId":"A","step":600}],"thresholds":"","title":"Desired Replicas","type":"singlestat","valueFontSize":"80%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"avg"},{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["rgba(245, 54, 54, 0.9)","rgba(237, 129, 40, 0.89)","rgba(50, 172, 45, 0.97)"],"datasource":"${DS_PROMETHEUS}","editable":true,"format":"none","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{"h":3,"w":6,"x":6,"y":5},"id":6,"interval":null,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":false},"tableColumn":"","targets":[{"expr":"min(kube_deployment_status_replicas_available{deployment=\"$deployment_name\",namespace=\"$deployment_namespace\"}) without (instance, pod)","intervalFactor":2,"refId":"A","step":600}],"thresholds":"","title":"Available Replicas","type":"singlestat","valueFontSize":"80%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"avg"},{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["rgba(245, 54, 54, 0.9)","rgba(237, 129, 40, 0.89)","rgba(50, 172, 45, 0.97)"],"datasource":"${DS_PROMETHEUS}","editable":true,"format":"none","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{"h":3,"w":6,"x":12,"y":5},"id":3,"interval":null,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":false},"tableColumn":"","targets":[{"expr":"max(kube_deployment_status_observed_generation{deployment=\"$deployment_name\",namespace=\"$deployment_namespace\"}) without (instance, pod)","intervalFactor":2,"refId":"A","step":600}],"thresholds":"","title":"Observed Generation","type":"singlestat","valueFontSize":"80%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"avg"},{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["rgba(245, 54, 54, 0.9)","rgba(237, 129, 40, 0.89)","rgba(50, 172, 45, 0.97)"],"datasource":"${DS_PROMETHEUS}","editable":true,"format":"none","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{"h":3,"w":6,"x":18,"y":5},"id":2,"interval":null,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":false},"tableColumn":"","targets":[{"expr":"max(kube_deployment_metadata_generation{deployment=\"$deployment_name\",namespace=\"$deployment_namespace\"}) without (instance, pod)","intervalFactor":2,"refId":"A","step":600}],"thresholds":"","title":"Metadata Generation","type":"singlestat","valueFontSize":"80%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"avg"},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"${DS_PROMETHEUS}","editable":true,"error":false,"fill":1,"grid":{"threshold1Color":"rgba(216, 200, 27, 0.27)","threshold2Color":"rgba(234, 112, 112, 0.22)"},"gridPos":{"h":9,"w":24,"x":0,"y":8},"id":1,"isNew":true,"legend":{"alignAsTable":false,"avg":false,"current":false,"hideEmpty":false,"hideZero":false,"max":false,"min":false,"rightSide":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":2,"links":[],"nullPointMode":"connected","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"max(kube_deployment_status_replicas{deployment=\"$deployment_name\",namespace=\"$deployment_namespace\"}) without (instance, pod)","intervalFactor":2,"legendFormat":"current replicas","refId":"A","step":30},{"expr":"min(kube_deployment_status_replicas_available{deployment=\"$deployment_name\",namespace=\"$deployment_namespace\"}) without (instance, pod)","intervalFactor":2,"legendFormat":"available","refId":"B","step":30},{"expr":"max(kube_deployment_status_replicas_unavailable{deployment=\"$deployment_name\",namespace=\"$deployment_namespace\"}) without (instance, pod)","intervalFactor":2,"legendFormat":"unavailable","refId":"C","step":30},{"expr":"min(kube_deployment_status_replicas_updated{deployment=\"$deployment_name\",namespace=\"$deployment_namespace\"}) without (instance, pod)","intervalFactor":2,"legendFormat":"updated","refId":"D","step":30},{"expr":"max(kube_deployment_spec_replicas{deployment=\"$deployment_name\",namespace=\"$deployment_namespace\"}) without (instance, pod)","intervalFactor":2,"legendFormat":"desired","refId":"E","step":30}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Replicas","tooltip":{"msResolution":true,"shared":true,"sort":0,"value_type":"cumulative"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"none","label":"","logBase":1,"show":true},{"format":"short","label":"","logBase":1,"show":false}],"yaxis":{"align":false,"alignLevel":null}}],"schemaVersion":16,"style":"dark","tags":[],"templating":{"list":[{"allValue":".*","current":{},"datasource":"${DS_PROMETHEUS}","hide":0,"includeAll":false,"label":"Namespace","multi":false,"name":"deployment_namespace","options":[],"query":"label_values(kube_deployment_metadata_generation, namespace)","refresh":1,"regex":"","skipUrlSync":false,"sort":0,"tagValuesQuery":null,"tags":[],"tagsQuery":"","type":"query","useTags":false},{"allValue":null,"current":{},"datasource":"${DS_PROMETHEUS}","hide":0,"includeAll":false,"label":"Deployment","multi":false,"name":"deployment_name","options":[],"query":"label_values(kube_deployment_metadata_generation{namespace=\"$deployment_namespace\"}, deployment)","refresh":1,"regex":"","skipUrlSync":false,"sort":0,"tagValuesQuery":"","tags":[],"tagsQuery":"deployment","type":"query","useTags":false}]},"time":{"from":"now-6h","to":"now"},"timepicker":{"refresh_intervals":["5s","10s","30s","1m","5m","15m","30m","1h","2h","1d"],"time_options":["5m","15m","1h","6h","12h","24h","2d","7d","30d"]},"timezone":"browser","title":"Deployment","uid":"kZdoIYxik","version":1},"inputs":[{"name":"DS_PROMETHEUS","pluginId":"prometheus","type":"datasource","value":"Rancher-Monitoring"}],"overwrite":false}
\ No newline at end of file

charts/rancher-monitoring/v0.0.2/charts/grafana/dashboards/w_pods-dashboard.json

+{"dashboard":{"__inputs":[{"name":"DS_PROMETHEUS","label":"Rancher-Monitoring","description":"","type":"datasource","pluginId":"prometheus","pluginName":"Prometheus"}],"__requires":[{"type":"grafana","id":"grafana","name":"Grafana","version":"5.3.0"},{"type":"panel","id":"graph","name":"Graph","version":"5.0.0"},{"type":"datasource","id":"prometheus","name":"Prometheus","version":"5.0.0"}],"annotations":{"list":[{"builtIn":1,"datasource":"-- Grafana --","enable":true,"hide":true,"iconColor":"rgba(0, 211, 255, 1)","name":"Annotations & Alerts","type":"dashboard"}]},"editable":true,"gnetId":null,"graphTooltip":1,"id":null,"iteration":1543396157762,"links":[],"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"${DS_PROMETHEUS}","editable":true,"error":false,"fill":1,"grid":{"threshold1Color":"rgba(216, 200, 27, 0.27)","threshold2Color":"rgba(234, 112, 112, 0.22)"},"gridPos":{"h":7,"w":24,"x":0,"y":0},"id":1,"isNew":false,"legend":{"alignAsTable":true,"avg":true,"current":true,"hideEmpty":false,"hideZero":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":true},"lines":true,"linewidth":2,"links":[],"nullPointMode":"connected","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum by(container_name) (container_memory_usage_bytes{pod_name=\"$pod\", container_name=~\"$container\", container_name!=\"POD\"})","interval":"10s","intervalFactor":1,"legendFormat":"Current: {{ container_name }}","metric":"container_memory_usage_bytes","refId":"A","step":15},{"expr":"kube_pod_container_resource_requests_memory_bytes{pod=\"$pod\", container=~\"$container\"}","interval":"10s","intervalFactor":2,"legendFormat":"Requested: {{ container }}","metric":"kube_pod_container_resource_requests_memory_bytes","refId":"B","step":20},{"expr":"kube_pod_container_resource_limits_memory_bytes{pod=\"$pod\", container=~\"$container\"}","interval":"10s","intervalFactor":2,"legendFormat":"Limit: {{ container }}","metric":"kube_pod_container_resource_limits_memory_bytes","refId":"C","step":20}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Memory Usage","tooltip":{"msResolution":true,"shared":true,"sort":0,"value_type":"cumulative"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"bytes","logBase":1,"show":true},{"format":"short","logBase":1,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"${DS_PROMETHEUS}","editable":true,"error":false,"fill":1,"grid":{"threshold1Color":"rgba(216, 200, 27, 0.27)","threshold2Color":"rgba(234, 112, 112, 0.22)"},"gridPos":{"h":7,"w":24,"x":0,"y":7},"id":2,"isNew":false,"legend":{"alignAsTable":true,"avg":true,"current":true,"hideEmpty":false,"hideZero":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":true},"lines":true,"linewidth":2,"links":[],"nullPointMode":"connected","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum by (container_name)(rate(container_cpu_usage_seconds_total{image!=\"\",container_name!=\"POD\",pod_name=\"$pod\"}[1m]))","intervalFactor":2,"legendFormat":"{{ container_name }}","refId":"A","step":30},{"expr":"kube_pod_container_resource_requests_cpu_cores{pod=\"$pod\", container=~\"$container\"}","interval":"10s","intervalFactor":2,"legendFormat":"Requested: {{ container }}","metric":"kube_pod_container_resource_requests_cpu_cores","refId":"B","step":20},{"expr":"kube_pod_container_resource_limits_cpu_cores{pod=\"$pod\", container=~\"$container\"}","interval":"10s","intervalFactor":2,"legendFormat":"Limit: {{ container }}","metric":"kube_pod_container_resource_limits_memory_bytes","refId":"C","step":20}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"CPU Usage","tooltip":{"msResolution":true,"shared":true,"sort":0,"value_type":"cumulative"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","logBase":1,"show":true},{"format":"short","logBase":1,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"${DS_PROMETHEUS}","editable":true,"error":false,"fill":1,"grid":{"threshold1Color":"rgba(216, 200, 27, 0.27)","threshold2Color":"rgba(234, 112, 112, 0.22)"},"gridPos":{"h":7,"w":24,"x":0,"y":14},"id":3,"isNew":false,"legend":{"alignAsTable":true,"avg":true,"current":true,"hideEmpty":false,"hideZero":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":true},"lines":true,"linewidth":2,"links":[],"nullPointMode":"connected","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sort_desc(sum by (pod_name) (rate(container_network_receive_bytes_total{pod_name=\"$pod\"}[1m])))","intervalFactor":2,"legendFormat":"{{ pod_name }}","refId":"A","step":30}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Network I/O","tooltip":{"msResolution":true,"shared":true,"sort":0,"value_type":"cumulative"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"bytes","logBase":1,"show":true},{"format":"short","logBase":1,"show":true}],"yaxis":{"align":false,"alignLevel":null}}],"refresh":false,"schemaVersion":16,"style":"dark","tags":[],"templating":{"list":[{"allValue":".*","current":{},"datasource":"${DS_PROMETHEUS}","hide":0,"includeAll":true,"label":"Namespace","multi":false,"name":"namespace","options":[],"query":"label_values(kube_pod_info, namespace)","refresh":1,"regex":"","skipUrlSync":false,"sort":0,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false},{"allValue":null,"current":{},"datasource":"${DS_PROMETHEUS}","hide":0,"includeAll":false,"label":"Pod","multi":false,"name":"pod","options":[],"query":"label_values(kube_pod_info{namespace=~\"$namespace\"}, pod)","refresh":1,"regex":"","skipUrlSync":false,"sort":0,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false},{"allValue":".*","current":{},"datasource":"${DS_PROMETHEUS}","hide":0,"includeAll":true,"label":"Container","multi":false,"name":"container","options":[],"query":"label_values(kube_pod_container_info{namespace=\"$namespace\", pod=\"$pod\"}, container)","refresh":1,"regex":"","skipUrlSync":false,"sort":0,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false}]},"time":{"from":"now-6h","to":"now"},"timepicker":{"refresh_intervals":["5s","10s","30s","1m","5m","15m","30m","1h","2h","1d"],"time_options":["5m","15m","1h","6h","12h","24h","2d","7d","30d"]},"timezone":"browser","title":"Pods","uid":"XSOTSYxiz","version":1},"inputs":[{"name":"DS_PROMETHEUS","pluginId":"prometheus","type":"datasource","value":"Rancher-Monitoring"}],"overwrite":false}
\ No newline at end of file

charts/rancher-monitoring/v0.0.2/charts/grafana/dashboards/w_statefulset-dashboard.json

+{"dashboard":{"__inputs":[{"name":"DS_PROMETHEUS","label":"Rancher-Monitoring","description":"","type":"datasource","pluginId":"prometheus","pluginName":"Prometheus"}],"__requires":[{"type":"grafana","id":"grafana","name":"Grafana","version":"5.3.0"},{"type":"panel","id":"graph","name":"Graph","version":"5.0.0"},{"type":"datasource","id":"prometheus","name":"Prometheus","version":"5.0.0"},{"type":"panel","id":"singlestat","name":"Singlestat","version":"5.0.0"}],"annotations":{"list":[{"builtIn":1,"datasource":"-- Grafana --","enable":true,"hide":true,"iconColor":"rgba(0, 211, 255, 1)","name":"Annotations & Alerts","type":"dashboard"}]},"editable":true,"gnetId":null,"graphTooltip":1,"id":null,"iteration":1543396179999,"links":[],"panels":[{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["rgba(245, 54, 54, 0.9)","rgba(237, 129, 40, 0.89)","rgba(50, 172, 45, 0.97)"],"datasource":"${DS_PROMETHEUS}","editable":true,"format":"none","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{"h":5,"w":8,"x":0,"y":0},"id":8,"interval":null,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"cores","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":true},"tableColumn":"","targets":[{"expr":"sum(rate(container_cpu_usage_seconds_total{namespace=\"$statefulset_namespace\",pod_name=~\"$statefulset_name.*\"}[3m]))","intervalFactor":2,"refId":"A","step":600}],"thresholds":"","title":"CPU","type":"singlestat","valueFontSize":"110%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"avg"},{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["rgba(245, 54, 54, 0.9)","rgba(237, 129, 40, 0.89)","rgba(50, 172, 45, 0.97)"],"datasource":"${DS_PROMETHEUS}","editable":true,"format":"none","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{"h":5,"w":8,"x":8,"y":0},"id":9,"interval":null,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"GB","postfixFontSize":"50%","prefix":"","prefixFontSize":"80%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":true},"tableColumn":"","targets":[{"expr":"sum(container_memory_usage_bytes{namespace=\"$statefulset_namespace\",pod_name=~\"$statefulset_name.*\"}) / 1024^3","intervalFactor":2,"refId":"A","step":600}],"thresholds":"","title":"Memory","type":"singlestat","valueFontSize":"110%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"avg"},{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["rgba(245, 54, 54, 0.9)","rgba(237, 129, 40, 0.89)","rgba(50, 172, 45, 0.97)"],"datasource":"${DS_PROMETHEUS}","editable":true,"format":"Bps","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":false},"gridPos":{"h":5,"w":8,"x":16,"y":0},"id":7,"interval":null,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":true},"tableColumn":"","targets":[{"expr":"sum(rate(container_network_transmit_bytes_total{namespace=\"$statefulset_namespace\",pod_name=~\"$statefulset_name.*\"}[3m])) + sum(rate(container_network_receive_bytes_total{namespace=\"$statefulset_namespace\",pod_name=~\"$statefulset_name.*\"}[3m]))","intervalFactor":2,"refId":"A","step":600}],"thresholds":"","title":"Network","type":"singlestat","valueFontSize":"80%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"avg"},{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["rgba(245, 54, 54, 0.9)","rgba(237, 129, 40, 0.89)","rgba(50, 172, 45, 0.97)"],"datasource":"${DS_PROMETHEUS}","editable":true,"format":"none","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":false},"gridPos":{"h":3,"w":6,"x":0,"y":5},"id":5,"interval":null,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":false},"tableColumn":"","targets":[{"expr":"max(kube_statefulset_replicas{statefulset=\"$statefulset_name\",namespace=\"$statefulset_namespace\"}) without (instance, pod)","intervalFactor":2,"metric":"kube_statefulset_replicas","refId":"A","step":600}],"thresholds":"","title":"Desired Replicas","type":"singlestat","valueFontSize":"80%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"avg"},{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["rgba(245, 54, 54, 0.9)","rgba(237, 129, 40, 0.89)","rgba(50, 172, 45, 0.97)"],"datasource":"${DS_PROMETHEUS}","editable":true,"format":"none","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{"h":3,"w":6,"x":6,"y":5},"id":6,"interval":null,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":false},"tableColumn":"","targets":[{"expr":"min(kube_statefulset_status_replicas{statefulset=\"$statefulset_name\",namespace=\"$statefulset_namespace\"}) without (instance, pod)","intervalFactor":2,"refId":"A","step":600}],"thresholds":"","title":"Available Replicas","type":"singlestat","valueFontSize":"80%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"avg"},{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["rgba(245, 54, 54, 0.9)","rgba(237, 129, 40, 0.89)","rgba(50, 172, 45, 0.97)"],"datasource":"${DS_PROMETHEUS}","editable":true,"format":"none","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{"h":3,"w":6,"x":12,"y":5},"id":3,"interval":null,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":false},"tableColumn":"","targets":[{"expr":"max(kube_statefulset_status_observed_generation{statefulset=\"$statefulset_name\",namespace=\"$statefulset_namespace\"}) without (instance, pod)","intervalFactor":2,"refId":"A","step":600}],"thresholds":"","title":"Observed Generation","type":"singlestat","valueFontSize":"80%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"avg"},{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["rgba(245, 54, 54, 0.9)","rgba(237, 129, 40, 0.89)","rgba(50, 172, 45, 0.97)"],"datasource":"${DS_PROMETHEUS}","editable":true,"format":"none","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{"h":3,"w":6,"x":18,"y":5},"id":2,"interval":null,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":false},"tableColumn":"","targets":[{"expr":"max(kube_statefulset_metadata_generation{statefulset=\"$statefulset_name\",namespace=\"$statefulset_namespace\"}) without (instance, pod)","intervalFactor":2,"refId":"A","step":600}],"thresholds":"","title":"Metadata Generation","type":"singlestat","valueFontSize":"80%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"avg"},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"${DS_PROMETHEUS}","editable":true,"error":false,"fill":1,"grid":{"threshold1Color":"rgba(216, 200, 27, 0.27)","threshold2Color":"rgba(234, 112, 112, 0.22)"},"gridPos":{"h":9,"w":24,"x":0,"y":8},"id":1,"isNew":true,"legend":{"alignAsTable":false,"avg":false,"current":false,"hideEmpty":false,"hideZero":false,"max":false,"min":false,"rightSide":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":2,"links":[],"nullPointMode":"connected","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"min(kube_statefulset_status_replicas{statefulset=\"$statefulset_name\",namespace=\"$statefulset_namespace\"}) without (instance, pod)","intervalFactor":2,"legendFormat":"available","refId":"B","step":30},{"expr":"max(kube_statefulset_replicas{statefulset=\"$statefulset_name\",namespace=\"$statefulset_namespace\"}) without (instance, pod)","intervalFactor":2,"legendFormat":"desired","refId":"E","step":30}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Replicas","tooltip":{"msResolution":true,"shared":true,"sort":0,"value_type":"cumulative"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"none","label":"","logBase":1,"show":true},{"format":"short","label":"","logBase":1,"show":false}],"yaxis":{"align":false,"alignLevel":null}}],"schemaVersion":16,"style":"dark","tags":[],"templating":{"list":[{"allValue":".*","current":{},"datasource":"${DS_PROMETHEUS}","hide":0,"includeAll":false,"label":"Namespace","multi":false,"name":"statefulset_namespace","options":[],"query":"label_values(kube_statefulset_metadata_generation, namespace)","refresh":1,"regex":"","skipUrlSync":false,"sort":0,"tagValuesQuery":null,"tags":[],"tagsQuery":"","type":"query","useTags":false},{"allValue":null,"current":{},"datasource":"${DS_PROMETHEUS}","hide":0,"includeAll":false,"label":"StatefulSet","multi":false,"name":"statefulset_name","options":[],"query":"label_values(kube_statefulset_metadata_generation{namespace=\"$statefulset_namespace\"}, statefulset)","refresh":1,"regex":"","skipUrlSync":false,"sort":0,"tagValuesQuery":"","tags":[],"tagsQuery":"statefulset","type":"query","useTags":false}]},"time":{"from":"now-6h","to":"now"},"timepicker":{"refresh_intervals":["5s","10s","30s","1m","5m","15m","30m","1h","2h","1d"],"time_options":["5m","15m","1h","6h","12h","24h","2d","7d","30d"]},"timezone":"browser","title":"StatefulSet","uid":"TDdTILbiz","version":1},"inputs":[{"name":"DS_PROMETHEUS","pluginId":"prometheus","type":"datasource","value":"Rancher-Monitoring"}],"overwrite":false}
\ No newline at end of file

charts/rancher-monitoring/v0.0.2/charts/grafana/templates/dashboards-configmap.yaml

+apiVersion: v1
+kind: ConfigMap
+metadata:
+  labels:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+  name: {{ template "app.dashboards.fullname" . }}
+data:
+{{- if eq .Values.level "cluster" }}
+{{ (.Files.Glob "dashboards/c_*.json").AsConfig | indent 2 }}
+{{- end }}
+{{ (.Files.Glob "dashboards/w_*.json").AsConfig | indent 2 }}
+  prometheus-datasource.json: |+
+    {
+      "access": "proxy",
+      "basicAuth": false,
+      "editable": false,
+      "isDefault": true,
+      "name": "Rancher-Monitoring",
+      "type": "prometheus",
+      "url": "{{ .Values.prometheusDatasourceURL }}"
+    }

charts/rancher-monitoring/v0.0.2/charts/grafana/templates/deployment.yaml

+apiVersion: {{ template "deployment_api_version" . }}
+kind: Deployment
+metadata:
+  labels:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+  name: {{ template "app.fullname" . }}
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: {{ template "app.name" . }}
+      chart: {{ template "app.version" . }}
+      release: {{ .Release.Name }}
+  template:
+    metadata:
+      labels:
+        app: {{ template "app.name" . }}
+        chart: {{ template "app.version" . }}
+        release: {{ .Release.Name }}
+    spec:
+      initContainers:
+      - name: grafana-init-plugin-json-copy
+        image: {{ .Values.image.repository }}:{{ .Values.image.tag }}
+        volumeMounts:
+        - name: grafana-static-hooks
+          mountPath: /run.sh
+          subPath: copy-datasource-plugin-json.sh
+        - name: grafana-static-contents
+          mountPath: /host
+        {{- if and .Values.resources .Values.resources.inits }}
+        resources:
+{{ toYaml .Values.resources.inits | indent 10 }}
+        {{- end }}
+      - name: grafana-init-plugin-json-modify
+        image: {{ .Values.image.inits.tools.repository }}:{{ .Values.image.inits.tools.tag }}
+        command:
+        - /usr/bin/modify-datasource-plugin-json.sh
+        volumeMounts:
+        - name: grafana-static-hooks
+          mountPath: /usr/bin/modify-datasource-plugin-json.sh
+          subPath: modify-datasource-plugin-json.sh
+        - name: grafana-static-contents
+          mountPath: /host
+        {{- if and .Values.resources .Values.resources.inits }}
+        resources:
+{{ toYaml .Values.resources.inits | indent 10 }}
+        {{- end }}
+      containers:
+      - name: grafana
+        image: {{ .Values.image.repository }}:{{ .Values.image.tag }}
+        env:
+        - name: GF_AUTH_BASIC_ENABLED
+          value: "true"
+        - name: GF_AUTH_ANONYMOUS_ENABLED
+          value: "true"
+        - name: GF_SECURITY_ADMIN_USER
+          valueFrom:
+            secretKeyRef:
+              name: {{ template "app.fullname" . }}
+              key: user
+        - name: GF_SECURITY_ADMIN_PASSWORD
+          valueFrom:
+            secretKeyRef:
+              name: {{ template "app.fullname" . }}
+              key: password
+{{- if .Values.extraVars }}
+{{ toYaml .Values.extraVars | indent 8 }}
+{{- end }}
+        volumeMounts:
+        - name: grafana-storage
+          mountPath: /var/lib/grafana
+        - name: grafana-static-contents
+          mountPath: /usr/share/grafana/public/app/plugins/datasource/prometheus/plugin.json
+          subPath: grafana/plugin.json
+      {{- if .Values.mountGrafanaConfig }}
+        - name: grafana-config
+          mountPath: /etc/grafana
+      {{- end }}
+        ports:
+        - name: web
+          containerPort: 3000
+          protocol: TCP
+        readinessProbe:
+          httpGet:
+            path: /api/health
+            port: 3000
+          periodSeconds: 1
+          timeoutSeconds: 1
+          successThreshold: 1
+          failureThreshold: 10
+        {{- if and .Values.resources .Values.resources.core }}
+        resources:
+{{ toYaml .Values.resources.core | indent 10 }}
+        {{- end }}
+      - name: grafana-watcher
+        image: {{ .Values.grafanaWatcher.repository }}:{{ .Values.grafanaWatcher.tag }}
+        args:
+          - '--grafana-url=http://127.0.0.1:3000'
+          - '--watch-dir=/var/grafana-dashboards'
+          {{- range .Values.dashboardConfigmaps }}
+          - '--watch-dir=/var/additional-dashboards/{{ . }}'
+          {{- end }}
+        env:
+        - name: GRAFANA_USER
+          valueFrom:
+            secretKeyRef:
+              name: {{ template "app.fullname" . }}
+              key: user
+        - name: GRAFANA_PASSWORD
+          valueFrom:
+            secretKeyRef:
+              name: {{ template "app.fullname" . }}
+              key: password
+        {{- if and .Values.resources .Values.resources.watcher }}
+        resources:
+{{ toYaml .Values.resources.watcher | indent 10 }}
+        {{- end }}
+        volumeMounts:
+          - name: grafana-dashboards
+            mountPath: /var/grafana-dashboards
+    {{- range .Values.dashboardConfigmaps }}
+          - name: {{ . }}
+            mountPath: /var/additional-dashboards/{{ . }}
+    {{- end }}
+      - name: grafana-proxy
+        image: {{ .Values.grafanaProxy.repository }}:{{ .Values.grafanaProxy.tag }}
+        args:
+        - nginx
+        - -g
+        - daemon off;
+        - -c
+        - /nginx/nginx.conf
+        ports:
+        - name: http
+          containerPort: 80
+          protocol: TCP
+        volumeMounts:
+        - mountPath: /nginx/
+          name: grafana-nginx
+        {{- if and .Values.resources .Values.resources.proxy }}
+        resources:
+{{ toYaml .Values.resources.proxy | indent 10 }}
+        {{- end }}
+    {{- if .Values.nodeSelector }}
+      nodeSelector:
+    {{ toYaml .Values.nodeSelector | indent 4 }}
+    {{- end }}
+    {{- if .Values.enabledRBAC }}
+      serviceAccountName: {{ .Values.serviceAccountName }}
+    {{- end }}
+    {{- if .Values.tolerations }}
+      tolerations:
+{{ toYaml .Values.tolerations | indent 8 }}
+    {{- end }}
+      securityContext:
+        fsGroup: 472
+      volumes:
+      - name: grafana-static-hooks
+        configMap:
+          name: {{ template "app.hooks.fullname" . }}
+          defaultMode: 0777
+      - name: grafana-static-contents
+        emptyDir: {}
+      - name: grafana-storage
+        {{- if or .Values.storageSpec .Values.persistence.enabled }}
+        persistentVolumeClaim:
+          claimName: {{ template "app.fullname" . }}
+        {{- else }}
+        emptyDir: {}
+        {{- end }}
+      - name: grafana-nginx
+        configMap:
+          defaultMode: 438
+          items:
+          - key: nginx.conf
+            mode: 438
+            path: nginx.conf
+          name: {{ template "app.nginx.fullname" . }}
+      - name: grafana-dashboards
+        configMap:
+          name: {{ template "app.dashboards.fullname" . }}
+      {{- range .Values.dashboardConfigmaps }}
+        - name: {{ . }}
+          configMap:
+            name: {{ . }}
+      {{- end }}

