mirror of
https://github.com/philippemerle/KubeDiagrams.git
synced 2026-05-18 09:46:33 +00:00
7146 lines
646 KiB
YAML
7146 lines
646 KiB
YAML
# The metadata label "app" should be replaced by "kubernetes.io/name"
|
|
# as this latter is officially recommanded by the Kubernetes communauty.
|
|
# There are 115 occurrences of label "app".
|
|
# See following '#TBR:' and '#ADDED' comments.
|
|
# The metadata label "chart" should be replaced by "helm.sh/chart"
|
|
# as this latter is officially recommanded by the Helm communauty.
|
|
# There are 105 occurrences of label "chart".
|
|
# See following '#UPDATED' comments.
|
|
# The metadata label 'release' is useless as Helm recommends to use "kubernetes.io/instance".
|
|
# There are 132 occurrences of label "release".
|
|
# See following '#TBR:' and '#ADDED' comments.
|
|
---
|
|
# Source: kube-prometheus-stack/charts/grafana/templates/serviceaccount.yaml
|
|
apiVersion: v1
|
|
kind: ServiceAccount
|
|
automountServiceAccountToken: true
|
|
metadata:
|
|
labels:
|
|
helm.sh/chart: grafana-8.8.2
|
|
app.kubernetes.io/name: grafana
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "11.4.0"
|
|
name: kube-prometheus-stack-grafana
|
|
namespace: default
|
|
---
|
|
# Source: kube-prometheus-stack/charts/kube-state-metrics/templates/serviceaccount.yaml
|
|
apiVersion: v1
|
|
kind: ServiceAccount
|
|
automountServiceAccountToken: true
|
|
metadata:
|
|
labels:
|
|
helm.sh/chart: kube-state-metrics-5.28.0
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/component: metrics
|
|
app.kubernetes.io/part-of: kube-state-metrics
|
|
app.kubernetes.io/name: kube-state-metrics
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "2.14.0"
|
|
#TBR: release: kube-prometheus-stack
|
|
name: kube-prometheus-stack-kube-state-metrics
|
|
namespace: default
|
|
---
|
|
# Source: kube-prometheus-stack/charts/prometheus-node-exporter/templates/serviceaccount.yaml
|
|
apiVersion: v1
|
|
kind: ServiceAccount
|
|
metadata:
|
|
name: kube-prometheus-stack-prometheus-node-exporter
|
|
namespace: default
|
|
labels:
|
|
helm.sh/chart: prometheus-node-exporter-4.43.1
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/component: metrics
|
|
app.kubernetes.io/part-of: prometheus-node-exporter
|
|
app.kubernetes.io/name: prometheus-node-exporter
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "1.8.2"
|
|
#TBR: release: kube-prometheus-stack
|
|
automountServiceAccountToken: false
|
|
---
|
|
# Source: kube-prometheus-stack/templates/alertmanager/serviceaccount.yaml
|
|
apiVersion: v1
|
|
kind: ServiceAccount
|
|
metadata:
|
|
name: kube-prometheus-stack-alertmanager
|
|
namespace: default
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack-alertmanager
|
|
app.kubernetes.io/name: kube-prometheus-stack-alertmanager
|
|
app.kubernetes.io/component: alertmanager
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
automountServiceAccountToken: true
|
|
---
|
|
# Source: kube-prometheus-stack/templates/prometheus-operator/serviceaccount.yaml
|
|
apiVersion: v1
|
|
kind: ServiceAccount
|
|
metadata:
|
|
name: kube-prometheus-stack-operator
|
|
namespace: default
|
|
labels:
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
#TBR: app: kube-prometheus-stack-operator
|
|
app.kubernetes.io/name: kube-prometheus-stack-prometheus-operator
|
|
app.kubernetes.io/component: prometheus-operator
|
|
automountServiceAccountToken: true
|
|
---
|
|
# Source: kube-prometheus-stack/templates/prometheus/serviceaccount.yaml
|
|
apiVersion: v1
|
|
kind: ServiceAccount
|
|
metadata:
|
|
name: kube-prometheus-stack-prometheus
|
|
namespace: default
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack-prometheus
|
|
app.kubernetes.io/name: kube-prometheus-stack-prometheus #ADDED
|
|
app.kubernetes.io/component: prometheus
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
automountServiceAccountToken: true
|
|
---
|
|
# Source: kube-prometheus-stack/charts/grafana/templates/secret.yaml
|
|
apiVersion: v1
|
|
kind: Secret
|
|
metadata:
|
|
name: kube-prometheus-stack-grafana
|
|
namespace: default
|
|
labels:
|
|
helm.sh/chart: grafana-8.8.2
|
|
app.kubernetes.io/name: grafana
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "11.4.0"
|
|
type: Opaque
|
|
data:
|
|
|
|
admin-user: "YWRtaW4="
|
|
admin-password: "cHJvbS1vcGVyYXRvcg=="
|
|
ldap-toml: ""
|
|
---
|
|
# Source: kube-prometheus-stack/templates/alertmanager/secret.yaml
|
|
apiVersion: v1
|
|
kind: Secret
|
|
metadata:
|
|
name: alertmanager-kube-prometheus-stack-alertmanager
|
|
namespace: default
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack-alertmanager
|
|
app.kubernetes.io/name: kube-prometheus-stack-alertmanager #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
data:
|
|
alertmanager.yaml: "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"
|
|
---
|
|
# Source: kube-prometheus-stack/charts/grafana/templates/configmap-dashboard-provider.yaml
|
|
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
labels:
|
|
helm.sh/chart: grafana-8.8.2
|
|
app.kubernetes.io/name: grafana
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "11.4.0"
|
|
name: kube-prometheus-stack-grafana-config-dashboards
|
|
namespace: default
|
|
data:
|
|
provider.yaml: |-
|
|
apiVersion: 1
|
|
providers:
|
|
- name: 'sidecarProvider'
|
|
orgId: 1
|
|
folder: ''
|
|
folderUid: ''
|
|
type: file
|
|
disableDeletion: false
|
|
allowUiUpdates: false
|
|
updateIntervalSeconds: 30
|
|
options:
|
|
foldersFromFilesStructure: false
|
|
path: /tmp/dashboards
|
|
---
|
|
# Source: kube-prometheus-stack/charts/grafana/templates/configmap.yaml
|
|
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
name: kube-prometheus-stack-grafana
|
|
namespace: default
|
|
labels:
|
|
helm.sh/chart: grafana-8.8.2
|
|
app.kubernetes.io/name: grafana
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "11.4.0"
|
|
data:
|
|
|
|
grafana.ini: |
|
|
[analytics]
|
|
check_for_updates = true
|
|
[grafana_net]
|
|
url = https://grafana.net
|
|
[log]
|
|
mode = console
|
|
[paths]
|
|
data = /var/lib/grafana/
|
|
logs = /var/log/grafana
|
|
plugins = /var/lib/grafana/plugins
|
|
provisioning = /etc/grafana/provisioning
|
|
[server]
|
|
domain = ''
|
|
---
|
|
# Source: kube-prometheus-stack/templates/grafana/configmaps-datasources.yaml
|
|
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
name: kube-prometheus-stack-grafana-datasource
|
|
namespace: default
|
|
labels:
|
|
grafana_datasource: "1"
|
|
#TBR: app: kube-prometheus-stack-grafana
|
|
app.kubernetes.io/name: kube-prometheus-stack-grafana #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
data:
|
|
datasource.yaml: |-
|
|
apiVersion: 1
|
|
datasources:
|
|
- name: "Prometheus"
|
|
type: prometheus
|
|
uid: prometheus
|
|
url: http://kube-prometheus-stack-prometheus.default:9090/
|
|
access: proxy
|
|
isDefault: true
|
|
jsonData:
|
|
httpMethod: POST
|
|
timeInterval: 30s
|
|
- name: "Alertmanager"
|
|
type: alertmanager
|
|
uid: alertmanager
|
|
url: http://kube-prometheus-stack-alertmanager.default:9093/
|
|
access: proxy
|
|
jsonData:
|
|
handleGrafanaManagedAlerts: false
|
|
implementation: prometheus
|
|
---
|
|
# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/alertmanager-overview.yaml
|
|
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
namespace: default
|
|
name: kube-prometheus-stack-alertmanager-overview
|
|
annotations:
|
|
{}
|
|
labels:
|
|
grafana_dashboard: "1"
|
|
#TBR: app: kube-prometheus-stack-grafana
|
|
app.kubernetes.io/name: kube-prometheus-stack-grafana #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
data:
|
|
alertmanager-overview.json: |-
|
|
{"graphTooltip":1,"panels":[{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":0},"id":1,"panels":[],"title":"Alerts","type":"row"},{"datasource":{"type":"prometheus","uid":"$datasource"},"description":"current set of alerts stored in the Alertmanager","fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","stacking":{"mode":"normal"}},"unit":"none"}},"gridPos":{"h":7,"w":12,"x":0,"y":1},"id":2,"options":{"legend":{"showLegend":false},"tooltip":{"mode":"multi"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"sum(alertmanager_alerts{namespace=~\"$namespace\",service=~\"$service\"}) by (namespace,service,instance)","intervalFactor":2,"legendFormat":"{{instance}}"}],"title":"Alerts","type":"timeseries"},{"datasource":{"type":"prometheus","uid":"$datasource"},"description":"rate of successful and invalid alerts received by the Alertmanager","fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","stacking":{"mode":"normal"}},"unit":"ops"}},"gridPos":{"h":7,"w":12,"x":12,"y":1},"id":3,"options":{"legend":{"showLegend":false},"tooltip":{"mode":"multi"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"sum(rate(alertmanager_alerts_received_total{namespace=~\"$namespace\",service=~\"$service\"}[$__rate_interval])) by (namespace,service,instance)","intervalFactor":2,"legendFormat":"{{instance}} Received"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"sum(rate(alertmanager_alerts_invalid_total{namespace=~\"$namespace\",service=~\"$service\"}[$__rate_interval])) by (namespace,service,instance)","intervalFactor":2,"legendFormat":"{{instance}} Invalid"}],"title":"Alerts receive rate","type":"timeseries"},{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":8},"id":4,"panels":[],"title":"Notifications","type":"row"},{"datasource":{"type":"prometheus","uid":"$datasource"},"description":"rate of successful and invalid notifications sent by the Alertmanager","fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","stacking":{"mode":"normal"}},"unit":"ops"}},"gridPos":{"h":7,"w":12,"x":0,"y":9},"id":5,"options":{"legend":{"showLegend":false},"tooltip":{"mode":"multi"}},"pluginVersion":"v11.4.0","repeat":"integration","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"sum(rate(alertmanager_notifications_total{namespace=~\"$namespace\",service=~\"$service\", integration=\"$integration\"}[$__rate_interval])) by (integration,namespace,service,instance)","intervalFactor":2,"legendFormat":"{{instance}} Total"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"sum(rate(alertmanager_notifications_failed_total{namespace=~\"$namespace\",service=~\"$service\", integration=\"$integration\"}[$__rate_interval])) by (integration,namespace,service,instance)","intervalFactor":2,"legendFormat":"{{instance}} Failed"}],"title":"$integration: Notifications Send Rate","type":"timeseries"},{"datasource":{"type":"prometheus","uid":"$datasource"},"description":"latency of notifications sent by the Alertmanager","fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","stacking":{"mode":"normal"}},"unit":"s"}},"gridPos":{"h":7,"w":12,"x":12,"y":9},"id":6,"options":{"legend":{"showLegend":false},"tooltip":{"mode":"multi"}},"pluginVersion":"v11.4.0","repeat":"integration","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"histogram_quantile(0.99,\n sum(rate(alertmanager_notification_latency_seconds_bucket{namespace=~\"$namespace\",service=~\"$service\", integration=\"$integration\"}[$__rate_interval])) by (le,namespace,service,instance)\n)\n","intervalFactor":2,"legendFormat":"{{instance}} 99th Percentile"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"histogram_quantile(0.50,\n sum(rate(alertmanager_notification_latency_seconds_bucket{namespace=~\"$namespace\",service=~\"$service\", integration=\"$integration\"}[$__rate_interval])) by (le,namespace,service,instance)\n)\n","intervalFactor":2,"legendFormat":"{{instance}} Median"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"sum(rate(alertmanager_notification_latency_seconds_sum{namespace=~\"$namespace\",service=~\"$service\", integration=\"$integration\"}[$__rate_interval])) by (namespace,service,instance)\n/\nsum(rate(alertmanager_notification_latency_seconds_count{namespace=~\"$namespace\",service=~\"$service\", integration=\"$integration\"}[$__rate_interval])) by (namespace,service,instance)\n","intervalFactor":2,"legendFormat":"{{instance}} Average"}],"title":"$integration: Notification Duration","type":"timeseries"}],"schemaVersion":39,"tags":["alertmanager-mixin"],"templating":{"list":[{"current":{"selected":false,"text":"Prometheus","value":"Prometheus"},"hide":0,"label":"Data Source","name":"datasource","query":"prometheus","type":"datasource"},{"current":{"selected":false,"text":"","value":""},"datasource":{"type":"prometheus","uid":"${datasource}"},"includeAll":false,"label":"namespace","name":"namespace","query":"label_values(alertmanager_alerts, namespace)","refresh":2,"sort":1,"type":"query"},{"current":{"selected":false,"text":"","value":""},"datasource":{"type":"prometheus","uid":"${datasource}"},"includeAll":false,"label":"service","name":"service","query":"label_values(alertmanager_alerts, service)","refresh":2,"sort":1,"type":"query"},{"current":{"selected":false,"text":"$__all","value":"$__all"},"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":2,"includeAll":true,"name":"integration","query":"label_values(alertmanager_notifications_total{integration=~\".*\"}, integration)","refresh":2,"sort":1,"type":"query"}]},"time":{"from":"now-1h","to":"now"},"timepicker":{"refresh_intervals":["30s"]},"timezone": "utc","title":"Alertmanager / Overview","uid":"alertmanager-overview"}
|
|
---
|
|
# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/apiserver.yaml
|
|
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
namespace: default
|
|
name: kube-prometheus-stack-apiserver
|
|
annotations:
|
|
{}
|
|
labels:
|
|
grafana_dashboard: "1"
|
|
#TBR: app: kube-prometheus-stack-grafana
|
|
app.kubernetes.io/name: kube-prometheus-stack-grafana #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
data:
|
|
apiserver.json: |-
|
|
{"editable":true,"links":[{"asDropdown":true,"includeVars":true,"keepTime":true,"tags":["kubernetes-mixin"],"targetBlank":false,"title":"Kubernetes","type":"dashboards"}],"panels":[{"datasource":{"type":"datasource","uid":"-- Mixed --"},"description":"The SLO (service level objective) and other metrics displayed on this dashboard are for informational purposes only.","gridPos":{"h":2,"w":24,"x":0,"y":0},"id":1,"options":{"content":"The SLO (service level objective) and other metrics displayed on this dashboard are for informational purposes only."},"pluginVersion":"v11.4.0","title":"Notice","type":"text"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"description":"How many percent of requests (both read and write) in 30 days have been answered successfully and fast enough?","fieldConfig":{"defaults":{"decimals":3,"unit":"percentunit"}},"gridPos":{"h":7,"w":8,"x":0,"y":2},"id":2,"interval":"1m","pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"apiserver_request:availability30d{verb=\"all\", cluster=\"$cluster\"}"}],"title":"Availability (30d) > 99.000%","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"description":"How much error budget is left looking at our 0.990% availability guarantees?","fieldConfig":{"defaults":{"custom":{"fillOpacity":100},"decimals":3,"unit":"percentunit"}},"gridPos":{"h":7,"w":16,"x":8,"y":2},"id":3,"interval":"1m","options":{"legend":{"asTable":true,"placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"100 * (apiserver_request:availability30d{verb=\"all\", cluster=\"$cluster\"} - 0.990000)","legendFormat":"errorbudget"}],"title":"ErrorBudget (30d) > 99.000%","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"description":"How many percent of read requests (LIST,GET) in 30 days have been answered successfully and fast enough?","fieldConfig":{"defaults":{"decimals":3,"unit":"percentunit"}},"gridPos":{"h":7,"w":6,"x":0,"y":9},"id":4,"interval":"1m","pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"apiserver_request:availability30d{verb=\"read\", cluster=\"$cluster\"}"}],"title":"Read Availability (30d)","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"description":"How many read requests (LIST,GET) per second do the apiservers get by code?","fieldConfig":{"defaults":{"custom":{"fillOpacity":100,"stacking":{"mode":"normal"}},"unit":"reqps"},"overrides":[{"matcher":{"id":"byRegexp","options":"/2../i"},"properties":[{"id":"color","value":"#56A64B"}]},{"matcher":{"id":"byRegexp","options":"/3../i"},"properties":[{"id":"color","value":"#F2CC0C"}]},{"matcher":{"id":"byRegexp","options":"/4../i"},"properties":[{"id":"color","value":"#3274D9"}]},{"matcher":{"id":"byRegexp","options":"/5../i"},"properties":[{"id":"color","value":"#E02F44"}]}]},"gridPos":{"h":7,"w":6,"x":6,"y":9},"id":5,"interval":"1m","options":{"legend":{"asTable":true,"placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (code) (code_resource:apiserver_request_total:rate5m{verb=\"read\", cluster=\"$cluster\"})","legendFormat":"{{ code }}"}],"title":"Read SLI - Requests","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"description":"How many percent of read requests (LIST,GET) per second are returned with errors (5xx)?","fieldConfig":{"defaults":{"min":0,"unit":"percentunit"}},"gridPos":{"h":7,"w":6,"x":12,"y":9},"id":6,"interval":"1m","options":{"legend":{"asTable":true,"placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (resource) (code_resource:apiserver_request_total:rate5m{verb=\"read\",code=~\"5..\", cluster=\"$cluster\"}) / sum by (resource) (code_resource:apiserver_request_total:rate5m{verb=\"read\", cluster=\"$cluster\"})","legendFormat":"{{ resource }}"}],"title":"Read SLI - Errors","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"description":"How many seconds is the 99th percentile for reading (LIST|GET) a given resource?","fieldConfig":{"defaults":{"unit":"s"}},"gridPos":{"h":7,"w":6,"x":18,"y":9},"id":7,"interval":"1m","options":{"legend":{"asTable":true,"placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"cluster_quantile:apiserver_request_sli_duration_seconds:histogram_quantile{verb=\"read\", cluster=\"$cluster\"}","legendFormat":"{{ resource }}"}],"title":"Read SLI - Duration","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"description":"How many percent of write requests (POST|PUT|PATCH|DELETE) in 30 days have been answered successfully and fast enough?","fieldConfig":{"defaults":{"decimals":3,"unit":"percentunit"}},"gridPos":{"h":7,"w":6,"x":0,"y":16},"id":8,"interval":"1m","pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"apiserver_request:availability30d{verb=\"write\", cluster=\"$cluster\"}"}],"title":"Write Availability (30d)","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"description":"How many write requests (POST|PUT|PATCH|DELETE) per second do the apiservers get by code?","fieldConfig":{"defaults":{"custom":{"fillOpacity":100,"stacking":{"mode":"normal"}},"unit":"reqps"},"overrides":[{"matcher":{"id":"byRegexp","options":"/2../i"},"properties":[{"id":"color","value":"#56A64B"}]},{"matcher":{"id":"byRegexp","options":"/3../i"},"properties":[{"id":"color","value":"#F2CC0C"}]},{"matcher":{"id":"byRegexp","options":"/4../i"},"properties":[{"id":"color","value":"#3274D9"}]},{"matcher":{"id":"byRegexp","options":"/5../i"},"properties":[{"id":"color","value":"#E02F44"}]}]},"gridPos":{"h":7,"w":6,"x":6,"y":16},"id":9,"interval":"1m","options":{"legend":{"asTable":true,"placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (code) (code_resource:apiserver_request_total:rate5m{verb=\"write\", cluster=\"$cluster\"})","legendFormat":"{{ code }}"}],"title":"Write SLI - Requests","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"description":"How many percent of write requests (POST|PUT|PATCH|DELETE) per second are returned with errors (5xx)?","fieldConfig":{"defaults":{"min":0,"unit":"percentunit"}},"gridPos":{"h":7,"w":6,"x":12,"y":16},"id":10,"interval":"1m","options":{"legend":{"asTable":true,"placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (resource) (code_resource:apiserver_request_total:rate5m{verb=\"write\",code=~\"5..\", cluster=\"$cluster\"}) / sum by (resource) (code_resource:apiserver_request_total:rate5m{verb=\"write\", cluster=\"$cluster\"})","legendFormat":"{{ resource }}"}],"title":"Write SLI - Errors","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"description":"How many seconds is the 99th percentile for writing (POST|PUT|PATCH|DELETE) a given resource?","fieldConfig":{"defaults":{"unit":"s"}},"gridPos":{"h":7,"w":6,"x":18,"y":16},"id":11,"interval":"1m","options":{"legend":{"asTable":true,"placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"cluster_quantile:apiserver_request_sli_duration_seconds:histogram_quantile{verb=\"write\", cluster=\"$cluster\"}","legendFormat":"{{ resource }}"}],"title":"Write SLI - Duration","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"min":0,"unit":"ops"}},"gridPos":{"h":7,"w":12,"x":0,"y":23},"id":12,"interval":"1m","options":{"legend":{"asTable":true,"placement":"right","showLegend":false},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(workqueue_adds_total{job=\"apiserver\", instance=~\"$instance\", cluster=\"$cluster\"}[$__rate_interval])) by (instance, name)","legendFormat":"{{instance}} {{name}}"}],"title":"Work Queue Add Rate","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"min":0,"unit":"short"}},"gridPos":{"h":7,"w":12,"x":12,"y":23},"id":13,"interval":"1m","options":{"legend":{"asTable":true,"placement":"right","showLegend":false},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(workqueue_depth{job=\"apiserver\", instance=~\"$instance\", cluster=\"$cluster\"}[$__rate_interval])) by (instance, name)","legendFormat":"{{instance}} {{name}}"}],"title":"Work Queue Depth","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"min":0,"unit":"s"}},"gridPos":{"h":7,"w":24,"x":0,"y":30},"id":14,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"histogram_quantile(0.99, sum(rate(workqueue_queue_duration_seconds_bucket{job=\"apiserver\", instance=~\"$instance\", cluster=\"$cluster\"}[$__rate_interval])) by (instance, name, le))","legendFormat":"{{instance}} {{name}}"}],"title":"Work Queue Latency","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"bytes"}},"gridPos":{"h":7,"w":8,"x":0,"y":37},"id":15,"interval":"1m","options":{"legend":{"asTable":true,"placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"process_resident_memory_bytes{job=\"apiserver\",instance=~\"$instance\", cluster=\"$cluster\"}","legendFormat":"{{instance}}"}],"title":"Memory","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"min":0,"unit":"short"}},"gridPos":{"h":7,"w":8,"x":8,"y":37},"id":16,"interval":"1m","options":{"legend":{"asTable":true,"placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"rate(process_cpu_seconds_total{job=\"apiserver\",instance=~\"$instance\", cluster=\"$cluster\"}[$__rate_interval])","legendFormat":"{{instance}}"}],"title":"CPU usage","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"short"}},"gridPos":{"h":7,"w":8,"x":16,"y":37},"id":17,"interval":"1m","options":{"legend":{"asTable":true,"placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"go_goroutines{job=\"apiserver\",instance=~\"$instance\", cluster=\"$cluster\"}","legendFormat":"{{instance}}"}],"title":"Goroutines","type":"timeseries"}],"refresh":"10s","schemaVersion":39,"tags":["kubernetes-mixin"],"templating":{"list":[{"current":{"selected":true,"text":"default","value":"default"},"hide":0,"label":"Data source","name":"datasource","query":"prometheus","regex":"","type":"datasource"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":2,"label":"cluster","name":"cluster","query":"label_values(up{job=\"apiserver\"}, cluster)","refresh":2,"sort":1,"type":"query","allValue":".*"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":0,"includeAll":true,"name":"instance","query":"label_values(up{job=\"apiserver\", cluster=\"$cluster\"}, instance)","refresh":2,"sort":1,"type":"query"}]},"time":{"from":"now-1h","to":"now"},"timezone": "utc","title":"Kubernetes / API server","uid":"09ec8aa1e996d6ffcd6817bbaff4db1b"}
|
|
---
|
|
# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/cluster-total.yaml
|
|
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
namespace: default
|
|
name: kube-prometheus-stack-cluster-total
|
|
annotations:
|
|
{}
|
|
labels:
|
|
grafana_dashboard: "1"
|
|
#TBR: app: kube-prometheus-stack-grafana
|
|
app.kubernetes.io/name: kube-prometheus-stack-grafana #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
data:
|
|
cluster-total.json: |-
|
|
{"editable":true,"links":[{"asDropdown":true,"includeVars":true,"keepTime":true,"tags":["kubernetes-mixin"],"targetBlank":false,"title":"Kubernetes","type":"dashboards"}],"panels":[{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"showPoints":"never"},"unit":"binBps"}},"gridPos":{"h":9,"w":12,"x":0,"y":0},"id":1,"interval":"1m","options":{"legend":{"asTable":true,"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (namespace) (\n rate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace!=\"\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","legendFormat":"__auto"}],"title":"Current Rate of Bytes Received","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"showPoints":"never"},"unit":"binBps"}},"gridPos":{"h":9,"w":12,"x":12,"y":0},"id":2,"interval":"1m","options":{"legend":{"asTable":true,"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (namespace) (\n rate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace!=\"\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","legendFormat":"__auto"}],"title":"Current Rate of Bytes Transmitted","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"overrides":[{"matcher":{"id":"byRegexp","options":"/Bytes/"},"properties":[{"id":"unit","value":"binBps"}]},{"matcher":{"id":"byRegexp","options":"/Packets/"},"properties":[{"id":"unit","value":"pps"}]},{"matcher":{"id":"byName","options":"Namespace"},"properties":[{"id":"links","value":[{"title":"Drill down","url":"/d/8b7a8b326d7a6f1f04244066368c67af/kubernetes-networking-namespace-pods?${datasource:queryparam}&var-cluster=${cluster}&var-namespace=${__data.fields.Namespace}"}]}]}]},"gridPos":{"h":9,"w":24,"x":0,"y":9},"id":3,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (namespace) (\n rate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace!=\"\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (namespace) (\n rate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace!=\"\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"avg by (namespace) (\n rate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace!=\"\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"avg by (namespace) (\n rate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace!=\"\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (namespace) (\n rate(container_network_receive_packets_total{cluster=\"$cluster\",namespace!=\"\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (namespace) (\n rate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace!=\"\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (namespace) (\n rate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace!=\"\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (namespace) (\n rate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace!=\"\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","format":"table","instant":true}],"title":"Current Status","transformations":[{"id":"joinByField","options":{"byField":"namespace","mode":"outer"}},{"id":"organize","options":{"excludeByName":{"Time":true,"Time 1":true,"Time 2":true,"Time 3":true,"Time 4":true,"Time 5":true,"Time 6":true,"Time 7":true,"Time 8":true},"indexByName":{"Time 1":0,"Time 2":1,"Time 3":2,"Time 4":3,"Time 5":4,"Time 6":5,"Time 7":6,"Time 8":7,"Value #A":9,"Value #B":10,"Value #C":11,"Value #D":12,"Value #E":13,"Value #F":14,"Value #G":15,"Value #H":16,"namespace":8},"renameByName":{"Value #A":"Rx Bytes","Value #B":"Tx Bytes","Value #C":"Rx Bytes (Avg)","Value #D":"Tx Bytes (Avg)","Value #E":"Rx Packets","Value #F":"Tx Packets","Value #G":"Rx Packets Dropped","Value #H":"Tx Packets Dropped","namespace":"Namespace"}}}],"type":"table"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"showPoints":"never"},"unit":"binBps"}},"gridPos":{"h":9,"w":12,"x":0,"y":18},"id":4,"interval":"1m","options":{"legend":{"asTable":true,"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"avg by (namespace) (\n rate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace!=\"\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","legendFormat":"__auto"}],"title":"Average Rate of Bytes Received","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"showPoints":"never"},"unit":"binBps"}},"gridPos":{"h":9,"w":12,"x":12,"y":18},"id":5,"interval":"1m","options":{"legend":{"asTable":true,"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"avg by (namespace) (\n rate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace!=\"\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","legendFormat":"__auto"}],"title":"Average Rate of Bytes Transmitted","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"showPoints":"never"},"unit":"binBps"}},"gridPos":{"h":9,"w":12,"x":0,"y":27},"id":6,"interval":"1m","options":{"legend":{"asTable":true,"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (namespace) (\n rate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace!=\"\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","legendFormat":"__auto"}],"title":"Receive Bandwidth","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"showPoints":"never"},"unit":"binBps"}},"gridPos":{"h":9,"w":12,"x":12,"y":27},"id":7,"interval":"1m","options":{"legend":{"asTable":true,"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (namespace) (\n rate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace!=\"\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","legendFormat":"__auto"}],"title":"Transmit Bandwidth","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"showPoints":"never"},"unit":"pps"}},"gridPos":{"h":9,"w":12,"x":0,"y":36},"id":8,"interval":"1m","options":{"legend":{"asTable":true,"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (namespace) (\n rate(container_network_receive_packets_total{cluster=\"$cluster\",namespace!=\"\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","legendFormat":"__auto"}],"title":"Rate of Received Packets","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"showPoints":"never"},"unit":"pps"}},"gridPos":{"h":9,"w":12,"x":12,"y":36},"id":9,"interval":"1m","options":{"legend":{"asTable":true,"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (namespace) (\n rate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace!=\"\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","legendFormat":"__auto"}],"title":"Rate of Transmitted Packets","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"showPoints":"never"},"unit":"pps"}},"gridPos":{"h":9,"w":12,"x":0,"y":45},"id":10,"interval":"1m","options":{"legend":{"asTable":true,"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (namespace) (\n rate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace!=\"\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","legendFormat":"__auto"}],"title":"Rate of Received Packets Dropped","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"showPoints":"never"},"unit":"pps"}},"gridPos":{"h":9,"w":12,"x":12,"y":45},"id":11,"interval":"1m","options":{"legend":{"asTable":true,"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (namespace) (\n rate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace!=\"\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","legendFormat":"__auto"}],"title":"Rate of Transmitted Packets Dropped","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"showPoints":"never"},"unit":"percentunit"}},"gridPos":{"h":9,"w":12,"x":0,"y":54},"id":12,"interval":"1m","options":{"legend":{"asTable":true,"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (instance) (\n rate(node_netstat_Tcp_RetransSegs{cluster=\"$cluster\"}[$__rate_interval]) / rate(node_netstat_Tcp_OutSegs{cluster=\"$cluster\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","legendFormat":"__auto"}],"title":"Rate of TCP Retransmits out of all sent segments","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"showPoints":"never"},"unit":"percentunit"}},"gridPos":{"h":9,"w":12,"x":12,"y":54},"id":13,"interval":"1m","options":{"legend":{"asTable":true,"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (instance) (\n rate(node_netstat_TcpExt_TCPSynRetrans{cluster=\"$cluster\"}[$__rate_interval]) / rate(node_netstat_Tcp_RetransSegs{cluster=\"$cluster\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","legendFormat":"__auto"}],"title":"Rate of TCP SYN Retransmits out of all retransmits","type":"timeseries"}],"refresh":"10s","schemaVersion":39,"tags":["kubernetes-mixin"],"templating":{"list":[{"current":{"selected":true,"text":"default","value":"default"},"hide":0,"label":"Data source","name":"datasource","query":"prometheus","regex":"","type":"datasource"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":2,"label":"cluster","name":"cluster","query":"label_values(up{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\"}, cluster)","refresh":2,"sort":1,"type":"query","allValue":".*"}]},"time":{"from":"now-1h","to":"now"},"timezone": "utc","title":"Kubernetes / Networking / Cluster","uid":"ff635a025bcfea7bc3dd4f508990a3e9"}
|
|
---
|
|
# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/controller-manager.yaml
|
|
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
namespace: default
|
|
name: kube-prometheus-stack-controller-manager
|
|
annotations:
|
|
{}
|
|
labels:
|
|
grafana_dashboard: "1"
|
|
#TBR: app: kube-prometheus-stack-grafana
|
|
app.kubernetes.io/name: kube-prometheus-stack-grafana #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
data:
|
|
controller-manager.json: |-
|
|
{"editable":true,"links":[{"asDropdown":true,"includeVars":true,"keepTime":true,"tags":["kubernetes-mixin"],"targetBlank":false,"title":"Kubernetes","type":"dashboards"}],"panels":[{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"none"}},"gridPos":{"h":7,"w":4,"x":0,"y":0},"id":1,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(up{cluster=\"$cluster\", job=\"kube-controller-manager\"})","instant":true}],"title":"Up","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"ops"}},"gridPos":{"h":7,"w":20,"x":4,"y":0},"id":2,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(workqueue_adds_total{cluster=\"$cluster\", job=\"kube-controller-manager\", instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance, name)","legendFormat":"{{cluster}} {{instance}} {{name}}"}],"title":"Work Queue Add Rate","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"short"}},"gridPos":{"h":7,"w":24,"x":0,"y":7},"id":3,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(workqueue_depth{cluster=\"$cluster\", job=\"kube-controller-manager\", instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance, name)","legendFormat":"{{cluster}} {{instance}} {{name}}"}],"title":"Work Queue Depth","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"s"}},"gridPos":{"h":7,"w":24,"x":0,"y":14},"id":4,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"histogram_quantile(0.99, sum(rate(workqueue_queue_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-controller-manager\", instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance, name, le))","legendFormat":"{{cluster}} {{instance}} {{name}}"}],"title":"Work Queue Latency","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"ops"}},"gridPos":{"h":7,"w":8,"x":0,"y":21},"id":5,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(rest_client_requests_total{job=\"kube-controller-manager\", instance=~\"$instance\",code=~\"2..\"}[$__rate_interval]))","legendFormat":"2xx"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(rest_client_requests_total{job=\"kube-controller-manager\", instance=~\"$instance\",code=~\"3..\"}[$__rate_interval]))","legendFormat":"3xx"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(rest_client_requests_total{job=\"kube-controller-manager\", instance=~\"$instance\",code=~\"4..\"}[$__rate_interval]))","legendFormat":"4xx"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(rest_client_requests_total{job=\"kube-controller-manager\", instance=~\"$instance\",code=~\"5..\"}[$__rate_interval]))","legendFormat":"5xx"}],"title":"Kube API Request Rate","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"s"}},"gridPos":{"h":7,"w":16,"x":8,"y":21},"id":6,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-controller-manager\", instance=~\"$instance\", verb=\"POST\"}[$__rate_interval])) by (verb, url, le))","legendFormat":"{{verb}} {{url}}"}],"title":"Post Request Latency 99th Quantile","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"s"}},"gridPos":{"h":7,"w":24,"x":0,"y":28},"id":7,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-controller-manager\", instance=~\"$instance\", verb=\"GET\"}[$__rate_interval])) by (verb, url, le))","legendFormat":"{{verb}} {{url}}"}],"title":"Get Request Latency 99th Quantile","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"bytes"}},"gridPos":{"h":7,"w":8,"x":0,"y":35},"id":8,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"process_resident_memory_bytes{cluster=\"$cluster\", job=\"kube-controller-manager\",instance=~\"$instance\"}","legendFormat":"{{instance}}"}],"title":"Memory","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"short"}},"gridPos":{"h":7,"w":8,"x":8,"y":35},"id":9,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"rate(process_cpu_seconds_total{cluster=\"$cluster\", job=\"kube-controller-manager\",instance=~\"$instance\"}[$__rate_interval])","legendFormat":"{{instance}}"}],"title":"CPU usage","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"short"}},"gridPos":{"h":7,"w":8,"x":16,"y":35},"id":10,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"go_goroutines{cluster=\"$cluster\", job=\"kube-controller-manager\",instance=~\"$instance\"}","legendFormat":"{{instance}}"}],"title":"Goroutines","type":"timeseries"}],"refresh":"10s","schemaVersion":39,"tags":["kubernetes-mixin"],"templating":{"list":[{"current":{"selected":true,"text":"default","value":"default"},"hide":0,"label":"Data source","name":"datasource","query":"prometheus","regex":"","type":"datasource"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":2,"label":"cluster","name":"cluster","query":"label_values(up{job=\"kube-controller-manager\"}, cluster)","refresh":2,"sort":1,"type":"query","allValue":".*"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":0,"includeAll":true,"label":"instance","name":"instance","query":"label_values(up{cluster=\"$cluster\", job=\"kube-controller-manager\"}, instance)","refresh":2,"sort":1,"type":"query"}]},"time":{"from":"now-1h","to":"now"},"timezone": "utc","title":"Kubernetes / Controller Manager","uid":"72e0e05bef5099e5f049b05fdc429ed4"}
|
|
---
|
|
# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/etcd.yaml
|
|
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
namespace: default
|
|
name: kube-prometheus-stack-etcd
|
|
annotations:
|
|
{}
|
|
labels:
|
|
grafana_dashboard: "1"
|
|
#TBR: app: kube-prometheus-stack-grafana
|
|
app.kubernetes.io/name: kube-prometheus-stack-grafana #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
data:
|
|
etcd.json: |-
|
|
{"description":"etcd sample Grafana dashboard with Prometheus","panels":[{"datasource":{"type":"datasource","uid":"-- Mixed --"},"gridPos":{"h":7,"w":6,"x":0,"y":0},"id":1,"interval":"1m","options":{"colorMode":"none","graphMode":"none","reduceOptions":{"calcs":["lastNotNull"]}},"pluginVersion":"v10.0.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"sum(etcd_server_has_leader{job=~\".*etcd.*\", job=\"$cluster\"})","legendFormat":"{{cluster}} - {{namespace}}\n"}],"title":"Up","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":0,"lineWidth":2,"showPoints":"never"},"unit":"ops"}},"gridPos":{"h":7,"w":10,"x":6,"y":0},"id":2,"interval":"1m","pluginVersion":"v10.0.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"sum(rate(grpc_server_started_total{job=~\".*etcd.*\", job=\"$cluster\",grpc_type=\"unary\"}[$__rate_interval]))","legendFormat":"RPC rate"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"sum(rate(grpc_server_handled_total{job=~\".*etcd.*\", job=\"$cluster\",grpc_type=\"unary\",grpc_code=~\"Unknown|FailedPrecondition|ResourceExhausted|Internal|Unavailable|DataLoss|DeadlineExceeded\"}[$__rate_interval]))","legendFormat":"RPC failed rate"}],"title":"RPC rate","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":0,"lineWidth":2,"showPoints":"never"}}},"gridPos":{"h":7,"w":8,"x":16,"y":0},"id":3,"interval":"1m","pluginVersion":"v10.0.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"sum(grpc_server_started_total{job=~\".*etcd.*\",job=\"$cluster\",grpc_service=\"etcdserverpb.Watch\",grpc_type=\"bidi_stream\"}) - sum(grpc_server_handled_total{job=\"$cluster\",grpc_service=\"etcdserverpb.Watch\",grpc_type=\"bidi_stream\"})","legendFormat":"Watch streams"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"sum(grpc_server_started_total{job=~\".*etcd.*\",job=\"$cluster\",grpc_service=\"etcdserverpb.Lease\",grpc_type=\"bidi_stream\"}) - sum(grpc_server_handled_total{job=\"$cluster\",grpc_service=\"etcdserverpb.Lease\",grpc_type=\"bidi_stream\"})","legendFormat":"Lease streams"}],"title":"Active streams","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":0,"lineWidth":2,"showPoints":"never"},"unit":"bytes"}},"gridPos":{"h":7,"w":8,"x":0,"y":25},"id":4,"interval":"1m","pluginVersion":"v10.0.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"etcd_mvcc_db_total_size_in_bytes{job=~\".*etcd.*\", job=\"$cluster\"}","legendFormat":"{{instance}} DB size"}],"title":"DB size","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":0,"lineWidth":2,"showPoints":"never"},"unit":"s"}},"gridPos":{"h":7,"w":8,"x":8,"y":25},"id":5,"interval":"1m","pluginVersion":"v10.0.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"histogram_quantile(0.99, sum(rate(etcd_disk_wal_fsync_duration_seconds_bucket{job=~\".*etcd.*\", job=\"$cluster\"}[$__rate_interval])) by (instance, le))","legendFormat":"{{instance}} WAL fsync"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"histogram_quantile(0.99, sum(rate(etcd_disk_backend_commit_duration_seconds_bucket{job=~\".*etcd.*\", job=\"$cluster\"}[$__rate_interval])) by (instance, le))","legendFormat":"{{instance}} DB fsync"}],"title":"Disk sync duration","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":0,"lineWidth":2,"showPoints":"never"},"unit":"bytes"}},"gridPos":{"h":7,"w":8,"x":16,"y":25},"id":6,"interval":"1m","pluginVersion":"v10.0.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"process_resident_memory_bytes{job=~\".*etcd.*\", job=\"$cluster\"}","legendFormat":"{{instance}} resident memory"}],"title":"Memory","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":0,"lineWidth":2,"showPoints":"never"},"unit":"Bps"}},"gridPos":{"h":7,"w":6,"x":0,"y":50},"id":7,"interval":"1m","pluginVersion":"v10.0.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"rate(etcd_network_client_grpc_received_bytes_total{job=~\".*etcd.*\", job=\"$cluster\"}[$__rate_interval])","legendFormat":"{{instance}} client traffic in"}],"title":"Client traffic in","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":0,"lineWidth":2,"showPoints":"never"},"unit":"Bps"}},"gridPos":{"h":7,"w":6,"x":6,"y":50},"id":8,"interval":"1m","pluginVersion":"v10.0.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"rate(etcd_network_client_grpc_sent_bytes_total{job=~\".*etcd.*\", job=\"$cluster\"}[$__rate_interval])","legendFormat":"{{instance}} client traffic out"}],"title":"Client traffic out","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":0,"lineWidth":2,"showPoints":"never"},"unit":"Bps"}},"gridPos":{"h":7,"w":6,"x":12,"y":50},"id":9,"interval":"1m","pluginVersion":"v10.0.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"sum(rate(etcd_network_peer_received_bytes_total{job=~\".*etcd.*\", job=\"$cluster\"}[$__rate_interval])) by (instance)","legendFormat":"{{instance}} peer traffic in"}],"title":"Peer traffic in","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":0,"lineWidth":2,"showPoints":"never"},"unit":"Bps"}},"gridPos":{"h":7,"w":6,"x":18,"y":50},"id":10,"interval":"1m","pluginVersion":"v10.0.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"sum(rate(etcd_network_peer_sent_bytes_total{job=~\".*etcd.*\", job=\"$cluster\"}[$__rate_interval])) by (instance)","legendFormat":"{{instance}} peer traffic out"}],"title":"Peer traffic out","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":0,"lineWidth":2,"showPoints":"never"}}},"gridPos":{"h":7,"w":8,"x":0,"y":75},"id":11,"interval":"1m","pluginVersion":"v10.0.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"changes(etcd_server_leader_changes_seen_total{job=~\".*etcd.*\", job=\"$cluster\"}[1d])","legendFormat":"{{instance}} total leader elections per day"}],"title":"Raft proposals","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":0,"lineWidth":2,"showPoints":"never"}}},"gridPos":{"h":7,"w":8,"x":8,"y":75},"id":12,"interval":"1m","pluginVersion":"v10.0.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"changes(etcd_server_leader_changes_seen_total{job=~\".*etcd.*\", job=\"$cluster\"}[1d])","legendFormat":"{{instance}} total leader elections per day"}],"title":"Total leader elections per day","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":0,"lineWidth":2,"showPoints":"never"},"unit":"s"}},"gridPos":{"h":7,"w":8,"x":16,"y":75},"id":13,"interval":"1m","pluginVersion":"v10.0.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"histogram_quantile(0.99, sum by (instance, le) (rate(etcd_network_peer_round_trip_time_seconds_bucket{job=~\".*etcd.*\", job=\"$cluster\"}[$__rate_interval])))","legendFormat":"{{instance}} peer round trip time"}],"title":"Peer round trip time","type":"timeseries"}],"refresh":"10s","schemaVersion":36,"tags":["etcd-mixin"],"templating":{"list":[{"label":"Data Source","name":"datasource","query":"prometheus","type":"datasource"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"label":"cluster","name":"cluster","query":"label_values(etcd_server_has_leader{job=~\".*etcd.*\"}, job)","refresh":2,"type":"query","allValue":".*","hide":2}]},"time":{"from":"now-15m","to":"now"},"timezone": "utc","title":"etcd","uid":"c2f4e12cdf69feb95caa41a5a1b423d9"}
