Add Rancher-Monitoring Chart

        (+) Only use for Rancher 2.0 Monitoring and Alerting
        (+) Support Grafana to proxy with authorization bearer token to
        Prometheus-Auth agent
        (+) Support Prometheus web to proxy with authorization bearer token
        to Prometheus-Auth agent
        (+) Rich metrics for Kubernetes and Rancher
Co-authored-by: aiwantaozi <michelia.feng@gmail.com>
Co-authored-by: orangedeng <jxfa0043379@hotmail.com>

charts/rancher-monitoring/v0.0.1/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/v0.0.1/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: {}
+  # limits:
+  #   memory: 200Mi
+  #   cpu: 200m
+  # requests:
+  #   memory: 100Mi
+  #   cpu: 100m
+
+
+## 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/v0.0.1/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/v0.0.1/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/v0.0.1/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/v0.0.1/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/v0.0.1/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/v0.0.1/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/v0.0.1/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/v0.0.1/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/v0.0.1/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/v0.0.1/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/v0.0.1/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