charts/rancher-monitoring/v0.0.2/charts/grafana/templates/hooks-configmap.yaml

+apiVersion: v1
+kind: ConfigMap
+metadata:
+  labels:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+  name: {{ template "app.hooks.fullname" . }}
+data:
+  copy-datasource-plugin-json.sh: |-
+    #!/bin/bash
+
+    srcpath="/usr/share/grafana/public/app/plugins/datasource/prometheus/plugin.json"
+    dstpath="/host/grafana/raw-plugin.json"
+
+    if [[ -f $srcpath ]] && [[ -d /host ]]; then
+      mkdir -p /host/grafana
+      cp -f $srcpath $dstpath
+      cat $srcpath
+
+      exit 0
+    fi
+
+    exit 1
+
+  modify-datasource-plugin-json.sh: |-
+    #!/bin/sh
+
+    srcpath="/host/grafana/raw-plugin.json"
+    dstpath="/host/grafana/plugin.json"
+
+    if [ -f $srcpath ] && [ -d /host ]; then
+      mkdir -p /host/grafana
+
+      token=$(cat /var/run/secrets/kubernetes.io/serviceaccount/token)
+
+      cat $srcpath | K8S_BEARERTOKEN="Bearer $token" jq 'to_entries | . + [{"key":"routes","value":[{"path":"api/v1","url":"{{ .Values.prometheusDatasourceURL }}/api/v1","headers":[{"name":"Authorization","content":env.K8S_BEARERTOKEN}]}]}] | from_entries' > $dstpath
+      cat $dstpath
+
+      exit 0
+    fi
+
+    exit 1
+
+

charts/rancher-monitoring/v0.0.2/charts/grafana/templates/metrics-service.yaml

+apiVersion: v1
+kind: Service
+metadata:
+  name: expose-grafana-metrics
+  labels:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+    monitoring.cattle.io: "true"
+spec:
+  type: ClusterIP
+  selector:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    release: {{ .Release.Name }}
+  ports:
+    - name: web
+      port: 3000
+      targetPort: web
\ No newline at end of file

charts/rancher-monitoring/v0.0.2/charts/grafana/templates/nginx-configmap.yaml

+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: {{ template "app.nginx.fullname" . }}
+  labels:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+    component: nginx
+data:
+  nginx.conf: |-
+    user  nginx;
+    worker_processes  auto;
+    error_log  /dev/null warn;
+    pid        /var/run/nginx.pid;
+    
+    events {
+       worker_connections  1024;
+    }
+
+    http {
+      include /etc/nginx/mime.types;
+
+      log_format  main  '[$time_local - $status] $remote_addr - $remote_user $request ($http_referer)';
+
+      server {
+        listen 80;
+
+        access_log off;
+
+        gzip on;
+        gzip_min_length 1k;
+        gzip_comp_level 2;
+        gzip_types text/plain application/javascript application/x-javascript text/css application/xml text/javascript image/jpeg image/gif image/png;
+        gzip_vary on;
+        gzip_disable "MSIE [1-6]\.";
+
+        proxy_set_header Host $host;
+        proxy_set_header X-Real-IP $remote_addr;
+        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
+        proxy_set_header X-Forwarded-Proto $scheme;
+
+        location /api/dashboards {
+          proxy_pass     http://localhost:3000;
+        }
+
+        location /api/search {
+          proxy_pass     http://localhost:3000;
+
+          sub_filter_types application/json;
+          sub_filter_once off;
+          sub_filter '"url":"/d' '"url":"d';
+        }
+
+        location / {
+          proxy_pass     http://localhost:3000/;
+
+          sub_filter_types text/html;
+          sub_filter_once off;
+          sub_filter '"appSubUrl":""' '"appSubUrl":"."';
+          sub_filter '"url":"/' '"url":"./';
+          sub_filter ':"/avatar/' ':"avatar/';
+        }
+
+      }
+
+    }

charts/rancher-monitoring/v0.0.2/charts/grafana/templates/pvc.yaml

+{{- if or .Values.storageSpec .Values.persistence.enabled -}}
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  labels:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+  name: {{ template "app.fullname" . }}
+spec:
+  {{- if .Values.storageSpec }}
+{{ toYaml .Values.storageSpec | indent 2 }}
+  {{- else }}
+  accessModes:
+    - {{ default "ReadWriteOnce" .Values.persistence.accessMode }}
+  {{ if and .Values.persistence.storageClass (ne "default" .Values.persistence.storageClass) }}
+  storageClassName: {{ .Values.persistence.storageClass }}
+  {{ end }}
+  resources:
+    requests:
+      storage: {{ .Values.persistence.size | quote }}
+  {{- end }}
+{{- end -}}

charts/rancher-monitoring/v0.0.2/charts/grafana/templates/secret.yaml

+apiVersion: v1
+kind: Secret
+metadata:
+  labels:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+  name: {{ template "app.fullname" . }}
+type: Opaque
+data:
+  user: {{ .Values.adminUser | b64enc | quote }}
+  {{- if .Values.adminPassword }}
+  password: {{ .Values.adminPassword | b64enc | quote }}
+  {{- else }}
+  password: {{ randAlphaNum 10 | b64enc | quote }}
+  {{- end }}

charts/rancher-monitoring/v0.0.2/charts/grafana/templates/service.yaml

+apiVersion: v1
+kind: Service
+metadata:
+  name: access-grafana
+  labels:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+    kubernetes.io/cluster-service: "true"
+spec:
+  type: ClusterIP
+  sessionAffinity: ClientIP
+  selector:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    release: {{ .Release.Name }}
+  ports:
+    - name: http
+      port: 80
+      targetPort: http

charts/rancher-monitoring/v0.0.2/charts/grafana/templates/servicemonitor.yaml

+apiVersion: {{ template "operator_api_version" . }}
+kind: ServiceMonitor
+metadata:
+  labels:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+    source: rancher-monitoring
+    {{- if .Values.serviceMonitor.labels }}
+{{ toYaml .Values.serviceMonitor.labels | indent 4 }}
+    {{- end }}    
+  name: {{ template "app.fullname" . }}
+spec:
+  jobLabel: grafana
+  selector:
+    matchLabels:
+      app: {{ template "app.name" . }}
+      chart: {{ template "app.version" . }}
+      release: {{ .Release.Name }}
+      monitoring.cattle.io: "true"
+  namespaceSelector:
+    matchNames:
+      - {{ .Release.Namespace | quote }}
+  endpoints:
+  - port: web
+    interval: 30s

charts/rancher-monitoring/v0.0.2/charts/grafana/values.yaml

+level: cluster
+
+enabledRBAC: true
+
+## Already exist ServiceAccount
+##
+serviceAccountName: ""
+
+enabledPSP: true
+
+## CRD apiGroup
+##
+apiGroup: "monitoring.coreos.com"
+
+## Node labels for Grafana pod assignment
+## Ref: https://kubernetes.io/docs/user-guide/node-selection/
+##
+nodeSelector: {}
+
+## Tolerations for use with node taints
+## Ref: https://kubernetes.io/docs/concepts/configuration/taint-and-toleration/
+##
+tolerations: {}
+  #  - key: "key"
+  #    operator: "Equal"
+  #    value: "value"
+  #    effect: "NoSchedule"
+
+serviceMonitor:
+  ## Custom Labels to be added to ServiceMonitor
+  ##
+  labels: {}
+
+## Pass extra environment variables to the Grafana container.
+##
+# extraVars:
+# - name: EXTRA_VAR_1
+#   value: extra-var-value-1
+# - name: EXTRA_VAR_2
+#   value: extra-var-value-2
+extraVars:
+
+adminUser: "admin"
+adminPassword: "admin"
+
+## Grafana Docker image
+##
+image:
+  repository: grafana/grafana
+  tag: 5.3.0
+  inits:
+    tools:
+      repository: maiwj/curl
+      tag: 7.56.1-r0
+
+storageSpec: {}
+#   storageClassName: default
+#   accessModes:
+#     - ReadWriteOnce
+#   resources:
+#     requests:
+#       storage: 2Gi
+#   selector: {}
+
+## Easy way to create persistent data
+##
+persistence: {}
+#  enabled: true
+#  storageClass: gluster
+#  accessMode: "ReadWriteOnce"
+#  size: 50Gi
+
+## Resource limits & requests
+## Ref: https://kubernetes.io/docs/user-guide/compute-resources/
+resources:
+  inits:
+    limits:
+      memory: 50Mi
+      cpu: 50m
+    requests:
+      memory: 50Mi
+      cpu: 50m
+  core:
+    limits:
+      memory: 200Mi
+      cpu: 200m
+    requests:
+      memory: 100Mi
+      cpu: 100m
+  proxy:
+    limits:
+      memory: 100Mi
+      cpu: 100m
+    requests:
+      memory: 50Mi
+      cpu: 50m
+  watcher:
+    limits:
+      memory: 50Mi
+      cpu: 50m
+    requests:
+      memory: 50Mi
+      cpu: 50m
+
+
+## A list of additional configmaps that contain -dashboard.json and/or -datasource.json files
+## that should be imported into grafana.
+dashboardConfigmaps: []
+
+prometheusDatasourceURL: ""
+
+grafanaProxy:
+  repository: nginx
+  tag: 1.15.2
+
+grafanaWatcher:
+  repository: quay.io/coreos/grafana-watcher
+  tag: v0.0.8
+
+  ## Resource limits & requests
+  ## Ref: https://kubernetes.io/docs/user-guide/compute-resources/
+  resources: {}
+    #requests:
+    #  memory: "16Mi"
+    #  cpu: "50m"
+    #limits:
+    #  memory: "32Mi"
+    #  cpu: "100m"

charts/rancher-monitoring/v0.0.2/charts/metric-expression-cluster/Chart.yaml

+apiVersion: v1
+description: Creates Metrics CRD of Rancher monitoring graph
+engine: gotpl
+maintainers:
+- name: aiwantaozi
+  email: michelia.feng@gmail.com
+name: metric-expression-cluster
+version: 0.0.1
+

charts/rancher-monitoring/v0.0.2/charts/metric-expression-cluster/templates/expressionapiserver.yaml

+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: apiserver-request-latency-milliseconds-avg
+  labels:
+    app: metric-expression
+    component: apiserver
+    details: "false"
+    level: cluster
+    metric: request-latency-milliseconds-avg
+    source: rancher-monitoring
+spec:
+  expression: avg(apiserver_request_latencies_sum / apiserver_request_latencies_count)
+    by (instance) /1e+06
+  legendFormat: '[[instance]]'
+  description: apiserver request latency milliseconds avg
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: apiserver-request-latency-milliseconds-avg-details
+  labels:
+    app: metric-expression
+    component: apiserver
+    details: "true"
+    level: cluster
+    metric: request-latency-milliseconds-avg
+    source: rancher-monitoring
+spec:
+  expression: avg(apiserver_request_latencies_sum / apiserver_request_latencies_count)
+    by (instance, verb) /1e+06
+  legendFormat: '[[verb]]([[instance]])'
+  description: apiserver request latency milliseconds avg
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: apiserver-request-count-sum-rate
+  labels:
+    app: metric-expression
+    component: apiserver
+    details: "false"
+    graph: request-count
+    level: cluster
+    metric: request-count-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(apiserver_request_count[5m])) by (instance)
+  legendFormat: '[[instance]]'
+  description: apiserver request count sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: apiserver-request-count-sum-rate-details
+  labels:
+    app: metric-expression
+    component: apiserver
+    details: "true"
+    graph: request-count
+    level: cluster
+    metric: request-count-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(apiserver_request_count[5m])) by (instance,
+    code)
+  legendFormat: '[[code]]([[instance]])'
+  description: apiserver request count sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: apiserver-request-error-count-sum-rate
+  labels:
+    app: metric-expression
+    component: apiserver
+    details: "false"
+    graph: request-count
+    level: cluster
+    metric: request-error-count-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(apiserver_request_count{instance=~"$instance", code!~"2.."}[5m]))
+    by (instance)
+  legendFormat: '[[instance]]'
+  description: apiserver request error count sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: apiserver-request-error-count-sum-rate-details
+  labels:
+    app: metric-expression
+    component: apiserver
+    details: "true"
+    graph: request-count
+    level: cluster
+    metric: request-error-count-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(apiserver_request_count{instance=~"$instance", code!~"2.."}[5m]))
+    by (instance, code)
+  legendFormat: '[[code]]([[instance]])'
+  description: apiserver request error count sum rate
+---

charts/rancher-monitoring/v0.0.2/charts/metric-expression-cluster/templates/expressioncluster.yaml

+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: cluster-disk-io-reads-bytes-sum-rate
+  labels:
+    app: metric-expression
+    component: cluster
+    details: "false"
+    graph: disk-io
+    level: cluster
+    metric: disk-io-reads-bytes-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(node_disk_read_bytes_total[5m])) by
+    () * 8 / 1024
+  legendFormat: Read
+  description: cluster disk io reads bytes sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: cluster-disk-io-reads-bytes-sum-rate-details
+  labels:
+    app: metric-expression
+    component: cluster
+    details: "true"
+    graph: disk-io
+    level: cluster
+    metric: disk-io-reads-bytes-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(node_disk_read_bytes_total[5m])) by
+    (instance) * 8 / 1024
+  legendFormat: Read([[instance]])
+  description: cluster disk io reads bytes sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: cluster-network-transmit-bytes-sum
+  labels:
+    app: metric-expression
+    component: cluster
+    details: "false"
+    graph: network-io
+    level: cluster
+    metric: network-transmit-bytes-sum
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(node_network_transmit_bytes_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*"}[5m]))
+     * 8 / 1024
+  legendFormat: Transmit
+  description: cluster network transmit bytes sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: cluster-network-transmit-bytes-sum-details
+  labels:
+    app: metric-expression
+    component: cluster
+    details: "true"
+    graph: network-io
+    level: cluster
+    metric: network-transmit-bytes-sum
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(node_network_transmit_bytes_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*"}[5m]))
+    by (instance) * 8 / 1024
+  legendFormat: Transmit([[instance]])
+  description: cluster network transmit bytes sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: cluster-cpu-load-5
+  labels:
+    app: metric-expression
+    component: cluster
+    details: "false"
+    graph: cpu-load
+    level: cluster
+    metric: cpu-load-5
+    source: rancher-monitoring
+spec:
+  expression: sum(node_load5)  / count(node_cpu_seconds_total{mode="system"})
+    
+  legendFormat: Load5
+  description: cluster cpu load 5
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: cluster-cpu-load-5-details
+  labels:
+    app: metric-expression
+    component: cluster
+    details: "true"
+    graph: cpu-load
+    level: cluster
+    metric: cpu-load-5
+    source: rancher-monitoring
+spec:
+  expression: sum(node_load5) by (instance) / count(node_cpu_seconds_total{mode="system"})
+    by (instance)
+  legendFormat: Load5([[instance]])
+  description: cluster cpu load 5
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: cluster-cpu-load-1
+  labels:
+    app: metric-expression
+    component: cluster
+    details: "false"
+    graph: cpu-load
+    level: cluster
+    metric: cpu-load-1
+    source: rancher-monitoring
+spec:
+  expression: sum(node_load1)  / count(node_cpu_seconds_total{mode="system"})
+    
+  legendFormat: Load1
+  description: cluster cpu load 1
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: cluster-cpu-load-1-details
+  labels:
+    app: metric-expression
+    component: cluster
+    details: "true"
+    graph: cpu-load
+    level: cluster
+    metric: cpu-load-1
+    source: rancher-monitoring
+spec:
+  expression: sum(node_load1) by (instance) / count(node_cpu_seconds_total{mode="system"})
+    by (instance)
+  legendFormat: Load1([[instance]])
+  description: cluster cpu load 1
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: cluster-disk-io-writes-bytes-sum-rate
+  labels:
+    app: metric-expression
+    component: cluster
+    details: "false"
+    graph: disk-io
+    level: cluster
+    metric: disk-io-writes-bytes-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(node_disk_written_bytes_total[5m]))
+     * 8 / 1024
+  legendFormat: Write
+  description: cluster disk io writes bytes sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: cluster-disk-io-writes-bytes-sum-rate-details
+  labels:
+    app: metric-expression
+    component: cluster
+    details: "true"
+    graph: disk-io
+    level: cluster
+    metric: disk-io-writes-bytes-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(node_disk_written_bytes_total[5m]))
+    by (instance) * 8 / 1024
+  legendFormat: Write([[instance]])
+  description: cluster disk io writes bytes sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: cluster-fs-usage-percent
+  labels:
+    app: metric-expression
+    component: cluster
+    details: "false"
+    level: cluster
+    metric: fs-usage-percent
+    source: rancher-monitoring
+spec:
+  expression: (sum(node_filesystem_size_bytes{device!="rootfs"})
+     - sum(node_filesystem_free_bytes{device!="rootfs"})
+    ) / sum(node_filesystem_size_bytes{device!="rootfs"})
+    
+  legendFormat: Disk usage
+  description: cluster fs usage percent
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: cluster-fs-usage-percent-details
+  labels:
+    app: metric-expression
+    component: cluster
+    details: "true"
+    level: cluster
+    metric: fs-usage-percent
+    source: rancher-monitoring
+spec:
+  expression: (sum(node_filesystem_size_bytes{device!="rootfs"})
+    by (instance) - sum(node_filesystem_free_bytes{device!="rootfs"})
+    by (instance)) / sum(node_filesystem_size_bytes{device!="rootfs"})
+    by (instance)
+  legendFormat: '[[instance]]'
+  description: cluster fs usage percent
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: cluster-network-receive-errors-sum
+  labels:
+    app: metric-expression
+    component: cluster
+    details: "false"
+    graph: network-packet
+    level: cluster
+    metric: network-receive-errors-sum
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(node_network_receive_errs_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*"}[5m]))
+    
+  legendFormat: Receive errors
+  description: cluster network receive errors sum
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: cluster-network-receive-errors-sum-details
+  labels:
+    app: metric-expression
+    component: cluster
+    details: "true"
+    graph: network-packet
+    level: cluster
+    metric: network-receive-errors-sum
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(node_network_receive_errs_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*"}[5m]))
+    by (instance)
+  legendFormat: Receive errors([[instance]])
+  description: cluster network receive errors sum
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: cluster-cpu-load-15
+  labels:
+    app: metric-expression
+    component: cluster
+    details: "false"
+    graph: cpu-load
+    level: cluster
+    metric: cpu-load-15
+    source: rancher-monitoring
+spec:
+  expression: sum(node_load15)  / count(node_cpu_seconds_total{mode="system"})
+    
+  legendFormat: Load15
+  description: cluster cpu load 15
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: cluster-cpu-load-15-details
+  labels:
+    app: metric-expression
+    component: cluster
+    details: "true"
+    graph: cpu-load
+    level: cluster
+    metric: cpu-load-15
+    source: rancher-monitoring
+spec:
+  expression: sum(node_load15) by (instance) / count(node_cpu_seconds_total{mode="system"})
+    by (instance)
+  legendFormat: Load15([[instance]])
+  description: cluster cpu load 15
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: cluster-network-receive-bytes-sum
+  labels:
+    app: metric-expression
+    component: cluster
+    details: "false"
+    graph: network-io
+    level: cluster
+    metric: network-receive-bytes-sum
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(node_network_receive_bytes_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*"}[5m]))
+     * 8 / 1024
+  legendFormat: Receive
+  description: cluster network receive bytes sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: cluster-network-receive-bytes-sum-details
+  labels:
+    app: metric-expression
+    component: cluster
+    details: "true"
+    graph: network-io
+    level: cluster
+    metric: network-receive-bytes-sum
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(node_network_receive_bytes_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*"}[5m]))
+    by (instance) * 8 / 1024
+  legendFormat: Receive([[instance]])
+  description: cluster network receive bytes sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: cluster-network-receive-packets-sum
+  labels:
+    app: metric-expression
+    component: cluster
+    details: "false"
+    graph: network-packet
+    level: cluster
+    metric: network-receive-packets-sum
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(node_network_receive_packets_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*"}[5m]))
+    
+  legendFormat: Receive packets
+  description: cluster network receive packets sum
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: cluster-network-receive-packets-sum-details
+  labels:
+    app: metric-expression
+    component: cluster
+    details: "true"
+    graph: network-packet
+    level: cluster
+    metric: network-receive-packets-sum
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(node_network_receive_packets_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*"}[5m]))
+    by (instance)
+  legendFormat: Receive packets([[instance]])
+  description: cluster network receive packets sum
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: cluster-network-transmit-errors-sum
+  labels:
+    app: metric-expression
+    component: cluster
+    details: "false"
+    graph: network-packet
+    level: cluster
+    metric: network-transmit-errors-sum
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(node_network_transmit_errs_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*"}[5m]))
+    
+  legendFormat: Transmit errors
+  description: cluster network transmit errors sum
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: cluster-network-transmit-errors-sum-details
+  labels:
+    app: metric-expression
+    component: cluster
+    details: "true"
+    graph: network-packet
+    level: cluster
+    metric: network-transmit-errors-sum
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(node_network_transmit_errs_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*"}[5m]))
+    by (instance)
+  legendFormat: Transmit errors([[instance]])
+  description: cluster network transmit errors sum
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: cluster-network-receive-packets-dropped-sum
+  labels:
+    app: metric-expression
+    component: cluster
+    details: "false"
+    graph: network-packet
+    level: cluster
+    metric: network-receive-packets-dropped-sum
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(node_network_receive_drop_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*"}[5m]))
+    
+  legendFormat: Receive dropped
+  description: cluster network receive packets dropped sum
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: cluster-network-receive-packets-dropped-sum-details
+  labels:
+    app: metric-expression
+    component: cluster
+    details: "true"
+    graph: network-packet
+    level: cluster
+    metric: network-receive-packets-dropped-sum
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(node_network_receive_drop_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*"}[5m]))
+    by (instance)
+  legendFormat: Receive dropped([[instance]])
+  description: cluster network receive packets dropped sum
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: cluster-network-transmit-packets-dropped-sum
+  labels:
+    app: metric-expression
+    component: cluster
+    details: "false"
+    graph: network-packet
+    level: cluster
+    metric: network-transmit-packets-dropped-sum
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(node_network_transmit_drop_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*"}[5m]))
+    
+  legendFormat: Transmit dropped
+  description: cluster network transmit packets dropped sum
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: cluster-network-transmit-packets-dropped-sum-details
+  labels:
+    app: metric-expression
+    component: cluster
+    details: "true"
+    graph: network-packet
+    level: cluster
+    metric: network-transmit-packets-dropped-sum
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(node_network_transmit_drop_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*"}[5m]))
+    by (instance)
+  legendFormat: Transmit dropped([[instance]])
+  description: cluster network transmit packets dropped sum
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: cluster-network-transmit-packets-sum
+  labels:
+    app: metric-expression
+    component: cluster
+    details: "false"
+    graph: network-packet
+    level: cluster
+    metric: network-transmit-packets-sum
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(node_network_transmit_packets_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*"}[5m]))
+    
+  legendFormat: Transmit packets
+  description: cluster network transmit packets sum
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: cluster-network-transmit-packets-sum-details
+  labels:
+    app: metric-expression
+    component: cluster
+    details: "true"
+    graph: network-packet
+    level: cluster
+    metric: network-transmit-packets-sum
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(node_network_transmit_packets_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*"}[5m]))
+    by (instance)
+  legendFormat: Transmit packets([[instance]])
+  description: cluster network transmit packets sum
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: cluster-cpu-usage-seconds-sum-rate
+  labels:
+    app: metric-expression
+    component: cluster
+    details: "false"
+    level: cluster
+    metric: cpu-usage-seconds-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: 1 - (avg(irate(node_cpu_seconds_total{mode="idle"}[5m])))
+  legendFormat: CPU usage
+  description: cluster cpu usage seconds sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: cluster-cpu-usage-seconds-sum-rate-details
+  labels:
+    app: metric-expression
+    component: cluster
+    details: "true"
+    level: cluster
+    metric: cpu-usage-seconds-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: 1 - (avg(irate(node_cpu_seconds_total{mode="idle"}[5m])) by (instance))
+  legendFormat: '[[instance]]'
+  description: cluster cpu usage seconds sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: cluster-memory-usage-percent
+  labels:
+    app: metric-expression
+    component: cluster
+    details: "false"
+    level: cluster
+    metric: memory-usage-percent
+    source: rancher-monitoring
+spec:
+  expression: 1 - sum(node_memory_MemAvailable_bytes) 
+    / sum(node_memory_MemTotal_bytes) 
+  legendFormat: Memory usage
+  description: cluster memory usage percent
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: cluster-memory-usage-percent-details
+  labels:
+    app: metric-expression
+    component: cluster
+    details: "true"
+    level: cluster
+    metric: memory-usage-percent
+    source: rancher-monitoring
+spec:
+  expression: 1 - sum(node_memory_MemAvailable_bytes) by (instance)
+    / sum(node_memory_MemTotal_bytes) by (instance)
+  legendFormat: '[[instance]]'
+  description: cluster memory usage percent
+---

charts/rancher-monitoring/v0.0.2/charts/metric-expression-cluster/templates/expressioncontainer.yaml