|
|
---
|
|
# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/grafana-overview.yaml
|
|
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
namespace: default
|
|
name: kube-prometheus-stack-grafana-overview
|
|
annotations:
|
|
{}
|
|
labels:
|
|
grafana_dashboard: "1"
|
|
#TBR: app: kube-prometheus-stack-grafana
|
|
app.kubernetes.io/name: kube-prometheus-stack-grafana #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
data:
|
|
grafana-overview.json: |-
|
|
{"annotations":{"list":[{"builtIn":1,"datasource":"-- Grafana --","enable":true,"hide":true,"iconColor":"rgba(0, 211, 255, 1)","name":"Annotations & Alerts","target":{"limit":100,"matchAny":false,"tags":[],"type":"dashboard"},"type":"dashboard"}]},"editable":true,"gnetId":null,"graphTooltip":0,"id":3085,"iteration":1631554945276,"links":[],"panels":[{"datasource":"$datasource","fieldConfig":{"defaults":{"mappings":[],"noValue":"0","thresholds":{"mode":"absolute","steps":[{"color":"green","value":null},{"color":"red","value":80}]}},"overrides":[]},"gridPos":{"h":5,"w":6,"x":0,"y":0},"id":6,"options":{"colorMode":"value","graphMode":"area","justifyMode":"auto","orientation":"auto","reduceOptions":{"calcs":["mean"],"fields":"","values":false},"text":{},"textMode":"auto"},"pluginVersion":"8.1.3","targets":[{"expr":"grafana_alerting_result_total{job=~\"$job\", instance=~\"$instance\", state=\"alerting\"}","instant":true,"interval":"","legendFormat":"","refId":"A"}],"timeFrom":null,"timeShift":null,"title":"Firing Alerts","type":"stat"},{"datasource":"$datasource","fieldConfig":{"defaults":{"mappings":[],"thresholds":{"mode":"absolute","steps":[{"color":"green","value":null},{"color":"red","value":80}]}},"overrides":[]},"gridPos":{"h":5,"w":6,"x":6,"y":0},"id":8,"options":{"colorMode":"value","graphMode":"area","justifyMode":"auto","orientation":"auto","reduceOptions":{"calcs":["mean"],"fields":"","values":false},"text":{},"textMode":"auto"},"pluginVersion":"8.1.3","targets":[{"expr":"sum(grafana_stat_totals_dashboard{job=~\"$job\", instance=~\"$instance\"})","interval":"","legendFormat":"","refId":"A"}],"timeFrom":null,"timeShift":null,"title":"Dashboards","type":"stat"},{"datasource":"$datasource","fieldConfig":{"defaults":{"custom":{"align":null,"displayMode":"auto"},"mappings":[],"thresholds":{"mode":"absolute","steps":[{"color":"green","value":null},{"color":"red","value":80}]}},"overrides":[]},"gridPos":{"h":5,"w":12,"x":12,"y":0},"id":10,"options":{"showHeader":true},"pluginVersion":"8.1.3","targets":[{"expr":"grafana_build_info{job=~\"$job\", instance=~\"$instance\"}","instant":true,"interval":"","legendFormat":"","refId":"A"}],"timeFrom":null,"timeShift":null,"title":"Build Info","transformations":[{"id":"labelsToFields","options":{}},{"id":"organize","options":{"excludeByName":{"Time":true,"Value":true,"branch":true,"container":true,"goversion":true,"namespace":true,"pod":true,"revision":true},"indexByName":{"Time":7,"Value":11,"branch":4,"container":8,"edition":2,"goversion":6,"instance":1,"job":0,"namespace":9,"pod":10,"revision":5,"version":3},"renameByName":{}}}],"type":"table"},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fieldConfig":{"defaults":{"links":[]},"overrides":[]},"fill":1,"fillGradient":0,"gridPos":{"h":8,"w":12,"x":0,"y":5},"hiddenSeries":false,"id":2,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"alertThreshold":true},"percentage":false,"pluginVersion":"8.1.3","pointradius":2,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":true,"steppedLine":false,"targets":[{"expr":"sum by (status_code) (irate(grafana_http_request_duration_seconds_count{job=~\"$job\", instance=~\"$instance\"}[1m])) ","interval":"","legendFormat":"{{status_code}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"RPS","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"$$hashKey":"object:157","format":"reqps","label":null,"logBase":1,"max":null,"min":null,"show":true},{"$$hashKey":"object:158","format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fieldConfig":{"defaults":{"links":[]},"overrides":[]},"fill":1,"fillGradient":0,"gridPos":{"h":8,"w":12,"x":12,"y":5},"hiddenSeries":false,"id":4,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"alertThreshold":true},"percentage":false,"pluginVersion":"8.1.3","pointradius":2,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"exemplar":true,"expr":"histogram_quantile(0.99, sum(irate(grafana_http_request_duration_seconds_bucket{instance=~\"$instance\", job=~\"$job\"}[$__rate_interval])) by (le)) * 1","interval":"","legendFormat":"99th Percentile","refId":"A"},{"exemplar":true,"expr":"histogram_quantile(0.50, sum(irate(grafana_http_request_duration_seconds_bucket{instance=~\"$instance\", job=~\"$job\"}[$__rate_interval])) by (le)) * 1","interval":"","legendFormat":"50th Percentile","refId":"B"},{"exemplar":true,"expr":"sum(irate(grafana_http_request_duration_seconds_sum{instance=~\"$instance\", job=~\"$job\"}[$__rate_interval])) * 1 / sum(irate(grafana_http_request_duration_seconds_count{instance=~\"$instance\", job=~\"$job\"}[$__rate_interval]))","interval":"","legendFormat":"Average","refId":"C"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Request Latency","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"$$hashKey":"object:210","format":"ms","label":null,"logBase":1,"max":null,"min":null,"show":true},{"$$hashKey":"object:211","format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}}],"schemaVersion":30,"style":"dark","tags":[],"templating":{"list":[{"current":{"selected":true,"text":"dev-cortex","value":"dev-cortex"},"description":null,"error":null,"hide":0,"includeAll":false,"label":null,"multi":false,"name":"datasource","options":[],"query":"prometheus","queryValue":"","refresh":1,"regex":"","skipUrlSync":false,"type":"datasource"},{"allValue":".*","current":{"selected":false,"text":["default/grafana"],"value":["default/grafana"]},"datasource":"$datasource","definition":"label_values(grafana_build_info, job)","description":null,"error":null,"hide":0,"includeAll":true,"label":null,"multi":true,"name":"job","options":[],"query":{"query":"label_values(grafana_build_info, job)","refId":"Billing Admin-job-Variable-Query"},"refresh":1,"regex":"","skipUrlSync":false,"sort":0,"tagValuesQuery":"","tagsQuery":"","type":"query","useTags":false},{"allValue":".*","current":{"selected":false,"text":"All","value":"$__all"},"datasource":"$datasource","definition":"label_values(grafana_build_info, instance)","description":null,"error":null,"hide":0,"includeAll":true,"label":null,"multi":true,"name":"instance","options":[],"query":{"query":"label_values(grafana_build_info, instance)","refId":"Billing Admin-instance-Variable-Query"},"refresh":1,"regex":"","skipUrlSync":false,"sort":0,"tagValuesQuery":"","tagsQuery":"","type":"query","useTags":false}]},"time":{"from":"now-6h","to":"now"},"timepicker":{"refresh_intervals":["10s","30s","1m","5m","15m","30m","1h","2h","1d"]},"timezone": "utc","title":"Grafana Overview","uid":"6be0s85Mk","version":2}
|
|
---
|
|
# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-coredns.yaml
|
|
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
namespace: default
|
|
name: kube-prometheus-stack-k8s-coredns
|
|
annotations:
|
|
{}
|
|
labels:
|
|
grafana_dashboard: "1"
|
|
#TBR: app: kube-prometheus-stack-grafana
|
|
app.kubernetes.io/name: kube-prometheus-stack-grafana #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
data:
|
|
k8s-coredns.json: |-
|
|
{"annotations":{"list":[{"builtIn":1,"datasource":{"type":"datasource","uid":"grafana"},"enable":true,"hide":true,"iconColor":"rgba(0, 211, 255, 1)","name":"Annotations & Alerts","type":"dashboard"}]},"description":"A dashboard for the CoreDNS DNS server with updated metrics for version 1.7.0+. Based on the CoreDNS dashboard by buhay.","editable":true,"fiscalYearStartMonth":0,"gnetId":12539,"graphTooltip":0,"id":7,"links":[{"icon":"external link","tags":[],"targetBlank":true,"title":"CoreDNS.io","type":"link","url":"https://coredns.io"}],"liveNow":false,"panels":[{"datasource":{"uid":"$datasource"},"fieldConfig":{"defaults":{"color":{"mode":"palette-classic"},"custom":{"axisBorderShow":false,"axisCenteredZero":false,"axisColorMode":"text","axisLabel":"","axisPlacement":"auto","barAlignment":0,"drawStyle":"line","fillOpacity":10,"gradientMode":"none","hideFrom":{"legend":false,"tooltip":false,"viz":false},"insertNulls":false,"lineInterpolation":"linear","lineWidth":2,"pointSize":5,"scaleDistribution":{"type":"linear"},"showPoints":"never","spanNulls":true,"stacking":{"group":"A","mode":"normal"},"thresholdsStyle":{"mode":"off"}},"links":[],"mappings":[],"min":0,"thresholds":{"mode":"absolute","steps":[{"color":"green","value":null},{"color":"red","value":80}]},"unit":"pps","unitScale":true},"overrides":[]},"gridPos":{"h":7,"w":8,"x":0,"y":0},"id":2,"links":[],"options":{"legend":{"calcs":[],"displayMode":"list","placement":"bottom","showLegend":true},"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"10.3.3","targets":[{"datasource":{"uid":"$datasource"},"expr":"sum(rate(coredns_dns_request_count_total{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\"}[5m])) by (proto) or\nsum(rate(coredns_dns_requests_total{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\"}[5m])) by (proto)","format":"time_series","interval":"","intervalFactor":2,"legendFormat":"{{ proto }}","refId":"A","step":60}],"title":"Requests (total)","type":"timeseries"},{"datasource":{"uid":"$datasource"},"fieldConfig":{"defaults":{"color":{"mode":"palette-classic"},"custom":{"axisBorderShow":false,"axisCenteredZero":false,"axisColorMode":"text","axisLabel":"","axisPlacement":"auto","barAlignment":0,"drawStyle":"line","fillOpacity":10,"gradientMode":"none","hideFrom":{"legend":false,"tooltip":false,"viz":false},"insertNulls":false,"lineInterpolation":"linear","lineWidth":2,"pointSize":5,"scaleDistribution":{"type":"linear"},"showPoints":"never","spanNulls":true,"stacking":{"group":"A","mode":"normal"},"thresholdsStyle":{"mode":"off"}},"links":[],"mappings":[],"min":0,"thresholds":{"mode":"absolute","steps":[{"color":"green","value":null},{"color":"red","value":80}]},"unit":"pps","unitScale":true},"overrides":[]},"gridPos":{"h":7,"w":8,"x":8,"y":0},"id":4,"links":[],"options":{"legend":{"calcs":[],"displayMode":"list","placement":"bottom","showLegend":true},"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"10.3.3","targets":[{"datasource":{"uid":"$datasource"},"expr":"sum(rate(coredns_dns_request_type_count_total{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\"}[5m])) by (type) or \nsum(rate(coredns_dns_requests_total{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\"}[5m])) by (type)","interval":"","intervalFactor":2,"legendFormat":"{{ type }}","refId":"A","step":60}],"title":"Requests (by qtype)","type":"timeseries"},{"datasource":{"uid":"$datasource"},"fieldConfig":{"defaults":{"color":{"mode":"palette-classic"},"custom":{"axisBorderShow":false,"axisCenteredZero":false,"axisColorMode":"text","axisLabel":"","axisPlacement":"auto","barAlignment":0,"drawStyle":"line","fillOpacity":10,"gradientMode":"none","hideFrom":{"legend":false,"tooltip":false,"viz":false},"insertNulls":false,"lineInterpolation":"linear","lineWidth":2,"pointSize":5,"scaleDistribution":{"type":"linear"},"showPoints":"never","spanNulls":true,"stacking":{"group":"A","mode":"normal"},"thresholdsStyle":{"mode":"off"}},"links":[],"mappings":[],"min":0,"thresholds":{"mode":"absolute","steps":[{"color":"green","value":null},{"color":"red","value":80}]},"unit":"pps","unitScale":true},"overrides":[]},"gridPos":{"h":7,"w":8,"x":16,"y":0},"id":6,"links":[],"options":{"legend":{"calcs":[],"displayMode":"list","placement":"bottom","showLegend":true},"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"10.3.3","targets":[{"datasource":{"uid":"$datasource"},"expr":"sum(rate(coredns_dns_request_count_total{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\"}[5m])) by (zone) or\nsum(rate(coredns_dns_requests_total{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\"}[5m])) by (zone)","interval":"","intervalFactor":2,"legendFormat":"{{ zone }}","refId":"A","step":60}],"title":"Requests (by zone)","type":"timeseries"},{"datasource":{"uid":"$datasource"},"fieldConfig":{"defaults":{"color":{"mode":"palette-classic"},"custom":{"axisBorderShow":false,"axisCenteredZero":false,"axisColorMode":"text","axisLabel":"","axisPlacement":"auto","barAlignment":0,"drawStyle":"line","fillOpacity":10,"gradientMode":"none","hideFrom":{"legend":false,"tooltip":false,"viz":false},"insertNulls":false,"lineInterpolation":"linear","lineWidth":2,"pointSize":5,"scaleDistribution":{"type":"linear"},"showPoints":"never","spanNulls":true,"stacking":{"group":"A","mode":"none"},"thresholdsStyle":{"mode":"off"}},"links":[],"mappings":[],"min":0,"thresholds":{"mode":"absolute","steps":[{"color":"green","value":null},{"color":"red","value":80}]},"unit":"pps","unitScale":true},"overrides":[]},"gridPos":{"h":7,"w":12,"x":0,"y":7},"id":8,"links":[],"options":{"legend":{"calcs":[],"displayMode":"list","placement":"bottom","showLegend":true},"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"10.3.3","targets":[{"datasource":{"uid":"$datasource"},"expr":"sum(rate(coredns_dns_request_do_count_total{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\"}[5m])) or\nsum(rate(coredns_dns_do_requests_total{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\"}[5m]))","interval":"","intervalFactor":2,"legendFormat":"DO","refId":"A","step":40},{"datasource":{"uid":"$datasource"},"expr":"sum(rate(coredns_dns_request_count_total{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\"}[5m])) or\nsum(rate(coredns_dns_requests_total{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\"}[5m]))","interval":"","intervalFactor":2,"legendFormat":"total","refId":"B","step":40}],"title":"Requests (DO bit)","type":"timeseries"},{"datasource":{"uid":"$datasource"},"fieldConfig":{"defaults":{"color":{"mode":"palette-classic"},"custom":{"axisBorderShow":false,"axisCenteredZero":false,"axisColorMode":"text","axisLabel":"","axisPlacement":"auto","barAlignment":0,"drawStyle":"line","fillOpacity":10,"gradientMode":"none","hideFrom":{"legend":false,"tooltip":false,"viz":false},"insertNulls":false,"lineInterpolation":"linear","lineWidth":2,"pointSize":5,"scaleDistribution":{"type":"linear"},"showPoints":"never","spanNulls":true,"stacking":{"group":"A","mode":"none"},"thresholdsStyle":{"mode":"off"}},"links":[],"mappings":[],"min":0,"thresholds":{"mode":"absolute","steps":[{"color":"green","value":null},{"color":"red","value":80}]},"unit":"bytes","unitScale":true},"overrides":[{"matcher":{"id":"byName","options":"tcp:90"},"properties":[{"id":"unit","value":"short"}]},{"matcher":{"id":"byName","options":"tcp:99 "},"properties":[{"id":"unit","value":"short"}]},{"matcher":{"id":"byName","options":"tcp:50"},"properties":[{"id":"unit","value":"short"}]}]},"gridPos":{"h":7,"w":6,"x":12,"y":7},"id":10,"links":[],"options":{"legend":{"calcs":[],"displayMode":"list","placement":"bottom","showLegend":true},"tooltip":{"mode":"multi","sort":"none"}},"pluginVersion":"10.3.3","targets":[{"datasource":{"uid":"$datasource"},"expr":"histogram_quantile(0.99, sum(rate(coredns_dns_request_size_bytes_bucket{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\",proto=\"udp\"}[5m])) by (le,proto))","interval":"","intervalFactor":2,"legendFormat":"{{ proto }}:99 ","refId":"A","step":60},{"datasource":{"uid":"$datasource"},"expr":"histogram_quantile(0.90, sum(rate(coredns_dns_request_size_bytes_bucket{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\",proto=\"udp\"}[5m])) by (le,proto))","intervalFactor":2,"legendFormat":"{{ proto }}:90","refId":"B","step":60},{"datasource":{"uid":"$datasource"},"expr":"histogram_quantile(0.50, sum(rate(coredns_dns_request_size_bytes_bucket{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\",proto=\"udp\"}[5m])) by (le,proto))","intervalFactor":2,"legendFormat":"{{ proto }}:50","refId":"C","step":60}],"title":"Requests (size, udp)","type":"timeseries"},{"datasource":{"uid":"$datasource"},"fieldConfig":{"defaults":{"color":{"mode":"palette-classic"},"custom":{"axisBorderShow":false,"axisCenteredZero":false,"axisColorMode":"text","axisLabel":"","axisPlacement":"auto","barAlignment":0,"drawStyle":"line","fillOpacity":10,"gradientMode":"none","hideFrom":{"legend":false,"tooltip":false,"viz":false},"insertNulls":false,"lineInterpolation":"linear","lineWidth":2,"pointSize":5,"scaleDistribution":{"type":"linear"},"showPoints":"never","spanNulls":true,"stacking":{"group":"A","mode":"none"},"thresholdsStyle":{"mode":"off"}},"links":[],"mappings":[],"min":0,"thresholds":{"mode":"absolute","steps":[{"color":"green","value":null},{"color":"red","value":80}]},"unit":"bytes","unitScale":true},"overrides":[]},"gridPos":{"h":7,"w":6,"x":18,"y":7},"id":12,"links":[],"options":{"legend":{"calcs":[],"displayMode":"list","placement":"bottom","showLegend":true},"tooltip":{"mode":"multi","sort":"none"}},"pluginVersion":"10.3.3","targets":[{"datasource":{"uid":"$datasource"},"expr":"histogram_quantile(0.99, sum(rate(coredns_dns_request_size_bytes_bucket{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\",proto=\"tcp\"}[5m])) by (le,proto))","format":"time_series","interval":"","intervalFactor":2,"legendFormat":"{{ proto }}:99 ","refId":"A","step":60},{"datasource":{"uid":"$datasource"},"expr":"histogram_quantile(0.90, sum(rate(coredns_dns_request_size_bytes_bucket{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\",proto=\"tcp\"}[5m])) by (le,proto))","format":"time_series","interval":"","intervalFactor":2,"legendFormat":"{{ proto }}:90","refId":"B","step":60},{"datasource":{"uid":"$datasource"},"expr":"histogram_quantile(0.50, sum(rate(coredns_dns_request_size_bytes_bucket{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\",proto=\"tcp\"}[5m])) by (le,proto))","format":"time_series","interval":"","intervalFactor":2,"legendFormat":"{{ proto }}:50","refId":"C","step":60}],"title":"Requests (size,tcp)","type":"timeseries"},{"datasource":{"uid":"$datasource"},"fieldConfig":{"defaults":{"color":{"mode":"palette-classic"},"custom":{"axisBorderShow":false,"axisCenteredZero":false,"axisColorMode":"text","axisLabel":"","axisPlacement":"auto","barAlignment":0,"drawStyle":"line","fillOpacity":10,"gradientMode":"none","hideFrom":{"legend":false,"tooltip":false,"viz":false},"insertNulls":false,"lineInterpolation":"linear","lineWidth":2,"pointSize":5,"scaleDistribution":{"type":"linear"},"showPoints":"never","spanNulls":true,"stacking":{"group":"A","mode":"normal"},"thresholdsStyle":{"mode":"off"}},"links":[],"mappings":[],"min":0,"thresholds":{"mode":"absolute","steps":[{"color":"green","value":null},{"color":"red","value":80}]},"unit":"pps","unitScale":true},"overrides":[]},"gridPos":{"h":7,"w":12,"x":0,"y":14},"id":14,"links":[],"options":{"legend":{"calcs":[],"displayMode":"list","placement":"bottom","showLegend":true},"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"10.3.3","targets":[{"datasource":{"uid":"$datasource"},"expr":"sum(rate(coredns_dns_response_rcode_count_total{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\"}[5m])) by (rcode) or\nsum(rate(coredns_dns_responses_total{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\"}[5m])) by (rcode)","interval":"","intervalFactor":2,"legendFormat":"{{ rcode }}","refId":"A","step":40}],"title":"Responses (by rcode)","type":"timeseries"},{"datasource":{"uid":"$datasource"},"fieldConfig":{"defaults":{"color":{"mode":"palette-classic"},"custom":{"axisBorderShow":false,"axisCenteredZero":false,"axisColorMode":"text","axisLabel":"","axisPlacement":"auto","barAlignment":0,"drawStyle":"line","fillOpacity":10,"gradientMode":"none","hideFrom":{"legend":false,"tooltip":false,"viz":false},"insertNulls":false,"lineInterpolation":"linear","lineWidth":2,"pointSize":5,"scaleDistribution":{"type":"linear"},"showPoints":"never","spanNulls":true,"stacking":{"group":"A","mode":"none"},"thresholdsStyle":{"mode":"off"}},"links":[],"mappings":[],"min":0,"thresholds":{"mode":"absolute","steps":[{"color":"green","value":null},{"color":"red","value":80}]},"unit":"s","unitScale":true},"overrides":[]},"gridPos":{"h":7,"w":12,"x":12,"y":14},"id":32,"links":[],"options":{"legend":{"calcs":[],"displayMode":"list","placement":"bottom","showLegend":true},"tooltip":{"mode":"multi","sort":"none"}},"pluginVersion":"10.3.3","targets":[{"datasource":{"uid":"$datasource"},"expr":"histogram_quantile(0.99, sum(rate(coredns_dns_request_duration_seconds_bucket{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\"}[5m])) by (le, job))","format":"time_series","intervalFactor":2,"legendFormat":"99%","refId":"A","step":40},{"datasource":{"uid":"$datasource"},"expr":"histogram_quantile(0.90, sum(rate(coredns_dns_request_duration_seconds_bucket{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\"}[5m])) by (le))","format":"time_series","intervalFactor":2,"legendFormat":"90%","refId":"B","step":40},{"datasource":{"uid":"$datasource"},"expr":"histogram_quantile(0.50, sum(rate(coredns_dns_request_duration_seconds_bucket{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\"}[5m])) by (le))","format":"time_series","intervalFactor":2,"legendFormat":"50%","refId":"C","step":40}],"title":"Responses (duration)","type":"timeseries"},{"datasource":{"uid":"$datasource"},"fieldConfig":{"defaults":{"color":{"mode":"palette-classic"},"custom":{"axisBorderShow":false,"axisCenteredZero":false,"axisColorMode":"text","axisLabel":"","axisPlacement":"auto","barAlignment":0,"drawStyle":"line","fillOpacity":10,"gradientMode":"none","hideFrom":{"legend":false,"tooltip":false,"viz":false},"insertNulls":false,"lineInterpolation":"linear","lineWidth":2,"pointSize":5,"scaleDistribution":{"type":"linear"},"showPoints":"never","spanNulls":true,"stacking":{"group":"A","mode":"none"},"thresholdsStyle":{"mode":"off"}},"links":[],"mappings":[],"min":0,"thresholds":{"mode":"absolute","steps":[{"color":"green","value":null},{"color":"red","value":80}]},"unit":"bytes","unitScale":true},"overrides":[{"matcher":{"id":"byName","options":"tcp:50%"},"properties":[{"id":"unit","value":"short"}]},{"matcher":{"id":"byName","options":"tcp:90%"},"properties":[{"id":"unit","value":"short"}]},{"matcher":{"id":"byName","options":"tcp:99%"},"properties":[{"id":"unit","value":"short"}]}]},"gridPos":{"h":7,"w":12,"x":0,"y":21},"id":18,"links":[],"options":{"legend":{"calcs":[],"displayMode":"list","placement":"bottom","showLegend":true},"tooltip":{"mode":"multi","sort":"none"}},"pluginVersion":"10.3.3","targets":[{"datasource":{"uid":"$datasource"},"expr":"histogram_quantile(0.99, sum(rate(coredns_dns_response_size_bytes_bucket{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\",proto=\"udp\"}[5m])) by (le,proto)) ","interval":"","intervalFactor":2,"legendFormat":"{{ proto }}:99%","refId":"A","step":40},{"datasource":{"uid":"$datasource"},"expr":"histogram_quantile(0.90, sum(rate(coredns_dns_response_size_bytes_bucket{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\",proto=\"udp\"}[5m])) by (le,proto)) ","interval":"","intervalFactor":2,"legendFormat":"{{ proto }}:90%","refId":"B","step":40},{"datasource":{"uid":"$datasource"},"expr":"histogram_quantile(0.50, sum(rate(coredns_dns_response_size_bytes_bucket{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\",proto=\"udp\"}[5m])) by (le,proto)) ","hide":false,"intervalFactor":2,"legendFormat":"{{ proto }}:50%","metric":"","refId":"C","step":40}],"title":"Responses (size, udp)","type":"timeseries"},{"datasource":{"uid":"$datasource"},"fieldConfig":{"defaults":{"color":{"mode":"palette-classic"},"custom":{"axisBorderShow":false,"axisCenteredZero":false,"axisColorMode":"text","axisLabel":"","axisPlacement":"auto","barAlignment":0,"drawStyle":"line","fillOpacity":10,"gradientMode":"none","hideFrom":{"legend":false,"tooltip":false,"viz":false},"insertNulls":false,"lineInterpolation":"linear","lineWidth":2,"pointSize":5,"scaleDistribution":{"type":"linear"},"showPoints":"never","spanNulls":true,"stacking":{"group":"A","mode":"none"},"thresholdsStyle":{"mode":"off"}},"links":[],"mappings":[],"min":0,"thresholds":{"mode":"absolute","steps":[{"color":"green","value":null},{"color":"red","value":80}]},"unit":"bytes","unitScale":true},"overrides":[]},"gridPos":{"h":7,"w":12,"x":12,"y":21},"id":20,"links":[],"options":{"legend":{"calcs":[],"displayMode":"list","placement":"bottom","showLegend":true},"tooltip":{"mode":"multi","sort":"none"}},"pluginVersion":"10.3.3","targets":[{"datasource":{"uid":"$datasource"},"expr":"histogram_quantile(0.99, sum(rate(coredns_dns_response_size_bytes_bucket{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\",proto=\"tcp\"}[5m])) by (le,proto)) ","format":"time_series","intervalFactor":2,"legendFormat":"{{ proto }}:99%","refId":"A","step":40},{"datasource":{"uid":"$datasource"},"expr":"histogram_quantile(0.90, sum(rate(coredns_dns_response_size_bytes_bucket{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\",proto=\"tcp\"}[5m])) by (le,proto)) ","format":"time_series","intervalFactor":2,"legendFormat":"{{ proto }}:90%","refId":"B","step":40},{"datasource":{"uid":"$datasource"},"expr":"histogram_quantile(0.50, sum(rate(coredns_dns_response_size_bytes_bucket{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\",proto=\"tcp\"}[5m])) by (le, proto)) ","format":"time_series","intervalFactor":2,"legendFormat":"{{ proto }}:50%","metric":"","refId":"C","step":40}],"title":"Responses (size, tcp)","type":"timeseries"},{"datasource":{"uid":"$datasource"},"fieldConfig":{"defaults":{"color":{"mode":"palette-classic"},"custom":{"axisBorderShow":false,"axisCenteredZero":false,"axisColorMode":"text","axisLabel":"","axisPlacement":"auto","barAlignment":0,"drawStyle":"line","fillOpacity":10,"gradientMode":"none","hideFrom":{"legend":false,"tooltip":false,"viz":false},"insertNulls":false,"lineInterpolation":"linear","lineWidth":2,"pointSize":5,"scaleDistribution":{"type":"linear"},"showPoints":"never","spanNulls":true,"stacking":{"group":"A","mode":"normal"},"thresholdsStyle":{"mode":"off"}},"links":[],"mappings":[],"min":0,"thresholds":{"mode":"absolute","steps":[{"color":"green","value":null},{"color":"red","value":80}]},"unit":"decbytes","unitScale":true},"overrides":[]},"gridPos":{"h":7,"w":12,"x":0,"y":28},"id":22,"links":[],"options":{"legend":{"calcs":[],"displayMode":"list","placement":"bottom","showLegend":true},"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"10.3.3","targets":[{"datasource":{"uid":"$datasource"},"expr":"sum(coredns_cache_size{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\"}) by (type) or\nsum(coredns_cache_entries{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\"}) by (type)","interval":"","intervalFactor":2,"legendFormat":"{{ type }}","refId":"A","step":40}],"title":"Cache (size)","type":"timeseries"},{"datasource":{"uid":"$datasource"},"fieldConfig":{"defaults":{"color":{"mode":"palette-classic"},"custom":{"axisBorderShow":false,"axisCenteredZero":false,"axisColorMode":"text","axisLabel":"","axisPlacement":"auto","barAlignment":0,"drawStyle":"line","fillOpacity":10,"gradientMode":"none","hideFrom":{"legend":false,"tooltip":false,"viz":false},"insertNulls":false,"lineInterpolation":"linear","lineWidth":2,"pointSize":5,"scaleDistribution":{"type":"linear"},"showPoints":"never","spanNulls":true,"stacking":{"group":"A","mode":"normal"},"thresholdsStyle":{"mode":"off"}},"links":[],"mappings":[],"min":0,"thresholds":{"mode":"absolute","steps":[{"color":"green","value":null},{"color":"red","value":80}]},"unit":"pps","unitScale":true},"overrides":[]},"gridPos":{"h":7,"w":12,"x":12,"y":28},"id":24,"links":[],"options":{"legend":{"calcs":[],"displayMode":"list","placement":"bottom","showLegend":true},"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"10.3.3","targets":[{"datasource":{"uid":"$datasource"},"expr":"sum(rate(coredns_cache_hits_total{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\"}[5m])) by (type)","hide":false,"intervalFactor":2,"legendFormat":"hits:{{ type }}","refId":"A","step":40},{"datasource":{"uid":"$datasource"},"expr":"sum(rate(coredns_cache_misses_total{job=~\"$job\",cluster=~\"$cluster\",instance=~\"$instance\"}[5m])) by (type)","hide":false,"intervalFactor":2,"legendFormat":"misses","refId":"B","step":40}],"title":"Cache (hitrate)","type":"timeseries"}],"refresh":"10s","schemaVersion":39,"tags":["dns","coredns"],"templating":{"list":[{"current":{},"hide":0,"includeAll":false,"multi":false,"name":"datasource","options":[],"query":"prometheus","queryValue":"","refresh":1,"regex":"","skipUrlSync":false,"type":"datasource"},{"allValue":".*","current":{"selected":false,"text":"All","value":"$__all"},"datasource":{"type":"prometheus","uid":"$datasource"},"definition":"label_values(coredns_dns_requests_total, cluster)","hide":2,"includeAll":true,"label":"Cluster","multi":false,"name":"cluster","options":[],"query":"label_values(coredns_dns_requests_total, cluster)","refresh":2,"regex":"","skipUrlSync":false,"sort":1,"tagValuesQuery":"","tagsQuery":"","type":"query","useTags":false},{"allValue":".*","current":{"selected":false,"text":"All","value":"$__all"},"datasource":{"type":"prometheus","uid":"${datasource}"},"definition":"label_values(coredns_dns_requests_total{cluster=~\"$cluster\"},job)","hide":0,"includeAll":true,"label":"Job","multi":false,"name":"job","options":[],"query":{"qryType":1,"query":"label_values(coredns_dns_requests_total{cluster=~\"$cluster\"},job)","refId":"PrometheusVariableQueryEditor-VariableQuery"},"refresh":2,"regex":"","skipUrlSync":false,"sort":1,"type":"query"},{"allValue":".*","current":{"selected":false,"text":"All","value":"$__all"},"datasource":{"type":"prometheus","uid":"$datasource"},"definition":"label_values(coredns_dns_requests_total{job=~\"$job\",cluster=~\"$cluster\"}, instance)","hide":0,"includeAll":true,"label":"Instance","multi":false,"name":"instance","options":[],"query":"label_values(coredns_dns_requests_total{job=~\"$job\",cluster=~\"$cluster\"}, instance)","refresh":2,"regex":"","skipUrlSync":false,"sort":3,"tagValuesQuery":"","tagsQuery":"","type":"query","useTags":false}]},"time":{"from":"now-3h","to":"now"},"timepicker":{"refresh_intervals":["10s","30s","1m","5m","15m","30m","1h","2h","1d"]},"timezone": "utc","title":"CoreDNS","uid":"vkQ0UHxik","version":3,"weekStart":""}
|
|
---
|
|
# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-resources-cluster.yaml
|
|
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
namespace: default
|
|
name: kube-prometheus-stack-k8s-resources-cluster
|
|
annotations:
|
|
{}
|
|
labels:
|
|
grafana_dashboard: "1"
|
|
#TBR: app: kube-prometheus-stack-grafana
|
|
app.kubernetes.io/name: kube-prometheus-stack-grafana #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
data:
|
|
k8s-resources-cluster.json: |-
|
|
{"editable":true,"links":[{"asDropdown":true,"includeVars":true,"keepTime":true,"tags":["kubernetes-mixin"],"targetBlank":false,"title":"Kubernetes","type":"dashboards"}],"panels":[{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"percentunit"}},"gridPos":{"h":3,"w":4,"x":0,"y":0},"id":1,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"cluster:node_cpu:ratio_rate5m{cluster=\"$cluster\"}","instant":true}],"title":"CPU Utilisation","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"percentunit"}},"gridPos":{"h":3,"w":4,"x":4,"y":0},"id":2,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(namespace_cpu:kube_pod_container_resource_requests:sum{cluster=\"$cluster\"}) / sum(kube_node_status_allocatable{job=\"kube-state-metrics\",resource=\"cpu\",cluster=\"$cluster\"})","instant":true}],"title":"CPU Requests Commitment","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"percentunit"}},"gridPos":{"h":3,"w":4,"x":8,"y":0},"id":3,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(namespace_cpu:kube_pod_container_resource_limits:sum{cluster=\"$cluster\"}) / sum(kube_node_status_allocatable{job=\"kube-state-metrics\",resource=\"cpu\",cluster=\"$cluster\"})","instant":true}],"title":"CPU Limits Commitment","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"percentunit"}},"gridPos":{"h":3,"w":4,"x":12,"y":0},"id":4,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"1 - sum(:node_memory_MemAvailable_bytes:sum{cluster=\"$cluster\"}) / sum(node_memory_MemTotal_bytes{job=\"node-exporter\",cluster=\"$cluster\"})","instant":true}],"title":"Memory Utilisation","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"percentunit"}},"gridPos":{"h":3,"w":4,"x":16,"y":0},"id":5,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(namespace_memory:kube_pod_container_resource_requests:sum{cluster=\"$cluster\"}) / sum(kube_node_status_allocatable{job=\"kube-state-metrics\",resource=\"memory\",cluster=\"$cluster\"})","instant":true}],"title":"Memory Requests Commitment","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"percentunit"}},"gridPos":{"h":3,"w":4,"x":20,"y":0},"id":6,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(namespace_memory:kube_pod_container_resource_limits:sum{cluster=\"$cluster\"}) / sum(kube_node_status_allocatable{job=\"kube-state-metrics\",resource=\"memory\",cluster=\"$cluster\"})","instant":true}],"title":"Memory Limits Commitment","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true}}},"gridPos":{"h":6,"w":24,"x":0,"y":6},"id":7,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\"}) by (namespace)","legendFormat":"__auto"}],"title":"CPU Usage","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"overrides":[{"matcher":{"id":"byRegexp","options":"/%/"},"properties":[{"id":"unit","value":"percentunit"}]},{"matcher":{"id":"byName","options":"Namespace"},"properties":[{"id":"links","value":[{"title":"Drill down to pods","url":"/d/85a562078cdf77779eaa1add43ccec1e/k8s-resources-namespace?${datasource:queryparam}&var-cluster=$cluster&var-namespace=${__data.fields.Namespace}"}]}]}]},"gridPos":{"h":6,"w":24,"x":0,"y":12},"id":8,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(kube_pod_owner{job=\"kube-state-metrics\", cluster=\"$cluster\"}) by (namespace)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"count(avg(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\"}) by (workload, namespace)) by (namespace)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\"}) by (namespace)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(namespace_cpu:kube_pod_container_resource_requests:sum{cluster=\"$cluster\"}) by (namespace)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\"}) by (namespace) / sum(namespace_cpu:kube_pod_container_resource_requests:sum{cluster=\"$cluster\"}) by (namespace)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(namespace_cpu:kube_pod_container_resource_limits:sum{cluster=\"$cluster\"}) by (namespace)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\"}) by (namespace) / sum(namespace_cpu:kube_pod_container_resource_limits:sum{cluster=\"$cluster\"}) by (namespace)","format":"table","instant":true}],"title":"CPU Quota","transformations":[{"id":"joinByField","options":{"byField":"namespace","mode":"outer"}},{"id":"organize","options":{"excludeByName":{"Time":true,"Time 1":true,"Time 2":true,"Time 3":true,"Time 4":true,"Time 5":true,"Time 6":true,"Time 7":true},"indexByName":{"Time 1":0,"Time 2":1,"Time 3":2,"Time 4":3,"Time 5":4,"Time 6":5,"Time 7":6,"Value #A":8,"Value #B":9,"Value #C":10,"Value #D":11,"Value #E":12,"Value #F":13,"Value #G":14,"namespace":7},"renameByName":{"Value #A":"Pods","Value #B":"Workloads","Value #C":"CPU Usage","Value #D":"CPU Requests","Value #E":"CPU Requests %","Value #F":"CPU Limits","Value #G":"CPU Limits %","namespace":"Namespace"}}}],"type":"table"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"bytes"}},"gridPos":{"h":6,"w":24,"x":0,"y":18},"id":9,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(container_memory_rss{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", container!=\"\"}) by (namespace)","legendFormat":"__auto"}],"title":"Memory","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"overrides":[{"matcher":{"id":"byRegexp","options":"/%/"},"properties":[{"id":"unit","value":"percentunit"}]},{"matcher":{"id":"byName","options":"Memory Usage"},"properties":[{"id":"unit","value":"bytes"}]},{"matcher":{"id":"byName","options":"Memory Requests"},"properties":[{"id":"unit","value":"bytes"}]},{"matcher":{"id":"byName","options":"Memory Limits"},"properties":[{"id":"unit","value":"bytes"}]},{"matcher":{"id":"byName","options":"Namespace"},"properties":[{"id":"links","value":[{"title":"Drill down to pods","url":"/d/85a562078cdf77779eaa1add43ccec1e/k8s-resources-namespace?${datasource:queryparam}&var-cluster=$cluster&var-namespace=${__data.fields.Namespace}"}]}]}]},"gridPos":{"h":6,"w":24,"x":0,"y":24},"id":10,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(kube_pod_owner{job=\"kube-state-metrics\", cluster=\"$cluster\"}) by (namespace)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"count(avg(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\"}) by (workload, namespace)) by (namespace)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(container_memory_rss{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", container!=\"\"}) by (namespace)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(namespace_memory:kube_pod_container_resource_requests:sum{cluster=\"$cluster\"}) by (namespace)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(container_memory_rss{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", container!=\"\"}) by (namespace) / sum(namespace_memory:kube_pod_container_resource_requests:sum{cluster=\"$cluster\"}) by (namespace)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(namespace_memory:kube_pod_container_resource_limits:sum{cluster=\"$cluster\"}) by (namespace)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(container_memory_rss{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", container!=\"\"}) by (namespace) / sum(namespace_memory:kube_pod_container_resource_limits:sum{cluster=\"$cluster\"}) by (namespace)","format":"table","instant":true}],"title":"Memory Requests by Namespace","transformations":[{"id":"joinByField","options":{"byField":"namespace","mode":"outer"}},{"id":"organize","options":{"excludeByName":{"Time":true,"Time 1":true,"Time 2":true,"Time 3":true,"Time 4":true,"Time 5":true,"Time 6":true,"Time 7":true},"indexByName":{"Time 1":0,"Time 2":1,"Time 3":2,"Time 4":3,"Time 5":4,"Time 6":5,"Time 7":6,"Value #A":8,"Value #B":9,"Value #C":10,"Value #D":11,"Value #E":12,"Value #F":13,"Value #G":14,"namespace":7},"renameByName":{"Value #A":"Pods","Value #B":"Workloads","Value #C":"Memory Usage","Value #D":"Memory Requests","Value #E":"Memory Requests %","Value #F":"Memory Limits","Value #G":"Memory Limits %","namespace":"Namespace"}}}],"type":"table"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"overrides":[{"matcher":{"id":"byRegexp","options":"/Bandwidth/"},"properties":[{"id":"unit","value":"Bps"}]},{"matcher":{"id":"byRegexp","options":"/Packets/"},"properties":[{"id":"unit","value":"pps"}]},{"matcher":{"id":"byName","options":"Namespace"},"properties":[{"id":"links","value":[{"title":"Drill down to pods","url":"/d/85a562078cdf77779eaa1add43ccec1e/k8s-resources-namespace?${datasource:queryparam}&var-cluster=$cluster&var-namespace=${__data.fields.Namespace}"}]}]}]},"gridPos":{"h":6,"w":24,"x":0,"y":30},"id":11,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_receive_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_transmit_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_receive_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_transmit_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)","format":"table","instant":true}],"title":"Current Network Usage","transformations":[{"id":"joinByField","options":{"byField":"namespace","mode":"outer"}},{"id":"organize","options":{"excludeByName":{"Time":true,"Time 1":true,"Time 2":true,"Time 3":true,"Time 4":true,"Time 5":true,"Time 6":true},"indexByName":{"Time 1":0,"Time 2":1,"Time 3":2,"Time 4":3,"Time 5":4,"Time 6":5,"Value #A":7,"Value #B":8,"Value #C":9,"Value #D":10,"Value #E":11,"Value #F":12,"namespace":6},"renameByName":{"Value #A":"Current Receive Bandwidth","Value #B":"Current Transmit Bandwidth","Value #C":"Rate of Received Packets","Value #D":"Rate of Transmitted Packets","Value #E":"Rate of Received Packets Dropped","Value #F":"Rate of Transmitted Packets Dropped","namespace":"Namespace"}}}],"type":"table"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"Bps"}},"gridPos":{"h":6,"w":24,"x":0,"y":36},"id":12,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)","legendFormat":"__auto"}],"title":"Receive Bandwidth","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"Bps"}},"gridPos":{"h":6,"w":24,"x":0,"y":42},"id":13,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)","legendFormat":"__auto"}],"title":"Transmit Bandwidth","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"Bps"}},"gridPos":{"h":6,"w":24,"x":0,"y":48},"id":14,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"avg(irate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)","legendFormat":"__auto"}],"title":"Average Container Bandwidth by Namespace: Received","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"Bps"}},"gridPos":{"h":6,"w":24,"x":0,"y":54},"id":15,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"avg(irate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)","legendFormat":"__auto"}],"title":"Average Container Bandwidth by Namespace: Transmitted","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"pps"}},"gridPos":{"h":6,"w":24,"x":0,"y":60},"id":16,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(irate(container_network_receive_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)","legendFormat":"__auto"}],"title":"Rate of Received Packets","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"pps"}},"gridPos":{"h":6,"w":24,"x":0,"y":66},"id":17,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(irate(container_network_transmit_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)","legendFormat":"__auto"}],"title":"Rate of Transmitted Packets","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"pps"}},"gridPos":{"h":6,"w":24,"x":0,"y":72},"id":18,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(irate(container_network_receive_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)","legendFormat":"__auto"}],"title":"Rate of Received Packets Dropped","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"pps"}},"gridPos":{"h":6,"w":24,"x":0,"y":78},"id":19,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(irate(container_network_transmit_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)","legendFormat":"__auto"}],"title":"Rate of Transmitted Packets Dropped","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"iops"}},"gridPos":{"h":6,"w":24,"x":0,"y":84},"id":20,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"ceil(sum by(namespace) (rate(container_fs_reads_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]) + rate(container_fs_writes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval])))","legendFormat":"__auto"}],"title":"IOPS(Reads+Writes)","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"Bps"}},"gridPos":{"h":6,"w":24,"x":0,"y":90},"id":21,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by(namespace) (rate(container_fs_reads_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]) + rate(container_fs_writes_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]))","legendFormat":"__auto"}],"title":"ThroughPut(Read+Write)","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"overrides":[{"matcher":{"id":"byRegexp","options":"/IOPS/"},"properties":[{"id":"unit","value":"iops"}]},{"matcher":{"id":"byRegexp","options":"/Throughput/"},"properties":[{"id":"unit","value":"Bps"}]},{"matcher":{"id":"byName","options":"Namespace"},"properties":[{"id":"links","value":[{"title":"Drill down to pods","url":"/d/85a562078cdf77779eaa1add43ccec1e/k8s-resources-namespace?${datasource:queryparam}&var-cluster=$cluster&var-namespace=${__data.fields.Namespace}"}]}]}]},"gridPos":{"h":6,"w":24,"x":0,"y":96},"id":22,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by(namespace) (rate(container_fs_reads_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]))","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by(namespace) (rate(container_fs_writes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]))","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by(namespace) (rate(container_fs_reads_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]) + rate(container_fs_writes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]))","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by(namespace) (rate(container_fs_reads_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]))","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by(namespace) (rate(container_fs_writes_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]))","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by(namespace) (rate(container_fs_reads_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]) + rate(container_fs_writes_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]))","format":"table","instant":true}],"title":"Current Storage IO","transformations":[{"id":"joinByField","options":{"byField":"namespace","mode":"outer"}},{"id":"organize","options":{"excludeByName":{"Time":true,"Time 1":true,"Time 2":true,"Time 3":true,"Time 4":true,"Time 5":true,"Time 6":true},"indexByName":{"Time 1":0,"Time 2":1,"Time 3":2,"Time 4":3,"Time 5":4,"Time 6":5,"Value #A":7,"Value #B":8,"Value #C":9,"Value #D":10,"Value #E":11,"Value #F":12,"namespace":6},"renameByName":{"Value #A":"IOPS(Reads)","Value #B":"IOPS(Writes)","Value #C":"IOPS(Reads + Writes)","Value #D":"Throughput(Read)","Value #E":"Throughput(Write)","Value #F":"Throughput(Read + Write)","namespace":"Namespace"}}}],"type":"table"}],"refresh":"10s","schemaVersion":39,"tags":["kubernetes-mixin"],"templating":{"list":[{"current":{"selected":true,"text":"default","value":"default"},"hide":0,"label":"Data source","name":"datasource","query":"prometheus","regex":"","type":"datasource"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":2,"label":"cluster","name":"cluster","query":"label_values(up{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\"}, cluster)","refresh":2,"sort":1,"type":"query","allValue":".*"}]},"time":{"from":"now-1h","to":"now"},"timezone": "utc","title":"Kubernetes / Compute Resources / Cluster","uid":"efa86fd1d0c121a26444b636a3f509a8"}
|
|
---
|
|
# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-resources-multicluster.yaml
|
|
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
namespace: default
|
|
name: kube-prometheus-stack-k8s-resources-multicluster
|
|
annotations:
|
|
{}
|
|
labels:
|
|
grafana_dashboard: "1"
|
|
#TBR: app: kube-prometheus-stack-grafana
|
|
app.kubernetes.io/name: kube-prometheus-stack-grafana #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
data:
|
|
k8s-resources-multicluster.json: |-
|
|
{"editable":true,"links":[{"asDropdown":true,"includeVars":true,"keepTime":true,"tags":["kubernetes-mixin"],"targetBlank":false,"title":"Kubernetes","type":"dashboards"}],"panels":[{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"none"}},"gridPos":{"h":3,"w":4,"x":0,"y":0},"id":1,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(cluster:node_cpu:ratio_rate5m) / count(cluster:node_cpu:ratio_rate5m)","instant":true}],"title":"CPU Utilisation","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"percentunit"}},"gridPos":{"h":3,"w":4,"x":4,"y":0},"id":2,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(kube_pod_container_resource_requests{job=\"kube-state-metrics\", resource=\"cpu\"}) / sum(kube_node_status_allocatable{job=\"kube-state-metrics\", resource=\"cpu\"})","instant":true}],"title":"CPU Requests Commitment","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"percentunit"}},"gridPos":{"h":3,"w":4,"x":8,"y":0},"id":3,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(kube_pod_container_resource_limits{job=\"kube-state-metrics\", resource=\"cpu\"}) / sum(kube_node_status_allocatable{job=\"kube-state-metrics\", resource=\"cpu\"})","instant":true}],"title":"CPU Limits Commitment","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"percentunit"}},"gridPos":{"h":3,"w":4,"x":12,"y":0},"id":4,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"1 - sum(:node_memory_MemAvailable_bytes:sum) / sum(node_memory_MemTotal_bytes{job=\"node-exporter\"})","instant":true}],"title":"Memory Utilisation","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"percentunit"}},"gridPos":{"h":3,"w":4,"x":16,"y":0},"id":5,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(kube_pod_container_resource_requests{job=\"kube-state-metrics\", resource=\"memory\"}) / sum(kube_node_status_allocatable{job=\"kube-state-metrics\", resource=\"memory\"})","instant":true}],"title":"Memory Requests Commitment","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"percentunit"}},"gridPos":{"h":3,"w":4,"x":20,"y":0},"id":6,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(kube_pod_container_resource_limits{job=\"kube-state-metrics\", resource=\"memory\"}) / sum(kube_node_status_allocatable{job=\"kube-state-metrics\", resource=\"memory\"})","instant":true}],"title":"Memory Limits Commitment","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"showPoints":"never"}}},"gridPos":{"h":7,"w":24,"x":0,"y":1},"id":7,"interval":"1m","options":{"legend":{"asTable":true,"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate) by (cluster)","legendFormat":"__auto"}],"title":"CPU Usage","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"overrides":[{"matcher":{"id":"byRegexp","options":"/%/"},"properties":[{"id":"unit","value":"percentunit"}]},{"matcher":{"id":"byName","options":"Cluster"},"properties":[{"id":"links","value":[{"title":"Drill down","url":"/d/efa86fd1d0c121a26444b636a3f509a8/kubernetes-compute-resources-cluster?${datasource:queryparam}&var-cluster=${__data.fields.Cluster}"}]}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":2},"id":8,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate) by (cluster)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(kube_pod_container_resource_requests{job=\"kube-state-metrics\", resource=\"cpu\"}) by (cluster)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate) by (cluster) / sum(kube_pod_container_resource_requests{job=\"kube-state-metrics\", resource=\"cpu\"}) by (cluster)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(kube_pod_container_resource_limits{job=\"kube-state-metrics\", resource=\"cpu\"}) by (cluster)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate) by (cluster) / sum(kube_pod_container_resource_limits{job=\"kube-state-metrics\", resource=\"cpu\"}) by (cluster)","format":"table","instant":true}],"title":"CPU Quota","transformations":[{"id":"joinByField","options":{"byField":"cluster","mode":"outer"}},{"id":"organize","options":{"excludeByName":{"Time":true,"Time 1":true,"Time 2":true,"Time 3":true,"Time 4":true,"Time 5":true},"indexByName":{"Time 1":0,"Time 2":1,"Time 3":2,"Time 4":3,"Time 5":4,"Value #A":6,"Value #B":7,"Value #C":8,"Value #D":9,"Value #E":10,"cluster":5},"renameByName":{"Value #A":"CPU Usage","Value #B":"CPU Requests","Value #C":"CPU Requests %","Value #D":"CPU Limits","Value #E":"CPU Limits %","cluster":"Cluster"}}}],"type":"table"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"showPoints":"never"},"unit":"bytes"}},"gridPos":{"h":7,"w":24,"x":0,"y":3},"id":9,"interval":"1m","options":{"legend":{"asTable":true,"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(container_memory_rss{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\"}) by (cluster)","legendFormat":"__auto"}],"title":"Memory Usage (w/o cache)","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"bytes"},"overrides":[{"matcher":{"id":"byRegexp","options":"/%/"},"properties":[{"id":"unit","value":"percentunit"}]},{"matcher":{"id":"byName","options":"Cluster"},"properties":[{"id":"links","value":[{"title":"Drill down","url":"/d/efa86fd1d0c121a26444b636a3f509a8/kubernetes-compute-resources-cluster?${datasource:queryparam}&var-cluster=${__data.fields.Cluster}"}]}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":4},"id":10,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(container_memory_rss{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\"}) by (cluster)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(kube_pod_container_resource_requests{job=\"kube-state-metrics\", resource=\"memory\"}) by (cluster)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(container_memory_rss{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\"}) by (cluster) / sum(kube_pod_container_resource_requests{job=\"kube-state-metrics\", resource=\"memory\"}) by (cluster)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(kube_pod_container_resource_limits{job=\"kube-state-metrics\", resource=\"memory\"}) by (cluster)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(container_memory_rss{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\"}) by (cluster) / sum(kube_pod_container_resource_limits{job=\"kube-state-metrics\", resource=\"memory\"}) by (cluster)","format":"table","instant":true}],"title":"Memory Requests by Cluster","transformations":[{"id":"joinByField","options":{"byField":"cluster","mode":"outer"}},{"id":"organize","options":{"excludeByName":{"Time":true,"Time 1":true,"Time 2":true,"Time 3":true,"Time 4":true,"Time 5":true},"indexByName":{"Time 1":0,"Time 2":1,"Time 3":2,"Time 4":3,"Time 5":4,"Value #A":6,"Value #B":7,"Value #C":8,"Value #D":9,"Value #E":10,"cluster":5},"renameByName":{"Value #A":"Memory Usage","Value #B":"Memory Requests","Value #C":"Memory Requests %","Value #D":"Memory Limits","Value #E":"Memory Limits %","cluster":"Cluster"}}}],"type":"table"}],"refresh":"10s","schemaVersion":39,"tags":["kubernetes-mixin"],"templating":{"list":[{"current":{"selected":true,"text":"default","value":"default"},"hide":0,"label":"Data source","name":"datasource","query":"prometheus","regex":"","type":"datasource"}]},"time":{"from":"now-1h","to":"now"},"timezone": "utc","title":"Kubernetes / Compute Resources / Multi-Cluster","uid":"b59e6c9f2fcbe2e16d77fc492374cc4f"}
|
|
---
|
|
# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-resources-namespace.yaml
|
|
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
namespace: default
|
|
name: kube-prometheus-stack-k8s-resources-namespace
|
|
annotations:
|
|
{}
|
|
labels:
|
|
grafana_dashboard: "1"
|
|
#TBR: app: kube-prometheus-stack-grafana
|
|
app.kubernetes.io/name: kube-prometheus-stack-grafana #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
data:
|
|
k8s-resources-namespace.json: |-
|
|
{"editable":true,"links":[{"asDropdown":true,"includeVars":true,"keepTime":true,"tags":["kubernetes-mixin"],"targetBlank":false,"title":"Kubernetes","type":"dashboards"}],"panels":[{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"percentunit"}},"gridPos":{"h":3,"w":6,"x":0,"y":0},"id":1,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}) / sum(kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"})","instant":true}],"title":"CPU Utilisation (from requests)","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"percentunit"}},"gridPos":{"h":3,"w":6,"x":6,"y":0},"id":2,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}) / sum(kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"})","instant":true}],"title":"CPU Utilisation (from limits)","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"percentunit"}},"gridPos":{"h":3,"w":6,"x":12,"y":0},"id":3,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) / sum(kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"})","instant":true}],"title":"Memory Utilisation (from requests)","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"percentunit"}},"gridPos":{"h":3,"w":6,"x":18,"y":0},"id":4,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) / sum(kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"})","instant":true}],"title":"Memory Utilisation (from limits)","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true}},"overrides":[{"matcher":{"id":"byFrameRefID","options":"B"},"properties":[{"id":"custom.lineStyle","value":{"fill":"dash"}},{"id":"custom.lineWidth","value":2},{"id":"color","value":{"fixedColor":"red","mode":"fixed"}}]},{"matcher":{"id":"byFrameRefID","options":"C"},"properties":[{"id":"custom.lineStyle","value":{"fill":"dash"}},{"id":"custom.lineWidth","value":2},{"id":"color","value":{"fixedColor":"orange","mode":"fixed"}}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":7},"id":5,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)","legendFormat":"__auto"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"scalar(max(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"requests.cpu\"}))","legendFormat":"quota - requests"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"scalar(max(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"limits.cpu\"}))","legendFormat":"quota - limits"}],"title":"CPU Usage","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"overrides":[{"matcher":{"id":"byRegexp","options":"/%/"},"properties":[{"id":"unit","value":"percentunit"}]},{"matcher":{"id":"byName","options":"Pod"},"properties":[{"id":"links","value":[{"title":"Drill down to pods","url":"/d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?${datasource:queryparam}&var-cluster=$cluster&var-namespace=$namespace&var-pod=${__data.fields.Pod}"}]}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":14},"id":6,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod) / sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod) / sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)","format":"table","instant":true}],"title":"CPU Quota","transformations":[{"id":"joinByField","options":{"byField":"pod","mode":"outer"}},{"id":"organize","options":{"excludeByName":{"Time":true,"Time 1":true,"Time 2":true,"Time 3":true,"Time 4":true,"Time 5":true},"indexByName":{"Time 1":0,"Time 2":1,"Time 3":2,"Time 4":3,"Time 5":4,"Value #A":6,"Value #B":7,"Value #C":8,"Value #D":9,"Value #E":10,"pod":5},"renameByName":{"Value #A":"CPU Usage","Value #B":"CPU Requests","Value #C":"CPU Requests %","Value #D":"CPU Limits","Value #E":"CPU Limits %","pod":"Pod"}}}],"type":"table"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"bytes"},"overrides":[{"matcher":{"id":"byFrameRefID","options":"B"},"properties":[{"id":"custom.lineStyle","value":{"fill":"dash"}},{"id":"custom.lineWidth","value":2},{"id":"color","value":{"fixedColor":"red","mode":"fixed"}}]},{"matcher":{"id":"byFrameRefID","options":"C"},"properties":[{"id":"custom.lineStyle","value":{"fill":"dash"}},{"id":"custom.lineWidth","value":2},{"id":"color","value":{"fixedColor":"orange","mode":"fixed"}}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":21},"id":7,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}) by (pod)","legendFormat":"__auto"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"scalar(max(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"requests.memory\"}))","legendFormat":"quota - requests"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"scalar(max(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"limits.memory\"}))","legendFormat":"quota - limits"}],"title":"Memory Usage (w/o cache)","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"bytes"},"overrides":[{"matcher":{"id":"byRegexp","options":"/%/"},"properties":[{"id":"unit","value":"percentunit"}]},{"matcher":{"id":"byName","options":"Pod"},"properties":[{"id":"links","value":[{"title":"Drill down to pods","url":"/d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?${datasource:queryparam}&var-cluster=$cluster&var-namespace=$namespace&var-pod=${__data.fields.Pod}"}]}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":28},"id":8,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) by (pod) / sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) by (pod) / sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(container_memory_rss{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\"}) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(container_memory_cache{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\"}) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(container_memory_swap{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\"}) by (pod)","format":"table","instant":true}],"title":"Memory Quota","transformations":[{"id":"joinByField","options":{"byField":"pod","mode":"outer"}},{"id":"organize","options":{"excludeByName":{"Time":true,"Time 1":true,"Time 2":true,"Time 3":true,"Time 4":true,"Time 5":true,"Time 6":true,"Time 7":true,"Time 8":true},"indexByName":{"Time 1":0,"Time 2":1,"Time 3":2,"Time 4":3,"Time 5":4,"Time 6":5,"Time 7":6,"Time 8":7,"Value #A":9,"Value #B":10,"Value #C":11,"Value #D":12,"Value #E":13,"Value #F":14,"Value #G":15,"Value #H":16,"pod":8},"renameByName":{"Value #A":"Memory Usage","Value #B":"Memory Requests","Value #C":"Memory Requests %","Value #D":"Memory Limits","Value #E":"Memory Limits %","Value #F":"Memory Usage (RSS)","Value #G":"Memory Usage (Cache)","Value #H":"Memory Usage (Swap)","pod":"Pod"}}}],"type":"table"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"overrides":[{"matcher":{"id":"byRegexp","options":"/Bandwidth/"},"properties":[{"id":"unit","value":"Bps"}]},{"matcher":{"id":"byRegexp","options":"/Packets/"},"properties":[{"id":"unit","value":"pps"}]},{"matcher":{"id":"byName","options":"Pod"},"properties":[{"id":"links","value":[{"title":"Drill down to pods","url":"/d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?${datasource:queryparam}&var-cluster=$cluster&var-namespace=$namespace&var-pod=${__data.fields.Pod}"}]}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":35},"id":9,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_receive_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_transmit_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_receive_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_transmit_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)","format":"table","instant":true}],"title":"Current Network Usage","transformations":[{"id":"joinByField","options":{"byField":"pod","mode":"outer"}},{"id":"organize","options":{"excludeByName":{"Time":true,"Time 1":true,"Time 2":true,"Time 3":true,"Time 4":true,"Time 5":true,"Time 6":true},"indexByName":{"Time 1":0,"Time 2":1,"Time 3":2,"Time 4":3,"Time 5":4,"Time 6":5,"Value #A":7,"Value #B":8,"Value #C":9,"Value #D":10,"Value #E":11,"Value #F":12,"pod":6},"renameByName":{"Value #A":"Current Receive Bandwidth","Value #B":"Current Transmit Bandwidth","Value #C":"Rate of Received Packets","Value #D":"Rate of Transmitted Packets","Value #E":"Rate of Received Packets Dropped","Value #F":"Rate of Transmitted Packets Dropped","pod":"Pod"}}}],"type":"table"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"Bps"}},"gridPos":{"h":7,"w":12,"x":0,"y":42},"id":10,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)","legendFormat":"__auto"}],"title":"Receive Bandwidth","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"Bps"}},"gridPos":{"h":7,"w":12,"x":12,"y":42},"id":11,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)","legendFormat":"__auto"}],"title":"Transmit Bandwidth","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"pps"}},"gridPos":{"h":7,"w":12,"x":0,"y":49},"id":12,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)","legendFormat":"__auto"}],"title":"Rate of Received Packets","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"pps"}},"gridPos":{"h":7,"w":12,"x":12,"y":49},"id":13,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)","legendFormat":"__auto"}],"title":"Rate of Transmitted Packets","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"pps"}},"gridPos":{"h":7,"w":12,"x":0,"y":56},"id":14,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)","legendFormat":"__auto"}],"title":"Rate of Received Packets Dropped","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"pps"}},"gridPos":{"h":7,"w":12,"x":12,"y":56},"id":15,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)","legendFormat":"__auto"}],"title":"Rate of Transmitted Packets Dropped","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"iops"}},"gridPos":{"h":7,"w":12,"x":0,"y":63},"id":16,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"ceil(sum by(pod) (rate(container_fs_reads_total{container!=\"\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]) + rate(container_fs_writes_total{container!=\"\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])))","legendFormat":"__auto"}],"title":"IOPS(Reads+Writes)","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"Bps"}},"gridPos":{"h":7,"w":12,"x":12,"y":63},"id":17,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by(pod) (rate(container_fs_reads_bytes_total{container!=\"\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]) + rate(container_fs_writes_bytes_total{container!=\"\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]))","legendFormat":"__auto"}],"title":"ThroughPut(Read+Write)","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"overrides":[{"matcher":{"id":"byRegexp","options":"/IOPS/"},"properties":[{"id":"unit","value":"iops"}]},{"matcher":{"id":"byRegexp","options":"/Throughput/"},"properties":[{"id":"unit","value":"Bps"}]},{"matcher":{"id":"byName","options":"Pod"},"properties":[{"id":"links","value":[{"title":"Drill down to pods","url":"/d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?${datasource:queryparam}&var-cluster=$cluster&var-namespace=$namespace&var-pod=${__data.fields.Pod}"}]}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":70},"id":18,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by(pod) (rate(container_fs_reads_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]))","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by(pod) (rate(container_fs_writes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]))","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by(pod) (rate(container_fs_reads_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]) + rate(container_fs_writes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]))","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by(pod) (rate(container_fs_reads_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]))","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by(pod) (rate(container_fs_writes_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]))","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by(pod) (rate(container_fs_reads_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]) + rate(container_fs_writes_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]))","format":"table","instant":true}],"title":"Current Storage IO","transformations":[{"id":"joinByField","options":{"byField":"pod","mode":"outer"}},{"id":"organize","options":{"excludeByName":{"Time":true,"Time 1":true,"Time 2":true,"Time 3":true,"Time 4":true,"Time 5":true,"Time 6":true},"indexByName":{"Time 1":0,"Time 2":1,"Time 3":2,"Time 4":3,"Time 5":4,"Time 6":5,"Value #A":7,"Value #B":8,"Value #C":9,"Value #D":10,"Value #E":11,"Value #F":12,"pod":6},"renameByName":{"Value #A":"IOPS(Reads)","Value #B":"IOPS(Writes)","Value #C":"IOPS(Reads + Writes)","Value #D":"Throughput(Read)","Value #E":"Throughput(Write)","Value #F":"Throughput(Read + Write)","pod":"Pod"}}}],"type":"table"}],"refresh":"10s","schemaVersion":39,"tags":["kubernetes-mixin"],"templating":{"list":[{"current":{"selected":true,"text":"default","value":"default"},"hide":0,"label":"Data source","name":"datasource","query":"prometheus","regex":"","type":"datasource"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":2,"label":"cluster","name":"cluster","query":"label_values(up{job=\"kube-state-metrics\"}, cluster)","refresh":2,"sort":1,"type":"query","allValue":".*"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":0,"label":"namespace","name":"namespace","query":"label_values(kube_namespace_status_phase{job=\"kube-state-metrics\", cluster=\"$cluster\"}, namespace)","refresh":2,"sort":1,"type":"query"}]},"time":{"from":"now-1h","to":"now"},"timezone": "utc","title":"Kubernetes / Compute Resources / Namespace (Pods)","uid":"85a562078cdf77779eaa1add43ccec1e"}
|
|
---
|
|
# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-resources-node.yaml
|
|
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
namespace: default
|
|
name: kube-prometheus-stack-k8s-resources-node
|
|
annotations:
|
|
{}
|
|
labels:
|
|
grafana_dashboard: "1"
|
|
#TBR: app: kube-prometheus-stack-grafana
|
|
app.kubernetes.io/name: kube-prometheus-stack-grafana #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
data:
|
|
k8s-resources-node.json: |-
|
|
{"editable":true,"links":[{"asDropdown":true,"includeVars":true,"keepTime":true,"tags":["kubernetes-mixin"],"targetBlank":false,"title":"Kubernetes","type":"dashboards"}],"panels":[{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true,"stacking":{"mode":"normal"}}},"overrides":[{"matcher":{"id":"byName","options":"max capacity"},"properties":[{"id":"color","value":{"fixedColor":"red","mode":"fixed"}},{"id":"custom.stacking","value":{"mode":"none"}},{"id":"custom.hideFrom","value":{"legend":false,"tooltip":true,"viz":false}},{"id":"custom.lineStyle","value":{"dash":[10,10],"fill":"dash"}}]}]},"gridPos":{"h":6,"w":24,"x":0,"y":0},"id":1,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(kube_node_status_capacity{cluster=\"$cluster\", job=\"kube-state-metrics\", node=~\"$node\", resource=\"cpu\"})","legendFormat":"max capacity"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", node=~\"$node\"}) by (pod)","legendFormat":"{{pod}}"}],"title":"CPU Usage","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"overrides":[{"matcher":{"id":"byRegexp","options":"/%/"},"properties":[{"id":"unit","value":"percentunit"}]},{"matcher":{"id":"byName","options":"Pod"},"properties":[{"id":"links","value":[{"title":"Drill down to pods","url":"/d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?${datasource:queryparam}&var-cluster=$cluster&var-namespace=$namespace&var-pod=${__data.fields.Pod}"}]}]}]},"gridPos":{"h":6,"w":24,"x":0,"y":6},"id":2,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", node=~\"$node\"}) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests{cluster=\"$cluster\", node=~\"$node\"}) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", node=~\"$node\"}) by (pod) / sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests{cluster=\"$cluster\", node=~\"$node\"}) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits{cluster=\"$cluster\", node=~\"$node\"}) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", node=~\"$node\"}) by (pod) / sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits{cluster=\"$cluster\", node=~\"$node\"}) by (pod)","format":"table","instant":true}],"title":"CPU Quota","transformations":[{"id":"joinByField","options":{"byField":"pod","mode":"outer"}},{"id":"organize","options":{"excludeByName":{"Time":true,"Time 1":true,"Time 2":true,"Time 3":true,"Time 4":true,"Time 5":true},"renameByName":{"Value #A":"CPU Usage","Value #B":"CPU Requests","Value #C":"CPU Requests %","Value #D":"CPU Limits","Value #E":"CPU Limits %","pod":"Pod"}}}],"type":"table"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true,"stacking":{"mode":"normal"}},"unit":"bytes"},"overrides":[{"matcher":{"id":"byName","options":"max capacity"},"properties":[{"id":"color","value":{"fixedColor":"red","mode":"fixed"}},{"id":"custom.stacking","value":{"mode":"none"}},{"id":"custom.hideFrom","value":{"legend":false,"tooltip":true,"viz":false}},{"id":"custom.lineStyle","value":{"dash":[10,10],"fill":"dash"}}]}]},"gridPos":{"h":6,"w":24,"x":0,"y":12},"id":3,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(kube_node_status_capacity{cluster=\"$cluster\", job=\"kube-state-metrics\", node=~\"$node\", resource=\"memory\"})","legendFormat":"max capacity"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=~\"$node\", container!=\"\"}) by (pod)","legendFormat":"{{pod}}"}],"title":"Memory Usage (w/cache)","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true,"stacking":{"mode":"normal"}},"unit":"bytes"},"overrides":[{"matcher":{"id":"byName","options":"max capacity"},"properties":[{"id":"color","value":{"fixedColor":"red","mode":"fixed"}},{"id":"custom.stacking","value":{"mode":"none"}},{"id":"custom.hideFrom","value":{"legend":false,"tooltip":true,"viz":false}},{"id":"custom.lineStyle","value":{"dash":[10,10],"fill":"dash"}}]}]},"gridPos":{"h":6,"w":24,"x":0,"y":18},"id":4,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(kube_node_status_capacity{cluster=\"$cluster\", job=\"kube-state-metrics\", node=~\"$node\", resource=\"memory\"})","legendFormat":"max capacity"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_memory_rss{cluster=\"$cluster\", node=~\"$node\", container!=\"\"}) by (pod)","legendFormat":"{{pod}}"}],"title":"Memory Usage (w/o cache)","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"bytes"},"overrides":[{"matcher":{"id":"byRegexp","options":"/%/"},"properties":[{"id":"unit","value":"percentunit"}]},{"matcher":{"id":"byName","options":"Pod"},"properties":[{"id":"links","value":[{"title":"Drill down to pods","url":"/d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?${datasource:queryparam}&var-cluster=$cluster&var-namespace=$namespace&var-pod=${__data.fields.Pod}"}]}]}]},"gridPos":{"h":6,"w":24,"x":0,"y":24},"id":5,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_requests{cluster=\"$cluster\", node=~\"$node\"}) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod) / sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_requests{cluster=\"$cluster\", node=~\"$node\"}) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_limits{cluster=\"$cluster\", node=~\"$node\"}) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod) / sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_limits{cluster=\"$cluster\", node=~\"$node\"}) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_memory_rss{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_memory_cache{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_memory_swap{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod)","format":"table","instant":true}],"title":"Memory Quota","transformations":[{"id":"joinByField","options":{"byField":"pod","mode":"outer"}},{"id":"organize","options":{"excludeByName":{"Time":true,"Time 1":true,"Time 2":true,"Time 3":true,"Time 4":true,"Time 5":true,"Time 6":true,"Time 7":true,"Time 8":true},"renameByName":{"Value #A":"Memory Usage","Value #B":"Memory Requests","Value #C":"Memory Requests %","Value #D":"Memory Limits","Value #E":"Memory Limits %","Value #F":"Memory Usage (RSS)","Value #G":"Memory Usage (Cache)","Value #H":"Memory Usage (Swap)","pod":"Pod"}}}],"type":"table"}],"refresh":"10s","schemaVersion":39,"tags":["kubernetes-mixin"],"templating":{"list":[{"current":{"selected":true,"text":"default","value":"default"},"hide":0,"label":"Data source","name":"datasource","query":"prometheus","regex":"","type":"datasource"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":2,"label":"cluster","name":"cluster","query":"label_values(up{job=\"kube-state-metrics\"}, cluster)","refresh":2,"sort":1,"type":"query","allValue":".*"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":0,"label":"node","multi":true,"name":"node","query":"label_values(kube_node_info{cluster=\"$cluster\"}, node)","refresh":2,"type":"query"}]},"time":{"from":"now-1h","to":"now"},"timezone": "utc","title":"Kubernetes / Compute Resources / Node (Pods)","uid":"200ac8fdbfbb74b39aff88118e4d1c2c"}
|
|
---
|
|
# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-resources-pod.yaml
|
|
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
namespace: default
|
|
name: kube-prometheus-stack-k8s-resources-pod
|
|
annotations:
|
|
{}
|
|
labels:
|
|
grafana_dashboard: "1"
|
|
#TBR: app: kube-prometheus-stack-grafana
|
|
app.kubernetes.io/name: kube-prometheus-stack-grafana #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
data:
|
|
k8s-resources-pod.json: |-
|
|
{"editable":true,"links":[{"asDropdown":true,"includeVars":true,"keepTime":true,"tags":["kubernetes-mixin"],"targetBlank":false,"title":"Kubernetes","type":"dashboards"}],"panels":[{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true}},"overrides":[{"matcher":{"id":"byFrameRefID","options":"B"},"properties":[{"id":"custom.lineStyle","value":{"fill":"dash"}},{"id":"custom.lineWidth","value":2},{"id":"color","value":{"fixedColor":"red","mode":"fixed"}}]},{"matcher":{"id":"byFrameRefID","options":"C"},"properties":[{"id":"custom.lineStyle","value":{"fill":"dash"}},{"id":"custom.lineWidth","value":2},{"id":"color","value":{"fixedColor":"orange","mode":"fixed"}}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":0},"id":1,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{namespace=\"$namespace\", pod=\"$pod\", cluster=\"$cluster\", container!=\"\"}) by (container)","legendFormat":"__auto"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"cpu\"}\n)\n","legendFormat":"requests"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"cpu\"}\n)\n","legendFormat":"limits"}],"title":"CPU Usage","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"axisColorMode":"thresholds","axisSoftMax":1,"axisSoftMin":0,"fillOpacity":10,"showPoints":"never","spanNulls":true,"thresholdsStyle":{"mode":"dashed+area"}},"unit":"percentunit"},"overrides":[{"matcher":{"id":"byFrameRefID","options":"A"},"properties":[{"id":"thresholds","value":{"mode":"absolute","steps":[{"color":"green","value":null},{"color":"red","value":0.25}]}},{"id":"color","value":{"mode":"thresholds","seriesBy":"lastNotNull"}}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":7},"id":2,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(increase(container_cpu_cfs_throttled_periods_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\", cluster=\"$cluster\"}[$__rate_interval])) by (container) /sum(increase(container_cpu_cfs_periods_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\", cluster=\"$cluster\"}[$__rate_interval])) by (container)","legendFormat":"__auto"}],"title":"CPU Throttling","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"overrides":[{"matcher":{"id":"byRegexp","options":"/%/"},"properties":[{"id":"unit","value":"percentunit"}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":14},"id":3,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\"}) by (container)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\"}) by (container)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\"}) by (container) / sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\"}) by (container)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\"}) by (container)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\"}) by (container) / sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\"}) by (container)","format":"table","instant":true}],"title":"CPU Quota","transformations":[{"id":"joinByField","options":{"byField":"container","mode":"outer"}},{"id":"organize","options":{"excludeByName":{"Time":true,"Time 1":true,"Time 2":true,"Time 3":true,"Time 4":true,"Time 5":true},"indexByName":{"Time 1":0,"Time 2":1,"Time 3":2,"Time 4":3,"Time 5":4,"Value #A":6,"Value #B":7,"Value #C":8,"Value #D":9,"Value #E":10,"container":5},"renameByName":{"Value #A":"CPU Usage","Value #B":"CPU Requests","Value #C":"CPU Requests %","Value #D":"CPU Limits","Value #E":"CPU Limits %","container":"Container"}}}],"type":"table"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"bytes"},"overrides":[{"matcher":{"id":"byFrameRefID","options":"B"},"properties":[{"id":"custom.lineStyle","value":{"fill":"dash"}},{"id":"custom.lineWidth","value":2},{"id":"color","value":{"fixedColor":"red","mode":"fixed"}}]},{"matcher":{"id":"byFrameRefID","options":"C"},"properties":[{"id":"custom.lineStyle","value":{"fill":"dash"}},{"id":"custom.lineWidth","value":2},{"id":"color","value":{"fixedColor":"orange","mode":"fixed"}}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":21},"id":4,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\", image!=\"\"}) by (container)","legendFormat":"__auto"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"memory\"}\n)\n","legendFormat":"requests"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"memory\"}\n)\n","legendFormat":"limits"}],"title":"Memory Usage (WSS)","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"bytes"},"overrides":[{"matcher":{"id":"byRegexp","options":"/%/"},"properties":[{"id":"unit","value":"percentunit"}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":28},"id":5,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\", image!=\"\"}) by (container)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", image!=\"\"}) by (container) / sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\", image!=\"\"}) by (container) / sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(container_memory_rss{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container != \"\", container != \"POD\"}) by (container)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(container_memory_cache{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container != \"\", container != \"POD\"}) by (container)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(container_memory_swap{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container != \"\", container != \"POD\"}) by (container)","format":"table","instant":true}],"title":"Memory Quota","transformations":[{"id":"joinByField","options":{"byField":"container","mode":"outer"}},{"id":"organize","options":{"excludeByName":{"Time":true,"Time 1":true,"Time 2":true,"Time 3":true,"Time 4":true,"Time 5":true,"Time 6":true,"Time 7":true,"Time 8":true},"indexByName":{"Time 1":0,"Time 2":1,"Time 3":2,"Time 4":3,"Time 5":4,"Time 6":5,"Time 7":6,"Time 8":7,"Value #A":9,"Value #B":10,"Value #C":11,"Value #D":12,"Value #E":13,"Value #F":14,"Value #G":15,"Value #H":16,"container":8},"renameByName":{"Value #A":"Memory Usage","Value #B":"Memory Requests","Value #C":"Memory Requests %","Value #D":"Memory Limits","Value #E":"Memory Limits %","Value #F":"Memory Usage (RSS)","Value #G":"Memory Usage (Cache)","Value #H":"Memory Usage (Swap)","container":"Container"}}}],"type":"table"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"Bps"}},"gridPos":{"h":7,"w":12,"x":0,"y":35},"id":6,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(irate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)","legendFormat":"__auto"}],"title":"Receive Bandwidth","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"Bps"}},"gridPos":{"h":7,"w":12,"x":12,"y":35},"id":7,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)","legendFormat":"__auto"}],"title":"Transmit Bandwidth","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"pps"}},"gridPos":{"h":7,"w":12,"x":0,"y":42},"id":8,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_receive_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)","legendFormat":"__auto"}],"title":"Rate of Received Packets","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"pps"}},"gridPos":{"h":7,"w":12,"x":12,"y":42},"id":9,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_transmit_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)","legendFormat":"__auto"}],"title":"Rate of Transmitted Packets","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"pps"}},"gridPos":{"h":7,"w":12,"x":0,"y":49},"id":10,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_receive_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)","legendFormat":"__auto"}],"title":"Rate of Received Packets Dropped","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"pps"}},"gridPos":{"h":7,"w":12,"x":12,"y":49},"id":11,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_transmit_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)","legendFormat":"__auto"}],"title":"Rate of Transmitted Packets Dropped","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"iops"}},"gridPos":{"h":7,"w":12,"x":0,"y":56},"id":12,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"ceil(sum by(pod) (rate(container_fs_reads_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])))","legendFormat":"Reads"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"ceil(sum by(pod) (rate(container_fs_writes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\",namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])))","legendFormat":"Writes"}],"title":"IOPS (Pod)","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"Bps"}},"gridPos":{"h":7,"w":12,"x":12,"y":56},"id":13,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by(pod) (rate(container_fs_reads_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval]))","legendFormat":"Reads"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by(pod) (rate(container_fs_writes_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval]))","legendFormat":"Writes"}],"title":"ThroughPut (Pod)","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"iops"}},"gridPos":{"h":7,"w":12,"x":0,"y":63},"id":14,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"ceil(sum by(container) (rate(container_fs_reads_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]) + rate(container_fs_writes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval])))","legendFormat":"__auto"}],"title":"IOPS (Containers)","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"Bps"}},"gridPos":{"h":7,"w":12,"x":12,"y":63},"id":15,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by(container) (rate(container_fs_reads_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]) + rate(container_fs_writes_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]))","legendFormat":"__auto"}],"title":"ThroughPut (Containers)","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"overrides":[{"matcher":{"id":"byRegexp","options":"/IOPS/"},"properties":[{"id":"unit","value":"iops"}]},{"matcher":{"id":"byRegexp","options":"/Throughput/"},"properties":[{"id":"unit","value":"Bps"}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":70},"id":16,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by(container) (rate(container_fs_reads_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]))","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by(container) (rate(container_fs_writes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\",device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]))","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by(container) (rate(container_fs_reads_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]) + rate(container_fs_writes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]))","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by(container) (rate(container_fs_reads_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]))","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by(container) (rate(container_fs_writes_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]))","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by(container) (rate(container_fs_reads_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]) + rate(container_fs_writes_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]))","format":"table","instant":true}],"title":"Current Storage IO","transformations":[{"id":"joinByField","options":{"byField":"container","mode":"outer"}},{"id":"organize","options":{"excludeByName":{"Time":true,"Time 1":true,"Time 2":true,"Time 3":true,"Time 4":true,"Time 5":true,"Time 6":true},"indexByName":{"Time 1":0,"Time 2":1,"Time 3":2,"Time 4":3,"Time 5":4,"Time 6":5,"Value #A":7,"Value #B":8,"Value #C":9,"Value #D":10,"Value #E":11,"Value #F":12,"container":6},"renameByName":{"Value #A":"IOPS(Reads)","Value #B":"IOPS(Writes)","Value #C":"IOPS(Reads + Writes)","Value #D":"Throughput(Read)","Value #E":"Throughput(Write)","Value #F":"Throughput(Read + Write)","container":"Container"}}}],"type":"table"}],"refresh":"10s","schemaVersion":39,"tags":["kubernetes-mixin"],"templating":{"list":[{"current":{"selected":true,"text":"default","value":"default"},"hide":0,"label":"Data source","name":"datasource","query":"prometheus","regex":"","type":"datasource"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":2,"label":"cluster","name":"cluster","query":"label_values(up{job=\"kube-state-metrics\"}, cluster)","refresh":2,"sort":1,"type":"query","allValue":".*"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":0,"label":"namespace","name":"namespace","query":"label_values(kube_namespace_status_phase{job=\"kube-state-metrics\", cluster=\"$cluster\"}, namespace)","refresh":2,"sort":1,"type":"query"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":0,"label":"pod","name":"pod","query":"label_values(kube_pod_info{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\"}, pod)","refresh":2,"sort":1,"type":"query"}]},"time":{"from":"now-1h","to":"now"},"timezone": "utc","title":"Kubernetes / Compute Resources / Pod","uid":"6581e46e4e5c7ba40a07646395ef7b23"}