+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: container-cpu-cfs-throttled-seconds-sum-rate
+  labels:
+    app: metric-expression
+    component: container
+    details: "false"
+    graph: container-cpu-usage-details
+    level: project
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_cpu_cfs_throttled_seconds_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name=~"$containerName"}[5m])) by (container_name)
+  legendFormat: CPU cfs throttled
+  description: container cpu cfs throttled seconds sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: container-cpu-cfs-throttled-seconds-sum-rate-details
+  labels:
+    app: metric-expression
+    component: container
+    details: "true"
+    graph: container-cpu-usage-details
+    level: project
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_cpu_cfs_throttled_seconds_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name=~"$containerName"}[5m])) by (container_name)
+  legendFormat: CPU cfs throttled([[container_name]])
+  description: container cpu cfs throttled seconds sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: container-cpu-usage-seconds-sum-rate
+  labels:
+    app: metric-expression
+    component: container
+    details: "false"
+    graph: container-cpu-usage
+    level: project
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_cpu_usage_seconds_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name=~"$containerName"}[5m])) by (container_name)
+  legendFormat: CPU usage
+  description: container cpu usage seconds sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: container-cpu-usage-seconds-sum-rate-details
+  labels:
+    app: metric-expression
+    component: container
+    details: "true"
+    graph: container-cpu-usage
+    level: project
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_cpu_usage_seconds_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name=~"$containerName"}[5m])) by (container_name)
+  legendFormat: CPU usage([[container_name]])
+  description: container cpu usage seconds sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: container-cpu-system-seconds-sum-rate
+  labels:
+    app: metric-expression
+    component: container
+    details: "false"
+    graph: container-cpu-usage-details
+    level: project
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_cpu_system_seconds_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name=~"$containerName"}[5m])) by (container_name)
+  legendFormat: CPU system seconds
+  description: container cpu system seconds sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: container-cpu-system-seconds-sum-rate-details
+  labels:
+    app: metric-expression
+    component: container
+    details: "true"
+    graph: container-cpu-usage-details
+    level: project
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_cpu_system_seconds_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name=~"$containerName"}[5m])) by (container_name)
+  legendFormat: CPU system seconds([[container_name]])
+  description: container cpu system seconds sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: container-cpu-user-seconds-sum-rate
+  labels:
+    app: metric-expression
+    component: container
+    details: "false"
+    graph: container-cpu-usage-details
+    level: project
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_cpu_user_seconds_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name=~"$containerName"}[5m])) by (container_name)
+  legendFormat: CPU user seconds
+  description: container cpu user seconds sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: container-cpu-user-seconds-sum-rate-details
+  labels:
+    app: metric-expression
+    component: container
+    details: "true"
+    graph: container-cpu-usage-details
+    level: project
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_cpu_user_seconds_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name=~"$containerName"}[5m])) by (container_name)
+  legendFormat: CPU user seconds([[container_name]])
+  description: container cpu user seconds sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: container-memory-usage-percent
+  labels:
+    app: metric-expression
+    component: container
+    details: "false"
+    level: project
+    metric: memory-usage-percent
+    source: rancher-monitoring
+spec:
+  expression: sum(container_memory_working_set_bytes{namespace=~"$namespace", pod_name=~"$podName",
+    container_name=~"$containerName"}) by (container_name) / sum(label_join(kube_pod_container_resource_limits_memory_bytes{namespace=~"$namespace",
+    pod=~"$podName", container=~"$containerName"},"container_name", "", "container"))
+    by (container_name)
+  legendFormat: Memory
+  description: container memory usage percent
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: container-memory-usage-percent-details
+  labels:
+    app: metric-expression
+    component: container
+    details: "true"
+    level: project
+    metric: memory-usage-percent
+    source: rancher-monitoring
+spec:
+  expression: sum(container_memory_working_set_bytes{namespace=~"$namespace", pod_name=~"$podName",
+    container_name=~"$containerName"}) by (container_name) / sum(label_join(kube_pod_container_resource_limits_memory_bytes{namespace=~"$namespace",
+    pod=~"$podName", container=~"$containerName"},"container_name", "", "container"))
+    by (container_name)
+  legendFormat: Memory([[container_name]])
+  description: container memory usage percent
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: container-memory-usage-bytes-sum
+  labels:
+    app: metric-expression
+    component: container
+    details: "false"
+    level: project
+    metric: memory-usage-bytes-sum
+    source: rancher-monitoring
+spec:
+  expression: sum(container_memory_working_set_bytes{name!~"POD", namespace=~"$namespace",pod_name=~"$podName",
+    container_name=~"$containerName"}) by (container_name)
+  legendFormat: Memory usage
+  description: container memory usage bytes sum
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: container-memory-usage-bytes-sum-details
+  labels:
+    app: metric-expression
+    component: container
+    details: "true"
+    level: project
+    metric: memory-usage-bytes-sum
+    source: rancher-monitoring
+spec:
+  expression: sum(container_memory_working_set_bytes{name!~"POD", namespace=~"$namespace",pod_name=~"$podName",
+    container_name=~"$containerName"}) by (container_name)
+  legendFormat: Memory usage([[container_name]])
+  description: container memory usage bytes sum
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: container-fs-bytes-sum
+  labels:
+    app: metric-expression
+    component: container
+    details: "false"
+    level: project
+    metric: fs-bytes-sum
+    source: rancher-monitoring
+spec:
+  expression: sum(container_fs_usage_bytes{namespace=~"$namespace", pod_name=~"$podName",
+    container_name=~"$containerName"}) by (container_name)
+  legendFormat: Filesystem usage
+  description: container fs bytes sum
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: container-fs-bytes-sum-details
+  labels:
+    app: metric-expression
+    component: container
+    details: "true"
+    level: project
+    metric: fs-bytes-sum
+    source: rancher-monitoring
+spec:
+  expression: sum(container_fs_usage_bytes{namespace=~"$namespace", pod_name=~"$podName",
+    container_name=~"$containerName"}) by (container_name)
+  legendFormat: Filesystem usage([[container_name]])
+  description: container fs bytes sum
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: container-disk-io-writes-bytes-sum-rate
+  labels:
+    app: metric-expression
+    component: container
+    details: "false"
+    graph: disk-io
+    level: project
+    metric: disk-io-writes-bytes-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_fs_writes_bytes_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name=~"$containerName"}[5m])) by (container_name) * 8 / 1024
+  legendFormat: Write
+  description: container disk io writes bytes sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: container-disk-io-writes-bytes-sum-rate-details
+  labels:
+    app: metric-expression
+    component: container
+    details: "true"
+    graph: disk-io
+    level: project
+    metric: disk-io-writes-bytes-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_fs_writes_bytes_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name=~"$containerName"}[5m])) by (container_name) * 8 / 1024
+  legendFormat: Write([[container_name]])
+  description: container disk io writes bytes sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: container-disk-io-reads-bytes-sum-rate
+  labels:
+    app: metric-expression
+    component: container
+    details: "false"
+    graph: disk-io
+    level: project
+    metric: disk-io-reads-bytes-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_fs_reads_bytes_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name=~"$containerName"}[5m])) by (container_name)  * 8 / 1024
+  legendFormat: Read
+  description: container disk io reads bytes sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: container-disk-io-reads-bytes-sum-rate-details
+  labels:
+    app: metric-expression
+    component: container
+    details: "true"
+    graph: disk-io
+    level: project
+    metric: disk-io-reads-bytes-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_fs_reads_bytes_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name=~"$containerName"}[5m])) by (container_name)  * 8 / 1024
+  legendFormat: Read([[container_name]])
+  description: container disk io reads bytes sum rate
+---

charts/rancher-monitoring/v0.0.2/charts/metric-expression-cluster/templates/expressioncontrollermanager.yaml

+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: controllermanager-volumes-depth
+  labels:
+    app: metric-expression
+    component: controllermanager
+    details: "false"
+    level: cluster
+    metric: volumes-depth
+    source: rancher-monitoring
+spec:
+  expression: sum(volumes_depth) 
+  legendFormat: Volumes depth
+  description: controllermanager volumes depth
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: controllermanager-volumes-depth-details
+  labels:
+    app: metric-expression
+    component: controllermanager
+    details: "true"
+    level: cluster
+    metric: volumes-depth
+    source: rancher-monitoring
+spec:
+  expression: sum(volumes_depth) by (instance)
+  legendFormat: Volumes depth([[instance]])
+  description: controllermanager volumes depth
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: controllermanager-deployment-depth
+  labels:
+    app: metric-expression
+    component: controllermanager
+    details: "false"
+    level: cluster
+    metric: deployment-depth
+    source: rancher-monitoring
+spec:
+  expression: sum(deployment_depth) 
+  legendFormat: Deployment depth
+  description: controllermanager deployment adds
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: controllermanager-deployment-depth-details
+  labels:
+    app: metric-expression
+    component: controllermanager
+    details: "true"
+    level: cluster
+    metric: deployment-depth
+    source: rancher-monitoring
+spec:
+  expression: sum(deployment_depth) by (instance)
+  legendFormat: Deployment depth([[instance]])
+  description: controllermanager deployment adds
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: controllermanager-replicaset-depth
+  labels:
+    app: metric-expression
+    component: controllermanager
+    details: "false"
+    level: cluster
+    metric: replicaset-depth
+    source: rancher-monitoring
+spec:
+  expression: sum(replicaset_depth) 
+  legendFormat: Replicaset depth
+  description: controllermanager replicaset depth
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: controllermanager-replicaset-depth-details
+  labels:
+    app: metric-expression
+    component: controllermanager
+    details: "true"
+    level: cluster
+    metric: replicaset-depth
+    source: rancher-monitoring
+spec:
+  expression: sum(replicaset_depth) by (instance)
+  legendFormat: Replicaset depth([[instance]])
+  description: controllermanager replicaset depth
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: controllermanager-service-depth
+  labels:
+    app: metric-expression
+    component: controllermanager
+    details: "false"
+    level: cluster
+    metric: service-depth
+    source: rancher-monitoring
+spec:
+  expression: sum(service_depth) 
+  legendFormat: Service depth
+  description: controllermanager service depth
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: controllermanager-service-depth-details
+  labels:
+    app: metric-expression
+    component: controllermanager
+    details: "true"
+    level: cluster
+    metric: service-depth
+    source: rancher-monitoring
+spec:
+  expression: sum(service_depth) by (instance)
+  legendFormat: Service depth([[instance]])
+  description: controllermanager service depth
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: controllermanager-serviceaccount-depth
+  labels:
+    app: metric-expression
+    component: controllermanager
+    details: "false"
+    level: cluster
+    metric: serviceaccount-depth
+    source: rancher-monitoring
+spec:
+  expression: sum(serviceaccount_depth) 
+  legendFormat: Serviceaccount depth
+  description: controllermanager serviceaccount depth
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: controllermanager-serviceaccount-depth-details
+  labels:
+    app: metric-expression
+    component: controllermanager
+    details: "true"
+    level: cluster
+    metric: serviceaccount-depth
+    source: rancher-monitoring
+spec:
+  expression: sum(serviceaccount_depth) by (instance)
+  legendFormat: Serviceaccount depth([[instance]])
+  description: controllermanager serviceaccount depth
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: controllermanager-endpoint-depth
+  labels:
+    app: metric-expression
+    component: controllermanager
+    details: "false"
+    level: cluster
+    metric: endpoint-depth
+    source: rancher-monitoring
+spec:
+  expression: sum(endpoint_depth) 
+  legendFormat: Endpoint depth
+  description: controllermanager endpoint depth
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: controllermanager-endpoint-depth-details
+  labels:
+    app: metric-expression
+    component: controllermanager
+    details: "true"
+    level: cluster
+    metric: endpoint-depth
+    source: rancher-monitoring
+spec:
+  expression: sum(endpoint_depth) by (instance)
+  legendFormat: Endpoint depth([[instance]])
+  description: controllermanager endpoint depth
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: controllermanager-daemonset-depth
+  labels:
+    app: metric-expression
+    component: controllermanager
+    details: "false"
+    level: cluster
+    metric: daemonset-depth
+    source: rancher-monitoring
+spec:
+  expression: sum(daemonset_depth) 
+  legendFormat: Daemonset depth
+  description: controllermanager daemonset depth
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: controllermanager-daemonset-depth-details
+  labels:
+    app: metric-expression
+    component: controllermanager
+    details: "true"
+    level: cluster
+    metric: daemonset-depth
+    source: rancher-monitoring
+spec:
+  expression: sum(daemonset_depth) by (instance)
+  legendFormat: Daemonset depth([[instance]])
+  description: controllermanager daemonset depth
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: controllermanager-deployment-depth
+  labels:
+    app: metric-expression
+    component: controllermanager
+    details: "false"
+    level: cluster
+    metric: deployment-depth
+    source: rancher-monitoring
+spec:
+  expression: sum(deployment_depth) 
+  legendFormat: Deployment depth
+  description: controllermanager deployment depth
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: controllermanager-deployment-depth-details
+  labels:
+    app: metric-expression
+    component: controllermanager
+    details: "true"
+    level: cluster
+    metric: deployment-depth
+    source: rancher-monitoring
+spec:
+  expression: sum(deployment_depth) by (instance)
+  legendFormat: Deployment depth([[instance]])
+  description: controllermanager deployment depth
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: controllermanager-statefulset-depth
+  labels:
+    app: metric-expression
+    component: controllermanager
+    details: "false"
+    level: cluster
+    metric: statefulset-depth
+    source: rancher-monitoring
+spec:
+  expression: sum(statefulset_depth) 
+  legendFormat: Statefulset depth
+  description: controllermanager statefulset adds
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: controllermanager-statefulset-depth-details
+  labels:
+    app: metric-expression
+    component: controllermanager
+    details: "true"
+    level: cluster
+    metric: statefulset-depth
+    source: rancher-monitoring
+spec:
+  expression: sum(statefulset_depth) by (instance)
+  legendFormat: Statefulset depth([[instance]])
+  description: controllermanager statefulset adds
+---

charts/rancher-monitoring/v0.0.2/charts/metric-expression-cluster/templates/expressionetcd.yaml

+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: etcd-server-failed-proposal
+  labels:
+    app: metric-expression
+    component: etcd
+    details: "false"
+    level: cluster
+    metric: server-failed-proposal
+    source: rancher-monitoring
+spec:
+  expression: count(up{job="exporter-kube-etcd-cluster-monitoring"}) by (instance)
+  legendFormat: Failed proposal
+  description: etcd Server failed proposal
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: etcd-server-failed-proposal-details
+  labels:
+    app: metric-expression
+    component: etcd
+    details: "true"
+    level: cluster
+    metric: server-failed-proposal
+    source: rancher-monitoring
+spec:
+  expression: count(up{job="exporter-kube-etcd-cluster-monitoring"}) by (instance)
+  legendFormat: Failed proposal
+  description: etcd Server failed proposal
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: etcd-server-leader-changes-seen-sum-increase
+  labels:
+    app: metric-expression
+    component: etcd
+    details: "false"
+    level: cluster
+    metric: server-leader-changes-seen-sum-increase
+    source: rancher-monitoring
+spec:
+  expression: max(etcd_server_leader_changes_seen_total)
+  legendFormat: Number of leader changes per hour
+  description: etcd server leader changes seen sum increase
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: etcd-server-leader-changes-seen-sum-increase-details
+  labels:
+    app: metric-expression
+    component: etcd
+    details: "true"
+    level: cluster
+    metric: server-leader-changes-seen-sum-increase
+    source: rancher-monitoring
+spec:
+  expression: max(etcd_server_leader_changes_seen_total)
+  legendFormat: Number of leader changes per hour
+  description: etcd server leader changes seen sum increase
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: etcd-grpc-client-receive-bytes-sum-rate
+  labels:
+    app: metric-expression
+    component: etcd
+    details: "false"
+    graph: rpc-client-traffic
+    level: cluster
+    metric: grpc-client-receive-bytes-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(etcd_network_client_grpc_received_bytes_total[5m]))  *
+    8 / 1024
+  legendFormat: Client traffic in
+  description: etcd grpc client receive bytes sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: etcd-grpc-client-receive-bytes-sum-rate-details
+  labels:
+    app: metric-expression
+    component: etcd
+    details: "true"
+    graph: rpc-client-traffic
+    level: cluster
+    metric: grpc-client-receive-bytes-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(etcd_network_client_grpc_received_bytes_total[5m])) by (instance)
+    * 8 / 1024
+  legendFormat: Client traffic in([[instance]])
+  description: etcd grpc client receive bytes sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: etcd-db-bytes-sum
+  labels:
+    app: metric-expression
+    component: etcd
+    details: "false"
+    level: cluster
+    metric: db-bytes-sum
+    source: rancher-monitoring
+spec:
+  expression: sum(etcd_debugging_mvcc_db_total_size_in_bytes) 
+  legendFormat: DB size
+  description: etcd db bytes sum
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: etcd-db-bytes-sum-details
+  labels:
+    app: metric-expression
+    component: etcd
+    details: "true"
+    level: cluster
+    metric: db-bytes-sum
+    source: rancher-monitoring
+spec:
+  expression: sum(etcd_debugging_mvcc_db_total_size_in_bytes) by (instance)
+  legendFormat: DB size([[instance]])
+  description: etcd db bytes sum
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: etcd-grpc-client-transmit-bytes-sum-rate
+  labels:
+    app: metric-expression
+    component: etcd
+    details: "false"
+    graph: rpc-client-traffic
+    level: cluster
+    metric: grpc-client-transmit-bytes-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(etcd_network_client_grpc_sent_bytes_total[5m])) 
+  legendFormat: Client traffic out
+  description: etcd grpc client transmit bytes sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: etcd-grpc-client-transmit-bytes-sum-rate-details
+  labels:
+    app: metric-expression
+    component: etcd
+    details: "true"
+    graph: rpc-client-traffic
+    level: cluster
+    metric: grpc-client-transmit-bytes-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(etcd_network_client_grpc_sent_bytes_total[5m])) by (instance)
+  legendFormat: Client traffic out([[instance]])
+  description: etcd grpc client transmit bytes sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: etcd-server-leader-sum
+  labels:
+    app: metric-expression
+    component: etcd
+    details: "false"
+    level: cluster
+    metric: server-leader-sum
+    source: rancher-monitoring
+spec:
+  expression: max(etcd_server_has_leader)
+  legendFormat: Has leader
+  description: etcd server leader sum
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: etcd-server-leader-sum-details
+  labels:
+    app: metric-expression
+    component: etcd
+    details: "true"
+    level: cluster
+    metric: server-leader-sum
+    source: rancher-monitoring
+spec:
+  expression: max(etcd_server_has_leader)
+  legendFormat: Has leader
+  description: etcd server leader sum
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: etcd-server-proposals-committed-sum-increase
+  labels:
+    app: metric-expression
+    component: etcd
+    details: "false"
+    graph: proposal
+    level: cluster
+    metric: server-proposals-committed-sum-increase
+    source: rancher-monitoring
+spec:
+  expression: sum(increase(etcd_server_proposals_committed_total[5m])) 
+  legendFormat: Proposal commit rate
+  description: etcd server proposals committed sum increase
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: etcd-server-proposals-committed-sum-increase-details
+  labels:
+    app: metric-expression
+    component: etcd
+    details: "true"
+    graph: proposal
+    level: cluster
+    metric: server-proposals-committed-sum-increase
+    source: rancher-monitoring
+spec:
+  expression: sum(increase(etcd_server_proposals_committed_total[5m])) by (instance)
+  legendFormat: Proposal commit rate([[instance]])
+  description: etcd server proposals committed sum increase
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: etcd-server-proposals-applied-sum-increase
+  labels:
+    app: metric-expression
+    component: etcd
+    details: "false"
+    graph: proposal
+    level: cluster
+    metric: server-proposals-applied-sum-increase
+    source: rancher-monitoring
+spec:
+  expression: sum(increase(etcd_server_proposals_applied_total[5m])) 
+  legendFormat: Proposals applied
+  description: etcd server proposals applied sum increase
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: etcd-server-proposals-applied-sum-increase-details
+  labels:
+    app: metric-expression
+    component: etcd
+    details: "true"
+    graph: proposal
+    level: cluster
+    metric: server-proposals-applied-sum-increase
+    source: rancher-monitoring
+spec:
+  expression: sum(increase(etcd_server_proposals_applied_total[5m])) by (instance)
+  legendFormat: proposals applied([[instance]])
+  description: etcd server proposals applied sum increase
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: etcd-server-proposals-failed-sum-increase
+  labels:
+    app: metric-expression
+    component: etcd
+    details: "false"
+    graph: proposal
+    level: cluster
+    metric: server-proposals-failed-sum-increase
+    source: rancher-monitoring
+spec:
+  expression: sum(increase(etcd_server_proposals_failed_total[5m])) 
+  legendFormat: Proposals failed
+  description: etcd server proposals failed sum increase
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: etcd-server-proposals-failed-sum-increase-details
+  labels:
+    app: metric-expression
+    component: etcd
+    details: "true"
+    graph: proposal
+    level: cluster
+    metric: server-proposals-failed-sum-increase
+    source: rancher-monitoring
+spec:
+  expression: sum(increase(etcd_server_proposals_failed_total[5m])) by (instance)
+  legendFormat: proposals failed([[instance]])
+  description: etcd server proposals failed sum increase
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: etcd-server-proposals-pending-sum-increase
+  labels:
+    app: metric-expression
+    component: etcd
+    details: "false"
+    graph: proposal
+    level: cluster
+    metric: server-proposals-pending-sum-increase
+    source: rancher-monitoring
+spec:
+  expression: sum(increase(etcd_server_proposals_pending[5m])) 
+  legendFormat: Proposals pending
+  description: etcd server proposals pending sum increase
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: etcd-server-proposals-pending-sum-increase-details
+  labels:
+    app: metric-expression
+    component: etcd
+    details: "true"
+    graph: proposal
+    level: cluster
+    metric: server-proposals-pending-sum-increase
+    source: rancher-monitoring
+spec:
+  expression: sum(increase(etcd_server_proposals_pending[5m])) by (instance)
+  legendFormat: proposals pending([[instance]])
+  description: etcd server proposals pending sum increase
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: etcd-disk-wal-fsync-duration-seconds-sum-quantile
+  labels:
+    app: metric-expression
+    component: etcd
+    details: "false"
+    graph: sync-duration
+    level: cluster
+    metric: disk-wal-fsync-duration-seconds-sum-quantile
+    source: rancher-monitoring
+spec:
+  expression: sum(histogram_quantile(0.99, rate(etcd_disk_wal_fsync_duration_seconds_bucket[5m])))
+    
+  legendFormat: WAL fsync
+  description: etcd disk wal fsync duration seconds sum quantile
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: etcd-disk-wal-fsync-duration-seconds-sum-quantile-details
+  labels:
+    app: metric-expression
+    component: etcd
+    details: "true"
+    graph: sync-duration
+    level: cluster
+    metric: disk-wal-fsync-duration-seconds-sum-quantile
+    source: rancher-monitoring
+spec:
+  expression: sum(histogram_quantile(0.99, rate(etcd_disk_wal_fsync_duration_seconds_bucket[5m])))
+    by (instance)
+  legendFormat: WAL fsync([[instance]])
+  description: etcd disk wal fsync duration seconds sum quantile
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: etcd-grpc-request-error-percent
+  labels:
+    app: metric-expression
+    component: etcd
+    details: "false"
+    level: cluster
+    metric: grpc-request-error-percent
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(grpc_server_handled_total{grpc_code!="OK"}[5m]))  / sum(rate(grpc_server_handled_total[5m]))
+    
+  legendFormat: Rpc failed rate
+  description: etcd grpc request error percent
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: etcd-grpc-request-error-percent-details
+  labels:
+    app: metric-expression
+    component: etcd
+    details: "true"
+    level: cluster
+    metric: grpc-request-error-percent
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(grpc_server_handled_total{grpc_code!="OK"}[5m])) by (instance)
+    / sum(rate(grpc_server_handled_total[5m])) by (instance)
+  legendFormat: RPC failed rate([[instance]])
+  description: etcd grpc request error percent
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: etcd-disk-commit-duration-seconds-sum-quantile
+  labels:
+    app: metric-expression
+    component: etcd
+    details: "false"
+    graph: sync-duration
+    level: cluster
+    metric: disk-commit-duration-seconds-sum-quantile
+    source: rancher-monitoring
+spec:
+  expression: sum(histogram_quantile(0.99, rate(etcd_disk_backend_commit_duration_seconds_bucket[5m])))
+    
+  legendFormat: DB fsync
+  description: etcd disk commit duration seconds sum quantile
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: etcd-disk-commit-duration-seconds-sum-quantile-details
+  labels:
+    app: metric-expression
+    component: etcd
+    details: "true"
+    graph: sync-duration
+    level: cluster
+    metric: disk-commit-duration-seconds-sum-quantile
+    source: rancher-monitoring
+spec:
+  expression: sum(histogram_quantile(0.99, rate(etcd_disk_backend_commit_duration_seconds_bucket[5m])))
+    by (instance)
+  legendFormat: DB fsync([[instance]])
+  description: etcd disk commit duration seconds sum quantile
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: etcd-grpc-request-slow-quantile
+  labels:
+    app: metric-expression
+    component: etcd
+    details: "false"
+    level: cluster
+    metric: grpc-request-slow-quantile
+    source: rancher-monitoring
+spec:
+  expression: sum(histogram_quantile(0.99, sum(rate(grpc_server_handling_seconds_bucket{grpc_type="unary"}[5m]))))
+    
+  legendFormat: Request slow"
+  description: etcd grpc request slow quantile
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: etcd-grpc-request-slow-quantile-details
+  labels:
+    app: metric-expression
+    component: etcd
+    details: "true"
+    level: cluster
+    metric: grpc-request-slow-quantile
+    source: rancher-monitoring
+spec:
+  expression: sum(histogram_quantile(0.99, sum(rate(grpc_server_handling_seconds_bucket{grpc_type="unary"}[5m]))))
+    by (instance)
+  legendFormat: Request slow([[instance]])
+  description: etcd grpc request slow quantile
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: etcd-active-watch-stream
+  labels:
+    app: metric-expression
+    component: etcd
+    details: "false"
+    graph: etcd-stream
+    level: cluster
+    metric: active-watch-stream
+    source: rancher-monitoring
+spec:
+  expression: sum(grpc_server_started_total{grpc_service="etcdserverpb.Watch",grpc_type="bidi_stream"})
+     - sum(grpc_server_handled_total{grpc_service="etcdserverpb.Watch",grpc_type="bidi_stream"})
+    
+  legendFormat: Watch streams
+  description: Etcd watch stream
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: etcd-active-watch-stream-details
+  labels:
+    app: metric-expression
+    component: etcd
+    details: "true"
+    graph: etcd-stream
+    level: cluster
+    metric: active-watch-stream
+    source: rancher-monitoring
+spec:
+  expression: sum(grpc_server_started_total{grpc_service="etcdserverpb.Watch",grpc_type="bidi_stream"})
+    by (instance) - sum(grpc_server_handled_total{grpc_service="etcdserverpb.Watch",grpc_type="bidi_stream"})
+    by (instance)
+  legendFormat: Watch streams([[instance]])
+  description: Etcd watch stream
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: etcd-lease-watch-stream
+  labels:
+    app: metric-expression
+    component: etcd
+    details: "false"
+    graph: etcd-stream
+    level: cluster
+    metric: lease-watch-stream
+    source: rancher-monitoring
+spec:
+  expression: sum(grpc_server_started_total{grpc_service="etcdserverpb.Lease",grpc_type="bidi_stream"})
+     - sum(grpc_server_handled_total{grpc_service="etcdserverpb.Lease",grpc_type="bidi_stream"})
+    
+  legendFormat: Lease watch stream
+  description: Etcd lease stream
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: etcd-lease-watch-stream-details
+  labels:
+    app: metric-expression
+    component: etcd
+    details: "true"
+    graph: etcd-stream
+    level: cluster
+    metric: lease-watch-stream
+    source: rancher-monitoring
+spec:
+  expression: sum(grpc_server_started_total{grpc_service="etcdserverpb.Lease",grpc_type="bidi_stream"})
+    by (instance) - sum(grpc_server_handled_total{grpc_service="etcdserverpb.Lease",grpc_type="bidi_stream"})
+    by (instance)
+  legendFormat: Lease watch stream([[instance]])
+  description: Etcd lease stream
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: etcd-peer-traffic-in
+  labels:
+    app: metric-expression
+    component: etcd
+    details: "false"
+    graph: etcd-peer-traffic
+    level: cluster
+    metric: peer-traffic-in
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(etcd_network_peer_received_bytes_total[5m]))  * 8 / 1024
+  legendFormat: Traffic in"
+  description: Etcd peer traffic in
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: etcd-peer-traffic-in-details
+  labels:
+    app: metric-expression
+    component: etcd
+    details: "true"
+    graph: etcd-peer-traffic
+    level: cluster
+    metric: peer-traffic-in
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(etcd_network_peer_received_bytes_total[5m])) by (instance)
+    * 8 / 1024
+  legendFormat: Traffic in([[instance]])
+  description: Etcd peer traffic in
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: etcd-peer-traffic-out
+  labels:
+    app: metric-expression
+    component: etcd
+    details: "false"
+    graph: etcd-peer-traffic
+    level: cluster
+    metric: peer-traffic-out
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(etcd_network_peer_sent_bytes_total[5m])) 
+  legendFormat: Traffic out"
+  description: Etcd peer traffic out
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: etcd-peer-traffic-out-details
+  labels:
+    app: metric-expression
+    component: etcd
+    details: "true"
+    graph: etcd-peer-traffic
+    level: cluster
+    metric: peer-traffic-out
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(etcd_network_peer_sent_bytes_total[5m])) by (instance)
+  legendFormat: Traffic out([[instance]])
+  description: Etcd peer traffic out
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: etcd-proposal-failure-rate
+  labels:
+    app: metric-expression
+    component: etcd
+    details: "false"
+    graph: proposal
+    level: cluster
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(etcd_server_proposals_failed_total[5m])) 
+  legendFormat: Proposal failure
+  description: Proposal Failure Rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: etcd-proposal-failure-rate-details
+  labels:
+    app: metric-expression
+    component: etcd
+    details: "true"
+    graph: proposal
+    level: cluster
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(etcd_server_proposals_failed_total[5m])) by (instance)
+  legendFormat: Proposal failure([[instance]])
+  description: Proposal Failure Rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: etcd-rpc-rate
+  labels:
+    app: metric-expression
+    component: etcd
+    details: "false"
+    graph: rpc-rate
+    level: cluster
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(grpc_server_started_total{grpc_type="unary"}[5m])) 
+  legendFormat: RPC rate
+  description: rpc-rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: etcd-rpc-rate-details
+  labels:
+    app: metric-expression
+    component: etcd
+    details: "true"
+    graph: rpc-rate
+    level: cluster
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(grpc_server_started_total{grpc_type="unary"}[5m])) by (instance)
+  legendFormat: Rpc rate([[instance]])
+  description: rpc-rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: etcd-rpc-rate-failed
+  labels:
+    app: metric-expression
+    component: etcd
+    details: "false"
+    graph: rpc-rate
+    level: cluster
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(grpc_server_handled_total{grpc_type="unary",grpc_code!="OK"}[5m]))
+    
+  legendFormat: Rpc failed rate
+  description: rpc-rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: etcd-rpc-rate-failed-details
+  labels:
+    app: metric-expression
+    component: etcd
+    details: "true"
+    graph: rpc-rate
+    level: cluster
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(grpc_server_handled_total{grpc_type="unary",grpc_code!="OK"}[5m]))
+    by (instance)
+  legendFormat: Rpc failed rate([[instance]])
+  description: rpc-rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: etcd-latency-distributions-of-commit-called-by-backend
+  labels:
+    app: metric-expression
+    component: etcd
+    details: "false"
+    graph: disk-operate
+    level: cluster
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(etcd_disk_backend_commit_duration_seconds_sum[1m])) 
+  legendFormat: Commit latency called by backend
+  description: The latency distributions of commit called by backend
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: etcd-latency-distributions-of-commit-called-by-backend-details
+  labels:
+    app: metric-expression
+    component: etcd
+    details: "true"
+    graph: disk-operate
+    level: cluster
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(etcd_disk_backend_commit_duration_seconds_sum[1m])) by (instance)
+  legendFormat: Commit latency called by backend([[instance]])
+  description: The latency distributions of commit called by backend
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: etcd-latency-distributions-of-fsync-called-by-wal
+  labels:
+    app: metric-expression
+    component: etcd
+    details: "false"
+    graph: disk-operate
+    level: cluster
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(etcd_disk_wal_fsync_duration_seconds_sum[1m])) 
+  legendFormat: Fsync latency called by wal
+  description: The latency distributions of fsync called by wal
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: etcd-latency-distributions-of-fsync-called-by-wal-details
+  labels:
+    app: metric-expression
+    component: etcd
+    details: "true"
+    graph: disk-operate
+    level: cluster
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(etcd_disk_wal_fsync_duration_seconds_sum[1m])) by (instance)
+  legendFormat: Fsync latency called by wal([[instance]])
+  description: The latency distributions of fsync called by wal
+---