|
|
---
|
|
# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-resources-workload.yaml
|
|
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
namespace: default
|
|
name: kube-prometheus-stack-k8s-resources-workload
|
|
annotations:
|
|
{}
|
|
labels:
|
|
grafana_dashboard: "1"
|
|
#TBR: app: kube-prometheus-stack-grafana
|
|
app.kubernetes.io/name: kube-prometheus-stack-grafana #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
data:
|
|
k8s-resources-workload.json: |-
|
|
{"editable":true,"links":[{"asDropdown":true,"includeVars":true,"keepTime":true,"tags":["kubernetes-mixin"],"targetBlank":false,"title":"Kubernetes","type":"dashboards"}],"panels":[{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true}}},"gridPos":{"h":7,"w":24,"x":0,"y":0},"id":1,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n","legendFormat":"__auto"}],"title":"CPU Usage","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"overrides":[{"matcher":{"id":"byRegexp","options":"/%/"},"properties":[{"id":"unit","value":"percentunit"}]},{"matcher":{"id":"byName","options":"Pod"},"properties":[{"id":"links","value":[{"title":"Drill down to pods","url":"/d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?${datasource:queryparam}&var-cluster=$cluster&var-namespace=$namespace&var-pod=${__data.fields.Pod}"}]}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":7},"id":2,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n","format":"table","instant":true}],"title":"CPU Quota","transformations":[{"id":"joinByField","options":{"byField":"pod","mode":"outer"}},{"id":"organize","options":{"excludeByName":{"Time":true,"Time 1":true,"Time 2":true,"Time 3":true,"Time 4":true,"Time 5":true},"indexByName":{"Time 1":0,"Time 2":1,"Time 3":2,"Time 4":3,"Time 5":4,"Value #A":6,"Value #B":7,"Value #C":8,"Value #D":9,"Value #E":10,"pod":5},"renameByName":{"Value #A":"CPU Usage","Value #B":"CPU Requests","Value #C":"CPU Requests %","Value #D":"CPU Limits","Value #E":"CPU Limits %","pod":"Pod"}}}],"type":"table"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"bytes"}},"gridPos":{"h":7,"w":24,"x":0,"y":14},"id":3,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n","legendFormat":"__auto"}],"title":"Memory Usage","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"bytes"},"overrides":[{"matcher":{"id":"byRegexp","options":"/%/"},"properties":[{"id":"unit","value":"percentunit"}]},{"matcher":{"id":"byName","options":"Pod"},"properties":[{"id":"links","value":[{"title":"Drill down to pods","url":"/d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?${datasource:queryparam}&var-cluster=$cluster&var-namespace=$namespace&var-pod=${__data.fields.Pod}"}]}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":21},"id":4,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n","format":"table","instant":true}],"title":"Memory Quota","transformations":[{"id":"joinByField","options":{"byField":"pod","mode":"outer"}},{"id":"organize","options":{"excludeByName":{"Time":true,"Time 1":true,"Time 2":true,"Time 3":true,"Time 4":true,"Time 5":true},"indexByName":{"Time 1":0,"Time 2":1,"Time 3":2,"Time 4":3,"Time 5":4,"Value #A":9,"Value #B":10,"Value #C":11,"Value #D":12,"Value #E":13,"pod":8},"renameByName":{"Value #A":"Memory Usage","Value #B":"Memory Requests","Value #C":"Memory Requests %","Value #D":"Memory Limits","Value #E":"Memory Limits %","pod":"Pod"}}}],"type":"table"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"overrides":[{"matcher":{"id":"byRegexp","options":"/Bandwidth/"},"properties":[{"id":"unit","value":"Bps"}]},{"matcher":{"id":"byRegexp","options":"/Packets/"},"properties":[{"id":"unit","value":"pps"}]},{"matcher":{"id":"byName","options":"Pod"},"properties":[{"id":"links","value":[{"title":"Drill down to pods","url":"/d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?${datasource:queryparam}&var-cluster=$cluster&var-namespace=$namespace&var-pod=${__data.fields.Pod}"}]}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":28},"id":5,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(sum(rate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(sum(rate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(sum(rate(container_network_receive_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(sum(rate(container_network_transmit_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(sum(rate(container_network_receive_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(sum(rate(container_network_transmit_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","format":"table","instant":true}],"title":"Current Network Usage","transformations":[{"id":"joinByField","options":{"byField":"pod","mode":"outer"}},{"id":"organize","options":{"excludeByName":{"Time":true,"Time 1":true,"Time 2":true,"Time 3":true,"Time 4":true,"Time 5":true,"Time 6":true},"indexByName":{"Time 1":0,"Time 2":1,"Time 3":2,"Time 4":3,"Time 5":4,"Time 6":5,"Value #A":7,"Value #B":8,"Value #C":9,"Value #D":10,"Value #E":11,"Value #F":12,"pod":6},"renameByName":{"Value #A":"Current Receive Bandwidth","Value #B":"Current Transmit Bandwidth","Value #C":"Rate of Received Packets","Value #D":"Rate of Transmitted Packets","Value #E":"Rate of Received Packets Dropped","Value #F":"Rate of Transmitted Packets Dropped","pod":"Pod"}}}],"type":"table"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"Bps"}},"gridPos":{"h":7,"w":12,"x":0,"y":35},"id":6,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(sum(rate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","legendFormat":"__auto"}],"title":"Receive Bandwidth","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"Bps"}},"gridPos":{"h":7,"w":12,"x":12,"y":35},"id":7,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(sum(rate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","legendFormat":"__auto"}],"title":"Transmit Bandwidth","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"Bps"}},"gridPos":{"h":7,"w":12,"x":0,"y":42},"id":8,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(avg(rate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","legendFormat":"__auto"}],"title":"Average Container Bandwidth by Pod: Received","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"Bps"}},"gridPos":{"h":7,"w":12,"x":12,"y":42},"id":9,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(avg(rate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","legendFormat":"__auto"}],"title":"Average Container Bandwidth by Pod: Transmitted","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"pps"}},"gridPos":{"h":7,"w":12,"x":0,"y":49},"id":10,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(sum(rate(container_network_receive_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","legendFormat":"__auto"}],"title":"Rate of Received Packets","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"pps"}},"gridPos":{"h":7,"w":12,"x":12,"y":49},"id":11,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(sum(rate(container_network_transmit_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","legendFormat":"__auto"}],"title":"Rate of Transmitted Packets","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"pps"}},"gridPos":{"h":7,"w":12,"x":0,"y":56},"id":12,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(sum(rate(container_network_receive_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","legendFormat":"__auto"}],"title":"Rate of Received Packets Dropped","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"pps"}},"gridPos":{"h":7,"w":12,"x":12,"y":56},"id":13,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(sum(rate(container_network_transmit_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","legendFormat":"__auto"}],"title":"Rate of Transmitted Packets Dropped","type":"timeseries"}],"refresh":"10s","schemaVersion":39,"tags":["kubernetes-mixin"],"templating":{"list":[{"current":{"selected":true,"text":"default","value":"default"},"hide":0,"label":"Data source","name":"datasource","query":"prometheus","regex":"","type":"datasource"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":2,"label":"cluster","name":"cluster","query":"label_values(up{job=\"kube-state-metrics\"}, cluster)","refresh":2,"sort":1,"type":"query","allValue":".*"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":0,"label":"namespace","name":"namespace","query":"label_values(kube_namespace_status_phase{job=\"kube-state-metrics\", cluster=\"$cluster\"}, namespace)","refresh":2,"sort":1,"type":"query"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":0,"includeAll":true,"label":"workload_type","name":"type","query":"label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\"}, workload_type)","refresh":2,"sort":1,"type":"query"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":0,"label":"workload","name":"workload","query":"label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}, workload)","refresh":2,"sort":1,"type":"query"}]},"time":{"from":"now-1h","to":"now"},"timezone": "utc","title":"Kubernetes / Compute Resources / Workload","uid":"a164a7f0339f99e89cea5cb47e9be617"}
|
|
---
|
|
# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-resources-workloads-namespace.yaml
|
|
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
namespace: default
|
|
name: kube-prometheus-stack-k8s-resources-workloads-namespace
|
|
annotations:
|
|
{}
|
|
labels:
|
|
grafana_dashboard: "1"
|
|
#TBR: app: kube-prometheus-stack-grafana
|
|
app.kubernetes.io/name: kube-prometheus-stack-grafana #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
data:
|
|
k8s-resources-workloads-namespace.json: |-
|
|
{"editable":true,"links":[{"asDropdown":true,"includeVars":true,"keepTime":true,"tags":["kubernetes-mixin"],"targetBlank":false,"title":"Kubernetes","type":"dashboards"}],"panels":[{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true}},"overrides":[{"matcher":{"id":"byFrameRefID","options":"B"},"properties":[{"id":"custom.lineStyle","value":{"fill":"dash"}},{"id":"custom.lineWidth","value":2},{"id":"color","value":{"fixedColor":"red","mode":"fixed"}}]},{"matcher":{"id":"byFrameRefID","options":"C"},"properties":[{"id":"custom.lineStyle","value":{"fill":"dash"}},{"id":"custom.lineWidth","value":2},{"id":"color","value":{"fixedColor":"orange","mode":"fixed"}}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":0},"id":1,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n","legendFormat":"{{workload}} - {{workload_type}}"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"scalar(max(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=~\"requests.cpu|cpu\"}))","legendFormat":"quota - requests"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"scalar(max(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=~\"limits.cpu\"}))","legendFormat":"quota - limits"}],"title":"CPU Usage","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"overrides":[{"matcher":{"id":"byRegexp","options":"/%/"},"properties":[{"id":"unit","value":"percentunit"}]},{"matcher":{"id":"byName","options":"Workload"},"properties":[{"id":"links","value":[{"title":"Drill down to workloads","url":"/d/a164a7f0339f99e89cea5cb47e9be617/k8s-resources-workload?${datasource:queryparam}&var-cluster=$cluster&var-namespace=$namespace&var-type=${__data.fields.Type}&var-workload=${__data.fields.Workload}"}]}]},{"matcher":{"id":"byName","options":"Running Pods"},"properties":[{"id":"unit","value":"none"}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":7},"id":2,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"count(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}) by (workload, workload_type)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n","format":"table","instant":true}],"title":"CPU Quota","transformations":[{"id":"joinByField","options":{"byField":"workload","mode":"outer"}},{"id":"organize","options":{"excludeByName":{"Time":true,"Time 1":true,"Time 2":true,"Time 3":true,"Time 4":true,"Time 5":true,"Time 6":true,"workload_type 2":true,"workload_type 3":true,"workload_type 4":true,"workload_type 5":true,"workload_type 6":true},"indexByName":{"Time 1":0,"Time 2":1,"Time 3":2,"Time 4":3,"Time 5":4,"Time 6":5,"Value #A":8,"Value #B":9,"Value #C":10,"Value #D":11,"Value #E":12,"Value #F":13,"workload":6,"workload_type 1":7,"workload_type 2":14,"workload_type 3":15,"workload_type 4":16,"workload_type 5":17,"workload_type 6":18},"renameByName":{"Value #A":"Running Pods","Value #B":"CPU Usage","Value #C":"CPU Requests","Value #D":"CPU Requests %","Value #E":"CPU Limits","Value #F":"CPU Limits %","workload":"Workload","workload_type 1":"Type"}}}],"type":"table"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"bytes"},"overrides":[{"matcher":{"id":"byFrameRefID","options":"B"},"properties":[{"id":"custom.lineStyle","value":{"fill":"dash"}},{"id":"custom.lineWidth","value":2},{"id":"color","value":{"fixedColor":"red","mode":"fixed"}}]},{"matcher":{"id":"byFrameRefID","options":"C"},"properties":[{"id":"custom.lineStyle","value":{"fill":"dash"}},{"id":"custom.lineWidth","value":2},{"id":"color","value":{"fixedColor":"orange","mode":"fixed"}}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":14},"id":3,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n","legendFormat":"{{workload}} - {{workload_type}}"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"scalar(max(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=~\"requests.memory|memory\"}))","legendFormat":"quota - requests"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"scalar(max(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=~\"limits.memory\"}))","legendFormat":"quota - limits"}],"title":"Memory Usage","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"bytes"},"overrides":[{"matcher":{"id":"byRegexp","options":"/%/"},"properties":[{"id":"unit","value":"percentunit"}]},{"matcher":{"id":"byName","options":"Workload"},"properties":[{"id":"links","value":[{"title":"Drill down to workloads","url":"/d/a164a7f0339f99e89cea5cb47e9be617/k8s-resources-workload?${datasource:queryparam}&var-cluster=$cluster&var-namespace=$namespace&var-type=${__data.fields.Type}&var-workload=${__data.fields.Workload}"}]}]},{"matcher":{"id":"byName","options":"Running Pods"},"properties":[{"id":"unit","value":"none"}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":21},"id":4,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"count(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}) by (workload, workload_type)","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(\n container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n","format":"table","instant":true}],"title":"Memory Quota","transformations":[{"id":"joinByField","options":{"byField":"workload","mode":"outer"}},{"id":"organize","options":{"excludeByName":{"Time":true,"Time 1":true,"Time 2":true,"Time 3":true,"Time 4":true,"Time 5":true,"Time 6":true,"workload_type 2":true,"workload_type 3":true,"workload_type 4":true,"workload_type 5":true,"workload_type 6":true},"indexByName":{"Time 1":0,"Time 2":1,"Time 3":2,"Time 4":3,"Time 5":4,"Time 6":5,"Value #A":8,"Value #B":9,"Value #C":10,"Value #D":11,"Value #E":12,"Value #F":13,"workload":6,"workload_type 1":7,"workload_type 2":14,"workload_type 3":15,"workload_type 4":16,"workload_type 5":17,"workload_type 6":18},"renameByName":{"Value #A":"Running Pods","Value #B":"Memory Usage","Value #C":"Memory Requests","Value #D":"Memory Requests %","Value #E":"Memory Limits","Value #F":"Memory Limits %","workload":"Workload","workload_type 1":"Type"}}}],"type":"table"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"overrides":[{"matcher":{"id":"byRegexp","options":"/Bandwidth/"},"properties":[{"id":"unit","value":"Bps"}]},{"matcher":{"id":"byRegexp","options":"/Packets/"},"properties":[{"id":"unit","value":"pps"}]},{"matcher":{"id":"byName","options":"Workload"},"properties":[{"id":"links","value":[{"title":"Drill down to workloads","url":"/d/a164a7f0339f99e89cea5cb47e9be617/k8s-resources-workload?${datasource:queryparam}&var-cluster=$cluster&var-namespace=$namespace&var-type=${__data.fields.Type}&var-workload=${__data.fields.Workload}"}]}]}]},"gridPos":{"h":7,"w":24,"x":0,"y":28},"id":5,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(sum(rate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}) by (workload))\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(sum(rate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}) by (workload))\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(sum(rate(container_network_receive_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}) by (workload))\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(sum(rate(container_network_transmit_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}) by (workload))\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(sum(rate(container_network_receive_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}) by (workload))\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(sum(rate(container_network_transmit_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}) by (workload))\n","format":"table","instant":true}],"title":"Current Network Usage","transformations":[{"id":"joinByField","options":{"byField":"workload","mode":"outer"}},{"id":"organize","options":{"excludeByName":{"Time":true,"Time 1":true,"Time 2":true,"Time 3":true,"Time 4":true,"Time 5":true,"Time 6":true},"indexByName":{"Time 1":0,"Time 2":1,"Time 3":2,"Time 4":3,"Time 5":4,"Time 6":5,"Value #A":7,"Value #B":8,"Value #C":9,"Value #D":10,"Value #E":11,"Value #F":12,"workload":6},"renameByName":{"Value #A":"Current Receive Bandwidth","Value #B":"Current Transmit Bandwidth","Value #C":"Rate of Received Packets","Value #D":"Rate of Transmitted Packets","Value #E":"Rate of Received Packets Dropped","Value #F":"Rate of Transmitted Packets Dropped","workload":"Workload"}}}],"type":"table"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"Bps"}},"gridPos":{"h":7,"w":12,"x":0,"y":35},"id":6,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(sum(rate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","legendFormat":"__auto"}],"title":"Receive Bandwidth","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"Bps"}},"gridPos":{"h":7,"w":12,"x":12,"y":35},"id":7,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(sum(rate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","legendFormat":"__auto"}],"title":"Transmit Bandwidth","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"Bps"}},"gridPos":{"h":7,"w":12,"x":0,"y":42},"id":8,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(avg(rate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","legendFormat":"__auto"}],"title":"Average Container Bandwidth by Workload: Received","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"Bps"}},"gridPos":{"h":7,"w":12,"x":12,"y":42},"id":9,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(avg(rate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","legendFormat":"__auto"}],"title":"Average Container Bandwidth by Workload: Transmitted","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"pps"}},"gridPos":{"h":7,"w":12,"x":0,"y":49},"id":10,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(sum(rate(container_network_receive_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","legendFormat":"__auto"}],"title":"Rate of Received Packets","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"pps"}},"gridPos":{"h":7,"w":12,"x":12,"y":49},"id":11,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(sum(rate(container_network_transmit_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","legendFormat":"__auto"}],"title":"Rate of Transmitted Packets","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"pps"}},"gridPos":{"h":7,"w":12,"x":0,"y":56},"id":12,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(sum(rate(container_network_receive_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","legendFormat":"__auto"}],"title":"Rate of Received Packets Dropped","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"pps"}},"gridPos":{"h":7,"w":12,"x":12,"y":56},"id":13,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(sum(rate(container_network_transmit_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","legendFormat":"__auto"}],"title":"Rate of Transmitted Packets Dropped","type":"timeseries"}],"refresh":"10s","schemaVersion":39,"tags":["kubernetes-mixin"],"templating":{"list":[{"current":{"selected":true,"text":"default","value":"default"},"hide":0,"label":"Data source","name":"datasource","query":"prometheus","regex":"","type":"datasource"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":2,"label":"cluster","name":"cluster","query":"label_values(up{job=\"kube-state-metrics\"}, cluster)","refresh":2,"sort":1,"type":"query","allValue":".*"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":0,"label":"namespace","name":"namespace","query":"label_values(kube_namespace_status_phase{job=\"kube-state-metrics\", cluster=\"$cluster\"}, namespace)","refresh":2,"sort":1,"type":"query"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":0,"includeAll":true,"label":"workload_type","name":"type","query":"label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\"}, workload_type)","refresh":2,"sort":1,"type":"query"}]},"time":{"from":"now-1h","to":"now"},"timezone": "utc","title":"Kubernetes / Compute Resources / Namespace (Workloads)","uid":"a87fb0d919ec0ea5f6543124e16c42a5"}
|
|
---
|
|
# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/kubelet.yaml
|
|
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
namespace: default
|
|
name: kube-prometheus-stack-kubelet
|
|
annotations:
|
|
{}
|
|
labels:
|
|
grafana_dashboard: "1"
|
|
#TBR: app: kube-prometheus-stack-grafana
|
|
app.kubernetes.io/name: kube-prometheus-stack-grafana #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
data:
|
|
kubelet.json: |-
|
|
{"editable":true,"links":[{"asDropdown":true,"includeVars":true,"keepTime":true,"tags":["kubernetes-mixin"],"targetBlank":false,"title":"Kubernetes","type":"dashboards"}],"panels":[{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"none"}},"gridPos":{"h":7,"w":4,"x":0,"y":0},"id":1,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(kubelet_node_name{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\"})","instant":true}],"title":"Running Kubelets","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"none"}},"gridPos":{"h":7,"w":4,"x":4,"y":0},"id":2,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(kubelet_running_pods{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"})","instant":true}],"title":"Running Pods","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"none"}},"gridPos":{"h":7,"w":4,"x":8,"y":0},"id":3,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(kubelet_running_containers{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"})","instant":true}],"title":"Running Containers","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"none"}},"gridPos":{"h":7,"w":4,"x":12,"y":0},"id":4,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(volume_manager_total_volumes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\", state=\"actual_state_of_world\"})","instant":true}],"title":"Actual Volume Count","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"none"}},"gridPos":{"h":7,"w":4,"x":16,"y":0},"id":5,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(volume_manager_total_volumes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\",state=\"desired_state_of_world\"})","instant":true}],"title":"Desired Volume Count","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"none"}},"gridPos":{"h":7,"w":4,"x":20,"y":0},"id":6,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(kubelet_node_config_error{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}[$__rate_interval]))","instant":true}],"title":"Config Error Count","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"ops"}},"gridPos":{"h":7,"w":12,"x":0,"y":7},"id":7,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(kubelet_runtime_operations_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])) by (operation_type, instance)","legendFormat":"{{instance}} {{operation_type}}"}],"title":"Operation Rate","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"ops"}},"gridPos":{"h":7,"w":12,"x":12,"y":7},"id":8,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(kubelet_runtime_operations_errors_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])) by (instance, operation_type)","legendFormat":"{{instance}} {{operation_type}}"}],"title":"Operation Error Rate","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"s"}},"gridPos":{"h":7,"w":24,"x":0,"y":14},"id":9,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"histogram_quantile(0.99, sum(rate(kubelet_runtime_operations_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])) by (instance, operation_type, le))","legendFormat":"{{instance}} {{operation_type}}"}],"title":"Operation Duration 99th quantile","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"ops"}},"gridPos":{"h":7,"w":12,"x":0,"y":21},"id":10,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(kubelet_pod_start_duration_seconds_count{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])) by (instance)","legendFormat":"{{instance}} pod"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(kubelet_pod_worker_duration_seconds_count{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])) by (instance)","legendFormat":"{{instance}} worker"}],"title":"Pod Start Rate","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"s"}},"gridPos":{"h":7,"w":12,"x":12,"y":21},"id":11,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"histogram_quantile(0.99, sum(rate(kubelet_pod_start_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])) by (instance, le))","legendFormat":"{{instance}} pod"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"histogram_quantile(0.99, sum(rate(kubelet_pod_worker_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])) by (instance, le))","legendFormat":"{{instance}} worker"}],"title":"Pod Start Duration","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"ops"}},"gridPos":{"h":7,"w":12,"x":0,"y":28},"id":12,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(storage_operation_duration_seconds_count{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])) by (instance, operation_name, volume_plugin)","legendFormat":"{{instance}} {{operation_name}} {{volume_plugin}}"}],"title":"Storage Operation Rate","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"ops"}},"gridPos":{"h":7,"w":12,"x":12,"y":28},"id":13,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(storage_operation_errors_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])) by (instance, operation_name, volume_plugin)","legendFormat":"{{instance}} {{operation_name}} {{volume_plugin}}"}],"title":"Storage Operation Error Rate","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"s"}},"gridPos":{"h":7,"w":24,"x":0,"y":35},"id":14,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"histogram_quantile(0.99, sum(rate(storage_operation_duration_seconds_bucket{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}[$__rate_interval])) by (instance, operation_name, volume_plugin, le))","legendFormat":"{{instance}} {{operation_name}} {{volume_plugin}}"}],"title":"Storage Operation Duration 99th quantile","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"ops"}},"gridPos":{"h":7,"w":12,"x":0,"y":42},"id":15,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(kubelet_cgroup_manager_duration_seconds_count{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}[$__rate_interval])) by (instance, operation_type)","legendFormat":"{{operation_type}}"}],"title":"Cgroup manager operation rate","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"s"}},"gridPos":{"h":7,"w":12,"x":12,"y":42},"id":16,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"histogram_quantile(0.99, sum(rate(kubelet_cgroup_manager_duration_seconds_bucket{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}[$__rate_interval])) by (instance, operation_type, le))","legendFormat":"{{instance}} {{operation_type}}"}],"title":"Cgroup manager 99th quantile","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"ops"}},"gridPos":{"h":7,"w":12,"x":0,"y":49},"id":17,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(kubelet_pleg_relist_duration_seconds_count{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}[$__rate_interval])) by (instance)","legendFormat":"{{instance}}"}],"title":"PLEG relist rate","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"s"}},"gridPos":{"h":7,"w":12,"x":12,"y":49},"id":18,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"histogram_quantile(0.99, sum(rate(kubelet_pleg_relist_interval_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])) by (instance, le))","legendFormat":"{{instance}}"}],"title":"PLEG relist interval","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"s"}},"gridPos":{"h":7,"w":24,"x":0,"y":56},"id":19,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"histogram_quantile(0.99, sum(rate(kubelet_pleg_relist_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])) by (instance, le))","legendFormat":"{{instance}}"}],"title":"PLEG relist duration","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"ops"}},"gridPos":{"h":7,"w":24,"x":0,"y":63},"id":20,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\",code=~\"2..\"}[$__rate_interval]))","legendFormat":"2xx"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\",code=~\"3..\"}[$__rate_interval]))","legendFormat":"3xx"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\",code=~\"4..\"}[$__rate_interval]))","legendFormat":"4xx"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\",code=~\"5..\"}[$__rate_interval]))","legendFormat":"5xx"}],"title":"RPC rate","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"s"}},"gridPos":{"h":7,"w":24,"x":0,"y":70},"id":21,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}[$__rate_interval])) by (instance, verb, url, le))","legendFormat":"{{instance}} {{verb}} {{url}}"}],"title":"Request duration 99th quantile","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"bytes"}},"gridPos":{"h":7,"w":8,"x":0,"y":77},"id":22,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"process_resident_memory_bytes{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}","legendFormat":"{{instance}}"}],"title":"Memory","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"short"}},"gridPos":{"h":7,"w":8,"x":8,"y":77},"id":23,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"rate(process_cpu_seconds_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])","legendFormat":"{{instance}}"}],"title":"CPU usage","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"short"}},"gridPos":{"h":7,"w":8,"x":16,"y":77},"id":24,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"go_goroutines{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}","legendFormat":"{{instance}}"}],"title":"Goroutines","type":"timeseries"}],"refresh":"10s","schemaVersion":39,"tags":["kubernetes-mixin"],"templating":{"list":[{"current":{"selected":true,"text":"default","value":"default"},"hide":0,"label":"Data source","name":"datasource","query":"prometheus","regex":"","type":"datasource"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":2,"label":"cluster","name":"cluster","query":"label_values(up{job=\"kubelet\", metrics_path=\"/metrics\"}, cluster)","refresh":2,"sort":1,"type":"query","allValue":".*"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":0,"includeAll":true,"label":"instance","name":"instance","query":"label_values(up{job=\"kubelet\", metrics_path=\"/metrics\",cluster=\"$cluster\"}, instance)","refresh":2,"type":"query"}]},"time":{"from":"now-1h","to":"now"},"timezone": "utc","title":"Kubernetes / Kubelet","uid":"3138fa155d5915769fbded898ac09fd9"}
|
|
---
|
|
# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/namespace-by-pod.yaml
|
|
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
namespace: default
|
|
name: kube-prometheus-stack-namespace-by-pod
|
|
annotations:
|
|
{}
|
|
labels:
|
|
grafana_dashboard: "1"
|
|
#TBR: app: kube-prometheus-stack-grafana
|
|
app.kubernetes.io/name: kube-prometheus-stack-grafana #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
data:
|
|
namespace-by-pod.json: |-
|
|
{"editable":true,"links":[{"asDropdown":true,"includeVars":true,"keepTime":true,"tags":["kubernetes-mixin"],"targetBlank":false,"title":"Kubernetes","type":"dashboards"}],"panels":[{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"displayName":"$namespace","max":10000000000,"min":0,"thresholds":{"steps":[{"color":"dark-green","index":0,"value":null},{"color":"dark-yellow","index":1,"value":5000000000},{"color":"dark-red","index":2,"value":7000000000}]},"unit":"Bps"}},"gridPos":{"h":9,"w":12,"x":0,"y":0},"id":1,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum (\n rate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","legendFormat":"__auto"}],"title":"Current Rate of Bytes Received","type":"gauge"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"displayName":"$namespace","max":10000000000,"min":0,"thresholds":{"steps":[{"color":"dark-green","index":0,"value":null},{"color":"dark-yellow","index":1,"value":5000000000},{"color":"dark-red","index":2,"value":7000000000}]},"unit":"Bps"}},"gridPos":{"h":9,"w":12,"x":12,"y":0},"id":2,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum (\n rate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","legendFormat":"__auto"}],"title":"Current Rate of Bytes Transmitted","type":"gauge"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"overrides":[{"matcher":{"id":"byRegexp","options":"/Bandwidth/"},"properties":[{"id":"unit","value":"Bps"}]},{"matcher":{"id":"byRegexp","options":"/Packets/"},"properties":[{"id":"unit","value":"pps"}]},{"matcher":{"id":"byName","options":"Pod"},"properties":[{"id":"links","value":[{"title":"Drill down","url":"/d/7a18067ce943a40ae25454675c19ff5c/kubernetes-networking-pod?${datasource:queryparam}&var-cluster=${cluster}&var-namespace=${namespace}&var-pod=${__data.fields.Pod}"}]}]}]},"gridPos":{"h":9,"w":24,"x":0,"y":9},"id":3,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (pod) (\n rate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (pod) (\n rate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (pod) (\n rate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (pod) (\n rate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (pod) (\n rate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (pod) (\n rate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","format":"table","instant":true}],"title":"Current Network Usage","transformations":[{"id":"joinByField","options":{"byField":"pod","mode":"outer"}},{"id":"organize","options":{"excludeByName":{"Time":true,"Time 1":true,"Time 2":true,"Time 3":true,"Time 4":true,"Time 5":true,"Time 6":true},"indexByName":{"Time 1":0,"Time 2":1,"Time 3":2,"Time 4":3,"Time 5":4,"Time 6":5,"Value #A":7,"Value #B":8,"Value #C":9,"Value #D":10,"Value #E":11,"Value #F":12,"pod":6},"renameByName":{"Value #A":"Current Receive Bandwidth","Value #B":"Current Transmit Bandwidth","Value #C":"Rate of Received Packets","Value #D":"Rate of Transmitted Packets","Value #E":"Rate of Received Packets Dropped","Value #F":"Rate of Transmitted Packets Dropped","pod":"Pod"}}}],"type":"table"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"showPoints":"never"},"unit":"binBps"}},"gridPos":{"h":9,"w":12,"x":0,"y":18},"id":4,"interval":"1m","options":{"legend":{"asTable":true,"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (pod) (\n rate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","legendFormat":"__auto"}],"title":"Receive Bandwidth","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"showPoints":"never"},"unit":"binBps"}},"gridPos":{"h":9,"w":12,"x":12,"y":18},"id":5,"interval":"1m","options":{"legend":{"asTable":true,"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (pod) (\n rate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","legendFormat":"__auto"}],"title":"Transmit Bandwidth","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"showPoints":"never"},"unit":"pps"}},"gridPos":{"h":9,"w":12,"x":0,"y":27},"id":6,"interval":"1m","options":{"legend":{"asTable":true,"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (pod) (\n rate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","legendFormat":"__auto"}],"title":"Rate of Received Packets","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"showPoints":"never"},"unit":"pps"}},"gridPos":{"h":9,"w":12,"x":12,"y":27},"id":7,"interval":"1m","options":{"legend":{"asTable":true,"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (pod) (\n rate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","legendFormat":"__auto"}],"title":"Rate of Transmitted Packets","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"showPoints":"never"},"unit":"pps"}},"gridPos":{"h":9,"w":12,"x":0,"y":36},"id":8,"interval":"1m","options":{"legend":{"asTable":true,"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (pod) (\n rate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace!=\"\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","legendFormat":"__auto"}],"title":"Rate of Received Packets Dropped","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"showPoints":"never"},"unit":"pps"}},"gridPos":{"h":9,"w":12,"x":12,"y":36},"id":9,"interval":"1m","options":{"legend":{"asTable":true,"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum by (pod) (\n rate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$__rate_interval])\n * on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n)\n","legendFormat":"__auto"}],"title":"Rate of Transmitted Packets Dropped","type":"timeseries"}],"refresh":"10s","schemaVersion":39,"tags":["kubernetes-mixin"],"templating":{"list":[{"current":{"selected":true,"text":"default","value":"default"},"hide":0,"label":"Data source","name":"datasource","query":"prometheus","regex":"","type":"datasource"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":2,"label":"cluster","name":"cluster","query":"label_values(up{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\"}, cluster)","refresh":2,"sort":1,"type":"query","allValue":".*"},{"allValue":".+","current":{"selected":false,"text":"kube-system","value":"kube-system"},"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":0,"includeAll":true,"label":"namespace","name":"namespace","query":"label_values(container_network_receive_packets_total{cluster=\"$cluster\"}, namespace)","refresh":2,"sort":1,"type":"query"}]},"time":{"from":"now-1h","to":"now"},"timezone": "utc","title":"Kubernetes / Networking / Namespace (Pods)","uid":"8b7a8b326d7a6f1f04244066368c67af"}
|
|
---
|
|
# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/namespace-by-workload.yaml
|
|
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
namespace: default
|
|
name: kube-prometheus-stack-namespace-by-workload
|
|
annotations:
|
|
{}
|
|
labels:
|
|
grafana_dashboard: "1"
|
|
#TBR: app: kube-prometheus-stack-grafana
|
|
app.kubernetes.io/name: kube-prometheus-stack-grafana #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
data:
|
|
namespace-by-workload.json: |-
|
|
{"editable":true,"links":[{"asDropdown":true,"includeVars":true,"keepTime":true,"tags":["kubernetes-mixin"],"targetBlank":false,"title":"Kubernetes","type":"dashboards"}],"panels":[{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"color":{"fixedColor":"green","mode":"fixed"},"unit":"Bps"}},"gridPos":{"h":9,"w":12,"x":0,"y":0},"id":1,"options":{"displayMode":"basic","showUnfilled":false},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(sum(rate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$__rate_interval])\n* on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n* on (cluster,namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","legendFormat":"__auto"}],"title":"Current Rate of Bytes Received","type":"bargauge"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"color":{"fixedColor":"green","mode":"fixed"},"unit":"Bps"}},"gridPos":{"h":9,"w":12,"x":12,"y":0},"id":2,"options":{"displayMode":"basic","showUnfilled":false},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(sum(rate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$__rate_interval])\n* on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n* on (cluster,namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","legendFormat":"__auto"}],"title":"Current Rate of Bytes Transmitted","type":"bargauge"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"overrides":[{"matcher":{"id":"byRegexp","options":"/Bytes/"},"properties":[{"id":"unit","value":"binBps"}]},{"matcher":{"id":"byRegexp","options":"/Packets/"},"properties":[{"id":"unit","value":"pps"}]},{"matcher":{"id":"byName","options":"Workload"},"properties":[{"id":"links","value":[{"title":"Drill down","url":"/d/728bf77cc1166d2f3133bf25846876cc/kubernetes-networking-workload?${datasource:queryparam}&var-cluster=${cluster}&var-namespace=${namespace}&var-type=${__data.fields.Type}&var-workload=${__data.fields.Workload}"}]}]}]},"gridPos":{"h":9,"w":24,"x":0,"y":9},"id":3,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(sum(rate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod) kube_pod_info{cluster=\"$cluster\",namespace=\"$namespace\",host_network=\"false\"}\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload, workload_type))\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(sum(rate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod) kube_pod_info{cluster=\"$cluster\",namespace=\"$namespace\",host_network=\"false\"}\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload, workload_type))\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(avg(rate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod) kube_pod_info{cluster=\"$cluster\",namespace=\"$namespace\",host_network=\"false\"}\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload, workload_type))\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(avg(rate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod) kube_pod_info{cluster=\"$cluster\",namespace=\"$namespace\",host_network=\"false\"}\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload, workload_type))\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(sum(rate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod) kube_pod_info{cluster=\"$cluster\",namespace=\"$namespace\",host_network=\"false\"}\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload, workload_type))\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(sum(rate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod) kube_pod_info{cluster=\"$cluster\",namespace=\"$namespace\",host_network=\"false\"}\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload, workload_type))\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(sum(rate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod) kube_pod_info{cluster=\"$cluster\",namespace=\"$namespace\",host_network=\"false\"}\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload, workload_type))\n","format":"table","instant":true},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(sum(rate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod) kube_pod_info{cluster=\"$cluster\",namespace=\"$namespace\",host_network=\"false\"}\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload, workload_type))\n","format":"table","instant":true}],"title":"Current Status","transformations":[{"id":"joinByField","options":{"byField":"workload","mode":"outer"}},{"id":"organize","options":{"excludeByName":{"Time":true,"Time 1":true,"Time 2":true,"Time 3":true,"Time 4":true,"Time 5":true,"Time 6":true,"Time 7":true,"Time 8":true,"workload_type 2":true,"workload_type 3":true,"workload_type 4":true,"workload_type 5":true,"workload_type 6":true,"workload_type 7":true,"workload_type 8":true},"indexByName":{"Time 1":0,"Time 2":1,"Time 3":2,"Time 4":3,"Time 5":4,"Time 6":5,"Time 7":6,"Time 8":7,"Value #A":10,"Value #B":11,"Value #C":12,"Value #D":13,"Value #E":14,"Value #F":15,"Value #G":16,"Value #H":17,"workload":8,"workload_type 1":9,"workload_type 2":18,"workload_type 3":19,"workload_type 4":20,"workload_type 5":21,"workload_type 6":22,"workload_type 7":23,"workload_type 8":24},"renameByName":{"Value #A":"Rx Bytes","Value #B":"Tx Bytes","Value #C":"Rx Bytes (Avg)","Value #D":"Tx Bytes (Avg)","Value #E":"Rx Packets","Value #F":"Tx Packets","Value #G":"Rx Packets Dropped","Value #H":"Tx Packets Dropped","workload":"Workload","workload_type 1":"Type"}}}],"type":"table"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"Bps"}},"gridPos":{"h":9,"w":12,"x":0,"y":18},"id":4,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(sum(rate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$__rate_interval])\n* on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n* on (cluster,namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","legendFormat":"__auto"}],"title":"Receive Bandwidth","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"Bps"}},"gridPos":{"h":9,"w":12,"x":12,"y":18},"id":5,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(sum(rate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$__rate_interval])\n* on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n* on (cluster,namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","legendFormat":"__auto"}],"title":"Transmit Bandwidth","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"Bps"}},"gridPos":{"h":9,"w":12,"x":0,"y":27},"id":6,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(avg(rate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$__rate_interval])\n* on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n* on (cluster,namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","legendFormat":"__auto"}],"title":"Average Container Bandwidth by Workload: Received","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"Bps"}},"gridPos":{"h":9,"w":12,"x":12,"y":27},"id":7,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(avg(rate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$__rate_interval])\n* on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n* on (cluster,namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","legendFormat":"__auto"}],"title":"Average Container Bandwidth by Workload: Transmitted","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"pps"}},"gridPos":{"h":9,"w":12,"x":0,"y":36},"id":8,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(sum(rate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$__rate_interval])\n* on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n* on (cluster,namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","legendFormat":"__auto"}],"title":"Rate of Received Packets","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"pps"}},"gridPos":{"h":9,"w":12,"x":12,"y":36},"id":9,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(sum(rate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$__rate_interval])\n* on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n* on (cluster,namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","legendFormat":"__auto"}],"title":"Rate of Transmitted Packets","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"pps"}},"gridPos":{"h":9,"w":12,"x":0,"y":45},"id":10,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(sum(rate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$__rate_interval])\n* on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n* on (cluster,namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","legendFormat":"__auto"}],"title":"Rate of Received Packets Dropped","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"pps"}},"gridPos":{"h":9,"w":12,"x":12,"y":45},"id":11,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(sum(rate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$__rate_interval])\n* on (cluster,namespace,pod) group_left ()\n topk by (cluster,namespace,pod) (\n 1,\n max by (cluster,namespace,pod) (kube_pod_info{host_network=\"false\"})\n )\n* on (cluster,namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","legendFormat":"__auto"}],"title":"Rate of Transmitted Packets Dropped","type":"timeseries"}],"refresh":"10s","schemaVersion":39,"tags":["kubernetes-mixin"],"templating":{"list":[{"current":{"selected":true,"text":"default","value":"default"},"hide":0,"label":"Data source","name":"datasource","query":"prometheus","regex":"","type":"datasource"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":2,"label":"cluster","name":"cluster","query":"label_values(up{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\"}, cluster)","refresh":2,"sort":1,"type":"query","allValue":".*"},{"current":{"selected":false,"text":"kube-system","value":"kube-system"},"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":0,"label":"namespace","name":"namespace","query":"label_values(container_network_receive_packets_total{cluster=\"$cluster\"}, namespace)","refresh":2,"sort":1,"type":"query"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":0,"includeAll":true,"label":"workload_type","name":"type","query":"label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\"}, workload_type)","refresh":2,"sort":1,"type":"query"}]},"time":{"from":"now-1h","to":"now"},"timezone": "utc","title":"Kubernetes / Networking / Namespace (Workload)","uid":"bbb2a765a623ae38130206c7d94a160f"}
|
|
---
|
|
# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/node-cluster-rsrc-use.yaml
|
|
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
namespace: default
|
|
name: kube-prometheus-stack-node-cluster-rsrc-use
|
|
annotations:
|
|
{}
|
|
labels:
|
|
grafana_dashboard: "1"
|
|
#TBR: app: kube-prometheus-stack-grafana
|
|
app.kubernetes.io/name: kube-prometheus-stack-grafana #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
data:
|
|
node-cluster-rsrc-use.json: |-
|
|
{
|
|
"graphTooltip": 1,
|
|
"panels": [
|
|
{
|
|
"collapsed": false,
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 0
|
|
},
|
|
"id": 1,
|
|
"panels": [
|
|
|
|
],
|
|
"title": "CPU",
|
|
"type": "row"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"custom": {
|
|
"fillOpacity": 100,
|
|
"showPoints": "never",
|
|
"stacking": {
|
|
"mode": "normal"
|
|
}
|
|
},
|
|
"unit": "percentunit"
|
|
}
|
|
},
|
|
"gridPos": {
|
|
"h": 7,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 1
|
|
},
|
|
"id": 2,
|
|
"options": {
|
|
"legend": {
|
|
"showLegend": false
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"pluginVersion": "v11.4.0",
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "$datasource"
|
|
},
|
|
"expr": "((\n instance:node_cpu_utilisation:rate5m{job=\"node-exporter\", cluster=\"$cluster\"}\n *\n instance:node_num_cpu:sum{job=\"node-exporter\", cluster=\"$cluster\"}\n) != 0 )\n/ scalar(sum(instance:node_num_cpu:sum{job=\"node-exporter\", cluster=\"$cluster\"}))\n",
|
|
"legendFormat": "{{ instance }}"
|
|
}
|
|
],
|
|
"title": "CPU Utilisation",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"custom": {
|
|
"fillOpacity": 100,
|
|
"showPoints": "never",
|
|
"stacking": {
|
|
"mode": "normal"
|
|
}
|
|
},
|
|
"unit": "percentunit"
|
|
}
|
|
},
|
|
"gridPos": {
|
|
"h": 7,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 1
|
|
},
|
|
"id": 3,
|
|
"options": {
|
|
"legend": {
|
|
"showLegend": false
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"pluginVersion": "v11.4.0",
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "$datasource"
|
|
},
|
|
"expr": "(\n instance:node_load1_per_cpu:ratio{job=\"node-exporter\", cluster=\"$cluster\"}\n / scalar(count(instance:node_load1_per_cpu:ratio{job=\"node-exporter\", cluster=\"$cluster\"}))\n) != 0\n",
|
|
"legendFormat": "{{ instance }}"
|
|
}
|
|
],
|
|
"title": "CPU Saturation (Load1 per CPU)",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"collapsed": false,
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 8
|
|
},
|
|
"id": 4,
|
|
"panels": [
|
|
|
|
],
|
|
"title": "Memory",
|
|
"type": "row"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"custom": {
|
|
"fillOpacity": 100,
|
|
"showPoints": "never",
|
|
"stacking": {
|
|
"mode": "normal"
|
|
}
|
|
},
|
|
"unit": "percentunit"
|
|
}
|
|
},
|
|
"gridPos": {
|
|
"h": 7,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 9
|
|
},
|
|
"id": 5,
|
|
"options": {
|
|
"legend": {
|
|
"showLegend": false
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"pluginVersion": "v11.4.0",
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "$datasource"
|
|
},
|
|
"expr": "(\n instance:node_memory_utilisation:ratio{job=\"node-exporter\", cluster=\"$cluster\"}\n / scalar(count(instance:node_memory_utilisation:ratio{job=\"node-exporter\", cluster=\"$cluster\"}))\n) != 0\n",
|
|
"legendFormat": "{{ instance }}"
|
|
}
|
|
],
|
|
"title": "Memory Utilisation",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"custom": {
|
|
"fillOpacity": 100,
|
|
"showPoints": "never",
|
|
"stacking": {
|
|
"mode": "normal"
|
|
}
|
|
},
|
|
"unit": "rds"
|
|
}
|
|
},
|
|
"gridPos": {
|
|
"h": 7,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 9
|
|
},
|
|
"id": 6,
|
|
"options": {
|
|
"legend": {
|
|
"showLegend": false
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"pluginVersion": "v11.4.0",
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "$datasource"
|
|
},
|
|
"expr": "instance:node_vmstat_pgmajfault:rate5m{job=\"node-exporter\", cluster=\"$cluster\"}",
|
|
"legendFormat": "{{ instance }}"
|
|
}
|
|
],
|
|
"title": "Memory Saturation (Major Page Faults)",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"collapsed": false,
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 16
|
|
},
|
|
"id": 7,
|
|
"panels": [
|
|
|
|
],
|
|
"title": "Network",
|
|
"type": "row"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"custom": {
|
|
"fillOpacity": 100,
|
|
"showPoints": "never",
|
|
"stacking": {
|
|
"mode": "normal"
|
|
}
|
|
},
|
|
"unit": "Bps"
|
|
},
|
|
"overrides": [
|
|
{
|
|
"matcher": {
|
|
"id": "byRegexp",
|
|
"options": "/Transmit/"
|
|
},
|
|
"properties": [
|
|
{
|
|
"id": "custom.transform",
|
|
"value": "negative-Y"
|
|
}
|
|
]
|
|
}
|
|
]
|
|
},
|
|
"gridPos": {
|
|
"h": 7,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 17
|
|
},
|
|
"id": 8,
|
|
"options": {
|
|
"legend": {
|
|
"showLegend": false
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"pluginVersion": "v11.4.0",
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "$datasource"
|
|
},
|
|
"expr": "instance:node_network_receive_bytes_excluding_lo:rate5m{job=\"node-exporter\", cluster=\"$cluster\"} != 0",
|
|
"legendFormat": "{{ instance }} Receive"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "$datasource"
|
|
},
|
|
"expr": "instance:node_network_transmit_bytes_excluding_lo:rate5m{job=\"node-exporter\", cluster=\"$cluster\"} != 0",
|
|
"legendFormat": "{{ instance }} Transmit"
|
|
}
|
|
],
|
|
"title": "Network Utilisation (Bytes Receive/Transmit)",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"custom": {
|
|
"fillOpacity": 100,
|
|
"showPoints": "never",
|
|
"stacking": {
|
|
"mode": "normal"
|
|
}
|
|
},
|
|
"unit": "Bps"
|
|
},
|
|
"overrides": [
|
|
{
|
|
"matcher": {
|
|
"id": "byRegexp",
|
|
"options": "/Transmit/"
|
|
},
|
|
"properties": [
|
|
{
|
|
"id": "custom.transform",
|
|
"value": "negative-Y"
|
|
}
|
|
]
|
|
}
|
|
]
|
|
},
|
|
"gridPos": {
|
|
"h": 7,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 17
|
|
},
|
|
"id": 9,
|
|
"options": {
|
|
"legend": {
|
|
"showLegend": false
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"pluginVersion": "v11.4.0",
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "$datasource"
|
|
},
|
|
"expr": "instance:node_network_receive_drop_excluding_lo:rate5m{job=\"node-exporter\", cluster=\"$cluster\"} != 0",
|
|
"legendFormat": "{{ instance }} Receive"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "$datasource"
|
|
},
|
|
"expr": "instance:node_network_transmit_drop_excluding_lo:rate5m{job=\"node-exporter\", cluster=\"$cluster\"} != 0",
|
|
"legendFormat": "{{ instance }} Transmit"
|
|
}
|
|
],
|
|
"title": "Network Saturation (Drops Receive/Transmit)",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"collapsed": false,
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 24
|
|
},
|
|
"id": 10,
|
|
"panels": [
|
|
|
|
],
|
|
"title": "Disk IO",
|
|
"type": "row"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"custom": {
|
|
"fillOpacity": 100,
|
|
"showPoints": "never",
|
|
"stacking": {
|
|
"mode": "normal"
|
|
}
|
|
},
|
|
"unit": "percentunit"
|
|
}
|
|
},
|
|
"gridPos": {
|
|
"h": 7,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 25
|
|
},
|
|
"id": 11,
|
|
"options": {
|
|
"legend": {
|
|
"showLegend": false
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"pluginVersion": "v11.4.0",
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "$datasource"
|
|
},
|
|
"expr": "instance_device:node_disk_io_time_seconds:rate5m{job=\"node-exporter\", cluster=\"$cluster\"}\n/ scalar(count(instance_device:node_disk_io_time_seconds:rate5m{job=\"node-exporter\", cluster=\"$cluster\"}))\n",
|
|
"legendFormat": "{{ instance }} {{device}}"
|
|
}
|
|
],
|
|
"title": "Disk IO Utilisation",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"custom": {
|
|
"fillOpacity": 100,
|
|
"showPoints": "never",
|
|
"stacking": {
|
|
"mode": "normal"
|
|
}
|
|
},
|
|
"unit": "percentunit"
|
|
}
|
|
},
|
|
"gridPos": {
|
|
"h": 7,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 25
|
|
},
|
|
"id": 12,
|
|
"options": {
|
|
"legend": {
|
|
"showLegend": false
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"pluginVersion": "v11.4.0",
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "$datasource"
|
|
},
|
|
"expr": "instance_device:node_disk_io_time_weighted_seconds:rate5m{job=\"node-exporter\", cluster=\"$cluster\"}\n/ scalar(count(instance_device:node_disk_io_time_weighted_seconds:rate5m{job=\"node-exporter\", cluster=\"$cluster\"}))\n",
|
|
"legendFormat": "{{ instance }} {{device}}"
|
|
}
|
|
],
|
|
"title": "Disk IO Saturation",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"collapsed": false,
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 34
|
|
},
|
|
"id": 13,
|
|
"panels": [
|
|
|
|
],
|
|
"title": "Disk Space",
|
|
"type": "row"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"custom": {
|
|
"fillOpacity": 100,
|
|
"showPoints": "never",
|
|
"stacking": {
|
|
"mode": "normal"
|
|
}
|
|
},
|
|
"unit": "percentunit"
|
|
}
|
|
},
|
|
"gridPos": {
|
|
"h": 7,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 35
|
|
},
|
|
"id": 14,
|
|
"options": {
|
|
"legend": {
|
|
"showLegend": false
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"pluginVersion": "v11.4.0",
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "$datasource"
|
|
},
|
|
"expr": "sum without (device) (\n max without (fstype, mountpoint) ((\n node_filesystem_size_bytes{job=\"node-exporter\", fstype!=\"\", mountpoint!=\"\", cluster=\"$cluster\"}\n -\n node_filesystem_avail_bytes{job=\"node-exporter\", fstype!=\"\", mountpoint!=\"\", cluster=\"$cluster\"}\n ) != 0)\n)\n/ scalar(sum(max without (fstype, mountpoint) (node_filesystem_size_bytes{job=\"node-exporter\", fstype!=\"\", mountpoint!=\"\", cluster=\"$cluster\"})))\n",
|
|
"legendFormat": "{{ instance }}"
|
|
}
|
|
],
|
|
"title": "Disk Space Utilisation",
|
|
"type": "timeseries"
|
|
}
|
|
],
|
|
"refresh": "30s",
|
|
"schemaVersion": 39,
|
|
"tags": [
|
|
"node-exporter-mixin"
|
|
],
|
|
"templating": {
|
|
"list": [
|
|
{
|
|
"name": "datasource",
|
|
"query": "prometheus",
|
|
"type": "datasource"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"hide": 2,
|
|
"includeAll": false,
|
|
"name": "cluster",
|
|
"query": "label_values(node_time_seconds, cluster)",
|
|
"refresh": 2,
|
|
"sort": 1,
|
|
"type": "query"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"refresh": 2,
|
|
"sort": 1
|
|
}
|
|
]
|
|
},
|
|
"time": {
|
|
"from": "now-1h",
|
|
"to": "now"
|
|
},
|
|
"timezone": "utc",
|
|
"title": "Node Exporter / USE Method / Cluster",
|
|
"uid": "3e97d1d02672cdd0861f4c97c64f89b2"
|
|
}
|
|
---
|
|
# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/node-rsrc-use.yaml
|
|
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
namespace: default
|
|
name: kube-prometheus-stack-node-rsrc-use
|
|
annotations:
|
|
{}
|
|
labels:
|
|
grafana_dashboard: "1"
|
|
#TBR: app: kube-prometheus-stack-grafana
|
|
app.kubernetes.io/name: kube-prometheus-stack-grafana #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
data:
|
|
node-rsrc-use.json: |-
|
|
{"graphTooltip":1,"panels":[{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":0},"id":1,"panels":[],"title":"CPU","type":"row"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":100,"showPoints":"never","stacking":{"mode":"normal"}},"unit":"percentunit"}},"gridPos":{"h":7,"w":12,"x":0,"y":1},"id":2,"options":{"legend":{"showLegend":false},"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"instance:node_cpu_utilisation:rate5m{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} != 0","legendFormat":"Utilisation"}],"title":"CPU Utilisation","type":"timeseries"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":100,"showPoints":"never","stacking":{"mode":"normal"}},"unit":"percentunit"}},"gridPos":{"h":7,"w":12,"x":12,"y":1},"id":3,"options":{"legend":{"showLegend":false},"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"instance:node_load1_per_cpu:ratio{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} != 0","legendFormat":"Saturation"}],"title":"CPU Saturation (Load1 per CPU)","type":"timeseries"},{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":8},"id":4,"panels":[],"title":"Memory","type":"row"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":100,"showPoints":"never","stacking":{"mode":"normal"}},"unit":"percentunit"}},"gridPos":{"h":7,"w":12,"x":0,"y":9},"id":5,"options":{"legend":{"showLegend":false},"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"instance:node_memory_utilisation:ratio{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} != 0","legendFormat":"Utilisation"}],"title":"Memory Utilisation","type":"timeseries"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":100,"showPoints":"never","stacking":{"mode":"normal"}},"unit":"rds"}},"gridPos":{"h":7,"w":12,"x":12,"y":9},"id":6,"options":{"legend":{"showLegend":false},"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"instance:node_vmstat_pgmajfault:rate5m{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} != 0","legendFormat":"Major page Faults"}],"title":"Memory Saturation (Major Page Faults)","type":"timeseries"},{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":16},"id":7,"panels":[],"title":"Network","type":"row"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":100,"showPoints":"never","stacking":{"mode":"normal"}},"unit":"Bps"},"overrides":[{"matcher":{"id":"byRegexp","options":"/Transmit/"},"properties":[{"id":"custom.transform","value":"negative-Y"}]}]},"gridPos":{"h":7,"w":12,"x":0,"y":17},"id":8,"options":{"legend":{"showLegend":false},"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"instance:node_network_receive_bytes_excluding_lo:rate5m{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} != 0","legendFormat":"Receive"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"instance:node_network_transmit_bytes_excluding_lo:rate5m{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} != 0","legendFormat":"Transmit"}],"title":"Network Utilisation (Bytes Receive/Transmit)","type":"timeseries"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":100,"showPoints":"never","stacking":{"mode":"normal"}},"unit":"Bps"},"overrides":[{"matcher":{"id":"byRegexp","options":"/Transmit/"},"properties":[{"id":"custom.transform","value":"negative-Y"}]}]},"gridPos":{"h":7,"w":12,"x":12,"y":17},"id":9,"options":{"legend":{"showLegend":false},"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"instance:node_network_receive_drop_excluding_lo:rate5m{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} != 0","legendFormat":"Receive"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"instance:node_network_transmit_drop_excluding_lo:rate5m{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} != 0","legendFormat":"Transmit"}],"title":"Network Saturation (Drops Receive/Transmit)","type":"timeseries"},{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":24},"id":10,"panels":[],"title":"Disk IO","type":"row"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":100,"showPoints":"never","stacking":{"mode":"normal"}},"unit":"percentunit"}},"gridPos":{"h":7,"w":12,"x":0,"y":25},"id":11,"options":{"legend":{"showLegend":false},"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"instance_device:node_disk_io_time_seconds:rate5m{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} != 0","legendFormat":"{{device}}"}],"title":"Disk IO Utilisation","type":"timeseries"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":100,"showPoints":"never","stacking":{"mode":"normal"}},"unit":"percentunit"}},"gridPos":{"h":7,"w":12,"x":12,"y":25},"id":12,"options":{"legend":{"showLegend":false},"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"instance_device:node_disk_io_time_weighted_seconds:rate5m{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} != 0","legendFormat":"{{device}}"}],"title":"Disk IO Saturation","type":"timeseries"},{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":34},"id":13,"panels":[],"title":"Disk Space","type":"row"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":100,"showPoints":"never","stacking":{"mode":"normal"}},"unit":"percentunit"}},"gridPos":{"h":7,"w":24,"x":0,"y":35},"id":14,"options":{"legend":{"showLegend":false},"tooltip":{"mode":"multi","sort":"desc"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"sort_desc(1 -\n (\n max without (mountpoint, fstype) (node_filesystem_avail_bytes{job=\"node-exporter\", fstype!=\"\", instance=\"$instance\", cluster=\"$cluster\"})\n /\n max without (mountpoint, fstype) (node_filesystem_size_bytes{job=\"node-exporter\", fstype!=\"\", instance=\"$instance\", cluster=\"$cluster\"})\n ) != 0\n)\n","legendFormat":"{{device}}"}],"title":"Disk Space Utilisation","type":"timeseries"}],"refresh":"30s","schemaVersion":39,"tags":["node-exporter-mixin"],"templating":{"list":[{"name":"datasource","query":"prometheus","type":"datasource"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":2,"includeAll":false,"name":"cluster","query":"label_values(node_time_seconds, cluster)","refresh":2,"sort":1,"type":"query","allValue":".*"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"name":"instance","query":"label_values(node_exporter_build_info{job=\"node-exporter\", cluster=\"$cluster\"}, instance)","refresh":2,"sort":1,"type":"query"}]},"time":{"from":"now-1h","to":"now"},"timezone": "utc","title":"Node Exporter / USE Method / Node","uid":"fac67cfbe174d3ef53eb473d73d9212f"}
|
|
---
|
|
# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/nodes-aix.yaml
|
|
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
namespace: default
|
|
name: kube-prometheus-stack-nodes-aix
|
|
annotations:
|
|
{}
|
|
labels:
|
|
grafana_dashboard: "1"
|
|
#TBR: app: kube-prometheus-stack-grafana
|
|
app.kubernetes.io/name: kube-prometheus-stack-grafana #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
data:
|
|
nodes-aix.json: |-
|
|
{"graphTooltip":1,"panels":[{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":0},"id":1,"panels":[],"title":"CPU","type":"row"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","stacking":{"mode":"normal"}},"max":1,"min":0,"unit":"percentunit"}},"gridPos":{"h":7,"w":12,"x":0,"y":1},"id":2,"options":{"tooltip":{"mode":"multi"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"(\n (1 - sum without (mode) (rate(node_cpu_seconds_total{job=\"node-exporter\", mode=~\"idle|iowait|steal\", instance=\"$instance\", cluster=\"$cluster\"}[$__rate_interval])))\n/ ignoring(cpu) group_left\n count without (cpu, mode) (node_cpu_seconds_total{job=\"node-exporter\", mode=\"idle\", instance=\"$instance\", cluster=\"$cluster\"})\n)\n","intervalFactor":5,"legendFormat":"{{cpu}}"}],"title":"CPU Usage","type":"timeseries"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":0,"showPoints":"never"},"min":0,"unit":"short"}},"gridPos":{"h":7,"w":12,"x":12,"y":1},"id":3,"options":{"tooltip":{"mode":"multi"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"node_load1{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"}","legendFormat":"1m load average"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"node_load5{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"}","legendFormat":"5m load average"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"node_load15{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"}","legendFormat":"15m load average"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"count(node_cpu_seconds_total{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\", mode=\"idle\"})","legendFormat":"logical cores"}],"title":"Load Average","type":"timeseries"},{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":8},"id":4,"title":"Memory","type":"row"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","stacking":{"mode":"none"}},"min":0,"unit":"bytes"}},"gridPos":{"h":7,"w":18,"x":0,"y":9},"id":5,"options":{"tooltip":{"mode":"multi"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"node_memory_total_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"}","legendFormat":"Physical Memory"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"(\n node_memory_total_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} -\n node_memory_available_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"}\n)\n","legendFormat":"Memory Used"}],"title":"Memory Usage","type":"timeseries"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"max":100,"min":0,"thresholds":{"steps":[{"color":"rgba(50, 172, 45, 0.97)"},{"color":"rgba(237, 129, 40, 0.89)","value":80},{"color":"rgba(245, 54, 54, 0.9)","value":90}]},"unit":"percent"}},"gridPos":{"h":7,"w":6,"x":18,"y":9},"id":6,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"100 -\n(\n avg(node_memory_available_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"}) /\n avg(node_memory_total_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"})\n * 100\n)\n"}],"title":"Memory Usage","type":"gauge"},{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":18},"id":7,"panels":[],"title":"Disk","type":"row"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":0,"showPoints":"never"},"min":0},"overrides":[{"matcher":{"id":"byRegexp","options":"/ read| written/"},"properties":[{"id":"unit","value":"Bps"}]},{"matcher":{"id":"byRegexp","options":"/ io time/"},"properties":[{"id":"unit","value":"percentunit"}]}]},"gridPos":{"h":7,"w":12,"x":0,"y":19},"id":8,"options":{"tooltip":{"mode":"multi"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"rate(node_disk_read_bytes_total{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\"}[$__rate_interval])","intervalFactor":1,"legendFormat":"{{device}} read"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"rate(node_disk_written_bytes_total{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\"}[$__rate_interval])","intervalFactor":1,"legendFormat":"{{device}} written"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"rate(node_disk_io_time_seconds_total{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\"}[$__rate_interval])","intervalFactor":1,"legendFormat":"{{device}} io time"}],"title":"Disk I/O","type":"timeseries"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"thresholds":{"steps":[{"color":"green"},{"color":"yellow","value":0.8},{"color":"red","value":0.9}]},"unit":"decbytes"},"overrides":[{"matcher":{"id":"byName","options":"Mounted on"},"properties":[{"id":"custom.width","value":260}]},{"matcher":{"id":"byName","options":"Size"},"properties":[{"id":"custom.width","value":93}]},{"matcher":{"id":"byName","options":"Used"},"properties":[{"id":"custom.width","value":72}]},{"matcher":{"id":"byName","options":"Available"},"properties":[{"id":"custom.width","value":88}]},{"matcher":{"id":"byName","options":"Used, %"},"properties":[{"id":"unit","value":"percentunit"},{"id":"custom.cellOptions","value":{"type":"gauge"}},{"id":"max","value":1},{"id":"min","value":0}]}]},"gridPos":{"h":7,"w":12,"x":12,"y":19},"id":9,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"max by (mountpoint) (node_filesystem_size_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\", fstype!=\"\", mountpoint!=\"\"})\n","format":"table","instant":true,"legendFormat":""},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"max by (mountpoint) (node_filesystem_avail_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\", fstype!=\"\", mountpoint!=\"\"})\n","format":"table","instant":true,"legendFormat":""}],"title":"Disk Space Usage","transformations":[{"id":"groupBy","options":{"fields":{"Value #A":{"aggregations":["lastNotNull"],"operation":"aggregate"},"Value #B":{"aggregations":["lastNotNull"],"operation":"aggregate"},"mountpoint":{"aggregations":[],"operation":"groupby"}}}},{"id":"merge"},{"id":"calculateField","options":{"alias":"Used","binary":{"left":"Value #A (lastNotNull)","operator":"-","reducer":"sum","right":"Value #B (lastNotNull)"},"mode":"binary","reduce":{"reducer":"sum"}}},{"id":"calculateField","options":{"alias":"Used, %","binary":{"left":"Used","operator":"/","reducer":"sum","right":"Value #A (lastNotNull)"},"mode":"binary","reduce":{"reducer":"sum"}}},{"id":"organize","options":{"excludeByName":{},"indexByName":{},"renameByName":{"Value #A (lastNotNull)":"Size","Value #B (lastNotNull)":"Available","mountpoint":"Mounted on"}}},{"id":"sortBy","options":{"fields":{},"sort":[{"field":"Mounted on"}]}}],"type":"table"},{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":26},"id":10,"panels":[],"title":"Network","type":"row"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"description":"Network received (bits/s)","fieldConfig":{"defaults":{"custom":{"fillOpacity":0,"showPoints":"never"},"min":0,"unit":"bps"}},"gridPos":{"h":7,"w":12,"x":0,"y":27},"id":11,"options":{"tooltip":{"mode":"multi"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"rate(node_network_receive_bytes_total{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\", device!=\"lo\"}[$__rate_interval]) * 8","intervalFactor":1,"legendFormat":"{{device}}"}],"title":"Network Received","type":"timeseries"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"description":"Network transmitted (bits/s)","fieldConfig":{"defaults":{"custom":{"fillOpacity":0},"min":0,"unit":"bps"}},"gridPos":{"h":7,"w":12,"x":12,"y":27},"id":12,"options":{"tooltip":{"mode":"multi"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"rate(node_network_transmit_bytes_total{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\", device!=\"lo\"}[$__rate_interval]) * 8","intervalFactor":1,"legendFormat":"{{device}}"}],"title":"Network Transmitted","type":"timeseries"}],"refresh":"30s","schemaVersion":39,"tags":["node-exporter-mixin"],"templating":{"list":[{"name":"datasource","query":"prometheus","type":"datasource"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":2,"label":"Cluster","name":"cluster","query":"label_values(node_uname_info{job=\"node-exporter\", sysname!=\"Darwin\"}, cluster)","refresh":2,"type":"query","allValue":".*"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"label":"Instance","name":"instance","query":"label_values(node_uname_info{job=\"node-exporter\", cluster=\"$cluster\", sysname!=\"Darwin\"}, instance)","refresh":2,"type":"query"}]},"time":{"from":"now-1h","to":"now"},"timezone": "utc","title":"Node Exporter / AIX","uid":"7e0a61e486f727d763fb1d86fdd629c2"}
|
|
---
|
|
# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/nodes-darwin.yaml
|
|
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
namespace: default
|
|
name: kube-prometheus-stack-nodes-darwin
|
|
annotations:
|
|
{}
|
|
labels:
|
|
grafana_dashboard: "1"
|
|
#TBR: app: kube-prometheus-stack-grafana
|
|
app.kubernetes.io/name: kube-prometheus-stack-grafana #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
data:
|
|
nodes-darwin.json: |-
|
|
{"graphTooltip":1,"panels":[{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":0},"id":1,"panels":[],"title":"CPU","type":"row"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","stacking":{"mode":"normal"}},"max":1,"min":0,"unit":"percentunit"}},"gridPos":{"h":7,"w":12,"x":0,"y":1},"id":2,"options":{"tooltip":{"mode":"multi"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"(\n (1 - sum without (mode) (rate(node_cpu_seconds_total{job=\"node-exporter\", mode=~\"idle|iowait|steal\", instance=\"$instance\", cluster=\"$cluster\"}[$__rate_interval])))\n/ ignoring(cpu) group_left\n count without (cpu, mode) (node_cpu_seconds_total{job=\"node-exporter\", mode=\"idle\", instance=\"$instance\", cluster=\"$cluster\"})\n)\n","intervalFactor":5,"legendFormat":"{{cpu}}"}],"title":"CPU Usage","type":"timeseries"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":0,"showPoints":"never"},"min":0,"unit":"short"}},"gridPos":{"h":7,"w":12,"x":12,"y":1},"id":3,"options":{"tooltip":{"mode":"multi"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"node_load1{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"}","legendFormat":"1m load average"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"node_load5{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"}","legendFormat":"5m load average"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"node_load15{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"}","legendFormat":"15m load average"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"count(node_cpu_seconds_total{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\", mode=\"idle\"})","legendFormat":"logical cores"}],"title":"Load Average","type":"timeseries"},{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":8},"id":4,"title":"Memory","type":"row"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","stacking":{"mode":"none"}},"min":0,"unit":"bytes"}},"gridPos":{"h":7,"w":18,"x":0,"y":9},"id":5,"options":{"tooltip":{"mode":"multi"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"node_memory_total_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"}","legendFormat":"Physical Memory"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"(\n node_memory_internal_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} -\n node_memory_purgeable_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} +\n node_memory_wired_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} +\n node_memory_compressed_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"}\n)\n","legendFormat":"Memory Used"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"(\n node_memory_internal_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} -\n node_memory_purgeable_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"}\n)\n","legendFormat":"App Memory"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"node_memory_wired_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"}","legendFormat":"Wired Memory"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"node_memory_compressed_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"}","legendFormat":"Compressed"}],"title":"Memory Usage","type":"timeseries"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"max":100,"min":0,"thresholds":{"steps":[{"color":"rgba(50, 172, 45, 0.97)"},{"color":"rgba(237, 129, 40, 0.89)","value":80},{"color":"rgba(245, 54, 54, 0.9)","value":90}]},"unit":"percent"}},"gridPos":{"h":7,"w":6,"x":18,"y":9},"id":6,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"(\n (\n avg(node_memory_internal_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"}) -\n avg(node_memory_purgeable_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"}) +\n avg(node_memory_wired_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"}) +\n avg(node_memory_compressed_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"})\n ) /\n avg(node_memory_total_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"})\n)\n*\n100\n"}],"title":"Memory Usage","type":"gauge"},{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":18},"id":7,"panels":[],"title":"Disk","type":"row"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":0,"showPoints":"never"},"min":0},"overrides":[{"matcher":{"id":"byRegexp","options":"/ read| written/"},"properties":[{"id":"unit","value":"Bps"}]},{"matcher":{"id":"byRegexp","options":"/ io time/"},"properties":[{"id":"unit","value":"percentunit"}]}]},"gridPos":{"h":7,"w":12,"x":0,"y":19},"id":8,"options":{"tooltip":{"mode":"multi"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"rate(node_disk_read_bytes_total{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\"}[$__rate_interval])","intervalFactor":1,"legendFormat":"{{device}} read"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"rate(node_disk_written_bytes_total{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\"}[$__rate_interval])","intervalFactor":1,"legendFormat":"{{device}} written"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"rate(node_disk_io_time_seconds_total{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\"}[$__rate_interval])","intervalFactor":1,"legendFormat":"{{device}} io time"}],"title":"Disk I/O","type":"timeseries"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"thresholds":{"steps":[{"color":"green"},{"color":"yellow","value":0.8},{"color":"red","value":0.9}]},"unit":"decbytes"},"overrides":[{"matcher":{"id":"byName","options":"Mounted on"},"properties":[{"id":"custom.width","value":260}]},{"matcher":{"id":"byName","options":"Size"},"properties":[{"id":"custom.width","value":93}]},{"matcher":{"id":"byName","options":"Used"},"properties":[{"id":"custom.width","value":72}]},{"matcher":{"id":"byName","options":"Available"},"properties":[{"id":"custom.width","value":88}]},{"matcher":{"id":"byName","options":"Used, %"},"properties":[{"id":"unit","value":"percentunit"},{"id":"custom.cellOptions","value":{"type":"gauge"}},{"id":"max","value":1},{"id":"min","value":0}]}]},"gridPos":{"h":7,"w":12,"x":12,"y":19},"id":9,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"max by (mountpoint) (node_filesystem_size_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\", fstype!=\"\", mountpoint!=\"\"})\n","format":"table","instant":true,"legendFormat":""},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"max by (mountpoint) (node_filesystem_avail_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\", fstype!=\"\", mountpoint!=\"\"})\n","format":"table","instant":true,"legendFormat":""}],"title":"Disk Space Usage","transformations":[{"id":"groupBy","options":{"fields":{"Value #A":{"aggregations":["lastNotNull"],"operation":"aggregate"},"Value #B":{"aggregations":["lastNotNull"],"operation":"aggregate"},"mountpoint":{"aggregations":[],"operation":"groupby"}}}},{"id":"merge"},{"id":"calculateField","options":{"alias":"Used","binary":{"left":"Value #A (lastNotNull)","operator":"-","reducer":"sum","right":"Value #B (lastNotNull)"},"mode":"binary","reduce":{"reducer":"sum"}}},{"id":"calculateField","options":{"alias":"Used, %","binary":{"left":"Used","operator":"/","reducer":"sum","right":"Value #A (lastNotNull)"},"mode":"binary","reduce":{"reducer":"sum"}}},{"id":"organize","options":{"excludeByName":{},"indexByName":{},"renameByName":{"Value #A (lastNotNull)":"Size","Value #B (lastNotNull)":"Available","mountpoint":"Mounted on"}}},{"id":"sortBy","options":{"fields":{},"sort":[{"field":"Mounted on"}]}}],"type":"table"},{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":26},"id":10,"panels":[],"title":"Network","type":"row"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"description":"Network received (bits/s)","fieldConfig":{"defaults":{"custom":{"fillOpacity":0,"showPoints":"never"},"min":0,"unit":"bps"}},"gridPos":{"h":7,"w":12,"x":0,"y":27},"id":11,"options":{"tooltip":{"mode":"multi"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"rate(node_network_receive_bytes_total{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\", device!=\"lo\"}[$__rate_interval]) * 8","intervalFactor":1,"legendFormat":"{{device}}"}],"title":"Network Received","type":"timeseries"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"description":"Network transmitted (bits/s)","fieldConfig":{"defaults":{"custom":{"fillOpacity":0},"min":0,"unit":"bps"}},"gridPos":{"h":7,"w":12,"x":12,"y":27},"id":12,"options":{"tooltip":{"mode":"multi"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"rate(node_network_transmit_bytes_total{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\", device!=\"lo\"}[$__rate_interval]) * 8","intervalFactor":1,"legendFormat":"{{device}}"}],"title":"Network Transmitted","type":"timeseries"}],"refresh":"30s","schemaVersion":39,"tags":["node-exporter-mixin"],"templating":{"list":[{"name":"datasource","query":"prometheus","type":"datasource"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":2,"label":"Cluster","name":"cluster","query":"label_values(node_uname_info{job=\"node-exporter\", sysname=\"Darwin\"}, cluster)","refresh":2,"type":"query","allValue":".*"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"label":"Instance","name":"instance","query":"label_values(node_uname_info{job=\"node-exporter\", cluster=\"$cluster\", sysname=\"Darwin\"}, instance)","refresh":2,"type":"query"}]},"time":{"from":"now-1h","to":"now"},"timezone": "utc","title":"Node Exporter / MacOS","uid":"629701ea43bf69291922ea45f4a87d37"}
|
|
---
|
|
# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/nodes.yaml
|
|
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
namespace: default
|
|
name: kube-prometheus-stack-nodes
|
|
annotations:
|
|
{}
|
|
labels:
|
|
grafana_dashboard: "1"
|
|
#TBR: app: kube-prometheus-stack-grafana
|
|
app.kubernetes.io/name: kube-prometheus-stack-grafana #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
data:
|
|
nodes.json: |-
|
|