charts/rancher-monitoring/v0.0.2/charts/metric-expression-cluster/templates/expressionfluentd.yaml

+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: input-record-number
+  labels:
+    app: metric-expression
+    component: fluentd
+    details: "false"
+    level: cluster
+    metric: input-record
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(fluentd_input_status_num_records_total[5m])) 
+  legendFormat: Input record number
+  description: Fluentd input status num records total
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: input-record-number-details
+  labels:
+    app: metric-expression
+    component: fluentd
+    details: "true"
+    level: cluster
+    metric: input-record
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(fluentd_input_status_num_records_total[5m])) by (instance)
+  legendFormat: Input record number([[instance]])
+  description: Fluentd input status num records total
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: output-record-number
+  labels:
+    app: metric-expression
+    component: fluentd
+    details: "false"
+    level: cluster
+    metric: output-record
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(fluentd_output_status_num_records_total[5m])) 
+  legendFormat: Output record number
+  description: Fluentd output status num records total
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: output-record-number-details
+  labels:
+    app: metric-expression
+    component: fluentd
+    details: "true"
+    level: cluster
+    metric: output-record
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(fluentd_output_status_num_records_total[5m])) by (instance)
+  legendFormat: Output record number([[instance]])
+  description: Fluentd output status num records total
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: output-errors
+  labels:
+    app: metric-expression
+    component: fluentd
+    details: "false"
+    level: cluster
+    metric: output-errors
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(fluentd_output_status_num_errors[5m])) 
+  legendFormat: Plugin Output errors
+  description: Fluentd output errors number
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: output-errors-details
+  labels:
+    app: metric-expression
+    component: fluentd
+    details: "true"
+    level: cluster
+    metric: output-errors
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(fluentd_output_status_num_errors[5m])) by (type)
+  legendFormat: Plugin([[type]])
+  description: Fluentd output errors number
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: buffer-queue-length
+  labels:
+    app: metric-expression
+    component: fluentd
+    details: "false"
+    level: cluster
+    metric: buffer-queue-length
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(fluentd_output_status_buffer_queue_length[5m])) 
+  legendFormat: Buffer queue
+  description: Fluentd Buffer queue length
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: buffer-queue-length-details
+  labels:
+    app: metric-expression
+    component: fluentd
+    details: "true"
+    level: cluster
+    metric: buffer-queue-length
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(fluentd_output_status_buffer_queue_length[5m])) by (instance)
+  legendFormat: '[[instance]]'
+  description: Fluentd Buffer queue length
+---

charts/rancher-monitoring/v0.0.2/charts/metric-expression-cluster/templates/expressioningresscontroller.yaml

+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: ingresscontroller-nginx-connection-reading
+  labels:
+    app: metric-expression
+    component: ingresscontroller
+    details: "false"
+    graph: nginx-connection
+    level: cluster
+    source: rancher-monitoring
+spec:
+  expression: sum(nginx_connections{state="reading"})
+  legendFormat: Reading connections
+  description: ingresscontroller nginx connection reading
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: ingresscontroller-nginx-connection-reading-details
+  labels:
+    app: metric-expression
+    component: ingresscontroller
+    details: "true"
+    graph: nginx-connection
+    level: cluster
+    source: rancher-monitoring
+spec:
+  expression: sum(nginx_connections{state="reading"}) by (instance)
+  legendFormat: Reading connections
+  description: ingresscontroller nginx connection reading
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: ingresscontroller-nginx-connection-waiting
+  labels:
+    app: metric-expression
+    component: ingresscontroller
+    details: "false"
+    graph: nginx-connection
+    level: cluster
+    source: rancher-monitoring
+spec:
+  expression: sum(nginx_connections{state="waiting"})
+  legendFormat: Nginx waiting connection
+  description: ingresscontroller nginx connection waiting
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: ingresscontroller-nginx-connection-waiting-details
+  labels:
+    app: metric-expression
+    component: ingresscontroller
+    details: "true"
+    graph: nginx-connection
+    level: cluster
+    source: rancher-monitoring
+spec:
+  expression: sum(nginx_connections{state="waiting"}) by (instance)
+  legendFormat: Nginx waiting connection
+  description: ingresscontroller nginx connection waiting
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: ingresscontroller-nginx-connection-writing
+  labels:
+    app: metric-expression
+    component: ingresscontroller
+    details: "false"
+    graph: nginx-connection
+    level: cluster
+    source: rancher-monitoring
+spec:
+  expression: sum(nginx_connections{state="writing"})
+  legendFormat: Writing connections
+  description: ingresscontroller nginx connection writing
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: ingresscontroller-nginx-connection-writing-details
+  labels:
+    app: metric-expression
+    component: ingresscontroller
+    details: "true"
+    graph: nginx-connection
+    level: cluster
+    source: rancher-monitoring
+spec:
+  expression: sum(nginx_connections{state="writing"}) by (instance)
+  legendFormat: Writing connections
+  description: ingresscontroller nginx connection writing
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: ingresscontroller-nginx-connection-accepted
+  labels:
+    app: metric-expression
+    component: ingresscontroller
+    details: "false"
+    graph: nginx-connection
+    level: cluster
+    source: rancher-monitoring
+spec:
+  expression: sum(nginx_connections{state="accepted"})
+  legendFormat: Accepted connections
+  description: ingresscontroller nginx connection accepted
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: ingresscontroller-nginx-connection-accepted-details
+  labels:
+    app: metric-expression
+    component: ingresscontroller
+    details: "true"
+    graph: nginx-connection
+    level: cluster
+    source: rancher-monitoring
+spec:
+  expression: sum(nginx_connections{state="accepted"}) by (instance)
+  legendFormat: Accepted connections
+  description: ingresscontroller nginx connection accepted
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: ingresscontroller-nginx-connection-active
+  labels:
+    app: metric-expression
+    component: ingresscontroller
+    details: "false"
+    graph: nginx-connection
+    level: cluster
+    source: rancher-monitoring
+spec:
+  expression: sum(nginx_connections{state="active"})
+  legendFormat: Active connections
+  description: ingresscontroller nginx connection active
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: ingresscontroller-nginx-connection-active-details
+  labels:
+    app: metric-expression
+    component: ingresscontroller
+    details: "true"
+    graph: nginx-connection
+    level: cluster
+    source: rancher-monitoring
+spec:
+  expression: sum(nginx_connections{state="active"}) by (instance)
+  legendFormat: Active connections
+  description: ingresscontroller nginx connection active
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: ingresscontroller-nginx-connection-handled
+  labels:
+    app: metric-expression
+    component: ingresscontroller
+    details: "false"
+    graph: nginx-connection
+    level: cluster
+    source: rancher-monitoring
+spec:
+  expression: sum(nginx_connections{state="handled"})
+  legendFormat: Handled connections
+  description: ingresscontroller nginx connection handled
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: ingresscontroller-nginx-connection-handled-details
+  labels:
+    app: metric-expression
+    component: ingresscontroller
+    details: "true"
+    graph: nginx-connection
+    level: cluster
+    source: rancher-monitoring
+spec:
+  expression: sum(nginx_connections{state="handled"}) by (instance)
+  legendFormat: Handled connections
+  description: ingresscontroller nginx connection handled
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: ingresscontroller-upstream-response-seconds-by-host
+  labels:
+    app: metric-expression
+    component: ingresscontroller
+    details: "false"
+    level: cluster
+    metric: upstream-response-seconds
+    source: rancher-monitoring
+spec:
+  expression: sort_desc(max(upstream_response_time_seconds_sum) by (host, path))
+  legendFormat: Upstream response seconds(host:[[host]] path:[[path]])
+  description: ingresscontroller nginx upstream response seconds by host
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: ingresscontroller-upstream-response-seconds-by-host-details
+  labels:
+    app: metric-expression
+    component: ingresscontroller
+    details: "true"
+    level: cluster
+    metric: upstream-response-seconds
+    source: rancher-monitoring
+spec:
+  expression: sort_desc(max(upstream_response_time_seconds_sum) by (host, path))
+  legendFormat: Upstream response seconds(host:[[host]] path:[[path]])
+  description: ingresscontroller nginx upstream response seconds by host
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: ingresscontroller-nginx-process-seconds-by-path
+  labels:
+    app: metric-expression
+    component: ingresscontroller
+    details: "false"
+    level: cluster
+    metric: request-process-seconds
+    source: rancher-monitoring
+spec:
+  expression: max(request_duration_seconds_bucket{le="1"}) by (host, path)
+  legendFormat: Request duration(host:[[host]] path:[[path]])
+  description: ingresscontroller nginx request duration by path
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: ingresscontroller-nginx-process-seconds-by-path-details
+  labels:
+    app: metric-expression
+    component: ingresscontroller
+    details: "true"
+    level: cluster
+    metric: request-process-seconds
+    source: rancher-monitoring
+spec:
+  expression: max(request_duration_seconds_bucket{le="1"}) by (host, path)
+  legendFormat: Request duration(host:[[host]] path:[[path]])
+  description: ingresscontroller nginx request duration by path
+---

charts/rancher-monitoring/v0.0.2/charts/metric-expression-cluster/templates/expressionnode.yaml

+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: node-network-transmit-bytes-sum-rate
+  labels:
+    app: metric-expression
+    component: node
+    details: "false"
+    graph: network-io
+    level: cluster
+    metric: network-transmit-bytes-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(node_network_transmit_bytes_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*",instance=~"$instance"}[5m]))
+     * 8 / 1024
+  legendFormat: Transmit
+  description: node network transmit bytes sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: node-network-transmit-bytes-sum-rate-details
+  labels:
+    app: metric-expression
+    component: node
+    details: "true"
+    graph: network-io
+    level: cluster
+    metric: network-transmit-bytes-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(node_network_transmit_bytes_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*",instance=~"$instance"}[5m]))
+    by (device) * 8 / 1024
+  legendFormat: '[[device]]'
+  description: node network transmit bytes sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: node-network-receive-packets-dropped-sum-rate
+  labels:
+    app: metric-expression
+    component: node
+    details: "false"
+    graph: network-packet
+    level: cluster
+    metric: network-receive-packets-dropped-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(node_network_receive_drop_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*",instance=~"$instance"}[5m]))
+    
+  legendFormat: Receive packets
+  description: node network receive packets dropped sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: node-network-receive-packets-dropped-sum-rate-details
+  labels:
+    app: metric-expression
+    component: node
+    details: "true"
+    graph: network-packet
+    level: cluster
+    metric: network-receive-packets-dropped-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(node_network_receive_drop_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*",instance=~"$instance"}[5m]))
+    by (device)
+  legendFormat: Receive packets([[device]])
+  description: node network receive packets dropped sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: node-network-transmit-packets-sum-rate
+  labels:
+    app: metric-expression
+    component: node
+    details: "false"
+    graph: network-packet
+    level: cluster
+    metric: network-transmit-packets-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(node_network_transmit_packets_total{instance=~"$instance"}[5m]))
+    
+  legendFormat: Transmit packets
+  description: node network transmit packets sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: node-network-transmit-packets-sum-rate-details
+  labels:
+    app: metric-expression
+    component: node
+    details: "true"
+    graph: network-packet
+    level: cluster
+    metric: network-transmit-packets-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(node_network_transmit_packets_total{instance=~"$instance"}[5m]))
+    by (device)
+  legendFormat: Transmit packets([[device]])
+  description: node network transmit packets sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: node-disk-io-writes-bytes-sum-rate
+  labels:
+    app: metric-expression
+    component: node
+    details: "false"
+    graph: disk-io
+    level: cluster
+    metric: disk-io-writes-bytes-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(node_disk_written_bytes_total{instance=~"$instance"}[5m]))
+     * 8 / 1024
+  legendFormat: Write
+  description: node disk io writes bytes sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: node-disk-io-writes-bytes-sum-rate-details
+  labels:
+    app: metric-expression
+    component: node
+    details: "true"
+    graph: disk-io
+    level: cluster
+    metric: disk-io-writes-bytes-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(node_disk_written_bytes_total{instance=~"$instance"}[5m]))
+    by (device) * 8 / 1024
+  legendFormat: Write([[device]])
+  description: node disk io writes bytes sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: node-disk-io-reads-bytes-sum-rate
+  labels:
+    app: metric-expression
+    component: node
+    details: "false"
+    graph: disk-io
+    level: cluster
+    metric: disk-io-reads-bytes-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(node_disk_read_bytes_total{instance=~"$instance"}[5m])) by
+    () * 8 / 1024
+  legendFormat: Read
+  description: node disk io reads bytes sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: node-disk-io-reads-bytes-sum-rate-details
+  labels:
+    app: metric-expression
+    component: node
+    details: "true"
+    graph: disk-io
+    level: cluster
+    metric: disk-io-reads-bytes-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(node_disk_read_bytes_total{instance=~"$instance"}[5m])) by
+    (device) * 8 / 1024
+  legendFormat: Read([[device]])
+  description: node disk io reads bytes sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: node-fs-usage-percent
+  labels:
+    app: metric-expression
+    component: node
+    details: "false"
+    level: cluster
+    metric: fs-usage-percent
+    source: rancher-monitoring
+spec:
+  expression: (sum(node_filesystem_size_bytes{device!="rootfs",instance=~"$instance"})
+     - sum(node_filesystem_free_bytes{device!="rootfs",instance=~"$instance"})
+    ) / sum(node_filesystem_size_bytes{device!="rootfs",instance=~"$instance"})
+    
+  legendFormat: Disk usage
+  description: node fs usage percent
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: node-fs-usage-percent-details
+  labels:
+    app: metric-expression
+    component: node
+    details: "true"
+    level: cluster
+    metric: fs-usage-percent
+    source: rancher-monitoring
+spec:
+  expression: (sum(node_filesystem_size_bytes{device!="rootfs",instance=~"$instance"})
+    by (device) - sum(node_filesystem_free_bytes{device!="rootfs",instance=~"$instance"})
+    by (device)) / sum(node_filesystem_size_bytes{device!="rootfs",instance=~"$instance"})
+    by (device)
+  legendFormat: '[[device]]'
+  description: node fs usage percent
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: node-network-receive-packets-sum-rate
+  labels:
+    app: metric-expression
+    component: node
+    details: "false"
+    graph: network-packet
+    level: cluster
+    metric: network-receive-packets-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(node_network_receive_packets_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*",instance=~"$instance"}[5m]))
+    
+  legendFormat: Receive packets
+  description: node network receive packets sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: node-network-receive-packets-sum-rate-details
+  labels:
+    app: metric-expression
+    component: node
+    details: "true"
+    graph: network-packet
+    level: cluster
+    metric: network-receive-packets-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(node_network_receive_packets_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*",instance=~"$instance"}[5m]))
+    by (device)
+  legendFormat: Receive packets([[device]])
+  description: node network receive packets sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: node-network-transmit-errors-sum-rate
+  labels:
+    app: metric-expression
+    component: node
+    details: "false"
+    graph: network-packet
+    level: cluster
+    metric: network-transmit-errors-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(node_network_transmit_errs_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*",instance=~"$instance"}[5m]))
+    
+  legendFormat: Transmit errors
+  description: node network transmit errors sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: node-network-transmit-errors-sum-rate-details
+  labels:
+    app: metric-expression
+    component: node
+    details: "true"
+    graph: network-packet
+    level: cluster
+    metric: network-transmit-errors-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(node_network_transmit_errs_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*",instance=~"$instance"}[5m]))
+    by (device)
+  legendFormat: Transmit errors([[device]])
+  description: node network transmit errors sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: node-cpu-load-5
+  labels:
+    app: metric-expression
+    component: node
+    details: "false"
+    graph: cpu-load
+    level: cluster
+    metric: cpu-load-5
+    source: rancher-monitoring
+spec:
+  expression: sum(node_load1{instance=~"$instance"})  / count(node_cpu_seconds_total{mode="system",instance=~"$instance"})
+    
+  legendFormat: Load1
+  description: node cpu load 1
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: node-cpu-load-5-details
+  labels:
+    app: metric-expression
+    component: node
+    details: "true"
+    graph: cpu-load
+    level: cluster
+    metric: cpu-load-5
+    source: rancher-monitoring
+spec:
+  expression: sum(node_load1{instance=~"$instance"})  / count(node_cpu_seconds_total{mode="system",instance=~"$instance"})
+    
+  legendFormat: Load1
+  description: node cpu load 1
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: node-cpu-load-15
+  labels:
+    app: metric-expression
+    component: node
+    details: "false"
+    graph: cpu-load
+    level: cluster
+    metric: cpu-load-15
+    source: rancher-monitoring
+spec:
+  expression: sum(node_load15{instance=~"$instance"})  / count(node_cpu_seconds_total{mode="system",instance=~"$instance"})
+    
+  legendFormat: Load15
+  description: node cpu load 15
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: node-cpu-load-15-details
+  labels:
+    app: metric-expression
+    component: node
+    details: "true"
+    graph: cpu-load
+    level: cluster
+    metric: cpu-load-15
+    source: rancher-monitoring
+spec:
+  expression: sum(node_load15{instance=~"$instance"})  / count(node_cpu_seconds_total{mode="system",instance=~"$instance"})
+    
+  legendFormat: Load15
+  description: node cpu load 15
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: node-cpu-usage-seconds-sum-rate
+  labels:
+    app: metric-expression
+    component: node
+    details: "false"
+    level: cluster
+    metric: cpu-usage-seconds-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: 1 - (avg(irate(node_cpu_seconds_total{mode="idle", instance=~"$instance"}[5m])) by (instance))
+  legendFormat: CPU
+  description: node cpu usage seconds sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: node-cpu-usage-seconds-sum-rate-details
+  labels:
+    app: metric-expression
+    component: node
+    details: "true"
+    level: cluster
+    metric: cpu-usage-seconds-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: avg(irate(node_cpu_seconds_total{instance=~"$instance"}[5m]))by (mode) 
+  legendFormat: '[[mode]]'
+  description: node cpu usage seconds sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: node-memory-usage-percent
+  labels:
+    app: metric-expression
+    component: node
+    details: "false"
+    level: cluster
+    metric: memory-usage-percent
+    source: rancher-monitoring
+spec:
+  expression: 1 - sum(node_memory_MemAvailable_bytes{instance=~"$instance"}) 
+    / sum(node_memory_MemTotal_bytes{instance=~"$instance"}) 
+  legendFormat: Memory usage
+  description: node memory usage percent
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: node-memory-usage-percent-details
+  labels:
+    app: metric-expression
+    component: node
+    details: "true"
+    level: cluster
+    metric: memory-usage-percent
+    source: rancher-monitoring
+spec:
+  expression: 1 - sum(node_memory_MemAvailable_bytes{instance=~"$instance"}) 
+    / sum(node_memory_MemTotal_bytes{instance=~"$instance"}) 
+  legendFormat: Memory usage
+  description: node memory usage percent
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: node-network-receive-bytes-sum-rate
+  labels:
+    app: metric-expression
+    component: node
+    details: "false"
+    graph: network-io
+    level: cluster
+    metric: network-receive-bytes-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(node_network_receive_bytes_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*",instance=~"$instance"}[5m]))
+     * 8 / 1024
+  legendFormat: Receive
+  description: node network receive bytes sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: node-network-receive-bytes-sum-rate-details
+  labels:
+    app: metric-expression
+    component: node
+    details: "true"
+    graph: network-io
+    level: cluster
+    metric: network-receive-bytes-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(node_network_receive_bytes_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*",instance=~"$instance"}[5m]))
+    by (device) * 8 / 1024
+  legendFormat: Receive([[device]])
+  description: node network receive bytes sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: node-network-receive-errors-sum-rate
+  labels:
+    app: metric-expression
+    component: node
+    details: "false"
+    graph: network-packet
+    level: cluster
+    metric: network-receive-errors-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(node_network_receive_errs_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*",instance=~"$instance"}[5m]))
+    
+  legendFormat: Receive packets
+  description: node network receive errors sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: node-network-receive-errors-sum-rate-details
+  labels:
+    app: metric-expression
+    component: node
+    details: "true"
+    graph: network-packet
+    level: cluster
+    metric: network-receive-errors-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(node_network_receive_errs_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*",instance=~"$instance"}[5m]))
+    by (device)
+  legendFormat: Receive packets([[device]])
+  description: node network receive errors sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: node-cpu-load-5
+  labels:
+    app: metric-expression
+    component: node
+    details: "false"
+    graph: cpu-load
+    level: cluster
+    metric: cpu-load-5
+    source: rancher-monitoring
+spec:
+  expression: sum(node_load5{instance=~"$instance"})  / count(node_cpu_seconds_total{mode="system",instance=~"$instance"})
+    
+  legendFormat: Load5
+  description: node cpu load 5
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: node-cpu-load-1-details
+  labels:
+    app: metric-expression
+    component: node
+    details: "true"
+    graph: cpu-load
+    level: cluster
+    metric: cpu-load-1
+    source: rancher-monitoring
+spec:
+  expression: sum(node_load5{instance=~"$instance"})  / count(node_cpu_seconds_total{mode="system",instance=~"$instance"})
+    
+  legendFormat: Load1
+  description: node cpu load 1
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: node-network-transmit-packets-dropped-sum-rate
+  labels:
+    app: metric-expression
+    component: node
+    details: "false"
+    graph: network-packet
+    level: cluster
+    metric: network-transmit-packets-dropped-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(node_network_transmit_drop_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*",instance=~"$instance"}[5m]))
+    
+  legendFormat: Transmit dropped
+  description: node network transmit packets dropped sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: node-network-transmit-packets-dropped-sum-rate-details
+  labels:
+    app: metric-expression
+    component: node
+    details: "true"
+    graph: network-packet
+    level: cluster
+    metric: network-transmit-packets-dropped-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(node_network_transmit_drop_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*",instance=~"$instance"}[5m]))
+    by (device)
+  legendFormat: Transmit dropped([[device]])
+  description: node network transmit packets dropped sum rate
+---

charts/rancher-monitoring/v0.0.2/charts/metric-expression-cluster/templates/expressionpod.yaml