{"graphTooltip":1,"panels":[{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":0},"id":1,"panels":[],"title":"CPU","type":"row"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","stacking":{"mode":"normal"}},"max":1,"min":0,"unit":"percentunit"}},"gridPos":{"h":7,"w":12,"x":0,"y":1},"id":2,"options":{"tooltip":{"mode":"multi"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"(\n (1 - sum without (mode) (rate(node_cpu_seconds_total{job=\"node-exporter\", mode=~\"idle|iowait|steal\", instance=\"$instance\", cluster=\"$cluster\"}[$__rate_interval])))\n/ ignoring(cpu) group_left\n count without (cpu, mode) (node_cpu_seconds_total{job=\"node-exporter\", mode=\"idle\", instance=\"$instance\", cluster=\"$cluster\"})\n)\n","intervalFactor":5,"legendFormat":"{{cpu}}"}],"title":"CPU Usage","type":"timeseries"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":0,"showPoints":"never"},"min":0,"unit":"short"}},"gridPos":{"h":7,"w":12,"x":12,"y":1},"id":3,"options":{"tooltip":{"mode":"multi"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"node_load1{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"}","legendFormat":"1m load average"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"node_load5{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"}","legendFormat":"5m load average"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"node_load15{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"}","legendFormat":"15m load average"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"count(node_cpu_seconds_total{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\", mode=\"idle\"})","legendFormat":"logical cores"}],"title":"Load Average","type":"timeseries"},{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":8},"id":4,"title":"Memory","type":"row"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","stacking":{"mode":"normal"}},"min":0,"unit":"bytes"}},"gridPos":{"h":7,"w":18,"x":0,"y":9},"id":5,"options":{"tooltip":{"mode":"multi"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"(\n node_memory_MemTotal_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"}\n-\n node_memory_MemFree_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"}\n-\n node_memory_Buffers_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"}\n-\n node_memory_Cached_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"}\n)\n","legendFormat":"memory used"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"node_memory_Buffers_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"}","legendFormat":"memory buffers"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"node_memory_Cached_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"}","legendFormat":"memory cached"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"node_memory_MemFree_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"}","legendFormat":"memory free"}],"title":"Memory Usage","type":"timeseries"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"max":100,"min":0,"thresholds":{"steps":[{"color":"rgba(50, 172, 45, 0.97)"},{"color":"rgba(237, 129, 40, 0.89)","value":80},{"color":"rgba(245, 54, 54, 0.9)","value":90}]},"unit":"percent"}},"gridPos":{"h":7,"w":6,"x":18,"y":9},"id":6,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"100 -\n(\n avg(node_memory_MemAvailable_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"}) /\n avg(node_memory_MemTotal_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"})\n* 100\n)\n"}],"title":"Memory Usage","type":"gauge"},{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":18},"id":7,"panels":[],"title":"Disk","type":"row"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":0,"showPoints":"never"},"min":0},"overrides":[{"matcher":{"id":"byRegexp","options":"/ read| written/"},"properties":[{"id":"unit","value":"Bps"}]},{"matcher":{"id":"byRegexp","options":"/ io time/"},"properties":[{"id":"unit","value":"percentunit"}]}]},"gridPos":{"h":7,"w":12,"x":0,"y":19},"id":8,"options":{"tooltip":{"mode":"multi"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"rate(node_disk_read_bytes_total{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\"}[$__rate_interval])","intervalFactor":1,"legendFormat":"{{device}} read"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"rate(node_disk_written_bytes_total{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\"}[$__rate_interval])","intervalFactor":1,"legendFormat":"{{device}} written"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"rate(node_disk_io_time_seconds_total{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\"}[$__rate_interval])","intervalFactor":1,"legendFormat":"{{device}} io time"}],"title":"Disk I/O","type":"timeseries"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"fieldConfig":{"defaults":{"thresholds":{"steps":[{"color":"green"},{"color":"yellow","value":0.8},{"color":"red","value":0.9}]},"unit":"decbytes"},"overrides":[{"matcher":{"id":"byName","options":"Mounted on"},"properties":[{"id":"custom.width","value":260}]},{"matcher":{"id":"byName","options":"Size"},"properties":[{"id":"custom.width","value":93}]},{"matcher":{"id":"byName","options":"Used"},"properties":[{"id":"custom.width","value":72}]},{"matcher":{"id":"byName","options":"Available"},"properties":[{"id":"custom.width","value":88}]},{"matcher":{"id":"byName","options":"Used, %"},"properties":[{"id":"unit","value":"percentunit"},{"id":"custom.cellOptions","value":{"type":"gauge"}},{"id":"max","value":1},{"id":"min","value":0}]}]},"gridPos":{"h":7,"w":12,"x":12,"y":19},"id":9,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"max by (mountpoint) (node_filesystem_size_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\", fstype!=\"\", mountpoint!=\"\"})\n","format":"table","instant":true,"legendFormat":""},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"max by (mountpoint) (node_filesystem_avail_bytes{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\", fstype!=\"\", mountpoint!=\"\"})\n","format":"table","instant":true,"legendFormat":""}],"title":"Disk Space Usage","transformations":[{"id":"groupBy","options":{"fields":{"Value #A":{"aggregations":["lastNotNull"],"operation":"aggregate"},"Value #B":{"aggregations":["lastNotNull"],"operation":"aggregate"},"mountpoint":{"aggregations":[],"operation":"groupby"}}}},{"id":"merge"},{"id":"calculateField","options":{"alias":"Used","binary":{"left":"Value #A (lastNotNull)","operator":"-","reducer":"sum","right":"Value #B (lastNotNull)"},"mode":"binary","reduce":{"reducer":"sum"}}},{"id":"calculateField","options":{"alias":"Used, %","binary":{"left":"Used","operator":"/","reducer":"sum","right":"Value #A (lastNotNull)"},"mode":"binary","reduce":{"reducer":"sum"}}},{"id":"organize","options":{"excludeByName":{},"indexByName":{},"renameByName":{"Value #A (lastNotNull)":"Size","Value #B (lastNotNull)":"Available","mountpoint":"Mounted on"}}},{"id":"sortBy","options":{"fields":{},"sort":[{"field":"Mounted on"}]}}],"type":"table"},{"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":26},"id":10,"panels":[],"title":"Network","type":"row"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"description":"Network received (bits/s)","fieldConfig":{"defaults":{"custom":{"fillOpacity":0,"showPoints":"never"},"min":0,"unit":"bps"}},"gridPos":{"h":7,"w":12,"x":0,"y":27},"id":11,"options":{"tooltip":{"mode":"multi"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"rate(node_network_receive_bytes_total{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\", device!=\"lo\"}[$__rate_interval]) * 8","intervalFactor":1,"legendFormat":"{{device}}"}],"title":"Network Received","type":"timeseries"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"description":"Network transmitted (bits/s)","fieldConfig":{"defaults":{"custom":{"fillOpacity":0},"min":0,"unit":"bps"}},"gridPos":{"h":7,"w":12,"x":12,"y":27},"id":12,"options":{"tooltip":{"mode":"multi"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"rate(node_network_transmit_bytes_total{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\", device!=\"lo\"}[$__rate_interval]) * 8","intervalFactor":1,"legendFormat":"{{device}}"}],"title":"Network Transmitted","type":"timeseries"}],"refresh":"30s","schemaVersion":39,"tags":["node-exporter-mixin"],"templating":{"list":[{"name":"datasource","query":"prometheus","type":"datasource"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":2,"label":"Cluster","name":"cluster","query":"label_values(node_uname_info{job=\"node-exporter\", sysname!=\"Darwin\"}, cluster)","refresh":2,"type":"query","allValue":".*"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"label":"Instance","name":"instance","query":"label_values(node_uname_info{job=\"node-exporter\", cluster=\"$cluster\", sysname!=\"Darwin\"}, instance)","refresh":2,"type":"query"}]},"time":{"from":"now-1h","to":"now"},"timezone": "utc","title":"Node Exporter / Nodes","uid":"7d57716318ee0dddbac5a7f451fb7753"}
|
|
---
|
|
# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/persistentvolumesusage.yaml
|
|
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
namespace: default
|
|
name: kube-prometheus-stack-persistentvolumesusage
|
|
annotations:
|
|
{}
|
|
labels:
|
|
grafana_dashboard: "1"
|
|
#TBR: app: kube-prometheus-stack-grafana
|
|
app.kubernetes.io/name: kube-prometheus-stack-grafana #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
data:
|
|
persistentvolumesusage.json: |-
|
|
{"editable":true,"links":[{"asDropdown":true,"includeVars":true,"keepTime":true,"tags":["kubernetes-mixin"],"targetBlank":false,"title":"Kubernetes","type":"dashboards"}],"panels":[{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"bytes"}},"gridPos":{"h":7,"w":18,"y":0},"id":1,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(\n sum without(instance, node) (topk(1, (kubelet_volume_stats_capacity_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})))\n -\n sum without(instance, node) (topk(1, (kubelet_volume_stats_available_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})))\n)\n","legendFormat":"Used Space"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum without(instance, node) (topk(1, (kubelet_volume_stats_available_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})))\n","legendFormat":"Free Space"}],"title":"Volume Space Usage","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"color":{"mode":"thresholds"},"max":100,"min":0,"thresholds":{"mode":"absolute","steps":[{"color":"green","value":0},{"color":"orange","value":80},{"color":"red","value":90}]},"unit":"percent"}},"gridPos":{"h":7,"w":6,"x":18,"y":0},"id":2,"interval":"1m","pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"max without(instance,node) (\n(\n topk(1, kubelet_volume_stats_capacity_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n -\n topk(1, kubelet_volume_stats_available_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n)\n/\ntopk(1, kubelet_volume_stats_capacity_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n* 100)\n","instant":true}],"title":"Volume Space Usage","type":"gauge"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"none"}},"gridPos":{"h":7,"w":18,"y":7},"id":3,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum without(instance, node) (topk(1, (kubelet_volume_stats_inodes_used{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})))","legendFormat":"Used inodes"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"(\n sum without(instance, node) (topk(1, (kubelet_volume_stats_inodes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})))\n -\n sum without(instance, node) (topk(1, (kubelet_volume_stats_inodes_used{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})))\n)\n","legendFormat":"Free inodes"}],"title":"Volume inodes Usage","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"color":{"mode":"thresholds"},"max":100,"min":0,"thresholds":{"mode":"absolute","steps":[{"color":"green","value":0},{"color":"orange","value":80},{"color":"red","value":90}]},"unit":"percent"}},"gridPos":{"h":7,"w":6,"x":18,"y":7},"id":4,"interval":"1m","pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"max without(instance,node) (\ntopk(1, kubelet_volume_stats_inodes_used{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n/\ntopk(1, kubelet_volume_stats_inodes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n* 100)\n","instant":true}],"title":"Volume inodes Usage","type":"gauge"}],"refresh":"10s","schemaVersion":39,"tags":["kubernetes-mixin"],"templating":{"list":[{"current":{"selected":true,"text":"default","value":"default"},"hide":0,"label":"Data source","name":"datasource","query":"prometheus","regex":"","type":"datasource"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":2,"label":"cluster","name":"cluster","query":"label_values(kubelet_volume_stats_capacity_bytes{job=\"kubelet\", metrics_path=\"/metrics\"}, cluster)","refresh":2,"sort":1,"type":"query","allValue":".*"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":0,"label":"Namespace","name":"namespace","query":"label_values(kubelet_volume_stats_capacity_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\"}, namespace)","refresh":2,"sort":1,"type":"query"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":0,"label":"PersistentVolumeClaim","name":"volume","query":"label_values(kubelet_volume_stats_capacity_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\"}, persistentvolumeclaim)","refresh":2,"sort":1,"type":"query"}]},"time":{"from":"now-1h","to":"now"},"timezone": "utc","title":"Kubernetes / Persistent Volumes","uid":"919b92a8e8041bd567af9edab12c840c"}
|
|
---
|
|
# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/pod-total.yaml
|
|
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
namespace: default
|
|
name: kube-prometheus-stack-pod-total
|
|
annotations:
|
|
{}
|
|
labels:
|
|
grafana_dashboard: "1"
|
|
#TBR: app: kube-prometheus-stack-grafana
|
|
app.kubernetes.io/name: kube-prometheus-stack-grafana #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
data:
|
|
pod-total.json: |-
|
|
{"editable":true,"links":[{"asDropdown":true,"includeVars":true,"keepTime":true,"tags":["kubernetes-mixin"],"targetBlank":false,"title":"Kubernetes","type":"dashboards"}],"panels":[{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"displayName":"$pod","max":10000000000,"min":0,"thresholds":{"steps":[{"color":"dark-green","index":0,"value":null},{"color":"dark-yellow","index":1,"value":5000000000},{"color":"dark-red","index":2,"value":7000000000}]},"unit":"Bps"}},"gridPos":{"h":9,"w":12,"x":0,"y":0},"id":1,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$__rate_interval]))","legendFormat":"__auto"}],"title":"Current Rate of Bytes Received","type":"gauge"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"displayName":"$pod","max":10000000000,"min":0,"thresholds":{"steps":[{"color":"dark-green","index":0,"value":null},{"color":"dark-yellow","index":1,"value":5000000000},{"color":"dark-red","index":2,"value":7000000000}]},"unit":"Bps"}},"gridPos":{"h":9,"w":12,"x":12,"y":0},"id":2,"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$__rate_interval]))","legendFormat":"__auto"}],"title":"Current Rate of Bytes Transmitted","type":"gauge"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"showPoints":"never"},"unit":"binBps"}},"gridPos":{"h":9,"w":12,"x":0,"y":9},"id":3,"interval":"1m","options":{"legend":{"asTable":true,"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)","legendFormat":"__auto"}],"title":"Receive Bandwidth","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"showPoints":"never"},"unit":"binBps"}},"gridPos":{"h":9,"w":12,"x":12,"y":9},"id":4,"interval":"1m","options":{"legend":{"asTable":true,"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)","legendFormat":"__auto"}],"title":"Transmit Bandwidth","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"showPoints":"never"},"unit":"pps"}},"gridPos":{"h":9,"w":12,"x":0,"y":18},"id":5,"interval":"1m","options":{"legend":{"asTable":true,"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)","legendFormat":"__auto"}],"title":"Rate of Received Packets","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"showPoints":"never"},"unit":"pps"}},"gridPos":{"h":9,"w":12,"x":12,"y":18},"id":6,"interval":"1m","options":{"legend":{"asTable":true,"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)","legendFormat":"__auto"}],"title":"Rate of Transmitted Packets","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"showPoints":"never"},"unit":"pps"}},"gridPos":{"h":9,"w":12,"x":0,"y":27},"id":7,"interval":"1m","options":{"legend":{"asTable":true,"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)","legendFormat":"__auto"}],"title":"Rate of Received Packets Dropped","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"showPoints":"never"},"unit":"pps"}},"gridPos":{"h":9,"w":12,"x":12,"y":27},"id":8,"interval":"1m","options":{"legend":{"asTable":true,"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)","legendFormat":"__auto"}],"title":"Rate of Transmitted Packets Dropped","type":"timeseries"}],"refresh":"10s","schemaVersion":39,"tags":["kubernetes-mixin"],"templating":{"list":[{"current":{"selected":true,"text":"default","value":"default"},"hide":0,"label":"Data source","name":"datasource","query":"prometheus","regex":"","type":"datasource"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":2,"label":"cluster","name":"cluster","query":"label_values(up{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\"}, cluster)","refresh":2,"sort":1,"type":"query","allValue":".*"},{"allValue":".+","current":{"selected":false,"text":"kube-system","value":"kube-system"},"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":0,"includeAll":true,"label":"namespace","name":"namespace","query":"label_values(container_network_receive_packets_total{cluster=\"$cluster\"}, namespace)","refresh":2,"sort":1,"type":"query"},{"current":{"selected":false,"text":"kube-system","value":"kube-system"},"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":0,"label":"pod","name":"pod","query":"label_values(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}, pod)","refresh":2,"sort":1,"type":"query"}]},"time":{"from":"now-1h","to":"now"},"timezone": "utc","title":"Kubernetes / Networking / Pod","uid":"7a18067ce943a40ae25454675c19ff5c"}
|
|
---
|
|
# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/prometheus.yaml
|
|
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
namespace: default
|
|
name: kube-prometheus-stack-prometheus
|
|
annotations:
|
|
{}
|
|
labels:
|
|
grafana_dashboard: "1"
|
|
#TBR: app: kube-prometheus-stack-grafana
|
|
app.kubernetes.io/name: kube-prometheus-stack-grafana #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
data:
|
|
prometheus.json: |-
|
|
{"annotations":{"list":[]},"editable":true,"gnetId":null,"graphTooltip":0,"hideControls":false,"links":[],"refresh":"60s","rows":[{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":1,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":12,"stack":false,"steppedLine":false,"styles":[{"alias":"Time","dateFormat":"YYYY-MM-DD HH:mm:ss","pattern":"Time","type":"hidden"},{"alias":"Count","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #A","thresholds":[],"type":"hidden","unit":"short"},{"alias":"Uptime","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #B","thresholds":[],"type":"number","unit":"s"},{"alias":"Cluster","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"cluster","thresholds":[],"type":"number","unit":"short"},{"alias":"Instance","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"instance","thresholds":[],"type":"number","unit":"short"},{"alias":"Job","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"job","thresholds":[],"type":"number","unit":"short"},{"alias":"Version","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"version","thresholds":[],"type":"number","unit":"short"},{"alias":"","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"pattern":"/.*/","thresholds":[],"type":"string","unit":"short"}],"targets":[{"expr":"count by (cluster, job, instance, version) (prometheus_build_info{cluster=~\"$cluster\", job=~\"$job\", instance=~\"$instance\"})","format":"table","instant":true,"legendFormat":"","refId":"A"},{"expr":"max by (cluster, job, instance) (time() - process_start_time_seconds{cluster=~\"$cluster\", job=~\"$job\", instance=~\"$instance\"})","format":"table","instant":true,"legendFormat":"","refId":"B"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Prometheus Stats","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"transform":"table","type":"table","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Prometheus Stats","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":2,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(prometheus_target_sync_length_seconds_sum{cluster=~\"$cluster\",job=~\"$job\",instance=~\"$instance\"}[5m])) by (cluster, job, scrape_job, instance) * 1e3","format":"time_series","legendFormat":"{{cluster}}:{{job}}:{{instance}}:{{scrape_job}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Target Sync","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"ms","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":3,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"sum by (cluster, job, instance) (prometheus_sd_discovered_targets{cluster=~\"$cluster\", job=~\"$job\",instance=~\"$instance\"})","format":"time_series","legendFormat":"{{cluster}}:{{job}}:{{instance}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Targets","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Discovery","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":4,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":4,"stack":false,"steppedLine":false,"targets":[{"expr":"rate(prometheus_target_interval_length_seconds_sum{cluster=~\"$cluster\", job=~\"$job\",instance=~\"$instance\"}[5m]) / rate(prometheus_target_interval_length_seconds_count{cluster=~\"$cluster\", job=~\"$job\",instance=~\"$instance\"}[5m]) * 1e3","format":"time_series","legendFormat":"{{cluster}}:{{job}}:{{instance}} {{interval}} configured","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Average Scrape Interval Duration","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"ms","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":5,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":4,"stack":true,"steppedLine":false,"targets":[{"expr":"sum by (cluster, job, instance) (rate(prometheus_target_scrapes_exceeded_body_size_limit_total{cluster=~\"$cluster\",job=~\"$job\",instance=~\"$instance\"}[1m]))","format":"time_series","legendFormat":"exceeded body size limit: {{cluster}} {{job}} {{instance}}","legendLink":null},{"expr":"sum by (cluster, job, instance) (rate(prometheus_target_scrapes_exceeded_sample_limit_total{cluster=~\"$cluster\",job=~\"$job\",instance=~\"$instance\"}[1m]))","format":"time_series","legendFormat":"exceeded sample limit: {{cluster}} {{job}} {{instance}}","legendLink":null},{"expr":"sum by (cluster, job, instance) (rate(prometheus_target_scrapes_sample_duplicate_timestamp_total{cluster=~\"$cluster\",job=~\"$job\",instance=~\"$instance\"}[1m]))","format":"time_series","legendFormat":"duplicate timestamp: {{cluster}} {{job}} {{instance}}","legendLink":null},{"expr":"sum by (cluster, job, instance) (rate(prometheus_target_scrapes_sample_out_of_bounds_total{cluster=~\"$cluster\",job=~\"$job\",instance=~\"$instance\"}[1m]))","format":"time_series","legendFormat":"out of bounds: {{cluster}} {{job}} {{instance}}","legendLink":null},{"expr":"sum by (cluster, job, instance) (rate(prometheus_target_scrapes_sample_out_of_order_total{cluster=~\"$cluster\",job=~\"$job\",instance=~\"$instance\"}[1m]))","format":"time_series","legendFormat":"out of order: {{cluster}} {{job}} {{instance}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Scrape failures","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":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":6,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":4,"stack":true,"steppedLine":false,"targets":[{"expr":"rate(prometheus_tsdb_head_samples_appended_total{cluster=~\"$cluster\", job=~\"$job\",instance=~\"$instance\"}[5m])","format":"time_series","legendFormat":"{{cluster}} {{job}} {{instance}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Appended Samples","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":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Retrieval","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":7,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"prometheus_tsdb_head_series{cluster=~\"$cluster\",job=~\"$job\",instance=~\"$instance\"}","format":"time_series","legendFormat":"{{cluster}} {{job}} {{instance}} head series","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Head Series","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":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":8,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"prometheus_tsdb_head_chunks{cluster=~\"$cluster\",job=~\"$job\",instance=~\"$instance\"}","format":"time_series","legendFormat":"{{cluster}} {{job}} {{instance}} head chunks","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Head Chunks","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":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Storage","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":9,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"rate(prometheus_engine_query_duration_seconds_count{cluster=~\"$cluster\",job=~\"$job\",instance=~\"$instance\",slice=\"inner_eval\"}[5m])","format":"time_series","legendFormat":"{{cluster}} {{job}} {{instance}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Query Rate","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":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":10,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"max by (slice) (prometheus_engine_query_duration_seconds{quantile=\"0.9\",cluster=~\"$cluster\", job=~\"$job\",instance=~\"$instance\"}) * 1e3","format":"time_series","legendFormat":"{{slice}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Stage Duration","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"ms","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Query","titleSize":"h6"}],"schemaVersion":14,"style":"dark","tags":["prometheus-mixin"],"templating":{"list":[{"current":{"text":"default","value":"default"},"hide":0,"label":"Data source","name":"datasource","options":[],"query":"prometheus","refresh":1,"regex":"","type":"datasource"},{"allValue":".*","current":{"selected":true,"text":"All","value":"$__all"},"datasource":"$datasource","hide":2,"includeAll":true,"label":"cluster","multi":true,"name":"cluster","options":[],"query":"label_values(prometheus_build_info{}, cluster)","refresh":1,"regex":"","sort":2,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false},{"allValue":".+","current":{"selected":true,"text":"All","value":"$__all"},"datasource":"$datasource","hide":0,"includeAll":true,"label":"job","multi":true,"name":"job","options":[],"query":"label_values(prometheus_build_info{cluster=~\"$cluster\"}, job)","refresh":1,"regex":"","sort":2,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false},{"allValue":".+","current":{"selected":true,"text":"All","value":"$__all"},"datasource":"$datasource","hide":0,"includeAll":true,"label":"instance","multi":true,"name":"instance","options":[],"query":"label_values(prometheus_build_info{cluster=~\"$cluster\", job=~\"$job\"}, instance)","refresh":1,"regex":"","sort":2,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false}]},"time":{"from":"now-1h","to":"now"},"timepicker":{"refresh_intervals":["5s","10s","30s","1m","5m","15m","30m","1h","2h","1d"],"time_options":["5m","15m","1h","6h","12h","24h","2d","7d","30d"]},"timezone": "utc","title":"Prometheus / Overview","uid":"","version":0}
|
|
---
|
|
# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/proxy.yaml
|
|
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
namespace: default
|
|
name: kube-prometheus-stack-proxy
|
|
annotations:
|
|
{}
|
|
labels:
|
|
grafana_dashboard: "1"
|
|
#TBR: app: kube-prometheus-stack-grafana
|
|
app.kubernetes.io/name: kube-prometheus-stack-grafana #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
data:
|
|
proxy.json: |-
|
|
{"editable":true,"links":[{"asDropdown":true,"includeVars":true,"keepTime":true,"tags":["kubernetes-mixin"],"targetBlank":false,"title":"Kubernetes","type":"dashboards"}],"panels":[{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"none"}},"gridPos":{"h":7,"w":4,"x":0,"y":0},"id":1,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(up{cluster=\"$cluster\", job=\"kube-proxy\"})","instant":true}],"title":"Up","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"ops"}},"gridPos":{"h":7,"w":10,"x":4,"y":0},"id":2,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(kubeproxy_sync_proxy_rules_duration_seconds_count{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\"}[$__rate_interval]))","legendFormat":"rate"}],"title":"Rules Sync Rate","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"s"}},"gridPos":{"h":7,"w":10,"x":14,"y":0},"id":3,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"histogram_quantile(0.99,rate(kubeproxy_sync_proxy_rules_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\"}[$__rate_interval]))","legendFormat":"{{instance}}"}],"title":"Rules Sync Latency 99th Quantile","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"ops"}},"gridPos":{"h":7,"w":12,"x":0,"y":7},"id":4,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(kubeproxy_network_programming_duration_seconds_count{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\"}[$__rate_interval]))","legendFormat":"rate"}],"title":"Network Programming Rate","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"s"}},"gridPos":{"h":7,"w":12,"x":12,"y":7},"id":5,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"histogram_quantile(0.99, sum(rate(kubeproxy_network_programming_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\"}[$__rate_interval])) by (instance, le))","legendFormat":"{{instance}}"}],"title":"Network Programming Latency 99th Quantile","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"ops"}},"gridPos":{"h":7,"w":8,"x":0,"y":14},"id":6,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kube-proxy\", instance=~\"$instance\",code=~\"2..\"}[$__rate_interval]))","legendFormat":"2xx"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kube-proxy\", instance=~\"$instance\",code=~\"3..\"}[$__rate_interval]))","legendFormat":"3xx"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kube-proxy\", instance=~\"$instance\",code=~\"4..\"}[$__rate_interval]))","legendFormat":"4xx"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kube-proxy\", instance=~\"$instance\",code=~\"5..\"}[$__rate_interval]))","legendFormat":"5xx"}],"title":"Kube API Request Rate","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"ops"}},"gridPos":{"h":7,"w":16,"x":8,"y":14},"id":7,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-proxy\",instance=~\"$instance\",verb=\"POST\"}[$__rate_interval])) by (verb, url, le))","legendFormat":"{{verb}} {{url}}"}],"title":"Post Request Latency 99th Quantile","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"s"}},"gridPos":{"h":7,"w":24,"x":0,"y":21},"id":8,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\", verb=\"GET\"}[$__rate_interval])) by (verb, url, le))","legendFormat":"{{verb}} {{url}}"}],"title":"Get Request Latency 99th Quantile","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"bytes"}},"gridPos":{"h":7,"w":8,"x":0,"y":28},"id":9,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"process_resident_memory_bytes{cluster=\"$cluster\", job=\"kube-proxy\",instance=~\"$instance\"}","legendFormat":"{{instance}}"}],"title":"Memory","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"short"}},"gridPos":{"h":7,"w":8,"x":8,"y":28},"id":10,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"rate(process_cpu_seconds_total{cluster=\"$cluster\", job=\"kube-proxy\",instance=~\"$instance\"}[$__rate_interval])","legendFormat":"{{instance}}"}],"title":"CPU usage","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"short"}},"gridPos":{"h":7,"w":8,"x":16,"y":28},"id":11,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"go_goroutines{cluster=\"$cluster\", job=\"kube-proxy\",instance=~\"$instance\"}","legendFormat":"{{instance}}"}],"title":"Goroutines","type":"timeseries"}],"refresh":"10s","schemaVersion":39,"tags":["kubernetes-mixin"],"templating":{"list":[{"current":{"selected":true,"text":"default","value":"default"},"hide":0,"label":"Data source","name":"datasource","query":"prometheus","regex":"","type":"datasource"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":2,"label":"cluster","name":"cluster","query":"label_values(up{job=\"kube-proxy\"}, cluster)","refresh":2,"sort":1,"type":"query","allValue":".*"},{"allValue":".+","datasource":{"type":"prometheus","uid":"${datasource}"},"hide":0,"includeAll":true,"label":"instance","name":"instance","query":"label_values(up{job=\"kube-proxy\", cluster=\"$cluster\", job=\"kube-proxy\"}, instance)","refresh":2,"type":"query"}]},"time":{"from":"now-1h","to":"now"},"timezone": "utc","title":"Kubernetes / Proxy","uid":"632e265de029684c40b21cb76bca4f94"}
|
|
---
|
|
# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/scheduler.yaml
|
|
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
namespace: default
|
|
name: kube-prometheus-stack-scheduler
|
|
annotations:
|
|
{}
|
|
labels:
|
|
grafana_dashboard: "1"
|
|
#TBR: app: kube-prometheus-stack-grafana
|
|
app.kubernetes.io/name: kube-prometheus-stack-grafana #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
data:
|
|
scheduler.json: |-
|
|
{"editable":true,"links":[{"asDropdown":true,"includeVars":true,"keepTime":true,"tags":["kubernetes-mixin"],"targetBlank":false,"title":"Kubernetes","type":"dashboards"}],"panels":[{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"unit":"none"}},"gridPos":{"h":7,"w":4,"x":0,"y":0},"id":1,"interval":"1m","options":{"colorMode":"none"},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(up{cluster=\"$cluster\", job=\"kube-scheduler\"})","instant":true}],"title":"Up","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"ops"}},"gridPos":{"h":7,"w":10,"x":4,"y":0},"id":2,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(scheduler_e2e_scheduling_duration_seconds_count{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance)","legendFormat":"{{cluster}} {{instance}} e2e"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(scheduler_binding_duration_seconds_count{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance)","legendFormat":"{{cluster}} {{instance}} binding"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(scheduler_scheduling_algorithm_duration_seconds_count{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance)","legendFormat":"{{cluster}} {{instance}} scheduling algorithm"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(scheduler_volume_scheduling_duration_seconds_count{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance)","legendFormat":"{{cluster}} {{instance}} volume"}],"title":"Scheduling Rate","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"s"}},"gridPos":{"h":7,"w":10,"x":14,"y":0},"id":3,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"histogram_quantile(0.99, sum(rate(scheduler_e2e_scheduling_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\",instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance, le))","legendFormat":"{{cluster}} {{instance}} e2e"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"histogram_quantile(0.99, sum(rate(scheduler_binding_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\",instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance, le))","legendFormat":"{{cluster}} {{instance}} binding"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"histogram_quantile(0.99, sum(rate(scheduler_scheduling_algorithm_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\",instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance, le))","legendFormat":"{{cluster}} {{instance}} scheduling algorithm"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"histogram_quantile(0.99, sum(rate(scheduler_volume_scheduling_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\",instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance, le))","legendFormat":"{{cluster}} {{instance}} volume"}],"title":"Scheduling latency 99th Quantile","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"ops"}},"gridPos":{"h":7,"w":8,"x":0,"y":7},"id":4,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\",code=~\"2..\"}[$__rate_interval]))","legendFormat":"2xx"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\",code=~\"3..\"}[$__rate_interval]))","legendFormat":"3xx"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\",code=~\"4..\"}[$__rate_interval]))","legendFormat":"4xx"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\",code=~\"5..\"}[$__rate_interval]))","legendFormat":"5xx"}],"title":"Kube API Request Rate","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"ops"}},"gridPos":{"h":7,"w":16,"x":8,"y":7},"id":5,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\", verb=\"POST\"}[$__rate_interval])) by (verb, url, le))","legendFormat":"{{verb}} {{url}}"}],"title":"Post Request Latency 99th Quantile","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"s"}},"gridPos":{"h":7,"w":24,"x":0,"y":14},"id":6,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\", verb=\"GET\"}[$__rate_interval])) by (verb, url, le))","legendFormat":"{{verb}} {{url}}"}],"title":"Get Request Latency 99th Quantile","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"bytes"}},"gridPos":{"h":7,"w":8,"x":0,"y":21},"id":7,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"process_resident_memory_bytes{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}","legendFormat":"{{instance}}"}],"title":"Memory","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"short"}},"gridPos":{"h":7,"w":8,"x":8,"y":21},"id":8,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"rate(process_cpu_seconds_total{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[$__rate_interval])","legendFormat":"{{instance}}"}],"title":"CPU usage","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"short"}},"gridPos":{"h":7,"w":8,"x":16,"y":21},"id":9,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"go_goroutines{cluster=\"$cluster\", job=\"kube-scheduler\",instance=~\"$instance\"}","legendFormat":"{{instance}}"}],"title":"Goroutines","type":"timeseries"}],"refresh":"10s","schemaVersion":39,"tags":["kubernetes-mixin"],"templating":{"list":[{"current":{"selected":true,"text":"default","value":"default"},"hide":0,"label":"Data source","name":"datasource","query":"prometheus","regex":"","type":"datasource"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":2,"label":"cluster","name":"cluster","query":"label_values(up{job=\"kube-scheduler\"}, cluster)","refresh":2,"sort":1,"type":"query","allValue":".*"},{"allValue":".+","datasource":{"type":"prometheus","uid":"${datasource}"},"hide":0,"includeAll":true,"label":"instance","name":"instance","query":"label_values(up{job=\"kube-scheduler\", cluster=\"$cluster\"}, instance)","refresh":2,"type":"query"}]},"time":{"from":"now-1h","to":"now"},"timezone": "utc","title":"Kubernetes / Scheduler","uid":"2e6b6a3b4bddf1427b3a55aa1311c656"}
|
|
---
|
|
# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/workload-total.yaml
|
|
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
namespace: default
|
|
name: kube-prometheus-stack-workload-total
|
|
annotations:
|
|
{}
|
|
labels:
|
|
grafana_dashboard: "1"
|
|
#TBR: app: kube-prometheus-stack-grafana
|
|
app.kubernetes.io/name: kube-prometheus-stack-grafana #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
data:
|
|
workload-total.json: |-
|
|
{"editable":true,"links":[{"asDropdown":true,"includeVars":true,"keepTime":true,"tags":["kubernetes-mixin"],"targetBlank":false,"title":"Kubernetes","type":"dashboards"}],"panels":[{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"color":{"fixedColor":"green","mode":"fixed"},"unit":"Bps"}},"gridPos":{"h":9,"w":12,"x":0,"y":0},"id":1,"options":{"displayMode":"basic","showUnfilled":false},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(sum(rate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","legendFormat":"__auto"}],"title":"Current Rate of Bytes Received","type":"bargauge"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"color":{"fixedColor":"green","mode":"fixed"},"unit":"Bps"}},"gridPos":{"h":9,"w":12,"x":12,"y":0},"id":2,"options":{"displayMode":"basic","showUnfilled":false},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(sum(rate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","legendFormat":"__auto"}],"title":"Current Rate of Bytes Transmitted","type":"bargauge"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"color":{"fixedColor":"green","mode":"fixed"},"unit":"Bps"}},"gridPos":{"h":9,"w":12,"x":0,"y":9},"id":3,"options":{"displayMode":"basic","showUnfilled":false},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(avg(rate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","legendFormat":"__auto"}],"title":"Average Rate of Bytes Received","type":"bargauge"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"color":{"fixedColor":"green","mode":"fixed"},"unit":"Bps"}},"gridPos":{"h":9,"w":12,"x":12,"y":9},"id":4,"options":{"displayMode":"basic","showUnfilled":false},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(avg(rate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","legendFormat":"__auto"}],"title":"Average Rate of Bytes Transmitted","type":"bargauge"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"binBps"}},"gridPos":{"h":9,"w":12,"x":0,"y":18},"id":5,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(sum(rate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","legendFormat":"__auto"}],"title":"Receive Bandwidth","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"binBps"}},"gridPos":{"h":9,"w":12,"x":12,"y":18},"id":6,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(sum(rate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","legendFormat":"__auto"}],"title":"Transmit Bandwidth","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"pps"}},"gridPos":{"h":9,"w":12,"x":0,"y":27},"id":7,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(sum(rate(container_network_receive_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","legendFormat":"__auto"}],"title":"Rate of Received Packets","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"pps"}},"gridPos":{"h":9,"w":12,"x":12,"y":27},"id":8,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(sum(rate(container_network_transmit_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","legendFormat":"__auto"}],"title":"Rate of Transmitted Packets","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"pps"}},"gridPos":{"h":9,"w":12,"x":0,"y":36},"id":9,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(sum(rate(container_network_receive_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","legendFormat":"__auto"}],"title":"Rate of Received Packets Dropped","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":10,"showPoints":"never","spanNulls":true},"unit":"pps"}},"gridPos":{"h":9,"w":12,"x":12,"y":36},"id":10,"interval":"1m","options":{"legend":{"asTable":true,"calcs":["lastNotNull"],"displayMode":"table","placement":"right","showLegend":true},"tooltip":{"mode":"single"}},"pluginVersion":"v11.4.0","targets":[{"datasource":{"type":"prometheus","uid":"${datasource}"},"expr":"sort_desc(sum(rate(container_network_transmit_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","legendFormat":"__auto"}],"title":"Rate of Transmitted Packets Dropped","type":"timeseries"}],"refresh":"10s","schemaVersion":39,"tags":["kubernetes-mixin"],"templating":{"list":[{"current":{"selected":true,"text":"default","value":"default"},"hide":0,"label":"Data source","name":"datasource","query":"prometheus","regex":"","type":"datasource"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":2,"label":"cluster","name":"cluster","query":"label_values(kube_pod_info{job=\"kube-state-metrics\"}, cluster)","refresh":2,"sort":1,"type":"query","allValue":".*"},{"allValue":".+","current":{"selected":false,"text":"kube-system","value":"kube-system"},"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":0,"includeAll":true,"label":"namespace","name":"namespace","query":"label_values(container_network_receive_packets_total{cluster=\"$cluster\"}, namespace)","refresh":2,"sort":1,"type":"query"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"hide":0,"label":"workload","name":"workload","query":"label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\"}, workload)","refresh":2,"sort":1,"type":"query"},{"allValue":".+","datasource":{"type":"prometheus","uid":"${datasource}"},"hide":0,"includeAll":true,"label":"workload_type","name":"type","query":"label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\"}, workload_type)","refresh":2,"sort":1,"type":"query"}]},"time":{"from":"now-1h","to":"now"},"timezone": "utc","title":"Kubernetes / Networking / Workload","uid":"728bf77cc1166d2f3133bf25846876cc"}
|
|
---
|
|
# Source: kube-prometheus-stack/charts/grafana/templates/clusterrole.yaml
|
|
kind: ClusterRole
|
|
apiVersion: rbac.authorization.k8s.io/v1
|
|
metadata:
|
|
labels:
|
|
|
|
helm.sh/chart: grafana-8.8.2
|
|
app.kubernetes.io/name: grafana
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "11.4.0"
|
|
name: kube-prometheus-stack-grafana-clusterrole
|
|
rules:
|
|
- apiGroups: [""] # "" indicates the core API group
|
|
resources: ["configmaps", "secrets"]
|
|
verbs: ["get", "watch", "list"]
|
|
---
|
|
# Source: kube-prometheus-stack/charts/kube-state-metrics/templates/role.yaml
|
|
apiVersion: rbac.authorization.k8s.io/v1
|
|
kind: ClusterRole
|
|
metadata:
|
|
labels:
|
|
helm.sh/chart: kube-state-metrics-5.28.0
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/component: metrics
|
|
app.kubernetes.io/part-of: kube-state-metrics
|
|
app.kubernetes.io/name: kube-state-metrics
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "2.14.0"
|
|
#TBR: release: kube-prometheus-stack
|
|
name: kube-prometheus-stack-kube-state-metrics
|
|
rules:
|
|
|
|
- apiGroups: ["certificates.k8s.io"]
|
|
resources:
|
|
- certificatesigningrequests
|
|
verbs: ["list", "watch"]
|
|
|
|
- apiGroups: [""]
|
|
resources:
|
|
- configmaps
|
|
verbs: ["list", "watch"]
|
|
|
|
- apiGroups: ["batch"]
|
|
resources:
|
|
- cronjobs
|
|
verbs: ["list", "watch"]
|
|
|
|
- apiGroups: ["extensions", "apps"]
|
|
resources:
|
|
- daemonsets
|
|
verbs: ["list", "watch"]
|
|
|
|
- apiGroups: ["extensions", "apps"]
|
|
resources:
|
|
- deployments
|
|
verbs: ["list", "watch"]
|
|
|
|
- apiGroups: [""]
|
|
resources:
|
|
- endpoints
|
|
verbs: ["list", "watch"]
|
|
|
|
- apiGroups: ["autoscaling"]
|
|
resources:
|
|
- horizontalpodautoscalers
|
|
verbs: ["list", "watch"]
|
|
|
|
- apiGroups: ["extensions", "networking.k8s.io"]
|
|
resources:
|
|
- ingresses
|
|
verbs: ["list", "watch"]
|
|
|
|
- apiGroups: ["batch"]
|
|
resources:
|
|
- jobs
|
|
verbs: ["list", "watch"]
|
|
|
|
- apiGroups: ["coordination.k8s.io"]
|
|
resources:
|
|
- leases
|
|
verbs: ["list", "watch"]
|
|
|
|
- apiGroups: [""]
|
|
resources:
|
|
- limitranges
|
|
verbs: ["list", "watch"]
|
|
|
|
- apiGroups: ["admissionregistration.k8s.io"]
|
|
resources:
|
|
- mutatingwebhookconfigurations
|
|
verbs: ["list", "watch"]
|
|
|
|
- apiGroups: [""]
|
|
resources:
|
|
- namespaces
|
|
verbs: ["list", "watch"]
|
|
|
|
- apiGroups: ["networking.k8s.io"]
|
|
resources:
|
|
- networkpolicies
|
|
verbs: ["list", "watch"]
|
|
|
|
- apiGroups: [""]
|
|
resources:
|
|
- nodes
|
|
verbs: ["list", "watch"]
|
|
|
|
- apiGroups: [""]
|
|
resources:
|
|
- persistentvolumeclaims
|
|
verbs: ["list", "watch"]
|
|
|
|
- apiGroups: [""]
|
|
resources:
|
|
- persistentvolumes
|
|
verbs: ["list", "watch"]
|
|
|
|
- apiGroups: ["policy"]
|
|
resources:
|
|
- poddisruptionbudgets
|
|
verbs: ["list", "watch"]
|
|
|
|
- apiGroups: [""]
|
|
resources:
|
|
- pods
|
|
verbs: ["list", "watch"]
|
|
|
|
- apiGroups: ["extensions", "apps"]
|
|
resources:
|
|
- replicasets
|
|
verbs: ["list", "watch"]
|
|
|
|
- apiGroups: [""]
|
|
resources:
|
|
- replicationcontrollers
|
|
verbs: ["list", "watch"]
|
|
|
|
- apiGroups: [""]
|
|
resources:
|
|
- resourcequotas
|
|
verbs: ["list", "watch"]
|
|
|
|
- apiGroups: [""]
|
|
resources:
|
|
- secrets
|
|
verbs: ["list", "watch"]
|
|
|
|
- apiGroups: [""]
|
|
resources:
|
|
- services
|
|
verbs: ["list", "watch"]
|
|
|
|
- apiGroups: ["apps"]
|
|
resources:
|
|
- statefulsets
|
|
verbs: ["list", "watch"]
|
|
|
|
- apiGroups: ["storage.k8s.io"]
|
|
resources:
|
|
- storageclasses
|
|
verbs: ["list", "watch"]
|
|
|
|
- apiGroups: ["admissionregistration.k8s.io"]
|
|
resources:
|
|
- validatingwebhookconfigurations
|
|
verbs: ["list", "watch"]
|
|
|
|
- apiGroups: ["storage.k8s.io"]
|
|
resources:
|
|
- volumeattachments
|
|
verbs: ["list", "watch"]
|
|
---
|
|
# Source: kube-prometheus-stack/templates/prometheus-operator/clusterrole.yaml
|
|
apiVersion: rbac.authorization.k8s.io/v1
|
|
kind: ClusterRole
|
|
metadata:
|
|
name: kube-prometheus-stack-operator
|
|
labels:
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
#TBR: app: kube-prometheus-stack-operator
|
|
app.kubernetes.io/name: kube-prometheus-stack-prometheus-operator
|
|
app.kubernetes.io/component: prometheus-operator
|
|
rules:
|
|
- apiGroups:
|
|
- monitoring.coreos.com
|
|
resources:
|
|
- alertmanagers
|
|
- alertmanagers/finalizers
|
|
- alertmanagers/status
|
|
- alertmanagerconfigs
|
|
- prometheuses
|
|
- prometheuses/finalizers
|
|
- prometheuses/status
|
|
- prometheusagents
|
|
- prometheusagents/finalizers
|
|
- prometheusagents/status
|
|
- thanosrulers
|
|
- thanosrulers/finalizers
|
|
- thanosrulers/status
|
|
- scrapeconfigs
|
|
- servicemonitors
|
|
- podmonitors
|
|
- probes
|
|
- prometheusrules
|
|
verbs:
|
|
- '*'
|
|
- apiGroups:
|
|
- apps
|
|
resources:
|
|
- statefulsets
|
|
verbs:
|
|
- '*'
|
|
- apiGroups:
|
|
- ""
|
|
resources:
|
|
- configmaps
|
|
- secrets
|
|
verbs:
|
|
- '*'
|
|
- apiGroups:
|
|
- ""
|
|
resources:
|
|
- pods
|
|
verbs:
|
|
- list
|
|
- delete
|
|
- apiGroups:
|
|
- ""
|
|
resources:
|
|
- services
|
|
- services/finalizers
|
|
- endpoints
|
|
verbs:
|
|
- get
|
|
- create
|
|
- update
|
|
- delete
|
|
- apiGroups:
|
|
- ""
|
|
resources:
|
|
- nodes
|
|
verbs:
|
|
- list
|
|
- watch
|
|
- apiGroups:
|
|
- ""
|
|
resources:
|
|
- namespaces
|
|
verbs:
|
|
- get
|
|
- list
|
|
- watch
|
|
- apiGroups:
|
|
- ""
|
|
resources:
|
|
- events
|
|
verbs:
|
|
- patch
|
|
- create
|
|
- apiGroups:
|
|
- networking.k8s.io
|
|
resources:
|
|
- ingresses
|
|
verbs:
|
|
- get
|
|
- list
|
|
- watch
|
|
- apiGroups:
|
|
- storage.k8s.io
|
|
resources:
|
|
- storageclasses
|
|
verbs:
|
|
- get
|
|
---
|
|
# Source: kube-prometheus-stack/templates/prometheus/clusterrole.yaml
|
|
apiVersion: rbac.authorization.k8s.io/v1
|
|
kind: ClusterRole
|
|
metadata:
|
|
name: kube-prometheus-stack-prometheus
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack-prometheus
|
|
app.kubernetes.io/name: kube-prometheus-stack-prometheus #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
rules:
|
|
# This permission are not in the kube-prometheus repo
|
|
# they're grabbed from https://github.com/prometheus/prometheus/blob/master/documentation/examples/rbac-setup.yml
|
|
- apiGroups: [""]
|
|
resources:
|
|
- nodes
|
|
- nodes/metrics
|
|
- services
|
|
- endpoints
|
|
- pods
|
|
verbs: ["get", "list", "watch"]
|
|
- apiGroups: ["discovery.k8s.io"]
|
|
resources:
|
|
- endpointslices
|
|
verbs: ["get", "list", "watch"]
|
|
- apiGroups:
|
|
- "networking.k8s.io"
|
|
resources:
|
|
- ingresses
|
|
verbs: ["get", "list", "watch"]
|
|
- nonResourceURLs: ["/metrics", "/metrics/cadvisor"]
|
|
verbs: ["get"]
|
|
---
|
|
# Source: kube-prometheus-stack/charts/grafana/templates/clusterrolebinding.yaml
|
|
kind: ClusterRoleBinding
|
|
apiVersion: rbac.authorization.k8s.io/v1
|
|
metadata:
|
|
name: kube-prometheus-stack-grafana-clusterrolebinding
|
|
labels:
|
|
|
|
helm.sh/chart: grafana-8.8.2
|
|
app.kubernetes.io/name: grafana
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "11.4.0"
|
|
subjects:
|
|
- kind: ServiceAccount
|
|
name: kube-prometheus-stack-grafana
|
|
namespace: default
|
|
roleRef:
|
|
kind: ClusterRole
|
|
name: kube-prometheus-stack-grafana-clusterrole
|
|
apiGroup: rbac.authorization.k8s.io
|
|
---
|
|
# Source: kube-prometheus-stack/charts/kube-state-metrics/templates/clusterrolebinding.yaml
|
|
apiVersion: rbac.authorization.k8s.io/v1
|
|
kind: ClusterRoleBinding
|
|
metadata:
|
|
labels:
|
|
helm.sh/chart: kube-state-metrics-5.28.0
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/component: metrics
|
|
app.kubernetes.io/part-of: kube-state-metrics
|
|
app.kubernetes.io/name: kube-state-metrics
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "2.14.0"
|
|
#TBR: release: kube-prometheus-stack
|
|
name: kube-prometheus-stack-kube-state-metrics
|
|
roleRef:
|
|
apiGroup: rbac.authorization.k8s.io
|
|
kind: ClusterRole
|
|
name: kube-prometheus-stack-kube-state-metrics
|
|
subjects:
|
|
- kind: ServiceAccount
|
|
name: kube-prometheus-stack-kube-state-metrics
|
|
namespace: default
|
|
---
|
|
# Source: kube-prometheus-stack/templates/prometheus-operator/clusterrolebinding.yaml
|
|
apiVersion: rbac.authorization.k8s.io/v1
|
|
kind: ClusterRoleBinding
|
|
metadata:
|
|
name: kube-prometheus-stack-operator
|
|
labels:
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
#TBR: app: kube-prometheus-stack-operator
|
|
app.kubernetes.io/name: kube-prometheus-stack-prometheus-operator
|
|
app.kubernetes.io/component: prometheus-operator
|
|
roleRef:
|
|
apiGroup: rbac.authorization.k8s.io
|
|
kind: ClusterRole
|
|
name: kube-prometheus-stack-operator
|
|
subjects:
|
|
- kind: ServiceAccount
|
|
name: kube-prometheus-stack-operator
|
|
namespace: default
|
|
---
|
|
# Source: kube-prometheus-stack/templates/prometheus/clusterrolebinding.yaml
|
|
apiVersion: rbac.authorization.k8s.io/v1
|
|
kind: ClusterRoleBinding
|
|
metadata:
|
|
name: kube-prometheus-stack-prometheus
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack-prometheus
|
|
app.kubernetes.io/name: kube-prometheus-stack-prometheus #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
roleRef:
|
|
apiGroup: rbac.authorization.k8s.io
|
|
kind: ClusterRole
|
|
name: kube-prometheus-stack-prometheus
|
|
subjects:
|
|
- kind: ServiceAccount
|
|
name: kube-prometheus-stack-prometheus
|
|
namespace: default
|
|
---
|
|
# Source: kube-prometheus-stack/charts/grafana/templates/role.yaml
|
|
apiVersion: rbac.authorization.k8s.io/v1
|
|
kind: Role
|
|
metadata:
|
|
name: kube-prometheus-stack-grafana
|
|
namespace: default
|
|
labels:
|
|
|
|
helm.sh/chart: grafana-8.8.2
|
|
app.kubernetes.io/name: grafana
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "11.4.0"
|
|
rules: []
|
|
---
|
|
# Source: kube-prometheus-stack/charts/grafana/templates/rolebinding.yaml
|
|
apiVersion: rbac.authorization.k8s.io/v1
|
|
kind: RoleBinding
|
|
metadata:
|
|
name: kube-prometheus-stack-grafana
|
|
namespace: default
|
|
labels:
|
|
|
|
helm.sh/chart: grafana-8.8.2
|
|
app.kubernetes.io/name: grafana
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "11.4.0"
|
|
roleRef:
|
|
apiGroup: rbac.authorization.k8s.io
|
|
kind: Role
|
|
name: kube-prometheus-stack-grafana
|
|
subjects:
|
|
- kind: ServiceAccount
|
|
name: kube-prometheus-stack-grafana
|
|
namespace: default
|
|
---
|
|
# Source: kube-prometheus-stack/charts/grafana/templates/service.yaml
|
|
apiVersion: v1
|
|
kind: Service
|
|
metadata:
|
|
name: kube-prometheus-stack-grafana
|
|
namespace: default
|
|
labels:
|
|
|
|
helm.sh/chart: grafana-8.8.2
|
|
app.kubernetes.io/name: grafana
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "11.4.0"
|
|
spec:
|
|
type: ClusterIP
|
|
ports:
|
|
- name: http-web
|
|
port: 80
|
|
protocol: TCP
|
|
targetPort: 3000
|
|
selector:
|
|
app.kubernetes.io/name: grafana
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
---
|
|
# Source: kube-prometheus-stack/charts/kube-state-metrics/templates/service.yaml
|
|
apiVersion: v1
|
|
kind: Service
|
|
metadata:
|
|
name: kube-prometheus-stack-kube-state-metrics
|
|
namespace: default
|
|
labels:
|
|
helm.sh/chart: kube-state-metrics-5.28.0
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/component: metrics
|
|
app.kubernetes.io/part-of: kube-state-metrics
|
|
app.kubernetes.io/name: kube-state-metrics
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "2.14.0"
|
|
#TBR: release: kube-prometheus-stack
|
|
annotations:
|
|
prometheus.io/scrape: 'true'
|
|
spec:
|
|
type: "ClusterIP"
|
|
ports:
|
|
- name: "http"
|
|
protocol: TCP
|
|
port: 8080
|
|
targetPort: 8080
|
|
|
|
selector:
|
|
app.kubernetes.io/name: kube-state-metrics
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
---
|
|
# Source: kube-prometheus-stack/charts/prometheus-node-exporter/templates/service.yaml
|
|
apiVersion: v1
|
|
kind: Service
|
|
metadata:
|
|
name: kube-prometheus-stack-prometheus-node-exporter
|
|
namespace: default
|
|
labels:
|
|
helm.sh/chart: prometheus-node-exporter-4.43.1
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/component: metrics
|
|
app.kubernetes.io/part-of: prometheus-node-exporter
|
|
app.kubernetes.io/name: prometheus-node-exporter
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "1.8.2"
|
|
#TBR: release: kube-prometheus-stack
|
|
jobLabel: node-exporter
|
|
annotations:
|
|
prometheus.io/scrape: "true"
|
|
spec:
|
|
type: ClusterIP
|
|
ports:
|
|
- port: 9100
|
|
targetPort: 9100
|
|
protocol: TCP
|
|
name: http-metrics
|
|
selector:
|
|
app.kubernetes.io/name: prometheus-node-exporter
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
---
|
|
# Source: kube-prometheus-stack/templates/alertmanager/service.yaml
|
|
apiVersion: v1
|
|
kind: Service
|
|
metadata:
|
|
name: kube-prometheus-stack-alertmanager
|
|
namespace: default
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack-alertmanager
|
|
app.kubernetes.io/name: kube-prometheus-stack-alertmanager #ADDED
|
|
self-monitor: "true"
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
spec:
|
|
ports:
|
|
- name: http-web
|
|
port: 9093
|
|
targetPort: 9093
|
|
protocol: TCP
|
|
- name: reloader-web
|
|
appProtocol: http
|
|
port: 8080
|
|
targetPort: reloader-web
|
|
selector:
|
|
app.kubernetes.io/name: alertmanager
|
|
alertmanager: kube-prometheus-stack-alertmanager
|
|
sessionAffinity: None
|
|
type: "ClusterIP"
|
|
---
|
|
# Source: kube-prometheus-stack/templates/exporters/core-dns/service.yaml
|
|
apiVersion: v1
|
|
kind: Service
|
|
metadata:
|
|
name: kube-prometheus-stack-coredns
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack-coredns
|
|
app.kubernetes.io/name: kube-prometheus-stack-coredns #ADDED
|
|
jobLabel: coredns
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
namespace: kube-system
|
|
spec:
|
|
clusterIP: None
|
|
ports:
|
|
- name: http-metrics
|
|
port: 9153
|
|
protocol: TCP
|
|
targetPort: 9153
|
|
selector:
|
|
k8s-app: kube-dns
|
|
---
|
|
# Source: kube-prometheus-stack/templates/exporters/kube-controller-manager/service.yaml
|
|
apiVersion: v1
|
|
kind: Service
|
|
metadata:
|
|
name: kube-prometheus-stack-kube-controller-manager
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack-kube-controller-manager
|
|
app.kubernetes.io/name: kube-prometheus-stack-kube-controller-manager #ADDED
|
|
jobLabel: kube-controller-manager
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
namespace: kube-system
|
|
spec:
|
|
clusterIP: None
|
|
ports:
|
|
- name: http-metrics
|
|
port: 10257
|
|
protocol: TCP
|
|
targetPort: 10257
|
|
selector:
|
|
component: kube-controller-manager
|
|
type: ClusterIP
|
|
---
|
|
# Source: kube-prometheus-stack/templates/exporters/kube-etcd/service.yaml
|
|
apiVersion: v1
|
|
kind: Service
|
|
metadata:
|
|
name: kube-prometheus-stack-kube-etcd
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack-kube-etcd
|
|
app.kubernetes.io/name: kube-prometheus-stack-kube-etcd #ADDED
|
|
jobLabel: kube-etcd
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
namespace: kube-system
|
|
spec:
|
|
clusterIP: None
|
|
ports:
|
|
- name: http-metrics
|
|
port: 2381
|
|
protocol: TCP
|
|
targetPort: 2381
|
|
selector:
|
|
component: etcd
|
|
type: ClusterIP
|
|
---
|
|
# Source: kube-prometheus-stack/templates/exporters/kube-proxy/service.yaml
|
|
apiVersion: v1
|
|
kind: Service
|
|
metadata:
|
|
name: kube-prometheus-stack-kube-proxy
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack-kube-proxy
|
|
app.kubernetes.io/name: kube-prometheus-stack-kube-proxy #ADDED
|
|
jobLabel: kube-proxy
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
namespace: kube-system
|
|
spec:
|
|
clusterIP: None
|
|
ports:
|
|
- name: http-metrics
|
|
port: 10249
|
|
protocol: TCP
|
|
targetPort: 10249
|
|
selector:
|
|
k8s-app: kube-proxy
|
|
type: ClusterIP
|
|
---
|
|
# Source: kube-prometheus-stack/templates/exporters/kube-scheduler/service.yaml
|
|
apiVersion: v1
|
|
kind: Service
|
|
metadata:
|
|
name: kube-prometheus-stack-kube-scheduler
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack-kube-scheduler
|
|
app.kubernetes.io/name: kube-prometheus-stack-kube-scheduler #ADDED
|
|
jobLabel: kube-scheduler
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
namespace: kube-system
|
|
spec:
|
|
clusterIP: None
|
|
ports:
|
|
- name: http-metrics
|
|
port: 10259
|
|
protocol: TCP
|
|
targetPort: 10259
|
|
selector:
|
|
component: kube-scheduler
|
|
type: ClusterIP
|
|
---
|
|
# Source: kube-prometheus-stack/templates/prometheus-operator/service.yaml
|
|
apiVersion: v1
|
|
kind: Service
|
|
metadata:
|
|
name: kube-prometheus-stack-operator
|
|
namespace: default
|
|
labels:
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
#TBR: app: kube-prometheus-stack-operator
|
|
app.kubernetes.io/name: kube-prometheus-stack-prometheus-operator
|
|
app.kubernetes.io/component: prometheus-operator
|
|
spec:
|
|
ports:
|
|
- name: https
|
|
port: 443
|
|
targetPort: https
|
|
selector:
|
|
#TBR: app: kube-prometheus-stack-operator
|
|
app.kubernetes.io/name: kube-prometheus-stack-prometheus-operator #ADDED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
type: "ClusterIP"
|
|
---
|
|
# Source: kube-prometheus-stack/templates/prometheus/service.yaml
|
|
apiVersion: v1
|
|
kind: Service
|
|
metadata:
|
|
name: kube-prometheus-stack-prometheus
|
|
namespace: default
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack-prometheus
|
|
app.kubernetes.io/name: kube-prometheus-stack-prometheus #ADDED
|
|
self-monitor: "true"
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
spec:
|
|
ports:
|
|
- name: http-web
|
|
port: 9090
|
|
targetPort: 9090
|
|
- name: reloader-web
|
|
appProtocol: http
|
|
port: 8080
|
|
targetPort: reloader-web
|
|
publishNotReadyAddresses: false
|
|
selector:
|
|
app.kubernetes.io/name: prometheus
|
|
operator.prometheus.io/name: kube-prometheus-stack-prometheus
|
|
sessionAffinity: None
|
|
type: "ClusterIP"
|
|
---
|
|
# Source: kube-prometheus-stack/charts/prometheus-node-exporter/templates/daemonset.yaml
|
|
apiVersion: apps/v1
|
|
kind: DaemonSet
|
|
metadata:
|
|
name: kube-prometheus-stack-prometheus-node-exporter
|
|
namespace: default
|
|
labels:
|
|
helm.sh/chart: prometheus-node-exporter-4.43.1
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/component: metrics
|
|
app.kubernetes.io/part-of: prometheus-node-exporter
|
|
app.kubernetes.io/name: prometheus-node-exporter
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "1.8.2"
|
|
#TBR: release: kube-prometheus-stack
|
|
spec:
|
|
selector:
|
|
matchLabels:
|
|
app.kubernetes.io/name: prometheus-node-exporter
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
revisionHistoryLimit: 10
|
|
updateStrategy:
|
|
rollingUpdate:
|
|
maxUnavailable: 1
|
|
type: RollingUpdate
|
|
template:
|
|
metadata:
|
|
annotations:
|
|
cluster-autoscaler.kubernetes.io/safe-to-evict: "true"
|
|
labels:
|
|
helm.sh/chart: prometheus-node-exporter-4.43.1
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/component: metrics
|
|
app.kubernetes.io/part-of: prometheus-node-exporter
|
|
app.kubernetes.io/name: prometheus-node-exporter
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "1.8.2"
|
|
#TBR: release: kube-prometheus-stack
|
|
jobLabel: node-exporter
|
|
spec:
|
|
automountServiceAccountToken: false
|
|
securityContext:
|
|
fsGroup: 65534
|
|
runAsGroup: 65534
|
|
runAsNonRoot: true
|
|
runAsUser: 65534
|
|
serviceAccountName: kube-prometheus-stack-prometheus-node-exporter
|
|
containers:
|
|
- name: node-exporter
|
|
image: quay.io/prometheus/node-exporter:v1.8.2
|
|
imagePullPolicy: IfNotPresent
|
|
args:
|
|
- --path.procfs=/host/proc
|
|
- --path.sysfs=/host/sys
|
|
- --path.rootfs=/host/root
|
|
- --path.udev.data=/host/root/run/udev/data
|
|
- --web.listen-address=[$(HOST_IP)]:9100
|
|
- --collector.filesystem.mount-points-exclude=^/(dev|proc|sys|var/lib/docker/.+|var/lib/kubelet/.+)($|/)
|
|
- --collector.filesystem.fs-types-exclude=^(autofs|binfmt_misc|bpf|cgroup2?|configfs|debugfs|devpts|devtmpfs|fusectl|hugetlbfs|iso9660|mqueue|nsfs|overlay|proc|procfs|pstore|rpc_pipefs|securityfs|selinuxfs|squashfs|sysfs|tracefs)$
|
|
securityContext:
|
|
readOnlyRootFilesystem: true
|
|
env:
|
|
- name: HOST_IP
|
|
value: 0.0.0.0
|
|
ports:
|
|
- name: http-metrics
|
|
containerPort: 9100
|
|
protocol: TCP
|
|
livenessProbe:
|
|
failureThreshold: 3
|
|
httpGet:
|
|
httpHeaders:
|
|
path: /
|
|
port: 9100
|
|
scheme: HTTP
|
|
initialDelaySeconds: 0
|
|
periodSeconds: 10
|
|
successThreshold: 1
|
|
timeoutSeconds: 1
|
|
readinessProbe:
|
|
failureThreshold: 3
|
|
httpGet:
|
|
httpHeaders:
|
|
path: /
|
|
port: 9100
|
|
scheme: HTTP
|
|
initialDelaySeconds: 0
|
|
periodSeconds: 10
|
|
successThreshold: 1
|
|
timeoutSeconds: 1
|
|
volumeMounts:
|
|
- name: proc
|
|
mountPath: /host/proc
|
|
readOnly: true
|
|
- name: sys
|
|
mountPath: /host/sys
|
|
readOnly: true
|
|
- name: root
|
|
mountPath: /host/root
|
|
mountPropagation: HostToContainer
|
|
readOnly: true
|
|
hostNetwork: true
|
|
hostPID: true
|
|
hostIPC: false
|
|
affinity:
|
|
nodeAffinity:
|
|
requiredDuringSchedulingIgnoredDuringExecution:
|
|
nodeSelectorTerms:
|
|
- matchExpressions:
|
|
- key: eks.amazonaws.com/compute-type
|
|
operator: NotIn
|
|
values:
|
|
- fargate
|
|
- key: type
|
|
operator: NotIn
|
|
values:
|
|
- virtual-kubelet
|
|
nodeSelector:
|
|
kubernetes.io/os: linux
|
|
tolerations:
|
|
- effect: NoSchedule
|
|
operator: Exists
|
|
volumes:
|
|
- name: proc
|
|
hostPath:
|
|
path: /proc
|
|
- name: sys
|
|
hostPath:
|
|
path: /sys
|
|
- name: root
|
|
hostPath:
|
|
path: /
|
|
---
|
|
# Source: kube-prometheus-stack/charts/grafana/templates/deployment.yaml
|
|
apiVersion: apps/v1
|
|
kind: Deployment
|
|
metadata:
|
|
name: kube-prometheus-stack-grafana
|
|
namespace: default
|
|
labels:
|
|
|
|
helm.sh/chart: grafana-8.8.2
|
|
app.kubernetes.io/name: grafana
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "11.4.0"
|
|
spec:
|
|
replicas: 1
|
|
revisionHistoryLimit: 10
|
|
selector:
|
|
matchLabels:
|
|
app.kubernetes.io/name: grafana
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
strategy:
|
|
type: RollingUpdate
|
|
template:
|
|
metadata:
|
|
labels:
|
|
|
|
helm.sh/chart: grafana-8.8.2
|
|
app.kubernetes.io/name: grafana
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "11.4.0"
|
|
annotations:
|
|
checksum/config: 0e9cbd0ea8e24e32f7dfca5bab17a2ba05652642f0a09a4882833ae88e4cc4a3
|
|
checksum/sc-dashboard-provider-config: e70bf6a851099d385178a76de9757bb0bef8299da6d8443602590e44f05fdf24
|
|
checksum/secret: 032056e9c62bbe9d1daa41ee49cd3d9524c076f51ca4c65adadf4ef08ef28712
|
|
kubectl.kubernetes.io/default-container: grafana
|
|
spec:
|
|
|
|
serviceAccountName: kube-prometheus-stack-grafana
|
|
automountServiceAccountToken: true
|
|
securityContext:
|
|
fsGroup: 472
|
|
runAsGroup: 472
|
|
runAsNonRoot: true
|
|
runAsUser: 472
|
|
enableServiceLinks: true
|
|
containers:
|
|
- name: grafana-sc-dashboard
|
|
image: "quay.io/kiwigrid/k8s-sidecar:1.28.0"
|
|
imagePullPolicy: IfNotPresent
|
|
env:
|
|
- name: METHOD
|
|
value: WATCH
|
|
- name: LABEL
|
|
value: "grafana_dashboard"
|
|
- name: LABEL_VALUE
|
|
value: "1"
|
|
- name: FOLDER
|
|
value: "/tmp/dashboards"
|
|
- name: RESOURCE
|
|
value: "both"
|
|
- name: NAMESPACE
|
|
value: "ALL"
|
|
- name: REQ_USERNAME
|
|
valueFrom:
|
|
secretKeyRef:
|
|
name: kube-prometheus-stack-grafana
|
|
key: admin-user
|
|
- name: REQ_PASSWORD
|
|
valueFrom:
|
|
secretKeyRef:
|
|
name: kube-prometheus-stack-grafana
|
|
key: admin-password
|
|
- name: REQ_URL
|
|
value: http://localhost:3000/api/admin/provisioning/dashboards/reload
|
|
- name: REQ_METHOD
|
|
value: POST
|
|
securityContext:
|
|
allowPrivilegeEscalation: false
|
|
capabilities:
|
|
drop:
|
|
- ALL
|
|
seccompProfile:
|
|
type: RuntimeDefault
|
|
volumeMounts:
|
|
- name: sc-dashboard-volume
|
|
mountPath: "/tmp/dashboards"
|
|
- name: grafana-sc-datasources
|
|
image: "quay.io/kiwigrid/k8s-sidecar:1.28.0"
|
|
imagePullPolicy: IfNotPresent
|
|
env:
|
|
- name: METHOD
|
|
value: WATCH
|
|
- name: LABEL
|
|
value: "grafana_datasource"
|
|
- name: LABEL_VALUE
|
|
value: "1"
|
|
- name: FOLDER
|
|
value: "/etc/grafana/provisioning/datasources"
|
|
- name: RESOURCE
|
|
value: "both"
|
|
- name: REQ_USERNAME
|
|
valueFrom:
|
|
secretKeyRef:
|
|
name: kube-prometheus-stack-grafana
|
|
key: admin-user
|
|
- name: REQ_PASSWORD
|
|
valueFrom:
|
|
secretKeyRef:
|
|
name: kube-prometheus-stack-grafana
|
|
key: admin-password
|
|
- name: REQ_URL
|
|
value: http://localhost:3000/api/admin/provisioning/datasources/reload
|
|
- name: REQ_METHOD
|
|
value: POST
|
|
securityContext:
|
|
allowPrivilegeEscalation: false
|
|
capabilities:
|
|
drop:
|
|
- ALL
|
|
seccompProfile:
|
|
type: RuntimeDefault
|
|
volumeMounts:
|
|
- name: sc-datasources-volume
|
|
mountPath: "/etc/grafana/provisioning/datasources"
|
|
- name: grafana
|
|
image: "docker.io/grafana/grafana:11.4.0"
|
|
imagePullPolicy: IfNotPresent
|
|
securityContext:
|
|
allowPrivilegeEscalation: false
|
|
capabilities:
|
|
drop:
|
|
- ALL
|
|
seccompProfile:
|
|
type: RuntimeDefault
|
|
volumeMounts:
|
|
- name: config
|
|
mountPath: "/etc/grafana/grafana.ini"
|
|
subPath: grafana.ini
|
|
- name: storage
|
|
mountPath: "/var/lib/grafana"
|
|
- name: sc-dashboard-volume
|
|
mountPath: "/tmp/dashboards"
|
|
- name: sc-dashboard-provider
|
|
mountPath: "/etc/grafana/provisioning/dashboards/sc-dashboardproviders.yaml"
|
|
subPath: provider.yaml
|
|
- name: sc-datasources-volume
|
|
mountPath: "/etc/grafana/provisioning/datasources"
|
|
ports:
|
|
- name: grafana
|
|
containerPort: 3000
|
|
protocol: TCP
|
|
- name: gossip-tcp
|
|
containerPort: 9094
|
|
protocol: TCP
|
|
- name: gossip-udp
|
|
containerPort: 9094
|
|
protocol: UDP
|
|
- name: profiling
|
|
containerPort: 6060
|
|
protocol: TCP
|
|
env:
|
|
- name: POD_IP
|
|
valueFrom:
|
|
fieldRef:
|
|
fieldPath: status.podIP
|
|
- name: GF_SECURITY_ADMIN_USER
|
|
valueFrom:
|
|
secretKeyRef:
|
|
name: kube-prometheus-stack-grafana
|
|
key: admin-user
|
|
- name: GF_SECURITY_ADMIN_PASSWORD
|
|
valueFrom:
|
|
secretKeyRef:
|
|
name: kube-prometheus-stack-grafana
|
|
key: admin-password
|
|
- name: GF_PATHS_DATA
|
|
value: /var/lib/grafana/
|
|
- name: GF_PATHS_LOGS
|
|
value: /var/log/grafana
|
|
- name: GF_PATHS_PLUGINS
|
|
value: /var/lib/grafana/plugins
|
|
- name: GF_PATHS_PROVISIONING
|
|
value: /etc/grafana/provisioning
|
|
livenessProbe:
|
|
failureThreshold: 10
|
|
httpGet:
|
|
path: /api/health
|
|
port: 3000
|
|
initialDelaySeconds: 60
|
|
timeoutSeconds: 30
|
|
readinessProbe:
|
|
httpGet:
|
|
path: /api/health
|
|
port: 3000
|
|
volumes:
|
|
- name: config
|
|
configMap:
|
|
name: kube-prometheus-stack-grafana
|
|
- name: storage
|
|
emptyDir: {}
|
|
- name: sc-dashboard-volume
|
|
emptyDir:
|
|
{}
|
|
- name: sc-dashboard-provider
|
|
configMap:
|
|
name: kube-prometheus-stack-grafana-config-dashboards
|
|
- name: sc-datasources-volume
|
|
emptyDir:
|
|
{}
|
|
---
|
|
# Source: kube-prometheus-stack/charts/kube-state-metrics/templates/deployment.yaml
|
|
apiVersion: apps/v1
|
|
kind: Deployment
|
|
metadata:
|
|
name: kube-prometheus-stack-kube-state-metrics
|
|
namespace: default
|
|
labels:
|
|
helm.sh/chart: kube-state-metrics-5.28.0
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/component: metrics
|
|
app.kubernetes.io/part-of: kube-state-metrics
|
|
app.kubernetes.io/name: kube-state-metrics
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "2.14.0"
|
|
#TBR: release: kube-prometheus-stack
|
|
spec:
|
|
selector:
|
|
matchLabels:
|
|
app.kubernetes.io/name: kube-state-metrics
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
replicas: 1
|
|
strategy:
|
|
type: RollingUpdate
|
|
revisionHistoryLimit: 10
|
|
template:
|
|
metadata:
|
|
labels:
|
|
helm.sh/chart: kube-state-metrics-5.28.0
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/component: metrics
|
|
app.kubernetes.io/part-of: kube-state-metrics
|
|
app.kubernetes.io/name: kube-state-metrics
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "2.14.0"
|
|
#TBR: release: kube-prometheus-stack
|
|
spec:
|
|
automountServiceAccountToken: true
|
|
hostNetwork: false
|
|
serviceAccountName: kube-prometheus-stack-kube-state-metrics
|
|
securityContext:
|
|
fsGroup: 65534
|
|
runAsGroup: 65534
|
|
runAsNonRoot: true
|
|
runAsUser: 65534
|
|
seccompProfile:
|
|
type: RuntimeDefault
|
|
containers:
|
|
- name: kube-state-metrics
|
|
args:
|
|
- --port=8080
|
|
- --resources=certificatesigningrequests,configmaps,cronjobs,daemonsets,deployments,endpoints,horizontalpodautoscalers,ingresses,jobs,leases,limitranges,mutatingwebhookconfigurations,namespaces,networkpolicies,nodes,persistentvolumeclaims,persistentvolumes,poddisruptionbudgets,pods,replicasets,replicationcontrollers,resourcequotas,secrets,services,statefulsets,storageclasses,validatingwebhookconfigurations,volumeattachments
|
|
imagePullPolicy: IfNotPresent
|
|
image: registry.k8s.io/kube-state-metrics/kube-state-metrics:v2.14.0
|
|
ports:
|
|
- containerPort: 8080
|
|
name: "http"
|
|
livenessProbe:
|
|
failureThreshold: 3
|
|
httpGet:
|
|
httpHeaders:
|
|
path: /livez
|
|
port: 8080
|
|
scheme: HTTP
|
|
initialDelaySeconds: 5
|
|
periodSeconds: 10
|
|
successThreshold: 1
|
|
timeoutSeconds: 5
|
|
readinessProbe:
|
|
failureThreshold: 3
|
|
httpGet:
|
|
httpHeaders:
|
|
path: /readyz
|
|
port: 8081
|
|
scheme: HTTP
|
|
initialDelaySeconds: 5
|
|
periodSeconds: 10
|
|
successThreshold: 1
|
|
timeoutSeconds: 5
|
|
resources:
|
|
{}
|
|
securityContext:
|
|
allowPrivilegeEscalation: false
|
|
capabilities:
|
|
drop:
|
|
- ALL
|
|
readOnlyRootFilesystem: true
|
|
---
|
|
# Source: kube-prometheus-stack/templates/prometheus-operator/deployment.yaml
|
|
apiVersion: apps/v1
|
|
kind: Deployment
|
|
metadata:
|
|
name: kube-prometheus-stack-operator
|
|
namespace: default
|
|
labels:
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
#TBR: app: kube-prometheus-stack-operator
|
|
app.kubernetes.io/name: kube-prometheus-stack-prometheus-operator
|
|
app.kubernetes.io/component: prometheus-operator
|
|
spec:
|
|
replicas: 1
|
|
revisionHistoryLimit: 10
|
|
selector:
|
|
matchLabels:
|
|
#TBR: app: kube-prometheus-stack-operator
|
|
app.kubernetes.io/name: kube-prometheus-stack-prometheus-operator #ADDED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
template:
|
|
metadata:
|
|
labels:
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
#TBR: app: kube-prometheus-stack-operator
|
|
app.kubernetes.io/name: kube-prometheus-stack-prometheus-operator
|
|
app.kubernetes.io/component: prometheus-operator
|
|
spec:
|
|
containers:
|
|
- name: kube-prometheus-stack
|
|
image: "quay.io/prometheus-operator/prometheus-operator:v0.79.2"
|
|
imagePullPolicy: "IfNotPresent"
|
|
args:
|
|
- --kubelet-service=kube-system/kube-prometheus-stack-kubelet
|
|
- --kubelet-endpoints=true
|
|
- --kubelet-endpointslice=false
|
|
- --localhost=127.0.0.1
|
|
- --prometheus-config-reloader=quay.io/prometheus-operator/prometheus-config-reloader:v0.79.2
|
|
- --config-reloader-cpu-request=0
|
|
- --config-reloader-cpu-limit=0
|
|
- --config-reloader-memory-request=0
|
|
- --config-reloader-memory-limit=0
|
|
- --thanos-default-base-image=quay.io/thanos/thanos:v0.37.2
|
|
- --secret-field-selector=type!=kubernetes.io/dockercfg,type!=kubernetes.io/service-account-token,type!=helm.sh/release.v1
|
|
- --web.enable-tls=true
|
|
- --web.cert-file=/cert/cert
|
|
- --web.key-file=/cert/key
|
|
- --web.listen-address=:10250
|
|
- --web.tls-min-version=VersionTLS13
|
|
ports:
|
|
- containerPort: 10250
|
|
name: https
|
|
env:
|
|
- name: GOGC
|
|
value: "30"
|
|
resources:
|
|
{}
|
|
securityContext:
|
|
allowPrivilegeEscalation: false
|
|
capabilities:
|
|
drop:
|
|
- ALL
|
|
readOnlyRootFilesystem: true
|
|
volumeMounts:
|
|
- name: tls-secret
|
|
mountPath: /cert
|
|
readOnly: true
|
|
readinessProbe:
|
|
httpGet:
|
|
path: /healthz
|
|
port: https
|
|
scheme: HTTPS
|
|
initialDelaySeconds: 0
|
|
periodSeconds: 10
|
|
timeoutSeconds: 1
|
|
successThreshold: 1
|
|
failureThreshold: 3
|
|
livenessProbe:
|
|
httpGet:
|
|
path: /healthz
|
|
port: https
|
|
scheme: HTTPS
|
|
initialDelaySeconds: 0
|
|
periodSeconds: 10
|
|
timeoutSeconds: 1
|
|
successThreshold: 1
|
|
failureThreshold: 3
|
|
volumes:
|
|
- name: tls-secret
|
|
secret:
|
|
defaultMode: 420
|
|
secretName: kube-prometheus-stack-admission
|
|
securityContext:
|
|
fsGroup: 65534
|
|
runAsGroup: 65534
|
|
runAsNonRoot: true
|
|
runAsUser: 65534
|
|
seccompProfile:
|
|
type: RuntimeDefault
|
|
serviceAccountName: kube-prometheus-stack-operator
|
|
automountServiceAccountToken: true
|
|
---
|
|
# Source: kube-prometheus-stack/templates/alertmanager/alertmanager.yaml
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: Alertmanager
|
|
metadata:
|
|
name: kube-prometheus-stack-alertmanager
|
|
namespace: default
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack-alertmanager
|
|
app.kubernetes.io/name: kube-prometheus-stack-alertmanager #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
spec:
|
|
image: "quay.io/prometheus/alertmanager:v0.27.0"
|
|
version: v0.27.0
|
|
replicas: 1
|
|
listenLocal: false
|
|
serviceAccountName: kube-prometheus-stack-alertmanager
|
|
automountServiceAccountToken: true
|
|
externalUrl: http://kube-prometheus-stack-alertmanager.default:9093
|
|
paused: false
|
|
logFormat: "logfmt"
|
|
logLevel: "info"
|
|
retention: "120h"
|
|
alertmanagerConfigSelector: {}
|
|
alertmanagerConfigNamespaceSelector: {}
|
|
routePrefix: "/"
|
|
securityContext:
|
|
fsGroup: 2000
|
|
runAsGroup: 2000
|
|
runAsNonRoot: true
|
|
runAsUser: 1000
|
|
seccompProfile:
|
|
type: RuntimeDefault
|
|
affinity:
|
|
podAntiAffinity:
|
|
preferredDuringSchedulingIgnoredDuringExecution:
|
|
- weight: 100
|
|
podAffinityTerm:
|
|
topologyKey: kubernetes.io/hostname
|
|
labelSelector:
|
|
matchExpressions:
|
|
- {key: app.kubernetes.io/name, operator: In, values: [alertmanager]}
|
|
- {key: alertmanager, operator: In, values: [kube-prometheus-stack-alertmanager]}
|
|
portName: http-web
|
|
---
|
|
# Source: kube-prometheus-stack/templates/prometheus-operator/admission-webhooks/mutatingWebhookConfiguration.yaml
|
|
apiVersion: admissionregistration.k8s.io/v1
|
|
kind: MutatingWebhookConfiguration
|
|
metadata:
|
|
name: kube-prometheus-stack-admission
|
|
annotations:
|
|
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack-admission
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
app.kubernetes.io/name: kube-prometheus-stack-prometheus-operator
|
|
app.kubernetes.io/component: prometheus-operator-webhook
|
|
webhooks:
|
|
- name: prometheusrulemutate.monitoring.coreos.com
|
|
failurePolicy: Ignore
|
|
rules:
|
|
- apiGroups:
|
|
- monitoring.coreos.com
|
|
apiVersions:
|
|
- "*"
|
|
resources:
|
|
- prometheusrules
|
|
operations:
|
|
- CREATE
|
|
- UPDATE
|
|
clientConfig:
|
|
service:
|
|
namespace: default
|
|
name: kube-prometheus-stack-operator
|
|
path: /admission-prometheusrules/mutate
|
|
timeoutSeconds: 10
|
|
admissionReviewVersions: ["v1", "v1beta1"]
|
|
sideEffects: None
|
|
---
|
|
# Source: kube-prometheus-stack/templates/prometheus/prometheus.yaml
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: Prometheus
|
|
metadata:
|
|
name: kube-prometheus-stack-prometheus
|
|
namespace: default
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack-prometheus
|
|
app.kubernetes.io/name: kube-prometheus-stack-prometheus
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
spec:
|
|
automountServiceAccountToken: true
|
|
alerting:
|
|
alertmanagers:
|
|
- namespace: default
|
|
name: kube-prometheus-stack-alertmanager
|
|
port: http-web
|
|
pathPrefix: "/"
|
|
apiVersion: v2
|
|
image: "quay.io/prometheus/prometheus:v3.1.0"
|
|
version: v3.1.0
|
|
externalUrl: http://kube-prometheus-stack-prometheus.default:9090
|
|
paused: false
|
|
replicas: 1
|
|
shards: 1
|
|
logLevel: info
|
|
logFormat: logfmt
|
|
listenLocal: false
|
|
enableAdminAPI: false
|
|
retention: "10d"
|
|
tsdb:
|
|
outOfOrderTimeWindow: 0s
|
|
walCompression: true
|
|
routePrefix: "/"
|
|
serviceAccountName: kube-prometheus-stack-prometheus
|
|
serviceMonitorSelector:
|
|
matchLabels:
|
|
#TBR: release: "kube-prometheus-stack"
|
|
app.kubernetes.io/instance: kube-prometheus-stack #ADDED
|
|
|
|
serviceMonitorNamespaceSelector: {}
|
|
podMonitorSelector:
|
|
matchLabels:
|
|
#TBR: release: "kube-prometheus-stack"
|
|
app.kubernetes.io/instance: kube-prometheus-stack #ADDED
|
|
|
|
podMonitorNamespaceSelector: {}
|
|
probeSelector:
|
|
matchLabels:
|
|
#TBR: release: "kube-prometheus-stack"
|
|
app.kubernetes.io/instance: kube-prometheus-stack #ADDED
|
|
|
|
probeNamespaceSelector: {}
|
|
securityContext:
|
|
fsGroup: 2000
|
|
runAsGroup: 2000
|
|
runAsNonRoot: true
|
|
runAsUser: 1000
|
|
seccompProfile:
|
|
type: RuntimeDefault
|
|
ruleNamespaceSelector: {}
|
|
ruleSelector:
|
|
matchLabels:
|
|
#TBR: release: "kube-prometheus-stack"
|
|
app.kubernetes.io/instance: kube-prometheus-stack #ADDED
|
|
|
|
scrapeConfigSelector:
|
|
matchLabels:
|
|
#TBR: release: "kube-prometheus-stack"
|
|
app.kubernetes.io/instance: kube-prometheus-stack #ADDED
|
|
|
|
scrapeConfigNamespaceSelector: {}
|
|
affinity:
|
|
podAntiAffinity:
|
|
preferredDuringSchedulingIgnoredDuringExecution:
|
|
- weight: 100
|
|
podAffinityTerm:
|
|
topologyKey: kubernetes.io/hostname
|
|
labelSelector:
|
|
matchExpressions:
|
|
- {key: app.kubernetes.io/name, operator: In, values: [prometheus]}
|
|
- {key: prometheus, operator: In, values: [kube-prometheus-stack-prometheus]}
|
|
portName: http-web
|
|
hostNetwork: false
|
|
---
|
|
# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/alertmanager.rules.yaml
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: PrometheusRule
|
|
metadata:
|
|
name: kube-prometheus-stack-alertmanager.rules
|
|
namespace: default
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack
|
|
app.kubernetes.io/name: kube-prometheus-stack #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
spec:
|
|
groups:
|
|
- name: alertmanager.rules
|
|
rules:
|
|
- alert: AlertmanagerFailedReload
|
|
annotations:
|
|
description: Configuration has failed to load for {{ $labels.namespace }}/{{ $labels.pod}}.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/alertmanager/alertmanagerfailedreload
|
|
summary: Reloading an Alertmanager configuration has failed.
|
|
expr: |-
|
|
# Without max_over_time, failed scrapes could create false negatives, see
|
|
# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.
|
|
max_over_time(alertmanager_config_last_reload_successful{job="kube-prometheus-stack-alertmanager",namespace="default"}[5m]) == 0
|
|
for: 10m
|
|
labels:
|
|
severity: critical
|
|
- alert: AlertmanagerMembersInconsistent
|
|
annotations:
|
|
description: Alertmanager {{ $labels.namespace }}/{{ $labels.pod}} has only found {{ $value }} members of the {{$labels.job}} cluster.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/alertmanager/alertmanagermembersinconsistent
|
|
summary: A member of an Alertmanager cluster has not found all other cluster members.
|
|
expr: |-
|
|
# Without max_over_time, failed scrapes could create false negatives, see
|
|
# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.
|
|
max_over_time(alertmanager_cluster_members{job="kube-prometheus-stack-alertmanager",namespace="default"}[5m])
|
|
< on (namespace,service,cluster) group_left
|
|
count by (namespace,service,cluster) (max_over_time(alertmanager_cluster_members{job="kube-prometheus-stack-alertmanager",namespace="default"}[5m]))
|
|
for: 15m
|
|
labels:
|
|
severity: critical
|
|
- alert: AlertmanagerFailedToSendAlerts
|
|
annotations:
|
|
description: Alertmanager {{ $labels.namespace }}/{{ $labels.pod}} failed to send {{ $value | humanizePercentage }} of notifications to {{ $labels.integration }}.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/alertmanager/alertmanagerfailedtosendalerts
|
|
summary: An Alertmanager instance failed to send notifications.
|
|
expr: |-
|
|
(
|
|
rate(alertmanager_notifications_failed_total{job="kube-prometheus-stack-alertmanager",namespace="default"}[5m])
|
|
/
|
|
ignoring (reason) group_left rate(alertmanager_notifications_total{job="kube-prometheus-stack-alertmanager",namespace="default"}[5m])
|
|
)
|
|
> 0.01
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
- alert: AlertmanagerClusterFailedToSendAlerts
|
|
annotations:
|
|
description: The minimum notification failure rate to {{ $labels.integration }} sent from any instance in the {{$labels.job}} cluster is {{ $value | humanizePercentage }}.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/alertmanager/alertmanagerclusterfailedtosendalerts
|
|
summary: All Alertmanager instances in a cluster failed to send notifications to a critical integration.
|
|
expr: |-
|
|
min by (namespace,service, integration) (
|
|
rate(alertmanager_notifications_failed_total{job="kube-prometheus-stack-alertmanager",namespace="default", integration=~`.*`}[5m])
|
|
/
|
|
ignoring (reason) group_left rate(alertmanager_notifications_total{job="kube-prometheus-stack-alertmanager",namespace="default", integration=~`.*`}[5m])
|
|
)
|
|
> 0.01
|
|
for: 5m
|
|
labels:
|
|
severity: critical
|
|
- alert: AlertmanagerClusterFailedToSendAlerts
|
|
annotations:
|
|
description: The minimum notification failure rate to {{ $labels.integration }} sent from any instance in the {{$labels.job}} cluster is {{ $value | humanizePercentage }}.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/alertmanager/alertmanagerclusterfailedtosendalerts
|
|
summary: All Alertmanager instances in a cluster failed to send notifications to a non-critical integration.
|
|
expr: |-
|
|
min by (namespace,service, integration) (
|
|
rate(alertmanager_notifications_failed_total{job="kube-prometheus-stack-alertmanager",namespace="default", integration!~`.*`}[5m])
|
|
/
|
|
ignoring (reason) group_left rate(alertmanager_notifications_total{job="kube-prometheus-stack-alertmanager",namespace="default", integration!~`.*`}[5m])
|
|
)
|
|
> 0.01
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
- alert: AlertmanagerConfigInconsistent
|
|
annotations:
|
|
description: Alertmanager instances within the {{$labels.job}} cluster have different configurations.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/alertmanager/alertmanagerconfiginconsistent
|
|
summary: Alertmanager instances within the same cluster have different configurations.
|
|
expr: |-
|
|
count by (namespace,service,cluster) (
|
|
count_values by (namespace,service,cluster) ("config_hash", alertmanager_config_hash{job="kube-prometheus-stack-alertmanager",namespace="default"})
|
|
)
|
|
!= 1
|
|
for: 20m
|
|
labels:
|
|
severity: critical
|
|
- alert: AlertmanagerClusterDown
|
|
annotations:
|
|
description: '{{ $value | humanizePercentage }} of Alertmanager instances within the {{$labels.job}} cluster have been up for less than half of the last 5m.'
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/alertmanager/alertmanagerclusterdown
|
|
summary: Half or more of the Alertmanager instances within the same cluster are down.
|
|
expr: |-
|
|
(
|
|
count by (namespace,service,cluster) (
|
|
avg_over_time(up{job="kube-prometheus-stack-alertmanager",namespace="default"}[5m]) < 0.5
|
|
)
|
|
/
|
|
count by (namespace,service,cluster) (
|
|
up{job="kube-prometheus-stack-alertmanager",namespace="default"}
|
|
)
|
|
)
|
|
>= 0.5
|
|
for: 5m
|
|
labels:
|
|
severity: critical
|
|
- alert: AlertmanagerClusterCrashlooping
|
|
annotations:
|
|
description: '{{ $value | humanizePercentage }} of Alertmanager instances within the {{$labels.job}} cluster have restarted at least 5 times in the last 10m.'