+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: pod-cpu-cfs-throttled-seconds-sum-rate
+  labels:
+    app: metric-expression
+    component: pod
+    details: "false"
+    graph: container-cpu-usage-details
+    level: project
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_cpu_cfs_throttled_seconds_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}[5m])) 
+  legendFormat: CPU cfs throttled
+  description: pod cpu cfs throttled seconds sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: pod-cpu-cfs-throttled-seconds-sum-rate-details
+  labels:
+    app: metric-expression
+    component: pod
+    details: "true"
+    graph: container-cpu-usage-details
+    level: project
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_cpu_cfs_throttled_seconds_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}[5m])) by (container_name)
+  legendFormat: CPU cfs throttled([[container_name]])
+  description: pod cpu cfs throttled seconds sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: pod-memory-usage-percent
+  labels:
+    app: metric-expression
+    component: pod
+    details: "false"
+    level: project
+    metric: memory-usage-percent
+    source: rancher-monitoring
+spec:
+  expression: sum(container_memory_working_set_bytes{namespace=~"$namespace", pod_name=~"$podName",
+    container_name!=""})  / sum(label_join(kube_pod_container_resource_limits_memory_bytes{namespace=~"$namespace",
+    pod=~"$InstanceName"},"pod_name", "", "pod")) 
+  legendFormat: Memory
+  description: pod memory usage percent
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: pod-memory-usage-percent-details
+  labels:
+    app: metric-expression
+    component: pod
+    details: "true"
+    level: project
+    metric: memory-usage-percent
+    source: rancher-monitoring
+spec:
+  expression: sum(container_memory_working_set_bytes{namespace=~"$namespace", pod_name=~"$podName",
+    container_name!=""}) by (container_name) / sum(label_join(kube_pod_container_resource_limits_memory_bytes{namespace=~"$namespace",
+    pod=~"$InstanceName"},"pod_name", "", "pod")) by (container_name)
+  legendFormat: Memory([[container_name]])
+  description: pod memory usage percent
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: pod-fs-bytes-sum
+  labels:
+    app: metric-expression
+    component: pod
+    details: "false"
+    level: project
+    metric: fs-bytes-sum
+    source: rancher-monitoring
+spec:
+  expression: sum(container_fs_usage_bytes{namespace=~"$namespace", pod_name=~"$podName",
+    container_name!=""}) 
+  legendFormat: Filesystem usage
+  description: pod fs bytes sum
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: pod-fs-bytes-sum-details
+  labels:
+    app: metric-expression
+    component: pod
+    details: "true"
+    level: project
+    metric: fs-bytes-sum
+    source: rancher-monitoring
+spec:
+  expression: sum(container_fs_usage_bytes{namespace=~"$namespace", pod_name=~"$podName",
+    container_name!=""}) by (container_name)
+  legendFormat: Filesystem usage([[container_name]])
+  description: pod fs bytes sum
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: pod-network-receive-packets-sum-rate
+  labels:
+    app: metric-expression
+    component: pod
+    details: "false"
+    graph: network-packet
+    level: project
+    metric: network-receive-packets-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_network_receive_packets_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}[5m])) 
+  legendFormat: Receive packets
+  description: pod network receive packets sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: pod-network-receive-packets-sum-rate-details
+  labels:
+    app: metric-expression
+    component: pod
+    details: "true"
+    graph: network-packet
+    level: project
+    metric: network-receive-packets-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_network_receive_packets_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}[5m])) by (container_name)
+  legendFormat: Receive packets([[container_name]])
+  description: pod network receive packets sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: pod-network-transmit-packets-sum-rate
+  labels:
+    app: metric-expression
+    component: pod
+    details: "false"
+    graph: network-packet
+    level: project
+    metric: network-transmit-packets-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_network_transmit_packets_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}[5m])) 
+  legendFormat: Transmit packets
+  description: pod network transmit packets sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: pod-network-transmit-packets-sum-rate-details
+  labels:
+    app: metric-expression
+    component: pod
+    details: "true"
+    graph: network-packet
+    level: project
+    metric: network-transmit-packets-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_network_transmit_packets_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}[5m])) by (container_name)
+  legendFormat: Transmit packets([[container_name]])
+  description: pod network transmit packets sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: pod-cpu-user-seconds-sum-rate
+  labels:
+    app: metric-expression
+    component: pod
+    details: "false"
+    graph: container-cpu-usage-details
+    level: project
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_cpu_user_seconds_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}[5m])) 
+  legendFormat: CPU user seconds
+  description: pod cpu user seconds sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: pod-cpu-user-seconds-sum-rate-details
+  labels:
+    app: metric-expression
+    component: pod
+    details: "true"
+    graph: container-cpu-usage-details
+    level: project
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_cpu_user_seconds_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}[5m])) by (container_name)
+  legendFormat: CPU user seconds([[container_name]])
+  description: pod cpu user seconds sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: pod-disk-io-reads-bytes-sum-rate
+  labels:
+    app: metric-expression
+    component: pod
+    details: "false"
+    graph: disk-io
+    level: project
+    metric: disk-io-reads-bytes-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_fs_reads_bytes_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}[5m]))   * 8 / 1024
+  legendFormat: Read
+  description: pod disk io reads bytes sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: pod-disk-io-reads-bytes-sum-rate-details
+  labels:
+    app: metric-expression
+    component: pod
+    details: "true"
+    graph: disk-io
+    level: project
+    metric: disk-io-reads-bytes-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_fs_reads_bytes_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}[5m])) by (container_name)  * 8 / 1024
+  legendFormat: Read([[container_name]])
+  description: pod disk io reads bytes sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: pod-network-receive-bytes-sum-rate
+  labels:
+    app: metric-expression
+    component: pod
+    details: "false"
+    graph: network-io
+    level: project
+    metric: network-receive-bytes-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_network_receive_bytes_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}[5m]))  * 8 / 1024
+  legendFormat: Receive
+  description: pod network receive bytes sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: pod-network-receive-bytes-sum-rate-details
+  labels:
+    app: metric-expression
+    component: pod
+    details: "true"
+    graph: network-io
+    level: project
+    metric: network-receive-bytes-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_network_receive_bytes_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}[5m])) by (container_name) * 8 / 1024
+  legendFormat: Receive
+  description: pod network receive bytes sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: pod-network-transmit-bytes-sum-rate
+  labels:
+    app: metric-expression
+    component: pod
+    details: "false"
+    graph: network-io
+    level: project
+    metric: network-transmit-bytes-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_network_transmit_bytes_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}[5m]))  * 8 / 1024
+  legendFormat: Transmit
+  description: pod network transmit bytes sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: pod-network-transmit-bytes-sum-rate-details
+  labels:
+    app: metric-expression
+    component: pod
+    details: "true"
+    graph: network-io
+    level: project
+    metric: network-transmit-bytes-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_network_transmit_bytes_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}[5m])) by (container_name) * 8 / 1024
+  legendFormat: Transmit
+  description: pod network transmit bytes sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: pod-network-receive-packets-dropped-sum-rate
+  labels:
+    app: metric-expression
+    component: pod
+    details: "false"
+    graph: network-packet
+    level: project
+    metric: network-receive-packets-dropped-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_network_receive_packets_dropped_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}[5m])) 
+  legendFormat: Receive dropped
+  description: pod network receive packets dropped sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: pod-network-receive-packets-dropped-sum-rate-details
+  labels:
+    app: metric-expression
+    component: pod
+    details: "true"
+    graph: network-packet
+    level: project
+    metric: network-receive-packets-dropped-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_network_receive_packets_dropped_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}[5m])) by (container_name)
+  legendFormat: Receive dropped
+  description: pod network receive packets dropped sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: pod-memory-usage-bytes-sum
+  labels:
+    app: metric-expression
+    component: pod
+    details: "false"
+    level: project
+    metric: memory-usage-bytes-sum
+    source: rancher-monitoring
+spec:
+  expression: sum(container_memory_working_set_bytes{name!~"POD", namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}) 
+  legendFormat: Memory usage
+  description: pod memory usage bytes sum
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: pod-memory-usage-bytes-sum-details
+  labels:
+    app: metric-expression
+    component: pod
+    details: "true"
+    level: project
+    metric: memory-usage-bytes-sum
+    source: rancher-monitoring
+spec:
+  expression: sum(container_memory_working_set_bytes{name!~"POD", namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}) by (container_name)
+  legendFormat: Memory usage([[container_name]])
+  description: pod memory usage bytes sum
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: pod-disk-io-writes-bytes-sum-rate
+  labels:
+    app: metric-expression
+    component: pod
+    details: "false"
+    graph: disk-io
+    level: project
+    metric: disk-io-writes-bytes-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_fs_writes_bytes_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}[5m]))  * 8 / 1024
+  legendFormat: Write
+  description: pod disk io writes bytes sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: pod-disk-io-writes-bytes-sum-rate-details
+  labels:
+    app: metric-expression
+    component: pod
+    details: "true"
+    graph: disk-io
+    level: project
+    metric: disk-io-writes-bytes-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_fs_writes_bytes_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}[5m])) by (container_name) * 8 / 1024
+  legendFormat: Write([[container_name]])
+  description: pod disk io writes bytes sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: pod-network-receive-errors-sum-rate
+  labels:
+    app: metric-expression
+    component: pod
+    details: "false"
+    graph: network-packet
+    level: project
+    metric: network-receive-errors-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_network_receive_errors_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}[5m])) 
+  legendFormat: Receive errors
+  description: pod network receive errors sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: pod-network-receive-errors-sum-rate-details
+  labels:
+    app: metric-expression
+    component: pod
+    details: "true"
+    graph: network-packet
+    level: project
+    metric: network-receive-errors-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_network_receive_errors_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}[5m])) by (container_name)
+  legendFormat: Receive errors
+  description: pod network receive errors sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: pod-cpu-usage-seconds-sum-rate
+  labels:
+    app: metric-expression
+    component: pod
+    details: "false"
+    graph: container-cpu-usage
+    level: project
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_cpu_usage_seconds_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}[5m])) 
+  legendFormat: CPU usage
+  description: pod CPU usage sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: pod-cpu-usage-seconds-sum-rate-details
+  labels:
+    app: metric-expression
+    component: pod
+    details: "true"
+    graph: container-cpu-usage
+    level: project
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_cpu_usage_seconds_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}[5m])) by (container_name)
+  legendFormat: CPU usage([[container_name]])
+  description: pod CPU usage sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: pod-network-transmit-errors-sum-rate
+  labels:
+    app: metric-expression
+    component: pod
+    details: "false"
+    graph: network-packet
+    level: project
+    metric: network-transmit-errors-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_network_transmit_errors_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}[5m])) 
+  legendFormat: Transmit errors
+  description: pod network transmit errors sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: pod-network-transmit-errors-sum-rate-details
+  labels:
+    app: metric-expression
+    component: pod
+    details: "true"
+    graph: network-packet
+    level: project
+    metric: network-transmit-errors-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_network_transmit_errors_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}[5m])) by (container_name)
+  legendFormat: Transmit errors
+  description: pod network transmit errors sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: pod-network-transmit-packets-dropped-sum-rate
+  labels:
+    app: metric-expression
+    component: pod
+    details: "false"
+    graph: network-packet
+    level: project
+    metric: network-transmit-packets-dropped-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_network_transmit_packets_dropped_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}[5m])) 
+  legendFormat: Transmit dropped
+  description: pod network transmit packets dropped sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: pod-network-transmit-packets-dropped-sum-rate-details
+  labels:
+    app: metric-expression
+    component: pod
+    details: "true"
+    graph: network-packet
+    level: project
+    metric: network-transmit-packets-dropped-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_network_transmit_packets_dropped_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}[5m])) by (container_name)
+  legendFormat: Transmit dropped
+  description: pod network transmit packets dropped sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: pod-cpu-system-seconds-sum-rate
+  labels:
+    app: metric-expression
+    component: pod
+    details: "false"
+    graph: container-cpu-usage-details
+    level: project
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_cpu_system_seconds_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}[5m])) 
+  legendFormat: CPU system seconds
+  description: pod cpu system seconds sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: pod-cpu-system-seconds-sum-rate-details
+  labels:
+    app: metric-expression
+    component: pod
+    details: "true"
+    graph: container-cpu-usage-details
+    level: project
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_cpu_system_seconds_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}[5m])) by (container_name)
+  legendFormat: CPU system seconds([[container_name]])
+  description: pod cpu system seconds sum rate
+---

charts/rancher-monitoring/v0.0.2/charts/metric-expression-cluster/templates/expressionscheduler.yaml

+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: scheduler-e-2-e-scheduling-latency-seconds-quantile
+  labels:
+    app: metric-expression
+    component: scheduler
+    details: "false"
+    level: cluster
+    metric: e-2-e-scheduling-latency-seconds-quantile
+    source: rancher-monitoring
+spec:
+  expression: histogram_quantile(0.99, sum(scheduler_e2e_scheduling_latency_microseconds_bucket)
+    by (le, instance)) / 1e+06
+  legendFormat: E2E latency
+  description: scheduler e 2 e scheduling latency seconds quantile
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: scheduler-e-2-e-scheduling-latency-seconds-quantile-details
+  labels:
+    app: metric-expression
+    component: scheduler
+    details: "true"
+    level: cluster
+    metric: e-2-e-scheduling-latency-seconds-quantile
+    source: rancher-monitoring
+spec:
+  expression: histogram_quantile(0.99, sum(scheduler_e2e_scheduling_latency_microseconds_bucket)
+    by (le, instance)) / 1e+06
+  legendFormat: E2E latency([[instance]])
+  description: scheduler e 2 e scheduling latency seconds quantile
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: scheduler-total-preemption-attempts
+  labels:
+    app: metric-expression
+    component: scheduler
+    details: "false"
+    level: cluster
+    metric: total-preemption-attempts
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(scheduler_total_preemption_attempts[5m])) by (instance)
+  legendFormat: Preemption attempts
+  description: Scheduler scheduling algorithm latency seconds quantile
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: scheduler-total-preemption-attempts-details
+  labels:
+    app: metric-expression
+    component: scheduler
+    details: "true"
+    level: cluster
+    metric: total-preemption-attempts
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(scheduler_total_preemption_attempts[5m])) 
+  legendFormat: Preemption attempts([[instance]])
+  description: Scheduler scheduling algorithm latency seconds quantile
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: scheduler-pod-unscheduler
+  labels:
+    app: metric-expression
+    component: scheduler
+    details: "false"
+    level: cluster
+    metric: pod-unscheduler
+    source: rancher-monitoring
+spec:
+  expression: sum(kube_pod_status_scheduled{condition="false"})
+  legendFormat: Scheduling failed pods
+  description: pod unscheduler
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: scheduler-pod-unscheduler-details
+  labels:
+    app: metric-expression
+    component: scheduler
+    details: "true"
+    level: cluster
+    metric: pod-unscheduler
+    source: rancher-monitoring
+spec:
+  expression: sum(kube_pod_status_scheduled{condition="false"})
+  legendFormat: Scheduling failed pods
+  description: pod unscheduler
+---

charts/rancher-monitoring/v0.0.2/charts/metric-expression-cluster/templates/expressionworkload.yaml

+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: workload-disk-io-writes-bytes-sum-rate
+  labels:
+    app: metric-expression
+    component: workload
+    details: "false"
+    graph: disk-io
+    level: project
+    metric: disk-io-writes-bytes-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_fs_writes_bytes_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}[5m]))   * 8 / 1024
+  legendFormat: Write
+  description: workload disk io writes bytes sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: workload-disk-io-writes-bytes-sum-rate-details
+  labels:
+    app: metric-expression
+    component: workload
+    details: "true"
+    graph: disk-io
+    level: project
+    metric: disk-io-writes-bytes-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_fs_writes_bytes_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}[5m])) by (pod_name)  * 8 / 1024
+  legendFormat: Write([[pod_name]])
+  description: workload disk io writes bytes sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: workload-disk-io-reads-bytes-sum-rate
+  labels:
+    app: metric-expression
+    component: workload
+    details: "false"
+    graph: disk-io
+    level: project
+    metric: disk-io-reads-bytes-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_fs_reads_bytes_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}[5m]))  * 8 / 1024
+  legendFormat: Read
+  description: workload disk io reads bytes sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: workload-disk-io-reads-bytes-sum-rate-details
+  labels:
+    app: metric-expression
+    component: workload
+    details: "true"
+    graph: disk-io
+    level: project
+    metric: disk-io-reads-bytes-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_fs_reads_bytes_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}[5m])) by (pod_name) * 8 / 1024
+  legendFormat: Read([[pod_name]])
+  description: workload disk io reads bytes sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: workload-fs-bytes-sum
+  labels:
+    app: metric-expression
+    component: workload
+    details: "false"
+    level: project
+    metric: fs-bytes-sum
+    source: rancher-monitoring
+spec:
+  expression: sum(container_fs_usage_bytes{namespace=~"$namespace", pod_name=~"$podName",
+    container_name!=""}) 
+  legendFormat: File usage
+  description: workload fs bytes sum
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: workload-fs-bytes-sum-details
+  labels:
+    app: metric-expression
+    component: workload
+    details: "true"
+    level: project
+    metric: fs-bytes-sum
+    source: rancher-monitoring
+spec:
+  expression: sum(container_fs_usage_bytes{namespace=~"$namespace", pod_name=~"$podName",
+    container_name!=""}) by (pod_name)
+  legendFormat: pod_name]]
+  description: workload fs bytes sum
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: workload-network-transmit-packets-sum-rate
+  labels:
+    app: metric-expression
+    component: workload
+    details: "false"
+    graph: network-packet
+    level: project
+    metric: network-transmit-packets-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_network_transmit_packets_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}[5m])) 
+  legendFormat: Transmit packets
+  description: workload network transmit packets sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: workload-network-transmit-packets-sum-rate-details
+  labels:
+    app: metric-expression
+    component: workload
+    details: "true"
+    graph: network-packet
+    level: project
+    metric: network-transmit-packets-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_network_transmit_packets_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}[5m])) by (pod_name)
+  legendFormat: Transmit packets([[pod_name]])
+  description: workload network transmit packets sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: workload-network-receive-packets-dropped-sum-rate
+  labels:
+    app: metric-expression
+    component: workload
+    details: "false"
+    graph: network-packet
+    level: project
+    metric: network-receive-packets-dropped-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_network_receive_packets_dropped_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}[5m])) 
+  legendFormat: Receive dropped
+  description: workload network receive packets dropped sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: workload-network-receive-packets-dropped-sum-rate-details
+  labels:
+    app: metric-expression
+    component: workload
+    details: "true"
+    graph: network-packet
+    level: project
+    metric: network-receive-packets-dropped-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_network_receive_packets_dropped_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}[5m])) by (pod_name)
+  legendFormat: Receive dropped([[pod_name]])
+  description: workload network receive packets dropped sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: workload-cpu-usage-seconds-sum-rate
+  labels:
+    app: metric-expression
+    component: workload
+    details: "false"
+    graph: container-cpu-usage
+    level: project
+    metric: cpu-usage-seconds-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_cpu_usage_seconds_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}[5m])) 
+  legendFormat: CPU usage
+  description: workload cpu usage seconds sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: workload-cpu-usage-seconds-sum-rate-details
+  labels:
+    app: metric-expression
+    component: workload
+    details: "true"
+    graph: container-cpu-usage
+    level: project
+    metric: cpu-usage-seconds-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_cpu_usage_seconds_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}[5m])) by (pod_name)
+  legendFormat: CPU usage([[pod_name]])
+  description: workload cpu usage seconds sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: workload-cpu-system-seconds-sum-rate
+  labels:
+    app: metric-expression
+    component: workload
+    details: "false"
+    graph: container-cpu-usage-details
+    level: project
+    metric: cpu-system-seconds-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_cpu_system_seconds_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}[5m])) 
+  legendFormat: CPU system seconds
+  description: workload cpu system seconds sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: workload-cpu-system-seconds-sum-rate-details
+  labels:
+    app: metric-expression
+    component: workload
+    details: "true"
+    graph: container-cpu-usage-details
+    level: project
+    metric: cpu-system-seconds-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_cpu_system_seconds_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}[5m])) by (pod_name)
+  legendFormat: CPU system seconds([[pod_name]])
+  description: workload cpu system seconds sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: workload-network-receive-bytes-sum-rate
+  labels:
+    app: metric-expression
+    component: workload
+    details: "false"
+    graph: network-io
+    level: project
+    metric: network-receive-bytes-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_network_receive_bytes_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}[5m]))  * 8 / 1024
+  legendFormat: Receive
+  description: workload network receive bytes sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: workload-network-receive-bytes-sum-rate-details
+  labels:
+    app: metric-expression
+    component: workload
+    details: "true"
+    graph: network-io
+    level: project
+    metric: network-receive-bytes-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_network_receive_bytes_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}[5m])) by (pod_name) * 8 / 1024
+  legendFormat: Receive([[pod_name]])
+  description: workload network receive bytes sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: workload-network-receive-errors-sum-rate
+  labels:
+    app: metric-expression
+    component: workload
+    details: "false"
+    graph: network-packet
+    level: project
+    metric: network-receive-errors-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_network_receive_errors_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}[5m])) 
+  legendFormat: Receive errors
+  description: workload network receive errors sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: workload-network-receive-errors-sum-rate-details
+  labels:
+    app: metric-expression
+    component: workload
+    details: "true"
+    graph: network-packet
+    level: project
+    metric: network-receive-errors-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_network_receive_errors_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}[5m])) by (pod_name)
+  legendFormat: Receive errors([[pod_name]])
+  description: workload network receive errors sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: workload-network-receive-packets-sum-rate
+  labels:
+    app: metric-expression
+    component: workload
+    details: "false"
+    graph: network-packet
+    level: project
+    metric: network-receive-packets-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_network_receive_packets_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}[5m])) 
+  legendFormat: Receive packets
+  description: workload network receive packets sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: workload-network-receive-packets-sum-rate-details
+  labels:
+    app: metric-expression
+    component: workload
+    details: "true"
+    graph: network-packet
+    level: project
+    metric: network-receive-packets-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_network_receive_packets_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}[5m])) by (pod_name)
+  legendFormat: Receive packets([[pod_name]])
+  description: workload network receive packets sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: workload-memory-usage-bytes-sum
+  labels:
+    app: metric-expression
+    component: workload
+    details: "false"
+    level: project
+    metric: memory-usage-bytes-sum
+    source: rancher-monitoring
+spec:
+  expression: sum(container_memory_working_set_bytes{name!~"POD", namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}) 
+  legendFormat: Memory
+  description: workload memory usage bytes sum
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: workload-memory-usage-bytes-sum-details
+  labels:
+    app: metric-expression
+    component: workload
+    details: "true"
+    level: project
+    metric: memory-usage-bytes-sum
+    source: rancher-monitoring
+spec:
+  expression: sum(container_memory_working_set_bytes{name!~"POD", namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}) by (pod_name)
+  legendFormat: '[[pod_name]]'
+  description: workload memory usage bytes sum
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: workload-memory-usage-percent
+  labels:
+    app: metric-expression
+    component: workload
+    details: "false"
+    level: project
+    metric: memory-usage-percent
+    source: rancher-monitoring
+spec:
+  expression: sum(container_memory_working_set_bytes{namespace=~"$namespace", pod_name=~"$podName",
+    container_name!=""})  / sum(label_join(kube_pod_container_resource_limits_memory_bytes{namespace=~"$namespace",
+    pod=~"$InstanceName"},"pod_name", "", "pod")) 
+  legendFormat: Usage percent
+  description: workload memory usage percent
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: workload-memory-usage-percent-details
+  labels:
+    app: metric-expression
+    component: workload
+    details: "true"
+    level: project
+    metric: memory-usage-percent
+    source: rancher-monitoring
+spec:
+  expression: sum(container_memory_working_set_bytes{namespace=~"$namespace", pod_name=~"$podName",
+    container_name!=""}) by (pod_name) / sum(label_join(kube_pod_container_resource_limits_memory_bytes{namespace=~"$namespace",
+    pod=~"$InstanceName"},"pod_name", "", "pod")) by (pod_name)
+  legendFormat: Usage percent([[pod_name]])
+  description: workload memory usage percent
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: workload-network-transmit-bytes-sum-rate
+  labels:
+    app: metric-expression
+    component: workload
+    details: "false"
+    graph: network-io
+    level: project
+    metric: network-transmit-bytes-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_network_transmit_bytes_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}[5m]))  * 8 / 1024
+  legendFormat: Transmit
+  description: workload network transmit bytes sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: workload-network-transmit-bytes-sum-rate-details
+  labels:
+    app: metric-expression
+    component: workload
+    details: "true"
+    graph: network-io
+    level: project
+    metric: network-transmit-bytes-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_network_transmit_bytes_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}[5m])) by (pod_name) * 8 / 1024
+  legendFormat: Transmit([[pod_name]])
+  description: workload network transmit bytes sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: workload-network-transmit-errors-sum-rate
+  labels:
+    app: metric-expression
+    component: workload
+    details: "false"
+    graph: network-packet
+    level: project
+    metric: network-transmit-errors-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_network_transmit_errors_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}[5m])) 
+  legendFormat: Transmit errors
+  description: workload network transmit errors sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: workload-network-transmit-errors-sum-rate-details
+  labels:
+    app: metric-expression
+    component: workload
+    details: "true"
+    graph: network-packet
+    level: project
+    metric: network-transmit-errors-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_network_transmit_errors_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}[5m])) by (pod_name)
+  legendFormat: Transmit errors([[pod_name]])
+  description: workload network transmit errors sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: workload-network-transmit-packets-dropped-sum-rate
+  labels:
+    app: metric-expression
+    component: workload
+    details: "false"
+    graph: network-packet
+    level: project
+    metric: network-transmit-packets-dropped-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_network_transmit_packets_dropped_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}[5m])) 
+  legendFormat: Transmit dropped
+  description: workload network transmit packets dropped sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: workload-network-transmit-packets-dropped-sum-rate-details
+  labels:
+    app: metric-expression
+    component: workload
+    details: "true"
+    graph: network-packet
+    level: project
+    metric: network-transmit-packets-dropped-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_network_transmit_packets_dropped_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}[5m])) by (pod_name)
+  legendFormat: Transmit dropped([[pod_name]])
+  description: workload network transmit packets dropped sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: workload-cpu-user-seconds-sum-rate
+  labels:
+    app: metric-expression
+    component: workload
+    details: "false"
+    graph: container-cpu-usage-details
+    level: project
+    metric: cpu-user-seconds-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_cpu_user_seconds_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}[5m])) 
+  legendFormat: CPU user seconds
+  description: workload cpu user seconds sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: workload-cpu-user-seconds-sum-rate-details
+  labels:
+    app: metric-expression
+    component: workload
+    details: "true"
+    graph: container-cpu-usage-details
+    level: project
+    metric: cpu-user-seconds-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_cpu_user_seconds_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}[5m])) by (pod_name)
+  legendFormat: CPU user seconds([[pod_name]])
+  description: workload cpu user seconds sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: workload-cpu-cfs-throttled-seconds-sum-rate
+  labels:
+    app: metric-expression
+    component: workload
+    details: "false"
+    level: project
+    metric: cpu-cfs-throttled-seconds-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_cpu_cfs_throttled_seconds_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}[5m])) 
+  legendFormat: CPU cfs throttled
+  description: workload cpu cfs throttled seconds sum rate
+---
+kind: MonitorMetric
+apiVersion: management.cattle.io/v3
+metadata:
+  name: workload-cpu-cfs-throttled-seconds-sum-rate-details
+  labels:
+    app: metric-expression
+    component: workload
+    details: "true"
+    level: project
+    metric: cpu-cfs-throttled-seconds-sum-rate
+    source: rancher-monitoring
+spec:
+  expression: sum(rate(container_cpu_cfs_throttled_seconds_total{namespace=~"$namespace",pod_name=~"$podName",
+    container_name!=""}[5m])) by (pod_name)
+  legendFormat: CPU cfs throttled([[pod_name]])
+  description: workload cpu cfs throttled seconds sum rate
+---

charts/rancher-monitoring/v0.0.2/charts/metric-expression-cluster/templates/graphapiserver.yaml

+apiVersion: management.cattle.io/v3
+kind: ClusterMonitorGraph
+metadata:
+  labels:
+    app: metric-expression
+    source: rancher-monitoring
+    level: cluster
+    component: apiserver
+    cluster-graph: kube-component
+  name: apiserver-request-latency
+spec:
+  resourceType: apiserver
+  displayResourceType: kube-component
+  priority: 300
+  title: apiserver-request-latency
+  detailsMetricsSelector:
+    component: apiserver
+    details: "true"
+    metric: request-latency-milliseconds-avg
+  metricsSelector:
+    details: "false"
+    component: apiserver
+    metric: request-latency-milliseconds-avg
+  yAxis:
+    unit: ms
+---
+apiVersion: management.cattle.io/v3
+kind: ClusterMonitorGraph
+metadata:
+  labels:
+    app: metric-expression
+    source: rancher-monitoring
+    level: cluster
+    component: apiserver
+    cluster-graph: kube-component
+  name: apiserver-request-count
+spec:
+  resourceType: apiserver
+  displayResourceType: kube-component
+  priority: 301
+  title: apiserver-request-count
+  detailsMetricsSelector:
+    component: apiserver
+    details: "true"
+    metric: request-count-sum-rate
+  metricsSelector:
+    details: "false"
+    component: apiserver
+    metric: request-count-sum-rate
+  yAxis:
+    unit: number
\ No newline at end of file

charts/rancher-monitoring/v0.0.2/charts/metric-expression-cluster/templates/graphcluster.yaml

+apiVersion: management.cattle.io/v3
+kind: ClusterMonitorGraph
+metadata:
+  labels:
+    app: metric-expression
+    source: rancher-monitoring
+    level: cluster
+    component: cluster
+  name: cluster-cpu-usage
+spec:
+  resourceType: cluster
+  priority: 100
+  title: cluster-cpu-usage
+  metricsSelector:
+    details: "false"
+    component: cluster
+    metric: cpu-usage-seconds-sum-rate
+  detailsMetricsSelector:
+    details: "true"
+    component: cluster
+    metric: cpu-usage-seconds-sum-rate
+  yAxis:
+    unit: percent
+---
+apiVersion: management.cattle.io/v3
+kind: ClusterMonitorGraph
+metadata:
+  labels:
+    app: metric-expression
+    source: rancher-monitoring
+    level: cluster
+    component: cluster
+  name: cluster-cpu-load
+spec:
+  resourceType: cluster
+  priority: 101
+  title: cluster-cpu-load
+  metricsSelector:
+    details: "false"
+    component: cluster
+    graph: cpu-load
+  detailsMetricsSelector:
+    details: "true"
+    component: cluster
+    graph: cpu-load
+  yAxis:
+    unit: number
+---
+apiVersion: management.cattle.io/v3
+kind: ClusterMonitorGraph
+metadata:
+  labels:
+    app: metric-expression
+    source: rancher-monitoring
+    level: cluster
+    component: cluster
+  name: cluster-memory-usage
+spec:
+  resourceType: cluster
+  priority: 102
+  title: cluster-memory-usage
+  metricsSelector:
+    details: "false"
+    component: cluster
+    metric: memory-usage-percent
+  detailsMetricsSelector:
+    details: "true"
+    component: cluster
+    metric: memory-usage-percent
+  yAxis:
+    unit: percent
+---
+apiVersion: management.cattle.io/v3
+kind: ClusterMonitorGraph
+metadata:
+  labels:
+    app: metric-expression
+    source: rancher-monitoring
+    level: cluster
+    component: cluster
+  name: cluster-fs-usage-percent
+spec:
+  resourceType: cluster
+  priority: 103
+  title: cluster-fs-usage-percent
+  thresholds: 10
+  metricsSelector:
+    details: "false"
+    component: cluster
+    metric: fs-usage-percent
+  detailsMetricsSelector:
+    details: "true"
+    component: cluster
+    metric: fs-usage-percent
+  yAxis:
+    unit: percent
+---
+apiVersion: management.cattle.io/v3
+kind: ClusterMonitorGraph
+metadata:
+  labels:
+    app: metric-expression
+    source: rancher-monitoring
+    level: cluster
+    component: cluster
+  name: cluster-disk-io
+spec:
+  resourceType: cluster
+  priority: 104
+  title: cluster-disk-io
+  thresholds: 10
+  metricsSelector:
+    details: "false"
+    component: cluster
+    graph: disk-io
+  detailsMetricsSelector:
+    details: "true"
+    component: cluster
+    graph: disk-io
+  yAxis:
+    unit: kbps
+---
+apiVersion: management.cattle.io/v3
+kind: ClusterMonitorGraph
+metadata:
+  labels:
+    app: metric-expression
+    source: rancher-monitoring
+    level: cluster
+    component: cluster
+  name: cluster-network-io
+spec:
+  resourceType: cluster
+  priority: 105
+  title: cluster-network-io
+  thresholds: 10
+  metricsSelector:
+    details: "false"
+    component: cluster
+    graph: network-io
+  detailsMetricsSelector:
+    details: "true"
+    component: cluster
+    graph: network-io
+  yAxis:
+    unit: kbps
+---
+apiVersion: management.cattle.io/v3
+kind: ClusterMonitorGraph
+metadata:
+  labels:
+    app: metric-expression
+    source: rancher-monitoring
+    level: cluster
+    component: cluster
+  name: cluster-network-packet
+spec:
+  resourceType: cluster
+  priority: 106
+  title: cluster-network-packet
+  thresholds: 10
+  metricsSelector:
+    details: "false"
+    component: cluster
+    graph: network-packet
+  detailsMetricsSelector:
+    details: "true"
+    component: cluster
+    graph: network-packet
+  yAxis:
+    unit: pps
\ No newline at end of file

charts/rancher-monitoring/v0.0.2/charts/metric-expression-cluster/templates/graphcontrollermanager.yaml

+---
+apiVersion: management.cattle.io/v3
+kind: ClusterMonitorGraph
+metadata:
+  labels:
+    app: metric-expression
+    source: rancher-monitoring
+    level: cluster
+    component: controllermanager
+    cluster-graph: kube-component
+  name: controllermanager-queue-depth
+spec:
+  resourceType: controllermanager
+  displayResourceType: kube-component
+  priority: 310
+  title: controllermanager-queue-depth
+  metricsSelector:
+    details: "false"
+    component: controllermanager
+  detailsMetricsSelector:
+    details: "true"
+    component: controllermanager
+  yAxis:
+    unit: number

charts/rancher-monitoring/v0.0.2/charts/metric-expression-cluster/templates/graphetcd.yaml

+---
+apiVersion: management.cattle.io/v3
+kind: ClusterMonitorGraph
+metadata:
+  labels:
+    app: metric-expression
+    source: rancher-monitoring
+    level: cluster
+    component: etcd
+  name: etcd-server-leader-sum
+spec:
+  resourceType: etcd
+  priority: 200
+  title: etcd-server-leader-sum
+  description: etcd server leader sum
+  metricsSelector:
+    details: "false"
+    component: etcd
+    metric: server-leader-sum
+  detailsMetricsSelector:
+    details: "true"
+    component: etcd
+    metric: server-leader-sum
+  yAxis:
+    unit: number
+  graphType: singlestat
+---
+apiVersion: management.cattle.io/v3
+kind: ClusterMonitorGraph
+metadata:
+  labels:
+    app: metric-expression
+    source: rancher-monitoring
+    level: cluster
+    component: etcd
+  name: etcd-server-failed-proposal
+spec:
+  resourceType: etcd
+  priority: 201
+  title: etcd-server-failed-proposal
+  description: etcd server failed proposal
+  metricsSelector:
+    details: "false"
+    component: etcd
+    metric: server-failed-proposal
+  detailsMetricsSelector:
+    details: "true"
+    component: etcd
+    metric: server-failed-proposal
+  yAxis:
+    unit: number
+  graphType: singlestat
+---
+apiVersion: management.cattle.io/v3
+kind: ClusterMonitorGraph
+metadata:
+  labels:
+    app: metric-expression
+    source: rancher-monitoring
+    level: cluster
+    component: etcd
+  name: etcd-leader-change
+spec:
+  resourceType: etcd
+  priority: 202
+  title: etcd-leader-change
+  description: etcd leader change
+  metricsSelector:
+    details: "false"
+    component: etcd
+    metric: server-leader-changes-seen-sum-increase
+  detailsMetricsSelector:
+    details: "true"
+    component: etcd
+    metric: server-leader-changes-seen-sum-increase
+  yAxis:
+    unit: number
+  graphType: singlestat
+---
+apiVersion: management.cattle.io/v3
+kind: ClusterMonitorGraph
+metadata:
+  labels:
+    app: metric-expression
+    source: rancher-monitoring
+    level: cluster
+    component: etcd
+  name: etcd-grpc-client
+spec:
+  resourceType: etcd
+  priority: 203
+  title: etcd-grpc-client
+  description: etcd grpc client receive/send bytes sum rate
+  metricsSelector:
+    details: "false"
+    component: etcd
+    graph: rpc-client-traffic
+  detailsMetricsSelector:
+    details: "true"
+    component: etcd
+    graph: rpc-client-traffic
+  yAxis:
+    unit: kbps
+---
+apiVersion: management.cattle.io/v3
+kind: ClusterMonitorGraph
+metadata:
+  labels:
+    app: metric-expression
+    source: rancher-monitoring
+    level: cluster
+    component: etcd
+    metric: db-bytes-sum 
+  name: etcd-db-bytes-sum
+spec:
+  resourceType: etcd
+  priority: 204
+  title: etcd-db-bytes-sum
+  description: etcd db bytes sum
+  metricsSelector:
+    details: "false"
+    component: etcd
+    metric: db-bytes-sum 
+  detailsMetricsSelector:
+    details: "true"
+    component: etcd
+    metric: db-bytes-sum 
+  yAxis:
+    unit: byte
+---
+apiVersion: management.cattle.io/v3
+kind: ClusterMonitorGraph
+metadata:
+  labels:
+    app: metric-expression
+    source: rancher-monitoring
+    level: cluster
+    component: etcd
+  name: etcd-stream
+spec:
+  resourceType: etcd
+  priority: 205
+  title: etcd-stream
+  description: Etcd lease/watch stream
+  metricsSelector:
+    details: "false"
+    component: etcd
+    graph: etcd-stream
+  detailsMetricsSelector:
+    details: "true"
+    component: etcd
+    graph: etcd-stream
+  yAxis:
+    unit: number
+---
+apiVersion: management.cattle.io/v3
+kind: ClusterMonitorGraph
+metadata:
+  labels:
+    app: metric-expression
+    source: rancher-monitoring
+    level: cluster
+    component: etcd
+  name: etcd-peer-traffic
+spec:
+  resourceType: etcd
+  priority: 206
+  title: etcd-peer-traffic
+  description: Etcd peer traffic in/out
+  metricsSelector:
+    details: "false"
+    component: etcd
+    graph: etcd-peer-traffic
+  detailsMetricsSelector:
+    details: "true"
+    component: etcd
+    graph: etcd-peer-traffic
+  yAxis:
+    unit: kbps
+---
+apiVersion: management.cattle.io/v3
+kind: ClusterMonitorGraph
+metadata:
+  labels:
+    app: metric-expression
+    source: rancher-monitoring
+    level: cluster
+    component: etcd
+  name: etcd-raft-proposals
+spec:
+  resourceType: etcd
+  priority: 207
+  title: etcd-raft-proposals
+  description: Etcd raft proposals
+  metricsSelector:
+    details: "false"
+    component: etcd
+    graph: proposal
+  detailsMetricsSelector:
+    details: "true"
+    component: etcd
+    graph: proposal
+  yAxis:
+    unit: number
+---
+apiVersion: management.cattle.io/v3
+kind: ClusterMonitorGraph
+metadata:
+  labels:
+    app: metric-expression
+    source: rancher-monitoring
+    level: cluster
+    component: etcd
+  name: etcd-rpc-rate
+spec:
+  resourceType: etcd
+  priority: 208
+  title: etcd-rpc-rate
+  description: Etcd rpc-rate
+  metricsSelector:
+    details: "false"
+    component: etcd
+    graph: rpc-rate
+  detailsMetricsSelector:
+    details: "true"
+    component: etcd
+    graph: rpc-rate
+  yAxis:
+    unit: ops
+---
+apiVersion: management.cattle.io/v3
+kind: ClusterMonitorGraph
+metadata:
+  labels:
+    app: metric-expression
+    source: rancher-monitoring
+    level: cluster
+    component: etcd
+  name: etcd-disk-operate
+spec:
+  resourceType: etcd
+  priority: 209
+  title: etcd-disk-operate
+  description: Etcd disk operate
+  metricsSelector:
+    details: "false"
+    component: etcd
+    graph: disk-operate
+  detailsMetricsSelector:
+    details: "true"
+    component: etcd
+    graph: disk-operate
+  yAxis:
+    unit: seconds
+---
+apiVersion: management.cattle.io/v3
+kind: ClusterMonitorGraph
+metadata:
+  labels:
+    app: metric-expression
+    source: rancher-monitoring
+    level: cluster
+    component: etcd
+  name: etcd-sync-duration
+spec:
+  resourceType: etcd
+  priority: 209
+  title: etcd-sync-duration
+  description: Etcd sync-duration
+  metricsSelector:
+    details: "false"
+    component: etcd
+    graph: sync-duration
+  detailsMetricsSelector:
+    details: "true"
+    component: etcd
+    graph: sync-duration
+  yAxis:
+    unit: seconds
\ No newline at end of file

charts/rancher-monitoring/v0.0.2/charts/metric-expression-cluster/templates/graphfluentd.yaml

+apiVersion: management.cattle.io/v3
+kind: ClusterMonitorGraph
+metadata:
+  labels:
+    app: metric-expression
+    source: rancher-monitoring
+    level: cluster
+    component: fluentd
+    cluster-graph: rancher-component
+  name: fluentd-input-record-number
+spec:
+  resourceType: fluentd
+  displayResourceType: rancher-component
+  priority: 300
+  title: fluentd-input-record-number
+  metricsSelector:
+    details: "false"
+    component: fluentd
+    metric: input-record
+  detailsMetricsSelector:
+    details: "true"
+    component: fluentd
+    metric: input-record
+  yAxis:
+    unit: number
+---
+apiVersion: management.cattle.io/v3
+kind: ClusterMonitorGraph
+metadata:
+  labels:
+    app: metric-expression
+    source: rancher-monitoring
+    level: cluster
+    component: fluentd
+    cluster-graph: rancher-component
+  name: fluentd-output-record-number
+spec:
+  resourceType: fluentd
+  displayResourceType: rancher-component
+  priority: 301
+  title: fluentd-output-record-number
+  metricsSelector:
+    details: "false"
+    component: fluentd
+    metric: output-record
+  detailsMetricsSelector:
+    details: "true"
+    component: fluentd
+    metric: output-record
+  yAxis:
+    unit: number
+---
+apiVersion: management.cattle.io/v3
+kind: ClusterMonitorGraph
+metadata:
+  labels:
+    app: metric-expression
+    source: rancher-monitoring
+    level: cluster
+    component: fluentd
+    cluster-graph: rancher-component
+  name: fluentd-output-errors
+spec:
+  resourceType: fluentd
+  displayResourceType: rancher-component
+  priority: 301
+  title: fluentd-output-errors
+  metricsSelector:
+    details: "false"
+    component: fluentd
+    metric: output-errors
+  detailsMetricsSelector:
+    details: "true"
+    component: fluentd
+    metric: output-errors
+  yAxis:
+    unit: number
+---
+apiVersion: management.cattle.io/v3
+kind: ClusterMonitorGraph
+metadata:
+  labels:
+    app: metric-expression
+    source: rancher-monitoring
+    level: cluster
+    component: fluentd
+    cluster-graph: rancher-component
+  name: fluentd-buffer-queue-length
+spec:
+  resourceType: fluentd
+  displayResourceType: rancher-component
+  priority: 301
+  title: fluentd-buffer-queue-length
+  metricsSelector:
+    details: "false"
+    component: fluentd
+    metric: buffer-queue-length
+  detailsMetricsSelector:
+    details: "true"
+    component: fluentd
+    metric: buffer-queue-length
+  yAxis:
+    unit: number
\ No newline at end of file

charts/rancher-monitoring/v0.0.2/charts/metric-expression-cluster/templates/graphingresscontroller.yaml

+apiVersion: management.cattle.io/v3
+kind: ClusterMonitorGraph
+metadata:
+  labels:
+    app: metric-expression
+    source: rancher-monitoring
+    level: cluster
+    component: ingresscontroller
+    cluster-graph: kube-component
+  name: ingresscontroller-nginx-connection
+spec:
+  resourceType: ingresscontroller
+  displayResourceType: kube-component
+  priority: 330
+  title: ingresscontroller-nginx-connection
+  metricsSelector:
+    details: "false"
+    component: ingresscontroller
+    graph: nginx-connection
+  detailsMetricsSelector:
+    details: "true"
+    component: ingresscontroller
+    graph: nginx-connection
+  yAxis:
+    unit: number
+---
+apiVersion: management.cattle.io/v3
+kind: ClusterMonitorGraph
+metadata:
+  labels:
+    app: metric-expression
+    source: rancher-monitoring
+    level: cluster
+    component: ingresscontroller
+    cluster-graph: kube-component
+  name: ingresscontroller-request-process-time
+spec:
+  resourceType: ingresscontroller
+  displayResourceType: kube-component
+  priority: 331
+  title: ingresscontroller-request-process-time
+  metricsSelector:
+    details: "false"
+    component: ingresscontroller
+    metric: request-process-seconds
+  detailsMetricsSelector:
+    details: "true"
+    component: ingresscontroller
+    metric: request-process-seconds
+  yAxis:
+    unit: seconds
+---
+apiVersion: management.cattle.io/v3
+kind: ClusterMonitorGraph
+metadata:
+  labels:
+    app: metric-expression
+    source: rancher-monitoring
+    level: cluster
+    component: ingresscontroller
+    cluster-graph: kube-component
+  name: ingresscontroller-upstream-response-seconds
+spec:
+  resourceType: ingresscontroller
+  displayResourceType: kube-component
+  priority: 332
+  title: ingresscontroller-upstream-response-seconds
+  metricsSelector:
+    details: "false"
+    component: ingresscontroller
+    metric: upstream-response-seconds
+  detailsMetricsSelector:
+    details: "true"
+    component: ingresscontroller
+    metric: upstream-response-seconds
+  yAxis:
+    unit: seconds
+  graphType: singlestat
\ No newline at end of file

charts/rancher-monitoring/v0.0.2/charts/metric-expression-cluster/templates/graphnode.yaml

+apiVersion: management.cattle.io/v3
+kind: ClusterMonitorGraph
+metadata:
+  labels:
+    app: metric-expression
+    source: rancher-monitoring
+    level: cluster
+    component: node
+  name: node-cpu-usage
+spec:
+  resourceType: node
+  priority: 500
+  title: node-cpu-usage
+  metricsSelector:
+    details: "false"
+    component: node
+    metric: cpu-usage-seconds-sum-rate
+  detailsMetricsSelector:
+    details: "true"
+    component: node
+    metric: cpu-usage-seconds-sum-rate
+  yAxis:
+    unit: percent
+---
+apiVersion: management.cattle.io/v3
+kind: ClusterMonitorGraph
+metadata:
+  labels:
+    app: metric-expression
+    source: rancher-monitoring
+    level: cluster
+    component: node
+  name: node-cpu-load
+spec:
+  resourceType: node
+  priority: 501
+  title: node-cpu-load
+  metricsSelector:
+    details: "false"
+    component: node
+    graph: cpu-load
+  detailsMetricsSelector:
+    details: "true"
+    component: node
+    graph: cpu-load
+  yAxis:
+    unit: number
+---
+apiVersion: management.cattle.io/v3
+kind: ClusterMonitorGraph
+metadata:
+  labels:
+    app: metric-expression
+    source: rancher-monitoring
+    level: cluster
+    component: node
+  name: node-memory-usage
+spec:
+  resourceType: node
+  priority: 502
+  title: node-memory-usage
+  metricsSelector:
+    details: "false"
+    component: node
+    metric: memory-usage-percent
+  detailsMetricsSelector:
+    details: "true"
+    component: node
+    metric: memory-usage-percent
+  yAxis:
+    unit: percent
+---
+apiVersion: management.cattle.io/v3
+kind: ClusterMonitorGraph
+metadata:
+  labels:
+    app: metric-expression
+    source: rancher-monitoring
+    level: cluster
+    component: node
+  name: node-fs-usage-percent
+spec:
+  resourceType: node
+  priority: 503
+  title: node-fs-usage-percent
+  thresholds: 10
+  metricsSelector:
+    details: "false"
+    component: node
+    metric: fs-usage-percent
+  detailsMetricsSelector:
+    details: "true"
+    component: node
+    metric: fs-usage-percent
+  yAxis:
+    unit: percent
+---
+apiVersion: management.cattle.io/v3
+kind: ClusterMonitorGraph
+metadata:
+  labels:
+    app: metric-expression
+    source: rancher-monitoring
+    level: cluster
+    component: node
+  name: node-disk-io
+spec:
+  resourceType: node
+  priority: 504
+  title: node-disk-io
+  thresholds: 10
+  metricsSelector:
+    details: "false"
+    component: node
+    graph: disk-io
+  detailsMetricsSelector:
+    details: "true"
+    component: node
+    graph: disk-io
+  yAxis:
+    unit: kbps
+---
+apiVersion: management.cattle.io/v3
+kind: ClusterMonitorGraph
+metadata:
+  labels:
+    app: metric-expression
+    source: rancher-monitoring
+    level: cluster
+    component: node
+  name: node-network-io
+spec:
+  resourceType: node
+  priority: 505
+  title: node-network-io
+  thresholds: 10
+  metricsSelector:
+    details: "false"
+    component: node
+    graph: network-io
+  detailsMetricsSelector:
+    details: "true"
+    component: node
+    graph: network-io
+  yAxis:
+    unit: kbps
+---
+apiVersion: management.cattle.io/v3
+kind: ClusterMonitorGraph
+metadata:
+  labels:
+    app: metric-expression
+    source: rancher-monitoring
+    level: cluster
+    component: node
+  name: node-network-packet
+spec:
+  resourceType: node
+  priority: 506
+  title: node-network-packet
+  thresholds: 10
+  metricsSelector:
+    details: "false"
+    component: node
+    graph: network-packet
+  detailsMetricsSelector:
+    details: "true"
+    component: node
+    graph: network-packet
+  yAxis:
+    unit: pps
\ No newline at end of file

charts/rancher-monitoring/v0.0.2/charts/metric-expression-cluster/templates/graphscheduler.yaml

+apiVersion: management.cattle.io/v3
+kind: ClusterMonitorGraph
+metadata:
+  labels:
+    app: metric-expression
+    source: rancher-monitoring
+    level: cluster
+    component: scheduler
+    cluster-graph: kube-component
+  name: scheduler-e-2-e-scheduling-latency-seconds-quantile
+spec:
+  resourceType: scheduler
+  displayResourceType: kube-component
+  priority: 320
+  title: scheduler-e-2-e-scheduling-latency-seconds-quantile
+  thresholds: 10
+  metricsSelector:
+    details: "false"
+    component: scheduler
+    metric: e-2-e-scheduling-latency-seconds-quantile
+  detailsMetricsSelector:
+    details: "true"
+    component: scheduler
+    metric: e-2-e-scheduling-latency-seconds-quantile
+  yAxis:
+    unit: seconds
+---
+apiVersion: management.cattle.io/v3
+kind: ClusterMonitorGraph
+metadata:
+  labels:
+    app: metric-expression
+    source: rancher-monitoring
+    level: cluster
+    component: scheduler
+    cluster-graph: kube-component
+  name: scheduler-total-preemption-attempts
+spec:
+  resourceType: scheduler
+  displayResourceType: kube-component
+  priority: 321
+  title: scheduler-total-preemption-attempts
+  thresholds: 10
+  metricsSelector:
+    details: "false"
+    component: scheduler
+    metric: total-preemption-attempts
+  detailsMetricsSelector:
+    details: "true"
+    component: scheduler
+    metric: total-preemption-attempts
+  yAxis:
+    unit: number
+---
+apiVersion: management.cattle.io/v3
+kind: ClusterMonitorGraph
+metadata:
+  labels:
+    app: metric-expression
+    source: rancher-monitoring
+    level: cluster
+    component: scheduler
+    cluster-graph: kube-component
+  name: scheduler-pod-unscheduler
+spec:
+  resourceType: scheduler
+  displayResourceType: kube-component
+  priority: 322
+  title: scheduler-pod-unscheduler
+  thresholds: 10
+  metricsSelector:
+    details: "false"
+    component: scheduler
+    metric: pod-unscheduler
+  detailsMetricsSelector:
+    details: "true"
+    component: scheduler
+    metric: pod-unscheduler
+  yAxis:
+    unit: number
\ No newline at end of file

charts/rancher-monitoring/v0.0.2/charts/metric-expression-project/Chart.yaml

+apiVersion: v1
+description: Creates Metrics CRD of Rancher monitoring graph
+engine: gotpl
+maintainers:
+- name: aiwantaozi
+  email: michelia.feng@gmail.com
+name: metric-expression-project
+version: 0.0.1
+

charts/rancher-monitoring/v0.0.2/charts/metric-expression-project/templates/graphcontainer.yaml

+apiVersion: management.cattle.io/v3
+kind: ProjectMonitorGraph
+metadata:
+  labels:
+    app: metric-expression
+    source: rancher-monitoring
+    level: project
+    component: container
+  name: container-cpu-usage
+spec:
+  projectName: {{ .ProjectName }}
+  resourceType: container
+  priority: 800
+  title: container-cpu-usage
+  metricsSelector:
+    details: "false"
+    component: container
+    graph: container-cpu-usage
+  detailsMetricsSelector:
+    details: "true"
+    component: container
+    graph: container-cpu-usage-details
+  yAxis:
+    unit: mcpu
+---
+apiVersion: management.cattle.io/v3
+kind: ProjectMonitorGraph
+metadata:
+  labels:
+    app: metric-expression
+    source: rancher-monitoring
+    level: project
+    component: container
+  name: container-memory-usage-bytes-sum
+spec:
+  projectName: {{ .ProjectName }}
+  resourceType: container
+  priority: 801
+  title: container-memory-usage-bytes-sum
+  metricsSelector:
+    details: "false"
+    component: container
+    metric: memory-usage-bytes-sum
+  detailsMetricsSelector:
+    details: "true"
+    component: container
+    metric: memory-usage-bytes-sum
+  yAxis:
+    unit: byte
+---
+apiVersion: management.cattle.io/v3
+kind: ProjectMonitorGraph
+metadata:
+  labels:
+    app: metric-expression
+    source: rancher-monitoring
+    level: project
+    component: container
+  name: container-network-io
+spec:
+  projectName: {{ .ProjectName }}
+  resourceType: container
+  priority: 802
+  title: container-network-io
+  metricsSelector:
+    details: "false"
+    component: container
+    graph: network-io
+  detailsMetricsSelector:
+    details: "true"
+    component: container
+    graph: network-io
+  yAxis:
+    unit: kbps
+---
+apiVersion: management.cattle.io/v3
+kind: ProjectMonitorGraph
+metadata:
+  labels:
+    app: metric-expression
+    source: rancher-monitoring
+    level: project
+    component: container
+  name: container-network-packet
+spec:
+  projectName: {{ .ProjectName }}
+  resourceType: container
+  priority: 803
+  title: container-network-packet
+  metricsSelector:
+    details: "false"
+    component: container
+    graph: network-packet
+  detailsMetricsSelector:
+    details: "true"
+    component: container
+    graph: network-packet
+  yAxis:
+    unit: pps
+---
+apiVersion: management.cattle.io/v3
+kind: ProjectMonitorGraph
+metadata:
+  labels:
+    app: metric-expression
+    source: rancher-monitoring
+    level: project
+    component: container
+  name: container-disk-io
+spec:
+  projectName: {{ .ProjectName }}
+  resourceType: container
+  priority: 804
+  title: container-disk-io
+  metricsSelector:
+    details: "false"
+    component: container
+    graph: disk-io
+  detailsMetricsSelector:
+    details: "true"
+    component: container
+    graph: disk-io
+  yAxis:
+    unit: kbps
+---

charts/rancher-monitoring/v0.0.2/charts/metric-expression-project/templates/graphpod.yaml

+apiVersion: management.cattle.io/v3
+kind: ProjectMonitorGraph
+metadata:
+  labels:
+    app: metric-expression
+    source: rancher-monitoring
+    level: project
+    component: pod
+  name: pod-cpu-usage
+spec:
+  projectName: {{ .ProjectName }}
+  resourceType: pod
+  priority: 700
+  title: pod-cpu-usage
+  metricsSelector:
+    details: "false"
+    component: pod
+    graph: container-cpu-usage
+  detailsMetailsMetricsSelector:
+    details: "true"
+    component: pod
+    graph: container-cpu-usage-details
+  yAxis:
+    unit: mcpu
+---
+apiVersion: management.cattle.io/v3
+kind: ProjectMonitorGraph
+metadata:
+  labels:
+    app: metric-expression
+    source: rancher-monitoring
+    level: project
+    component: pod
+  name: pod-memory-usage-bytes-sum
+spec:
+  projectName: {{ .ProjectName }}
+  resourceType: pod
+  priority: 701
+  title: pod-memory-usage-bytes-sum
+  metricsSelector:
+    details: "false"
+    component: pod
+    metric: memory-usage-bytes-sum
+  detailsMetricsSelector:
+    details: "true"
+    component: pod
+    metric: memory-usage-bytes-sum
+  yAxis:
+    unit: byte
+---
+apiVersion: management.cattle.io/v3
+kind: ProjectMonitorGraph
+metadata:
+  labels:
+    app: metric-expression
+    source: rancher-monitoring
+    level: project
+    component: pod
+  name: pod-network-io
+spec:
+  projectName: {{ .ProjectName }}
+  resourceType: pod
+  priority: 702
+  title: pod-network-io
+  metricsSelector:
+    details: "false"
+    component: pod
+    graph: network-io
+  detailsMetricsSelector:
+    details: "true"
+    component: pod
+    graph: network-io
+  yAxis:
+    unit: kbps
+---
+apiVersion: management.cattle.io/v3
+kind: ProjectMonitorGraph
+metadata:
+  labels:
+    app: metric-expression
+    source: rancher-monitoring
+    level: project
+    component: pod
+  name: pod-network-packet
+spec:
+  projectName: {{ .ProjectName }}
+  resourceType: pod
+  priority: 703
+  title: pod-network-packet
+  metricsSelector:
+    details: "false"
+    component: pod
+    graph: network-packet
+  detailsMetricsSelector:
+    details: "true"
+    component: pod
+    graph: network-packet
+  yAxis:
+    unit: pps
+---
+apiVersion: management.cattle.io/v3
+kind: ProjectMonitorGraph
+metadata:
+  labels:
+    app: metric-expression
+    source: rancher-monitoring
+    level: project
+    component: pod
+  name: pod-disk-io
+spec:
+  projectName: {{ .ProjectName }}
+  resourceType: pod
+  priority: 704
+  title: pod-disk-io
+  metricsSelector:
+    details: "false"
+    component: pod
+    graph: disk-io
+  detailsMetricsSelector:
+    details: "true"
+    component: pod
+    graph: disk-io
+  yAxis:
+    unit: kbps
+---

charts/rancher-monitoring/v0.0.2/charts/metric-expression-project/templates/graphworkload.yaml

+apiVersion: management.cattle.io/v3
+kind: ProjectMonitorGraph
+metadata:
+  labels:
+    app: metric-expression
+    source: rancher-monitoring
+    level: project
+    component: workload
+  name: workload-cpu-usage
+spec:
+  projectName: {{ .ProjectName }}
+  resourceType: workload
+  priority: 600
+  title: workload-cpu-usage
+  metricsSelector:
+    details: "false"
+    component: workload
+    graph: container-cpu-usage
+  detailsMetailsMetricsSelector:
+    details: "true"
+    component: pod
+    graph: container-cpu-usage-details
+  yAxis:
+    unit: mcpu
+---
+apiVersion: management.cattle.io/v3
+kind: ProjectMonitorGraph
+metadata:
+  labels:
+    app: metric-expression
+    source: rancher-monitoring
+    level: project
+    component: workload
+  name: workload-memory-usage-bytes-sum
+spec:
+  projectName: {{ .ProjectName }}
+  resourceType: workload
+  priority: 601
+  title: workload-memory-usage-bytes-sum
+  metricsSelector:
+    details: "false"
+    component: workload
+    metric: memory-usage-bytes-sum
+  detailsMetricsSelector:
+    details: "true"
+    component: workload
+    metric: memory-usage-bytes-sum
+  yAxis:
+    unit: byte
+---
+apiVersion: management.cattle.io/v3
+kind: ProjectMonitorGraph
+metadata:
+  labels:
+    app: metric-expression
+    source: rancher-monitoring
+    level: project
+    component: workload
+  name: workload-network-io
+spec:
+  projectName: {{ .ProjectName }}
+  resourceType: workload
+  priority: 602
+  title: workload-network-io
+  metricsSelector:
+    details: "false"
+    component: workload
+    graph: network-io
+  detailsMetricsSelector:
+    details: "true"
+    component: workload
+    graph: network-io
+  yAxis:
+    unit: kbps
+---
+apiVersion: management.cattle.io/v3
+kind: ProjectMonitorGraph
+metadata:
+  labels:
+    app: metric-expression
+    source: rancher-monitoring
+    level: project
+    component: workload
+  name: workload-network-packet
+spec:
+  projectName: {{ .ProjectName }}
+  resourceType: workload
+  priority: 603
+  title: workload-network-packet
+  metricsSelector:
+    details: "false"
+    component: workload
+    graph: network-packet
+  detailsMetricsSelector:
+    details: "true"
+    component: workload
+    graph: network-packet
+  yAxis:
+    unit: pps
+---
+apiVersion: management.cattle.io/v3
+kind: ProjectMonitorGraph
+metadata:
+  labels:
+    app: metric-expression
+    source: rancher-monitoring
+    level: project
+    component: workload
+  name: workload-disk-io
+spec:
+  projectName: {{ .ProjectName }}
+  resourceType: workload
+  priority: 604
+  title: workload-disk-io
+  metricsSelector:
+    details: "false"
+    component: workload
+    graph: disk-io
+  detailsMetricsSelector:
+    details: "true"
+    component: workload
+    graph: disk-io
+  yAxis:
+    unit: kbps
+---

charts/rancher-monitoring/v0.0.2/charts/prometheus/Chart.yaml

+apiVersion: v1
+description: Creates Prometheus CRD instance for Kubernetes which maintaining by Rancher 2.
+engine: gotpl
+maintainers:
+- name: thxCode
+  email: frank@rancher.com
+name: prometheus
+version: 0.0.1

charts/rancher-monitoring/v0.0.2/charts/prometheus/templates/hooks-configmap.yaml

+apiVersion: v1
+kind: ConfigMap
+metadata:
+  labels:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+  name: {{ template "app.hooks.fullname" . }}
+data:
+  replace-config-by-auth.sh: |-
+    #!/bin/sh
+
+    srcpath="/template/nginx.conf"
+    dstpath="/host/nginx.conf"
+
+    if [ -f $srcpath ] && [ -d /host ]; then
+      token=$(cat /var/run/secrets/kubernetes.io/serviceaccount/token)
+
+      sed "s/REPLACE_PARAM_AUTHORIZATION/Bearer ${token}/g" $srcpath > $dstpath
+      cat $dstpath
+
+      exit 0
+    fi
+
+    exit 1
+
+

charts/rancher-monitoring/v0.0.2/charts/prometheus/templates/metrics-service.yaml

+apiVersion: v1
+kind: Service
+metadata:
+  name: expose-prometheus-metrics
+  labels:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+    monitoring.cattle.io: "true"
+spec:
+  type: ClusterIP
+  selector:
+{{- if .Values.labels }}
+{{ toYaml .Values.labels | indent 4 }}
+{{- else }}
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    release: {{ .Release.Name }}
+{{- end }}
+  ports:
+    - name: http
+      port: 9090
+      targetPort: web
\ No newline at end of file

charts/rancher-monitoring/v0.0.2/charts/prometheus/templates/nginx-comfigmap.yaml

+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: {{ template "app.nginx.fullname" . }}
+  labels:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+    component: nginx
+data:
+  nginx.conf: |-
+    user  nginx;
+    worker_processes  auto;
+    error_log  /dev/null warn;
+    pid        /var/run/nginx.pid;
+    
+    events {
+       worker_connections  1024;
+    }
+
+    http {
+      include /etc/nginx/mime.types;
+
+      log_format  main  '[$time_local - $status] $remote_addr - $remote_user $request ($http_referer)';
+
+      server {
+        listen 80;
+
+        access_log off;
+
+        gzip on;
+        gzip_min_length 1k;
+        gzip_comp_level 2;
+        gzip_types text/plain application/javascript application/x-javascript text/css application/xml text/javascript image/jpeg image/gif image/png;
+        gzip_vary on;
+        gzip_disable "MSIE [1-6]\.";
+
+        proxy_set_header Host $host;
+        proxy_set_header X-Real-IP $remote_addr;
+        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
+        proxy_set_header X-Forwarded-Proto $scheme;
+        proxy_set_header Authorization "REPLACE_PARAM_AUTHORIZATION";
+        proxy_pass_header  Authorization;
+
+        location / {
+          proxy_pass     http://prometheus-operated:9090/;
+
+          sub_filter_types text/html;
+          sub_filter_once off;
+          sub_filter 'var PATH_PREFIX = "";' 'var PATH_PREFIX = ".";';
+        }
+
+      }
+
+    }

charts/rancher-monitoring/v0.0.2/charts/prometheus/templates/nginx-deployment.yaml

+apiVersion: {{ template "deployment_api_version" . }}
+kind: Deployment
+metadata:
+  name: {{ template "app.nginx.fullname" . }}
+  labels:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+    component: nginx
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: {{ template "app.name" . }}
+      chart: {{ template "app.version" . }}
+      release: {{ .Release.Name }}
+      component: nginx
+  template:
+    metadata:
+      labels:
+        app: {{ template "app.name" . }}
+        chart: {{ template "app.version" . }}
+        release: {{ .Release.Name }}
+        component: nginx
+    spec:
+      {{- if .Values.enabledRBAC }}
+      serviceAccountName: {{ .Values.serviceAccountName }}
+      {{- end }}
+      initContainers:
+      - name: nginx-init-auth-add
+        image: {{ .Values.image.inits.tools.repository }}:{{ .Values.image.inits.tools.tag }}
+        command:
+        - /usr/bin/replace-config-by-auth.sh
+        volumeMounts:
+        - name: prometheus-static-hooks
+          mountPath: /usr/bin/replace-config-by-auth.sh
+          subPath: replace-config-by-auth.sh
+        - name: prometheus-static-contents
+          mountPath: /host
+        - name: prometheus-nginx-template
+          mountPath: /template
+      containers:
+      - name: nginx
+        image: nginx:1.15.2
+        args:
+        - nginx
+        - -g
+        - daemon off;
+        - -c
+        - /nginx/nginx.conf
+        volumeMounts:
+        - mountPath: /nginx
+          name: prometheus-static-contents
+        ports:
+        - name: http
+          containerPort: 80
+          protocol: TCP
+      volumes:
+      - name: prometheus-static-hooks
+        configMap:
+          name: {{ template "app.hooks.fullname" . }}
+          defaultMode: 0777
+      - name: prometheus-static-contents
+        emptyDir: {}
+      - name: prometheus-nginx-template
+        configMap:
+          name: {{ template "app.nginx.fullname" . }}
+          defaultMode: 438
+          items:
+          - key: nginx.conf
+            mode: 438
+            path: nginx.conf

charts/rancher-monitoring/v0.0.2/charts/prometheus/templates/prometheus.yaml

+apiVersion: {{ template "operator_api_version" . }}
+kind: Prometheus
+metadata:
+  labels:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+{{- if .Values.labels }}
+{{ toYaml .Values.labels | indent 4 }}
+{{- end }}
+  name: {{ .Release.Name }}
+spec:
+{{- if .Values.listenLocal }}
+  listenLocal: true
+{{- end }}
+  podMetadata:
+    labels:
+{{- if .Values.labels }}
+{{ toYaml .Values.labels | indent 6 }}
+{{- else }}
+      app: {{ template "app.name" . }}
+      chart: {{ template "app.version" . }}
+      release: {{ .Release.Name }}
+{{- end }}
+{{- if .Values.alertingEndpoints }}
+  alerting:
+    alertmanagers:
+{{ toYaml .Values.alertingEndpoints | indent 6 }}
+{{- else }}
+  alerting:
+    alertmanagers:
+      - namespace: {{ .Release.Namespace }}
+        name: alertmanager-operated
+        port: http
+{{- end }}
+  baseImage: "{{ .Values.image.repository }}"
+{{- if .Values.externalLabels }}
+  externalLabels:
+{{ toYaml .Values.externalLabels | indent 4}}
+{{- end }}
+{{- if .Values.externalUrl }}
+  externalUrl: "{{ .Values.externalUrl }}"
+{{- end }}
+{{- if .Values.nodeSelector }}
+  nodeSelector:
+{{ toYaml .Values.nodeSelector | indent 4 }}
+{{- end }}
+  paused: {{ .Values.paused }}
+  replicas: {{ .Values.replicaCount }}
+  logLevel:  {{ .Values.logLevel }}
+  resources:
+{{ toYaml .Values.resources | indent 4 }}
+  retention: "{{ .Values.retention }}"
+{{- if .Values.routePrefix }}
+  routePrefix: "{{ .Values.routePrefix }}"
+{{- end }}
+{{- if .Values.secrets }}
+  secrets:
+{{ toYaml .Values.secrets | indent 4 }}
+{{- end }}
+{{- if .Values.enabledRBAC }}
+  serviceAccountName: {{ .Values.serviceAccountName }}
+{{- end }}
+{{- if .Values.serviceMonitorNamespaceSelector }}
+  serviceMonitorNamespaceSelector:
+{{ toYaml .Values.serviceMonitorNamespaceSelector | indent 4 }}
+{{- end }}
+  serviceMonitorSelector:
+{{- if .Values.serviceMonitorsSelector }}
+{{ toYaml .Values.serviceMonitorsSelector | indent 4 }}
+{{- else }}
+    matchLabels:
+      source: rancher-monitoring
+      release: {{ .Release.Name }}
+{{- end }}
+{{- if .Values.remoteRead }}
+  remoteRead:
+{{ toYaml .Values.remoteRead | indent 4 }}
+{{- end }}
+{{- if .Values.remoteWrite }}
+  remoteWrite:
+{{ toYaml .Values.remoteWrite | indent 4 }}
+{{- end }}
+{{- if .Values.ruleNamespaceSelector }}
+  ruleNamespaceSelector:
+{{ toYaml .Values.ruleNamespaceSelector | indent 4 }}
+{{- end }}
+  ruleSelector:
+{{- if .Values.rulesSelector }}
+{{ toYaml .Values.rulesSelector | indent 4 }}
+{{- else }}
+    matchLabels:
+      source: rancher-monitoring
+      release: {{ .Release.Name }}
+{{- end }}
+{{- if or .Values.storageSpec .Values.persistence.enabled }}
+  storage:
+    volumeClaimTemplate:
+      spec:
+{{- if .Values.storageSpec }}
+{{ toYaml .Values.storageSpec | indent 8 }}
+{{- else }}
+        {{ if and .Values.persistence.storageClass (ne "default" .Values.persistence.storageClass) }}
+        storageClassName: {{ .Values.persistence.storageClass }}
+        {{ end }}
+        accessModes: 
+          - {{ default "ReadWriteOnce" .Values.persistence.accessMode }}
+        resources:
+          requests:
+            storage: {{ .Values.persistence.size | quote }}
+{{- end }}
+{{- end }}
+  version: "{{ .Values.image.tag }}"
+  affinity:
+    podAntiAffinity:
+      preferredDuringSchedulingIgnoredDuringExecution:
+      - weight: 100
+        podAffinityTerm:
+          topologyKey: kubernetes.io/hostname
+          labelSelector:
+            matchLabels:
+              app: {{ template "app.name" . }}
+              prometheus: {{ .Release.Name }}
+{{- if .Values.tolerations }}
+  tolerations:
+{{ toYaml .Values.tolerations | indent 4 }}
+{{- end }}
+  imagePullSecrets: 
+{{ toYaml .Values.image.pullSecrets | indent 4 }}
+{{- if and .Values.additionalScrapeConfigsEnabled .Values.additionalScrapeConfigs  }}
+  additionalScrapeConfigs:
+    name: {{ template "app.fullname" . }}-additional-scrape-configs
+    key: additional-scrape-configs.yaml
+{{- end }}
+{{- if and .Values.additionalAlertManagerConfigsEnabled .Values.additionalAlertManagerConfigs }}
+  additionalAlertManagerConfigs:
+    name: {{ template "app.fullname" . }}-additional-alertmanager-configs
+    key: additional-alertmanager-configs.yaml
+{{- end }}
+{{- if .Values.sidecarsSpec }}
+  containers:
+{{ toYaml .Values.sidecarsSpec | indent 4 }}
+{{- end }}

charts/rancher-monitoring/v0.0.2/charts/prometheus/templates/secrets.yaml

+{{- if and .Values.additionalScrapeConfigsEnabled .Values.additionalScrapeConfigs  }}
+apiVersion: v1
+kind: Secret
+metadata:
+  labels:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+  name: {{ template "app.fullname" . }}-additional-scrape-configs
+data:
+  additional-scrape-configs.yaml: {{ toYaml .Values.additionalScrapeConfigs | b64enc | quote }}
+{{- end }}
+
+{{- if and .Values.additionalAlertManagerConfigsEnabled .Values.additionalAlertManagerConfigs }}
+---
+apiVersion: v1
+kind: Secret
+metadata:
+  labels:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+  name: {{ template "app.fullname" . }}-additional-alertmanager-configs
+data:
+  additional-alertmanager-configs.yaml: {{ toYaml .Values.additionalAlertManagerConfigs | b64enc | quote }}
+{{- end }}

charts/rancher-monitoring/v0.0.2/charts/prometheus/templates/service.yaml

+apiVersion: v1
+kind: Service
+metadata:
+  name: access-prometheus
+  labels:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+    kubernetes.io/cluster-service: "true"
+spec:
+  type: ClusterIP
+  selector:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    release: {{ .Release.Name }}
+    component: nginx
+  ports:
+    - name: http
+      port: 80
+      targetPort: http

charts/rancher-monitoring/v0.0.2/charts/prometheus/templates/servicemonitor.yaml

+apiVersion: {{ template "operator_api_version" . }}
+kind: ServiceMonitor
+metadata:
+  labels:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+    source: rancher-monitoring
+    {{- if .Values.serviceMonitor.labels }}
+{{ toYaml .Values.serviceMonitor.labels | indent 4 }}
+    {{- end }}
+  name: {{ template "app.fullname" . }}
+spec:
+  jobLabel: prometheus
+  selector:
+    matchLabels:
+      app: {{ template "app.name" . }}
+      chart: {{ template "app.version" . }}
+      release: {{ .Release.Name }}
+      monitoring.cattle.io: "true"
+  namespaceSelector:
+    matchNames:
+      - {{ .Release.Namespace | quote }}
+  endpoints:
+  - port: http
+    interval: 30s

charts/rancher-monitoring/v0.0.2/charts/prometheus/values.yaml

+enabledRBAC: true
+
+## Already exist ServiceAccount
+##
+serviceAccountName: ""
+
+## CRD apiGroup
+##
+apiGroup: "monitoring.coreos.com"
+
+## Alertmanagers to which alerts will be sent
+## Ref: https://github.com/coreos/prometheus-operator/blob/master/Documentation/api.md#alertmanagerendpoints
+##
+alertingEndpoints: []
+#   - name: ""
+#     namespace: ""
+#     port: http
+#     scheme: http
+
+## External labels to add to any time series or alerts when communicating with external systems
+##
+externalLabels: {}
+
+## External URL at which Prometheus will be reachable
+##
+externalUrl: ""
+
+serviceMonitor:
+  ## Custom Labels to be added to ServiceMonitor
+  ##
+  labels: {}
+
+##Custom Labels to be added to Prometheus Rules CRDs
+##
+additionalRulesLabels: {}
+
+## Prometheus container image
+##
+image:
+  ## Reference to one or more secrets to be used when pulling images
+  ##
+  pullSecrets: []
+  repository: quay.io/prometheus/prometheus
+  tag: v2.4.3
+  inits:
+    tools:
+      repository: maiwj/curl
+      tag: 7.56.1-r0
+
+## Labels to be added to the Prometheus
+##
+# labels: {}
+
+## Node labels for Prometheus pod assignment
+## Ref: https://kubernetes.io/docs/user-guide/node-selection/
+##
+nodeSelector: {}
+
+## Tolerations for use with node taints
+## Ref: https://kubernetes.io/docs/concepts/configuration/taint-and-toleration/
+##
+tolerations: {}
+  #  - key: "key"
+  #    operator: "Equal"
+  #    value: "value"
+  #    effect: "NoSchedule"
+
+
+## If true, the Operator won't process any Prometheus configuration changes
+##
+paused: false
+
+
+## Number of Prometheus replicas desired
+##
+replicaCount: 1
+
+## The remote_read spec configuration for Prometheus.
+## Ref: https://github.com/coreos/prometheus-operator/blob/master/Documentation/api.md#remotereadspec
+remoteRead: {}
+  # remoteRead:
+  #   - url: http://remote1/read
+
+## The remote_write spec configuriation for Prometheus.
+## Ref: https://github.com/coreos/prometheus-operator/blob/master/Documentation/api.md#remotewritespec
+remoteWrite: {}
+  # remoteWrite:
+  #   - url: http://remote1/push
+
+## Resource limits & requests
+## Ref: https://kubernetes.io/docs/user-guide/compute-resources/
+##
+resources: {}
+  # requests:
+  #   memory: 400Mi
+
+## How long to retain metrics
+##
+retention: 24h
+
+## Prefix used to register routes, overriding externalUrl route.
+## Useful for proxies that rewrite URLs.
+##
+routePrefix: ""
+
+## Namespaces to be selected for PrometheusRules discovery.
+## If unspecified, only the same namespace as the Prometheus object is in is used.
+ruleNamespaceSelector: {}
+## Rules CRD selector
+## Ref: https://github.com/coreos/prometheus-operator/blob/master/Documentation/design.md
+##
+## 1. If `matchLabels` is used, `rules.additionalLabels` must contain all the labels from
+##    `matchLabels` in order to be be matched by Prometheus
+## 2. If `matchExpressions` is used `rules.additionalLabels` must contain at least one label
+##    from `matchExpressions` in order to be matched by Prometheus
+## Ref: https://kubernetes.io/docs/concepts/overview/working-with-objects/labels
+rulesSelector: {}
+ # rulesSelector: {
+ #   matchExpressions: [{key: prometheus, operator: In, values: [example-rules, example-rules-2]}]
+ # }
+ ### OR
+ # rulesSelector: {
+ #   matchLabels: {role: example-rules}
+ # }
+
+## List of Secrets in the same namespace as the Prometheus
+## object, which shall be mounted into the Prometheus Pods.
+## Ref: https://github.com/coreos/prometheus-operator/blob/master/Documentation/api.md#prometheusspec
+##
+secrets: []
+
+serviceMonitorNamespaceSelector: {}
+
+## Service monitors selector
+## Ref: https://github.com/coreos/prometheus-operator/blob/master/Documentation/design.md
+##
+serviceMonitorsSelector: {}
+
+logLevel: "info"
+
+## Prometheus StorageSpec for persistent data
+## Ref: https://github.com/coreos/prometheus-operator/blob/master/Documentation/user-guides/storage.md
+##
+storageSpec: {}
+#  storageClassName: gluster
+#  accessModes: ["ReadWriteOnce"]
+#  resources:
+#    requests:
+#      storage: 50Gi
+#  selector: {}
+
+## Easy way to create persistent data
+##
+persistence: {}
+#  enabled: true
+#  storageClass: gluster
+#  accessMode: "ReadWriteOnce"
+#  size: 50Gi
+
+## Prometheus AdditionalScrapeConfigs
+## Ref: https://github.com/coreos/prometheus-operator/blob/master/Documentation/api.md#prometheusspec
+##
+additionalScrapeConfigsEnabled: false
+additionalScrapeConfigs: []
+# - job_name: "prometheus"
+#   static_configs:
+#   - targets:
+#     - "localhost:9090"
+
+## Prometheus AdditionalAlertManagerConfigs
+## Ref: https://github.com/coreos/prometheus-operator/blob/master/Documentation/api.md#prometheusspec
+##
+additionalAlertManagerConfigsEnabled: false
+additionalAlertManagerConfigs: {}
+# static_configs:
+# - targets:
+#   - "localhost:9093"
+
+listenLocal: false
+
+sidecarsSpec: []
+# - name: sidecar
+#   image: registry/name:tag

charts/rancher-monitoring/v0.0.2/questions.yml

+categories:
+- Monitoring
+
+questions:

charts/rancher-monitoring/v0.0.2/requirements.yaml

+dependencies:
+  - name: alertmanager
+    version: 0.0.1
+    condition: alertmanager.enabled
+    repository: "file://./charts/alertmanager/"
+
+  - name: exporter-coredns
+    version: 0.0.1
+    condition: exporter-coredns.enabled
+    repository: "file://./charts/exporter-coredns/"
+
+  - name: exporter-kube-controller-manager
+    version: 0.0.1
+    condition: exporter-kube-controller-manager.enabled
+    repository: "file://./charts/exporter-kube-controller-manager/"
+
+  - name: exporter-kube-dns
+    version: 0.0.1
+    condition: exporter-kube-dns.enabled
+    repository: "file://./charts/exporter-kube-dns/"
+
+  - name: exporter-kube-etcd
+    version: 0.0.1
+    condition: exporter-kube-etcd.enabled
+    repository: "file://./charts/exporter-kube-etcd/"
+
+  - name: exporter-kube-scheduler
+    version: 0.0.1
+    condition: exporter-kube-scheduler.enabled
+    repository: "file://./charts/exporter-kube-scheduler/"
+
+  - name: exporter-kube-state
+    version: 0.0.1
+    condition: exporter-kube-state.enabled
+    repository: "file://./charts/exporter-kube-state/"
+
+  - name: exporter-kubelets
+    version: 0.0.1
+    condition: exporter-kubelets.enabled
+    repository: "file://./charts/exporter-kubelets/"
+
+  - name: exporter-kubernetes
+    version: 0.0.1
+    condition: exporter-kubernetes.enabled
+    repository: "file://./charts/exporter-kubernetes/"
+
+  - name: exporter-node
+    version: 0.0.1
+    condition: exporter-node.enabled
+    repository: "file://./charts/exporter-node/"
+
+  - name: grafana
+    version: 0.0.1
+    condition: grafana.enabled
+    repository: "file://./charts/grafana/"
+
+  - name: prometheus
+    version: 0.0.1
+    condition: prometheus.enabled
+    repository: "file://./charts/prometheus/"
+
+  - name: metric-expression-project
+    version: 0.0.1
+    condition: metric-expression-project.enabled
+    repository: "file://./charts/metric-expression-project/"
+
+  - name: metric-expression-cluster
+    version: 0.0.1
+    condition: metric-expression-cluster.enabled
+    repository: "file://./charts/metric-expression-cluster/"
+
+  - name: exporter-fluentd
+    version: 0.0.1
+    condition: exporter-fluentd.enabled
+    repository: "file://./charts/exporter-fluentd/"
\ No newline at end of file

charts/rancher-monitoring/v0.0.2/templates/_helpers.tpl

+{{/* vim: set filetype=mustache: */}}
+
+{{- define "charts.exporter-kubelets.fullname" -}}
+{{- printf "exporter-kubelets-%s" .Release.Name -}}
+{{- end -}}
+
+
+{{- define "charts.prometheus.serviceaccount.fullname" -}}
+{{- printf "prometheus-%s" .Release.Name -}}
+{{- end -}}
+
+
+{{- define "app.name" -}}
+{{- default .Chart.Name .Values.nameOverride -}}
+{{- end -}}
+
+
+{{- define "app.version" -}}
+{{- $name := include "app.name" . -}}
+{{- $version := .Chart.Version | replace "+" "_" -}}
+{{- printf "%s-%s" $name $version -}}
+{{- end -}}
+
+
+{{- define "app.fullname" -}}
+{{- $name := include "app.name" . -}}
+{{- printf "%s-%s" $name .Release.Name -}}
+{{- end -}}
+
+
+{{- define "app.dnsname" -}}
+{{- include "app.fullname" . | trunc 63 | trimSuffix "-" -}}
+{{- end -}}
+
+
+{{- define "app.psp.fullname" -}}
+{{- $name := include "app.name" . -}}
+{{- printf "%s-%s-psp" $name .Release.Name -}}
+{{- end -}}
+
+
+{{- define "app.nginx.fullname" -}}
+{{- $name := include "app.name" . -}}
+{{- printf "%s-%s-nginx" $name .Release.Name -}}
+{{- end -}}
+
+
+{{- define "app.dashboards.fullname" -}}
+{{- $name := include "app.name" . -}}
+{{- printf "%s-%s-dashboards" $name .Release.Name -}}
+{{- end -}}
+
+
+{{- define "app.hooks.fullname" -}}
+{{- $name := include "app.name" . -}}
+{{- printf "%s-%s-hooks" $name .Release.Name -}}
+{{- end -}}
+
+
+{{- define "app.cleanup.fullname" -}}
+{{- $name := include "app.name" . -}}
+{{- printf "%s-%s-cleanup" $name .Release.Name -}}
+{{- end -}}
+
+
+{{- define "kube_version" -}}
+{{- printf "%s.%s" .Capabilities.KubeVersion.Major .Capabilities.KubeVersion.Minor -}}
+{{- end -}}
+
+
+{{- define "operator_api_version" -}}
+{{- default "monitoring.coreos.com/v1" (.Values.apiGroup | printf "%s/v1") -}}
+{{- end -}}
+
+
+{{- define "operator_api_group" -}}
+{{- $apiVersion := include "operator_api_version" . -}}
+{{- index (regexSplit "/" $apiVersion 2) 0 | printf "%s" -}}
+{{- end -}}
+
+
+{{- define "deployment_api_version" -}}
+{{- if .Capabilities.APIVersions.Has "apps/v1" -}}
+{{- "apps/v1" -}}
+{{- else if .Capabilities.APIVersions.Has "apps/v1beta2" -}}
+{{- "apps/v1beta1" -}}
+{{- else if .Capabilities.APIVersions.Has "apps/v1beta1" -}}
+{{- "apps/v1beta1" -}}
+{{- else -}}
+{{- "extensions/v1beta1" -}}
+{{- end -}}
+{{- end -}}
+
+
+{{- define "statefulset_api_version" -}}
+{{- if .Capabilities.APIVersions.Has "apps/v1" -}}
+{{- "apps/v1" -}}
+{{- else if .Capabilities.APIVersions.Has "apps/v1beta2" -}}
+{{- "apps/v1beta2" -}}
+{{- else -}}
+{{- "apps/v1beta1" -}}
+{{- end -}}
+{{- end -}}
+
+
+{{- define "daemonset_api_version" -}}
+{{- if .Capabilities.APIVersions.Has "apps/v1" -}}
+{{- "apps/v1" -}}
+{{- else if .Capabilities.APIVersions.Has "apps/v1beta2" -}}
+{{- "apps/v1beta2" -}}
+{{- else -}}
+{{- "extensions/v1beta1" -}}
+{{- end -}}
+{{- end -}}
+
+
+{{- define "rbac_api_version" -}}
+{{- if .Capabilities.APIVersions.Has "rbac.authorization.k8s.io/v1" -}}
+{{- "rbac.authorization.k8s.io/v1" -}}
+{{- else if .Capabilities.APIVersions.Has "rbac.authorization.k8s.io/v1beta1" -}}
+{{- "rbac.authorization.k8s.io/v1beta1" -}}
+{{- else -}}
+{{- "rbac.authorization.k8s.io/v1alpha1" -}}
+{{- end -}}
+{{- end -}}

charts/rancher-monitoring/v0.0.2/templates/deployment.yaml

+{{- if .Values.enabled }}
+apiVersion: {{ template "deployment_api_version" . }}
+kind: Deployment
+metadata:
+  labels:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+  name: {{ template "app.fullname" . }}
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: {{ template "app.name" . }}
+      chart: {{ template "app.version" . }}
+      release: {{ .Release.Name }}
+  template:
+    metadata:
+      labels:
+        app: {{ template "app.name" . }}
+        chart: {{ template "app.version" . }}
+        release: {{ .Release.Name }}
+    spec:
+      containers:
+        - name: prometheus-operator
+          image: "{{ .Values.image.repository }}:{{ .Values.image.tag }}"
+          args:
+            - --kubelet-service={{ .Release.Namespace }}/expose-kubelets-metrics
+            - --log-format={{ .Values.logFormat }}
+            - --log-level={{ .Values.logLevel }}
+            - --prometheus-config-reloader={{ .Values.image.prometheusConfigReloader.repository }}:{{ .Values.image.prometheusConfigReloader.tag }}
+            - --config-reloader-image={{ .Values.image.configmapReload.repository }}:{{ .Values.image.configmapReload.tag }}
+            - --labels=monitoring.cattle.io=true
+            - --crd-apigroup={{ template "operator_api_group" . }}
+            - --manage-crds={{ .Values.manageCRDs }}
+            - --with-validation={{ .Values.withValidation }}
+            - --disable-auto-user-group={{ .Values.disableAutoUserGroup }}
+          ports:
+            - containerPort: 8080
+              name: http
+          resources:
+{{ toYaml .Values.resources | indent 12 }}
+    {{- if .Values.nodeSelector }}
+      nodeSelector:
+{{ toYaml .Values.nodeSelector | indent 8 }}
+    {{- end }}
+    {{- if .Values.enabledRBAC }}
+      serviceAccountName: {{ .Values.serviceAccountName }}
+    {{- end }}
+    {{- if .Values.tolerations }}
+      tolerations:
+{{ toYaml .Values.tolerations | indent 8 }}
+    {{- end }}
+{{- end }}

charts/rancher-monitoring/v0.0.2/templates/metrics-service.yaml

+{{- if .Values.enabled }}
+apiVersion: v1
+kind: Service
+metadata:
+  name: expose-operator-metrics
+  labels:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+    monitoring.cattle.io: "true"
+spec:
+  type: ClusterIP
+  selector:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    release: {{ .Release.Name }}
+  ports:
+    - name: http
+      port: 8080
+      targetPort: http
+{{- end }}
\ No newline at end of file

charts/rancher-monitoring/v0.0.2/templates/servicemonitor.yaml

+{{- if .Values.enabled }}
+apiVersion: {{ template "operator_api_version" . }}
+kind: ServiceMonitor
+metadata:
+  labels:
+    app: {{ template "app.name" . }}
+    chart: {{ template "app.version" . }}
+    heritage: {{ .Release.Service }}
+    release: {{ .Release.Name }}
+    source: rancher-monitoring
+    {{- if .Values.serviceMonitor.labels }}
+{{ toYaml .Values.serviceMonitor.labels | indent 4 }}
+    {{- end }}
+  name: {{ template "app.fullname" . }}
+spec:
+  jobLabel: prometheus-operator
+  selector:
+    matchLabels:
+      app: {{ template "app.name" . }}
+      chart: {{ template "app.version" . }}
+      release: {{ .Release.Name }}
+      monitoring.cattle.io: "true"
+  namespaceSelector:
+    matchNames:
+      - {{ .Release.Namespace | quote }}
+  endpoints:
+  - port: http
+    interval: 30s
+    honorLabels: true
+{{- end }}

charts/rancher-monitoring/v0.0.2/values.yaml

+enabled: false
+
+nameOverride: "prometheus-operator"
+
+enabledRBAC: true
+
+## CRD apiGroup
+##
+apiGroup: "monitoring.coreos.com"
+
+## Prometheus-operator image
+##
+image:
+  # Reference to one or more secrets to be used when pulling images
+  pullSecrets: []
+  repository: quay.io/coreos/prometheus-operator
+  tag: v0.23.2
+  ## Prometheus-config-reloader image to use for config and rule reloading
+  ##
+  prometheusConfigReloader:
+    repository: quay.io/coreos/prometheus-config-reloader
+    tag: v0.23.2
+  ## Configmap-reload image to use for reloading configmaps
+  ##
+  configmapReload:
+    repository: quay.io/coreos/configmap-reload
+    tag: v0.0.1
+
+## Node labels for prometheus-operator pod assignment
+##
+nodeSelector:
+  beta.kubernetes.io/os: linux
+
+## Tolerations for use with node taints
+## Ref: https://kubernetes.io/docs/concepts/configuration/taint-and-toleration/
+##
+tolerations: {}
+
+logFormat: "logfmt"
+
+logLevel: "info"
+
+manageCRDs: false
+
+withValidation: true
+
+disableAutoUserGroup: false
+
+serviceMonitor:
+  ## Custom Labels to be added to ServiceMonitor
+  ##
+  labels: {}
+
+## Prometheus-operator resource limits & requests
+## Ref: https://kubernetes.io/docs/user-guide/compute-resources/
+##
+resources: {}
+  # limits:
+  #   cpu: 200m
+  #   memory: 100Mi
+  # requests:
+  #   cpu: 100m
+  #   memory: 50Mi
+
+## Already exist ServiceAccount
+##
+serviceAccountName: ""
+
+alertmanager:
+  enabled: false
+  apiGroup: "monitoring.coreos.com"
+  image:
+    repository: prom/alertmanager
+    tag: v0.15.2
+  nodeSelector:
+    beta.kubernetes.io/os: linux
+  config:
+    global:
+      resolve_timeout: 5m
+    route:
+      group_by: ['job']
+      group_wait: 30s
+      group_interval: 5m
+      repeat_interval: 12h
+      receiver: 'null'
+      routes:
+      - match:
+          alertname: DeadMansSwitch
+        receiver: 'null'
+    receivers:
+    - name: 'null'
+  persistence:
+    enabled: false
+    storageClass: ""
+    accessMode: "ReadWriteOnce"
+    size: 50Gi
+  ## Already exist ServiceAccount
+  ##
+  serviceAccountName: ""
+
+exporter-coredns:
+  enabled: false
+  apiGroup: "monitoring.coreos.com"
+  endpoints: []
+  ports:
+    metrics:
+      port: 9153
+
+exporter-kube-controller-manager:
+  enabled: false
+  apiGroup: "monitoring.coreos.com"
+  endpoints: []
+  ports:
+    metrics:
+      port: 10252
+
+exporter-kube-dns:
+  enabled: false
+  apiGroup: "monitoring.coreos.com"
+  endpoints: []
+  ports:
+    metrics:
+      dnsmasq:
+        port: 10054
+      skydns:
+        port: 10055
+
+exporter-kube-etcd:
+  enabled: false
+  apiGroup: "monitoring.coreos.com"
+  endpoints: []
+  ports:
+    metrics:
+      scheme: "https"
+      port: 4001
+  caFile: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
+  certFile: ""
+  keyFile: ""
+
+exporter-kube-scheduler:
+  enabled: false
+  apiGroup: "monitoring.coreos.com"
+  endpoints: []
+  ports:
+    metrics:
+      port: 10251
+
+exporter-kube-state:
+  enabled: false
+  apiGroup: "monitoring.coreos.com"
+  ports:
+    metrics:
+      port: 8080
+  image:
+    repository: quay.io/coreos/kube-state-metrics
+    tag: v1.4.0
+  nodeSelector:
+    beta.kubernetes.io/os: linux
+  ## Already exist ServiceAccount
+  ##
+  serviceAccountName: ""
+
+exporter-kubelets:
+  enabled: false
+  apiGroup: "monitoring.coreos.com"
+
+exporter-kubernetes:
+  enabled: false
+  apiGroup: "monitoring.coreos.com"
+
+exporter-node:
+  enabled: false
+  apiGroup: "monitoring.coreos.com"
+  image:
+    repository: prom/node-exporter
+    tag: v0.16.0
+  nodeSelector:
+    beta.kubernetes.io/os: linux
+  ports:
+    metrics:
+      port: 9100
+  ## Already exist ServiceAccount
+  ##
+  serviceAccountName: ""
+
+grafana:
+  enabled: false
+  level: cluster
+  apiGroup: "monitoring.coreos.com"
+  image:
+    repository: grafana/grafana
+    tag: 5.3.0
+    inits:
+      tools:
+        repository: rancher/prometheus-auth
+        tag: v0.1.0
+  nodeSelector:
+    beta.kubernetes.io/os: linux
+  resources:
+    inits:
+      limits:
+        memory: 50Mi
+        cpu: 50m
+      requests:
+        memory: 50Mi
+        cpu: 50m
+    core:
+      limits:
+        memory: 200Mi
+        cpu: 200m
+      requests:
+        memory: 100Mi
+        cpu: 100m
+    proxy:
+      limits:
+        memory: 100Mi
+        cpu: 100m
+      requests:
+        memory: 50Mi
+        cpu: 50m
+    watcher:
+      limits:
+        memory: 50Mi
+        cpu: 50m
+      requests:
+        memory: 50Mi
+        cpu: 50m
+  persistence:
+    enabled: false
+    storageClass: ""
+    accessMode: "ReadWriteOnce"
+    size: 50Gi
+  adminUser: "admin"
+  adminPassword: "admin"
+  ## Already exist ServiceAccount
+  ##
+  serviceAccountName: ""
+  prometheusDatasourceURL: "http://prometheus-operated:9090"
+
+prometheus:
+  enabled: false
+  apiGroup: "monitoring.coreos.com"
+  image:
+    ## Reference to one or more secrets to be used when pulling images
+    ##
+    pullSecrets: []
+    repository: prom/prometheus
+    tag: v2.5.0
+    inits:
+      tools:
+        repository: rancher/prometheus-auth
+        tag: v0.1.0
+  nodeSelector:
+    beta.kubernetes.io/os: linux
+  persistence:
+    enabled: false
+    storageClass: ""
+    accessMode: "ReadWriteOnce"
+    size: 50Gi
+  alertingEndpoints: []
+  secrets: []
+  ## Already exist ServiceAccount
+  ##
+  serviceAccountName: ""
+  sidecarsSpec:
+  - command:
+    - prometheus-auth
+    args:
+    - agent
+    - start
+    - --agent.proxy-url
+    - http://localhost:9090
+    - --listen.address
+    - $(POD_IP):9090
+    env:
+    - name: POD_IP
+      valueFrom:
+        fieldRef:
+          fieldPath: status.podIP
+    image: rancher/prometheus-auth:v0.1.0
+    livenessProbe:
+      failureThreshold: 6
+      httpGet:
+        path: /-/healthy
+        port: web
+        scheme: HTTP
+      periodSeconds: 5
+      successThreshold: 1
+      timeoutSeconds: 3
+    name: prometheus-agent
+    ports:
+    - containerPort: 9090
+      name: web
+      protocol: TCP
+    readinessProbe:
+      failureThreshold: 120
+      httpGet:
+        path: /-/ready
+        port: web
+        scheme: HTTP
+      periodSeconds: 5
+      successThreshold: 1
+      timeoutSeconds: 3
+  listenLocal: true
+  serviceMonitorsSelector:
+    matchExpressions:
+  additionalScrapeConfigsEnabled: true
+  additionalScrapeConfigs:
+  - job_name: 'ingress-nginx-endpoints'
+    kubernetes_sd_configs:
+    - role: pod
+      namespaces:
+        names:
+        - ingress-nginx
+        - kube-system
+    relabel_configs:
+    - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_scrape]
+      action: keep
+      regex: true
+    - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_scheme]
+      action: replace
+      target_label: __scheme__
+      regex: (https?)
+    - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_path]
+      action: replace
+      target_label: __metrics_path__
+      regex: (.+)
+    - source_labels: [__address__, __meta_kubernetes_pod_annotation_prometheus_io_port]
+      action: replace
+      target_label: __address__
+      regex: ([^:]+)(?::\d+)?;(\d+)
+      replacement: $1:$2
+    - source_labels: [__meta_kubernetes_service_name]
+      regex: prometheus-operated
+      action: drop
+
+metric-expression-project:
+  enabled: false
+
+metric-expression-cluster:
+  enabled: false
+
+exporter-fluentd:
+  enabled: false
+  apiGroup: "monitoring.coreos.com"