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/alertmanager/alertmanagerclustercrashlooping
|
|
summary: Half or more of the Alertmanager instances within the same cluster are crashlooping.
|
|
expr: |-
|
|
(
|
|
count by (namespace,service,cluster) (
|
|
changes(process_start_time_seconds{job="kube-prometheus-stack-alertmanager",namespace="default"}[10m]) > 4
|
|
)
|
|
/
|
|
count by (namespace,service,cluster) (
|
|
up{job="kube-prometheus-stack-alertmanager",namespace="default"}
|
|
)
|
|
)
|
|
>= 0.5
|
|
for: 5m
|
|
labels:
|
|
severity: critical
|
|
---
|
|
# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/config-reloaders.yaml
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: PrometheusRule
|
|
metadata:
|
|
name: kube-prometheus-stack-config-reloaders
|
|
namespace: default
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack
|
|
app.kubernetes.io/name: kube-prometheus-stack #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
spec:
|
|
groups:
|
|
- name: config-reloaders
|
|
rules:
|
|
- alert: ConfigReloaderSidecarErrors
|
|
annotations:
|
|
description: 'Errors encountered while the {{$labels.pod}} config-reloader sidecar attempts to sync config in {{$labels.namespace}} namespace.
|
|
|
|
As a result, configuration for service running in {{$labels.pod}} may be stale and cannot be updated anymore.'
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus-operator/configreloadersidecarerrors
|
|
summary: config-reloader sidecar has not had a successful reload for 10m
|
|
expr: max_over_time(reloader_last_reload_successful{namespace=~".+"}[5m]) == 0
|
|
for: 10m
|
|
labels:
|
|
severity: warning
|
|
---
|
|
# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/etcd.yaml
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: PrometheusRule
|
|
metadata:
|
|
name: kube-prometheus-stack-etcd
|
|
namespace: default
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack
|
|
app.kubernetes.io/name: kube-prometheus-stack #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
spec:
|
|
groups:
|
|
- name: etcd
|
|
rules:
|
|
- alert: etcdMembersDown
|
|
annotations:
|
|
description: 'etcd cluster "{{ $labels.job }}": members are down ({{ $value }}).'
|
|
summary: etcd cluster members are down.
|
|
expr: |-
|
|
max without (endpoint) (
|
|
sum without (instance, pod) (up{job=~".*etcd.*"} == bool 0)
|
|
or
|
|
count without (To) (
|
|
sum without (instance, pod) (rate(etcd_network_peer_sent_failures_total{job=~".*etcd.*"}[120s])) > 0.01
|
|
)
|
|
)
|
|
> 0
|
|
for: 10m
|
|
labels:
|
|
severity: critical
|
|
- alert: etcdInsufficientMembers
|
|
annotations:
|
|
description: 'etcd cluster "{{ $labels.job }}": insufficient members ({{ $value }}).'
|
|
summary: etcd cluster has insufficient number of members.
|
|
expr: sum(up{job=~".*etcd.*"} == bool 1) without (instance, pod) < ((count(up{job=~".*etcd.*"}) without (instance, pod) + 1) / 2)
|
|
for: 3m
|
|
labels:
|
|
severity: critical
|
|
- alert: etcdNoLeader
|
|
annotations:
|
|
description: 'etcd cluster "{{ $labels.job }}": member {{ $labels.instance }} has no leader.'
|
|
summary: etcd cluster has no leader.
|
|
expr: etcd_server_has_leader{job=~".*etcd.*"} == 0
|
|
for: 1m
|
|
labels:
|
|
severity: critical
|
|
- alert: etcdHighNumberOfLeaderChanges
|
|
annotations:
|
|
description: 'etcd cluster "{{ $labels.job }}": {{ $value }} leader changes within the last 15 minutes. Frequent elections may be a sign of insufficient resources, high network latency, or disruptions by other components and should be investigated.'
|
|
summary: etcd cluster has high number of leader changes.
|
|
expr: increase((max without (instance, pod) (etcd_server_leader_changes_seen_total{job=~".*etcd.*"}) or 0*absent(etcd_server_leader_changes_seen_total{job=~".*etcd.*"}))[15m:1m]) >= 4
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
- alert: etcdHighNumberOfFailedGRPCRequests
|
|
annotations:
|
|
description: 'etcd cluster "{{ $labels.job }}": {{ $value }}% of requests for {{ $labels.grpc_method }} failed on etcd instance {{ $labels.instance }}.'
|
|
summary: etcd cluster has high number of failed grpc requests.
|
|
expr: |-
|
|
100 * sum(rate(grpc_server_handled_total{job=~".*etcd.*", grpc_code=~"Unknown|FailedPrecondition|ResourceExhausted|Internal|Unavailable|DataLoss|DeadlineExceeded"}[5m])) without (grpc_type, grpc_code)
|
|
/
|
|
sum(rate(grpc_server_handled_total{job=~".*etcd.*"}[5m])) without (grpc_type, grpc_code)
|
|
> 1
|
|
for: 10m
|
|
labels:
|
|
severity: warning
|
|
- alert: etcdHighNumberOfFailedGRPCRequests
|
|
annotations:
|
|
description: 'etcd cluster "{{ $labels.job }}": {{ $value }}% of requests for {{ $labels.grpc_method }} failed on etcd instance {{ $labels.instance }}.'
|
|
summary: etcd cluster has high number of failed grpc requests.
|
|
expr: |-
|
|
100 * sum(rate(grpc_server_handled_total{job=~".*etcd.*", grpc_code=~"Unknown|FailedPrecondition|ResourceExhausted|Internal|Unavailable|DataLoss|DeadlineExceeded"}[5m])) without (grpc_type, grpc_code)
|
|
/
|
|
sum(rate(grpc_server_handled_total{job=~".*etcd.*"}[5m])) without (grpc_type, grpc_code)
|
|
> 5
|
|
for: 5m
|
|
labels:
|
|
severity: critical
|
|
- alert: etcdGRPCRequestsSlow
|
|
annotations:
|
|
description: 'etcd cluster "{{ $labels.job }}": 99th percentile of gRPC requests is {{ $value }}s on etcd instance {{ $labels.instance }} for {{ $labels.grpc_method }} method.'
|
|
summary: etcd grpc requests are slow
|
|
expr: |-
|
|
histogram_quantile(0.99, sum(rate(grpc_server_handling_seconds_bucket{job=~".*etcd.*", grpc_method!="Defragment", grpc_type="unary"}[5m])) without(grpc_type))
|
|
> 0.15
|
|
for: 10m
|
|
labels:
|
|
severity: critical
|
|
- alert: etcdMemberCommunicationSlow
|
|
annotations:
|
|
description: 'etcd cluster "{{ $labels.job }}": member communication with {{ $labels.To }} is taking {{ $value }}s on etcd instance {{ $labels.instance }}.'
|
|
summary: etcd cluster member communication is slow.
|
|
expr: |-
|
|
histogram_quantile(0.99, rate(etcd_network_peer_round_trip_time_seconds_bucket{job=~".*etcd.*"}[5m]))
|
|
> 0.15
|
|
for: 10m
|
|
labels:
|
|
severity: warning
|
|
- alert: etcdHighNumberOfFailedProposals
|
|
annotations:
|
|
description: 'etcd cluster "{{ $labels.job }}": {{ $value }} proposal failures within the last 30 minutes on etcd instance {{ $labels.instance }}.'
|
|
summary: etcd cluster has high number of proposal failures.
|
|
expr: rate(etcd_server_proposals_failed_total{job=~".*etcd.*"}[15m]) > 5
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
- alert: etcdHighFsyncDurations
|
|
annotations:
|
|
description: 'etcd cluster "{{ $labels.job }}": 99th percentile fsync durations are {{ $value }}s on etcd instance {{ $labels.instance }}.'
|
|
summary: etcd cluster 99th percentile fsync durations are too high.
|
|
expr: |-
|
|
histogram_quantile(0.99, rate(etcd_disk_wal_fsync_duration_seconds_bucket{job=~".*etcd.*"}[5m]))
|
|
> 0.5
|
|
for: 10m
|
|
labels:
|
|
severity: warning
|
|
- alert: etcdHighFsyncDurations
|
|
annotations:
|
|
description: 'etcd cluster "{{ $labels.job }}": 99th percentile fsync durations are {{ $value }}s on etcd instance {{ $labels.instance }}.'
|
|
summary: etcd cluster 99th percentile fsync durations are too high.
|
|
expr: |-
|
|
histogram_quantile(0.99, rate(etcd_disk_wal_fsync_duration_seconds_bucket{job=~".*etcd.*"}[5m]))
|
|
> 1
|
|
for: 10m
|
|
labels:
|
|
severity: critical
|
|
- alert: etcdHighCommitDurations
|
|
annotations:
|
|
description: 'etcd cluster "{{ $labels.job }}": 99th percentile commit durations {{ $value }}s on etcd instance {{ $labels.instance }}.'
|
|
summary: etcd cluster 99th percentile commit durations are too high.
|
|
expr: |-
|
|
histogram_quantile(0.99, rate(etcd_disk_backend_commit_duration_seconds_bucket{job=~".*etcd.*"}[5m]))
|
|
> 0.25
|
|
for: 10m
|
|
labels:
|
|
severity: warning
|
|
- alert: etcdDatabaseQuotaLowSpace
|
|
annotations:
|
|
description: 'etcd cluster "{{ $labels.job }}": database size exceeds the defined quota on etcd instance {{ $labels.instance }}, please defrag or increase the quota as the writes to etcd will be disabled when it is full.'
|
|
summary: etcd cluster database is running full.
|
|
expr: (last_over_time(etcd_mvcc_db_total_size_in_bytes{job=~".*etcd.*"}[5m]) / last_over_time(etcd_server_quota_backend_bytes{job=~".*etcd.*"}[5m]))*100 > 95
|
|
for: 10m
|
|
labels:
|
|
severity: critical
|
|
- alert: etcdExcessiveDatabaseGrowth
|
|
annotations:
|
|
description: 'etcd cluster "{{ $labels.job }}": Predicting running out of disk space in the next four hours, based on write observations within the past four hours on etcd instance {{ $labels.instance }}, please check as it might be disruptive.'
|
|
summary: etcd cluster database growing very fast.
|
|
expr: predict_linear(etcd_mvcc_db_total_size_in_bytes{job=~".*etcd.*"}[4h], 4*60*60) > etcd_server_quota_backend_bytes{job=~".*etcd.*"}
|
|
for: 10m
|
|
labels:
|
|
severity: warning
|
|
- alert: etcdDatabaseHighFragmentationRatio
|
|
annotations:
|
|
description: 'etcd cluster "{{ $labels.job }}": database size in use on instance {{ $labels.instance }} is {{ $value | humanizePercentage }} of the actual allocated disk space, please run defragmentation (e.g. etcdctl defrag) to retrieve the unused fragmented disk space.'
|
|
runbook_url: https://etcd.io/docs/v3.5/op-guide/maintenance/#defragmentation
|
|
summary: etcd database size in use is less than 50% of the actual allocated storage.
|
|
expr: (last_over_time(etcd_mvcc_db_total_size_in_use_in_bytes{job=~".*etcd.*"}[5m]) / last_over_time(etcd_mvcc_db_total_size_in_bytes{job=~".*etcd.*"}[5m])) < 0.5 and etcd_mvcc_db_total_size_in_use_in_bytes{job=~".*etcd.*"} > 104857600
|
|
for: 10m
|
|
labels:
|
|
severity: warning
|
|
---
|
|
# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/general.rules.yaml
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: PrometheusRule
|
|
metadata:
|
|
name: kube-prometheus-stack-general.rules
|
|
namespace: default
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack
|
|
app.kubernetes.io/name: kube-prometheus-stack #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
spec:
|
|
groups:
|
|
- name: general.rules
|
|
rules:
|
|
- alert: TargetDown
|
|
annotations:
|
|
description: '{{ printf "%.4g" $value }}% of the {{ $labels.job }}/{{ $labels.service }} targets in {{ $labels.namespace }} namespace are down.'
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/general/targetdown
|
|
summary: One or more targets are unreachable.
|
|
expr: 100 * (count(up == 0) BY (cluster, job, namespace, service) / count(up) BY (cluster, job, namespace, service)) > 10
|
|
for: 10m
|
|
labels:
|
|
severity: warning
|
|
- alert: Watchdog
|
|
annotations:
|
|
description: 'This is an alert meant to ensure that the entire alerting pipeline is functional.
|
|
|
|
This alert is always firing, therefore it should always be firing in Alertmanager
|
|
|
|
and always fire against a receiver. There are integrations with various notification
|
|
|
|
mechanisms that send a notification when this alert is not firing. For example the
|
|
|
|
"DeadMansSnitch" integration in PagerDuty.
|
|
|
|
'
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/general/watchdog
|
|
summary: An alert that should always be firing to certify that Alertmanager is working properly.
|
|
expr: vector(1)
|
|
labels:
|
|
severity: none
|
|
- alert: InfoInhibitor
|
|
annotations:
|
|
description: 'This is an alert that is used to inhibit info alerts.
|
|
|
|
By themselves, the info-level alerts are sometimes very noisy, but they are relevant when combined with
|
|
|
|
other alerts.
|
|
|
|
This alert fires whenever there''s a severity="info" alert, and stops firing when another alert with a
|
|
|
|
severity of ''warning'' or ''critical'' starts firing on the same namespace.
|
|
|
|
This alert should be routed to a null receiver and configured to inhibit alerts with severity="info".
|
|
|
|
'
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/general/infoinhibitor
|
|
summary: Info-level alert inhibition.
|
|
expr: ALERTS{severity = "info"} == 1 unless on (namespace) ALERTS{alertname != "InfoInhibitor", severity =~ "warning|critical", alertstate="firing"} == 1
|
|
labels:
|
|
severity: none
|
|
---
|
|
# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/k8s.rules.container_cpu_usage_seconds_total.yaml
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: PrometheusRule
|
|
metadata:
|
|
name: kube-prometheus-stack-k8s.rules.container-cpu-usage-seconds-tot
|
|
namespace: default
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack
|
|
app.kubernetes.io/name: kube-prometheus-stack #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
spec:
|
|
groups:
|
|
- name: k8s.rules.container_cpu_usage_seconds_total
|
|
rules:
|
|
- expr: |-
|
|
sum by (cluster, namespace, pod, container) (
|
|
irate(container_cpu_usage_seconds_total{job="kubelet", metrics_path="/metrics/cadvisor", image!=""}[5m])
|
|
) * on (cluster, namespace, pod) group_left(node) topk by (cluster, namespace, pod) (
|
|
1, max by (cluster, namespace, pod, node) (kube_pod_info{node!=""})
|
|
)
|
|
record: node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate
|
|
---
|
|
# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/k8s.rules.container_memory_cache.yaml
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: PrometheusRule
|
|
metadata:
|
|
name: kube-prometheus-stack-k8s.rules.container-memory-cache
|
|
namespace: default
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack
|
|
app.kubernetes.io/name: kube-prometheus-stack #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
spec:
|
|
groups:
|
|
- name: k8s.rules.container_memory_cache
|
|
rules:
|
|
- expr: |-
|
|
container_memory_cache{job="kubelet", metrics_path="/metrics/cadvisor", image!=""}
|
|
* on (cluster, namespace, pod) group_left(node) topk by (cluster, namespace, pod) (1,
|
|
max by (cluster, namespace, pod, node) (kube_pod_info{node!=""})
|
|
)
|
|
record: node_namespace_pod_container:container_memory_cache
|
|
---
|
|
# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/k8s.rules.container_memory_rss.yaml
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: PrometheusRule
|
|
metadata:
|
|
name: kube-prometheus-stack-k8s.rules.container-memory-rss
|
|
namespace: default
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack
|
|
app.kubernetes.io/name: kube-prometheus-stack #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
spec:
|
|
groups:
|
|
- name: k8s.rules.container_memory_rss
|
|
rules:
|
|
- expr: |-
|
|
container_memory_rss{job="kubelet", metrics_path="/metrics/cadvisor", image!=""}
|
|
* on (cluster, namespace, pod) group_left(node) topk by (cluster, namespace, pod) (1,
|
|
max by (cluster, namespace, pod, node) (kube_pod_info{node!=""})
|
|
)
|
|
record: node_namespace_pod_container:container_memory_rss
|
|
---
|
|
# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/k8s.rules.container_memory_swap.yaml
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: PrometheusRule
|
|
metadata:
|
|
name: kube-prometheus-stack-k8s.rules.container-memory-swap
|
|
namespace: default
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack
|
|
app.kubernetes.io/name: kube-prometheus-stack #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
spec:
|
|
groups:
|
|
- name: k8s.rules.container_memory_swap
|
|
rules:
|
|
- expr: |-
|
|
container_memory_swap{job="kubelet", metrics_path="/metrics/cadvisor", image!=""}
|
|
* on (cluster, namespace, pod) group_left(node) topk by (cluster, namespace, pod) (1,
|
|
max by (cluster, namespace, pod, node) (kube_pod_info{node!=""})
|
|
)
|
|
record: node_namespace_pod_container:container_memory_swap
|
|
---
|
|
# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/k8s.rules.container_memory_working_set_bytes.yaml
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: PrometheusRule
|
|
metadata:
|
|
name: kube-prometheus-stack-k8s.rules.container-memory-working-set-by
|
|
namespace: default
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack
|
|
app.kubernetes.io/name: kube-prometheus-stack #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
spec:
|
|
groups:
|
|
- name: k8s.rules.container_memory_working_set_bytes
|
|
rules:
|
|
- expr: |-
|
|
container_memory_working_set_bytes{job="kubelet", metrics_path="/metrics/cadvisor", image!=""}
|
|
* on (cluster, namespace, pod) group_left(node) topk by (cluster, namespace, pod) (1,
|
|
max by (cluster, namespace, pod, node) (kube_pod_info{node!=""})
|
|
)
|
|
record: node_namespace_pod_container:container_memory_working_set_bytes
|
|
---
|
|
# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/k8s.rules.container_resource.yaml
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: PrometheusRule
|
|
metadata:
|
|
name: kube-prometheus-stack-k8s.rules.container-resource
|
|
namespace: default
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack
|
|
app.kubernetes.io/name: kube-prometheus-stack #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
spec:
|
|
groups:
|
|
- name: k8s.rules.container_resource
|
|
rules:
|
|
- expr: |-
|
|
kube_pod_container_resource_requests{resource="memory",job="kube-state-metrics"} * on (namespace, pod, cluster)
|
|
group_left() max by (namespace, pod, cluster) (
|
|
(kube_pod_status_phase{phase=~"Pending|Running"} == 1)
|
|
)
|
|
record: cluster:namespace:pod_memory:active:kube_pod_container_resource_requests
|
|
- expr: |-
|
|
sum by (namespace, cluster) (
|
|
sum by (namespace, pod, cluster) (
|
|
max by (namespace, pod, container, cluster) (
|
|
kube_pod_container_resource_requests{resource="memory",job="kube-state-metrics"}
|
|
) * on (namespace, pod, cluster) group_left() max by (namespace, pod, cluster) (
|
|
kube_pod_status_phase{phase=~"Pending|Running"} == 1
|
|
)
|
|
)
|
|
)
|
|
record: namespace_memory:kube_pod_container_resource_requests:sum
|
|
- expr: |-
|
|
kube_pod_container_resource_requests{resource="cpu",job="kube-state-metrics"} * on (namespace, pod, cluster)
|
|
group_left() max by (namespace, pod, cluster) (
|
|
(kube_pod_status_phase{phase=~"Pending|Running"} == 1)
|
|
)
|
|
record: cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests
|
|
- expr: |-
|
|
sum by (namespace, cluster) (
|
|
sum by (namespace, pod, cluster) (
|
|
max by (namespace, pod, container, cluster) (
|
|
kube_pod_container_resource_requests{resource="cpu",job="kube-state-metrics"}
|
|
) * on (namespace, pod, cluster) group_left() max by (namespace, pod, cluster) (
|
|
kube_pod_status_phase{phase=~"Pending|Running"} == 1
|
|
)
|
|
)
|
|
)
|
|
record: namespace_cpu:kube_pod_container_resource_requests:sum
|
|
- expr: |-
|
|
kube_pod_container_resource_limits{resource="memory",job="kube-state-metrics"} * on (namespace, pod, cluster)
|
|
group_left() max by (namespace, pod, cluster) (
|
|
(kube_pod_status_phase{phase=~"Pending|Running"} == 1)
|
|
)
|
|
record: cluster:namespace:pod_memory:active:kube_pod_container_resource_limits
|
|
- expr: |-
|
|
sum by (namespace, cluster) (
|
|
sum by (namespace, pod, cluster) (
|
|
max by (namespace, pod, container, cluster) (
|
|
kube_pod_container_resource_limits{resource="memory",job="kube-state-metrics"}
|
|
) * on (namespace, pod, cluster) group_left() max by (namespace, pod, cluster) (
|
|
kube_pod_status_phase{phase=~"Pending|Running"} == 1
|
|
)
|
|
)
|
|
)
|
|
record: namespace_memory:kube_pod_container_resource_limits:sum
|
|
- expr: |-
|
|
kube_pod_container_resource_limits{resource="cpu",job="kube-state-metrics"} * on (namespace, pod, cluster)
|
|
group_left() max by (namespace, pod, cluster) (
|
|
(kube_pod_status_phase{phase=~"Pending|Running"} == 1)
|
|
)
|
|
record: cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits
|
|
- expr: |-
|
|
sum by (namespace, cluster) (
|
|
sum by (namespace, pod, cluster) (
|
|
max by (namespace, pod, container, cluster) (
|
|
kube_pod_container_resource_limits{resource="cpu",job="kube-state-metrics"}
|
|
) * on (namespace, pod, cluster) group_left() max by (namespace, pod, cluster) (
|
|
kube_pod_status_phase{phase=~"Pending|Running"} == 1
|
|
)
|
|
)
|
|
)
|
|
record: namespace_cpu:kube_pod_container_resource_limits:sum
|
|
---
|
|
# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/k8s.rules.pod_owner.yaml
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: PrometheusRule
|
|
metadata:
|
|
name: kube-prometheus-stack-k8s.rules.pod-owner
|
|
namespace: default
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack
|
|
app.kubernetes.io/name: kube-prometheus-stack #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
spec:
|
|
groups:
|
|
- name: k8s.rules.pod_owner
|
|
rules:
|
|
- expr: |-
|
|
max by (cluster, namespace, workload, pod) (
|
|
label_replace(
|
|
label_replace(
|
|
kube_pod_owner{job="kube-state-metrics", owner_kind="ReplicaSet"},
|
|
"replicaset", "$1", "owner_name", "(.*)"
|
|
) * on (replicaset, namespace) group_left(owner_name) topk by (replicaset, namespace) (
|
|
1, max by (replicaset, namespace, owner_name) (
|
|
kube_replicaset_owner{job="kube-state-metrics"}
|
|
)
|
|
),
|
|
"workload", "$1", "owner_name", "(.*)"
|
|
)
|
|
)
|
|
labels:
|
|
workload_type: deployment
|
|
record: namespace_workload_pod:kube_pod_owner:relabel
|
|
- expr: |-
|
|
max by (cluster, namespace, workload, pod) (
|
|
label_replace(
|
|
kube_pod_owner{job="kube-state-metrics", owner_kind="DaemonSet"},
|
|
"workload", "$1", "owner_name", "(.*)"
|
|
)
|
|
)
|
|
labels:
|
|
workload_type: daemonset
|
|
record: namespace_workload_pod:kube_pod_owner:relabel
|
|
- expr: |-
|
|
max by (cluster, namespace, workload, pod) (
|
|
label_replace(
|
|
kube_pod_owner{job="kube-state-metrics", owner_kind="StatefulSet"},
|
|
"workload", "$1", "owner_name", "(.*)"
|
|
)
|
|
)
|
|
labels:
|
|
workload_type: statefulset
|
|
record: namespace_workload_pod:kube_pod_owner:relabel
|
|
- expr: |-
|
|
max by (cluster, namespace, workload, pod) (
|
|
label_replace(
|
|
kube_pod_owner{job="kube-state-metrics", owner_kind="Job"},
|
|
"workload", "$1", "owner_name", "(.*)"
|
|
)
|
|
)
|
|
labels:
|
|
workload_type: job
|
|
record: namespace_workload_pod:kube_pod_owner:relabel
|
|
---
|
|
# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/kube-apiserver-availability.rules.yaml
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: PrometheusRule
|
|
metadata:
|
|
name: kube-prometheus-stack-kube-apiserver-availability.rules
|
|
namespace: default
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack
|
|
app.kubernetes.io/name: kube-prometheus-stack #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
spec:
|
|
groups:
|
|
- interval: 3m
|
|
name: kube-apiserver-availability.rules
|
|
rules:
|
|
- expr: avg_over_time(code_verb:apiserver_request_total:increase1h[30d]) * 24 * 30
|
|
record: code_verb:apiserver_request_total:increase30d
|
|
- expr: sum by (cluster, code) (code_verb:apiserver_request_total:increase30d{verb=~"LIST|GET"})
|
|
labels:
|
|
verb: read
|
|
record: code:apiserver_request_total:increase30d
|
|
- expr: sum by (cluster, code) (code_verb:apiserver_request_total:increase30d{verb=~"POST|PUT|PATCH|DELETE"})
|
|
labels:
|
|
verb: write
|
|
record: code:apiserver_request_total:increase30d
|
|
- expr: sum by (cluster, verb, scope, le) (increase(apiserver_request_sli_duration_seconds_bucket[1h]))
|
|
record: cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase1h
|
|
- expr: sum by (cluster, verb, scope, le) (avg_over_time(cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase1h[30d]) * 24 * 30)
|
|
record: cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d
|
|
- expr: sum by (cluster, verb, scope) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase1h{le="+Inf"})
|
|
record: cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase1h
|
|
- expr: sum by (cluster, verb, scope) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{le="+Inf"})
|
|
record: cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase30d
|
|
- expr: |-
|
|
1 - (
|
|
(
|
|
# write too slow
|
|
sum by (cluster) (cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase30d{verb=~"POST|PUT|PATCH|DELETE"})
|
|
-
|
|
sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~"POST|PUT|PATCH|DELETE",le="1"})
|
|
) +
|
|
(
|
|
# read too slow
|
|
sum by (cluster) (cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase30d{verb=~"LIST|GET"})
|
|
-
|
|
(
|
|
(
|
|
sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~"LIST|GET",scope=~"resource|",le="1"})
|
|
or
|
|
vector(0)
|
|
)
|
|
+
|
|
sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~"LIST|GET",scope="namespace",le="5"})
|
|
+
|
|
sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~"LIST|GET",scope="cluster",le="30"})
|
|
)
|
|
) +
|
|
# errors
|
|
sum by (cluster) (code:apiserver_request_total:increase30d{code=~"5.."} or vector(0))
|
|
)
|
|
/
|
|
sum by (cluster) (code:apiserver_request_total:increase30d)
|
|
labels:
|
|
verb: all
|
|
record: apiserver_request:availability30d
|
|
- expr: |-
|
|
1 - (
|
|
sum by (cluster) (cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase30d{verb=~"LIST|GET"})
|
|
-
|
|
(
|
|
# too slow
|
|
(
|
|
sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~"LIST|GET",scope=~"resource|",le="1"})
|
|
or
|
|
vector(0)
|
|
)
|
|
+
|
|
sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~"LIST|GET",scope="namespace",le="5"})
|
|
+
|
|
sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~"LIST|GET",scope="cluster",le="30"})
|
|
)
|
|
+
|
|
# errors
|
|
sum by (cluster) (code:apiserver_request_total:increase30d{verb="read",code=~"5.."} or vector(0))
|
|
)
|
|
/
|
|
sum by (cluster) (code:apiserver_request_total:increase30d{verb="read"})
|
|
labels:
|
|
verb: read
|
|
record: apiserver_request:availability30d
|
|
- expr: |-
|
|
1 - (
|
|
(
|
|
# too slow
|
|
sum by (cluster) (cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase30d{verb=~"POST|PUT|PATCH|DELETE"})
|
|
-
|
|
sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~"POST|PUT|PATCH|DELETE",le="1"})
|
|
)
|
|
+
|
|
# errors
|
|
sum by (cluster) (code:apiserver_request_total:increase30d{verb="write",code=~"5.."} or vector(0))
|
|
)
|
|
/
|
|
sum by (cluster) (code:apiserver_request_total:increase30d{verb="write"})
|
|
labels:
|
|
verb: write
|
|
record: apiserver_request:availability30d
|
|
- expr: sum by (cluster,code,resource) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[5m]))
|
|
labels:
|
|
verb: read
|
|
record: code_resource:apiserver_request_total:rate5m
|
|
- expr: sum by (cluster,code,resource) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[5m]))
|
|
labels:
|
|
verb: write
|
|
record: code_resource:apiserver_request_total:rate5m
|
|
- expr: sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb=~"LIST|GET|POST|PUT|PATCH|DELETE",code=~"2.."}[1h]))
|
|
record: code_verb:apiserver_request_total:increase1h
|
|
- expr: sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb=~"LIST|GET|POST|PUT|PATCH|DELETE",code=~"3.."}[1h]))
|
|
record: code_verb:apiserver_request_total:increase1h
|
|
- expr: sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb=~"LIST|GET|POST|PUT|PATCH|DELETE",code=~"4.."}[1h]))
|
|
record: code_verb:apiserver_request_total:increase1h
|
|
- expr: sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb=~"LIST|GET|POST|PUT|PATCH|DELETE",code=~"5.."}[1h]))
|
|
record: code_verb:apiserver_request_total:increase1h
|
|
---
|
|
# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/kube-apiserver-burnrate.rules.yaml
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: PrometheusRule
|
|
metadata:
|
|
name: kube-prometheus-stack-kube-apiserver-burnrate.rules
|
|
namespace: default
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack
|
|
app.kubernetes.io/name: kube-prometheus-stack #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
spec:
|
|
groups:
|
|
- name: kube-apiserver-burnrate.rules
|
|
rules:
|
|
- expr: |-
|
|
(
|
|
(
|
|
# too slow
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[1d]))
|
|
-
|
|
(
|
|
(
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le="1"}[1d]))
|
|
or
|
|
vector(0)
|
|
)
|
|
+
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le="5"}[1d]))
|
|
+
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le="30"}[1d]))
|
|
)
|
|
)
|
|
+
|
|
# errors
|
|
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[1d]))
|
|
)
|
|
/
|
|
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[1d]))
|
|
labels:
|
|
verb: read
|
|
record: apiserver_request:burnrate1d
|
|
- expr: |-
|
|
(
|
|
(
|
|
# too slow
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[1h]))
|
|
-
|
|
(
|
|
(
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le="1"}[1h]))
|
|
or
|
|
vector(0)
|
|
)
|
|
+
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le="5"}[1h]))
|
|
+
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le="30"}[1h]))
|
|
)
|
|
)
|
|
+
|
|
# errors
|
|
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[1h]))
|
|
)
|
|
/
|
|
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[1h]))
|
|
labels:
|
|
verb: read
|
|
record: apiserver_request:burnrate1h
|
|
- expr: |-
|
|
(
|
|
(
|
|
# too slow
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[2h]))
|
|
-
|
|
(
|
|
(
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le="1"}[2h]))
|
|
or
|
|
vector(0)
|
|
)
|
|
+
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le="5"}[2h]))
|
|
+
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le="30"}[2h]))
|
|
)
|
|
)
|
|
+
|
|
# errors
|
|
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[2h]))
|
|
)
|
|
/
|
|
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[2h]))
|
|
labels:
|
|
verb: read
|
|
record: apiserver_request:burnrate2h
|
|
- expr: |-
|
|
(
|
|
(
|
|
# too slow
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[30m]))
|
|
-
|
|
(
|
|
(
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le="1"}[30m]))
|
|
or
|
|
vector(0)
|
|
)
|
|
+
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le="5"}[30m]))
|
|
+
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le="30"}[30m]))
|
|
)
|
|
)
|
|
+
|
|
# errors
|
|
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[30m]))
|
|
)
|
|
/
|
|
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[30m]))
|
|
labels:
|
|
verb: read
|
|
record: apiserver_request:burnrate30m
|
|
- expr: |-
|
|
(
|
|
(
|
|
# too slow
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[3d]))
|
|
-
|
|
(
|
|
(
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le="1"}[3d]))
|
|
or
|
|
vector(0)
|
|
)
|
|
+
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le="5"}[3d]))
|
|
+
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le="30"}[3d]))
|
|
)
|
|
)
|
|
+
|
|
# errors
|
|
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[3d]))
|
|
)
|
|
/
|
|
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[3d]))
|
|
labels:
|
|
verb: read
|
|
record: apiserver_request:burnrate3d
|
|
- expr: |-
|
|
(
|
|
(
|
|
# too slow
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[5m]))
|
|
-
|
|
(
|
|
(
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le="1"}[5m]))
|
|
or
|
|
vector(0)
|
|
)
|
|
+
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le="5"}[5m]))
|
|
+
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le="30"}[5m]))
|
|
)
|
|
)
|
|
+
|
|
# errors
|
|
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[5m]))
|
|
)
|
|
/
|
|
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[5m]))
|
|
labels:
|
|
verb: read
|
|
record: apiserver_request:burnrate5m
|
|
- expr: |-
|
|
(
|
|
(
|
|
# too slow
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[6h]))
|
|
-
|
|
(
|
|
(
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le="1"}[6h]))
|
|
or
|
|
vector(0)
|
|
)
|
|
+
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le="5"}[6h]))
|
|
+
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le="30"}[6h]))
|
|
)
|
|
)
|
|
+
|
|
# errors
|
|
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[6h]))
|
|
)
|
|
/
|
|
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[6h]))
|
|
labels:
|
|
verb: read
|
|
record: apiserver_request:burnrate6h
|
|
- expr: |-
|
|
(
|
|
(
|
|
# too slow
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[1d]))
|
|
-
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le="1"}[1d]))
|
|
)
|
|
+
|
|
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[1d]))
|
|
)
|
|
/
|
|
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[1d]))
|
|
labels:
|
|
verb: write
|
|
record: apiserver_request:burnrate1d
|
|
- expr: |-
|
|
(
|
|
(
|
|
# too slow
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[1h]))
|
|
-
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le="1"}[1h]))
|
|
)
|
|
+
|
|
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[1h]))
|
|
)
|
|
/
|
|
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[1h]))
|
|
labels:
|
|
verb: write
|
|
record: apiserver_request:burnrate1h
|
|
- expr: |-
|
|
(
|
|
(
|
|
# too slow
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[2h]))
|
|
-
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le="1"}[2h]))
|
|
)
|
|
+
|
|
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[2h]))
|
|
)
|
|
/
|
|
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[2h]))
|
|
labels:
|
|
verb: write
|
|
record: apiserver_request:burnrate2h
|
|
- expr: |-
|
|
(
|
|
(
|
|
# too slow
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[30m]))
|
|
-
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le="1"}[30m]))
|
|
)
|
|
+
|
|
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[30m]))
|
|
)
|
|
/
|
|
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[30m]))
|
|
labels:
|
|
verb: write
|
|
record: apiserver_request:burnrate30m
|
|
- expr: |-
|
|
(
|
|
(
|
|
# too slow
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[3d]))
|
|
-
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le="1"}[3d]))
|
|
)
|
|
+
|
|
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[3d]))
|
|
)
|
|
/
|
|
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[3d]))
|
|
labels:
|
|
verb: write
|
|
record: apiserver_request:burnrate3d
|
|
- expr: |-
|
|
(
|
|
(
|
|
# too slow
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[5m]))
|
|
-
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le="1"}[5m]))
|
|
)
|
|
+
|
|
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[5m]))
|
|
)
|
|
/
|
|
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[5m]))
|
|
labels:
|
|
verb: write
|
|
record: apiserver_request:burnrate5m
|
|
- expr: |-
|
|
(
|
|
(
|
|
# too slow
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[6h]))
|
|
-
|
|
sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le="1"}[6h]))
|
|
)
|
|
+
|
|
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[6h]))
|
|
)
|
|
/
|
|
sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[6h]))
|
|
labels:
|
|
verb: write
|
|
record: apiserver_request:burnrate6h
|
|
---
|
|
# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/kube-apiserver-histogram.rules.yaml
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: PrometheusRule
|
|
metadata:
|
|
name: kube-prometheus-stack-kube-apiserver-histogram.rules
|
|
namespace: default
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack
|
|
app.kubernetes.io/name: kube-prometheus-stack #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
spec:
|
|
groups:
|
|
- name: kube-apiserver-histogram.rules
|
|
rules:
|
|
- expr: histogram_quantile(0.99, sum by (cluster, le, resource) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[5m]))) > 0
|
|
labels:
|
|
quantile: '0.99'
|
|
verb: read
|
|
record: cluster_quantile:apiserver_request_sli_duration_seconds:histogram_quantile
|
|
- expr: histogram_quantile(0.99, sum by (cluster, le, resource) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[5m]))) > 0
|
|
labels:
|
|
quantile: '0.99'
|
|
verb: write
|
|
record: cluster_quantile:apiserver_request_sli_duration_seconds:histogram_quantile
|
|
---
|
|
# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/kube-apiserver-slos.yaml
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: PrometheusRule
|
|
metadata:
|
|
name: kube-prometheus-stack-kube-apiserver-slos
|
|
namespace: default
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack
|
|
app.kubernetes.io/name: kube-prometheus-stack #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
spec:
|
|
groups:
|
|
- name: kube-apiserver-slos
|
|
rules:
|
|
- alert: KubeAPIErrorBudgetBurn
|
|
annotations:
|
|
description: The API server is burning too much error budget.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeapierrorbudgetburn
|
|
summary: The API server is burning too much error budget.
|
|
expr: |-
|
|
sum by (cluster) (apiserver_request:burnrate1h) > (14.40 * 0.01000)
|
|
and on (cluster)
|
|
sum by (cluster) (apiserver_request:burnrate5m) > (14.40 * 0.01000)
|
|
for: 2m
|
|
labels:
|
|
long: 1h
|
|
severity: critical
|
|
short: 5m
|
|
- alert: KubeAPIErrorBudgetBurn
|
|
annotations:
|
|
description: The API server is burning too much error budget.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeapierrorbudgetburn
|
|
summary: The API server is burning too much error budget.
|
|
expr: |-
|
|
sum by (cluster) (apiserver_request:burnrate6h) > (6.00 * 0.01000)
|
|
and on (cluster)
|
|
sum by (cluster) (apiserver_request:burnrate30m) > (6.00 * 0.01000)
|
|
for: 15m
|
|
labels:
|
|
long: 6h
|
|
severity: critical
|
|
short: 30m
|
|
- alert: KubeAPIErrorBudgetBurn
|
|
annotations:
|
|
description: The API server is burning too much error budget.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeapierrorbudgetburn
|
|
summary: The API server is burning too much error budget.
|
|
expr: |-
|
|
sum by (cluster) (apiserver_request:burnrate1d) > (3.00 * 0.01000)
|
|
and on (cluster)
|
|
sum by (cluster) (apiserver_request:burnrate2h) > (3.00 * 0.01000)
|
|
for: 1h
|
|
labels:
|
|
long: 1d
|
|
severity: warning
|
|
short: 2h
|
|
- alert: KubeAPIErrorBudgetBurn
|
|
annotations:
|
|
description: The API server is burning too much error budget.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeapierrorbudgetburn
|
|
summary: The API server is burning too much error budget.
|
|
expr: |-
|
|
sum by (cluster) (apiserver_request:burnrate3d) > (1.00 * 0.01000)
|
|
and on (cluster)
|
|
sum by (cluster) (apiserver_request:burnrate6h) > (1.00 * 0.01000)
|
|
for: 3h
|
|
labels:
|
|
long: 3d
|
|
severity: warning
|
|
short: 6h
|
|
---
|
|
# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/kube-prometheus-general.rules.yaml
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: PrometheusRule
|
|
metadata:
|
|
name: kube-prometheus-stack-kube-prometheus-general.rules
|
|
namespace: default
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack
|
|
app.kubernetes.io/name: kube-prometheus-stack #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
spec:
|
|
groups:
|
|
- name: kube-prometheus-general.rules
|
|
rules:
|
|
- expr: count without(instance, pod, node) (up == 1)
|
|
record: count:up1
|
|
- expr: count without(instance, pod, node) (up == 0)
|
|
record: count:up0
|
|
---
|
|
# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/kube-prometheus-node-recording.rules.yaml
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: PrometheusRule
|
|
metadata:
|
|
name: kube-prometheus-stack-kube-prometheus-node-recording.rules
|
|
namespace: default
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack
|
|
app.kubernetes.io/name: kube-prometheus-stack #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
spec:
|
|
groups:
|
|
- name: kube-prometheus-node-recording.rules
|
|
rules:
|
|
- expr: sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait",mode!="steal"}[3m])) BY (instance)
|
|
record: instance:node_cpu:rate:sum
|
|
- expr: sum(rate(node_network_receive_bytes_total[3m])) BY (instance)
|
|
record: instance:node_network_receive_bytes:rate:sum
|
|
- expr: sum(rate(node_network_transmit_bytes_total[3m])) BY (instance)
|
|
record: instance:node_network_transmit_bytes:rate:sum
|
|
- expr: sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait",mode!="steal"}[5m])) WITHOUT (cpu, mode) / ON (instance) GROUP_LEFT() count(sum(node_cpu_seconds_total) BY (instance, cpu)) BY (instance)
|
|
record: instance:node_cpu:ratio
|
|
- expr: sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait",mode!="steal"}[5m]))
|
|
record: cluster:node_cpu:sum_rate5m
|
|
- expr: cluster:node_cpu:sum_rate5m / count(sum(node_cpu_seconds_total) BY (instance, cpu))
|
|
record: cluster:node_cpu:ratio
|
|
---
|
|
# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/kube-scheduler.rules.yaml
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: PrometheusRule
|
|
metadata:
|
|
name: kube-prometheus-stack-kube-scheduler.rules
|
|
namespace: default
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack
|
|
app.kubernetes.io/name: kube-prometheus-stack #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
spec:
|
|
groups:
|
|
- name: kube-scheduler.rules
|
|
rules:
|
|
- expr: histogram_quantile(0.99, sum(rate(scheduler_e2e_scheduling_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod))
|
|
labels:
|
|
quantile: '0.99'
|
|
record: cluster_quantile:scheduler_e2e_scheduling_duration_seconds:histogram_quantile
|
|
- expr: histogram_quantile(0.99, sum(rate(scheduler_scheduling_algorithm_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod))
|
|
labels:
|
|
quantile: '0.99'
|
|
record: cluster_quantile:scheduler_scheduling_algorithm_duration_seconds:histogram_quantile
|
|
- expr: histogram_quantile(0.99, sum(rate(scheduler_binding_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod))
|
|
labels:
|
|
quantile: '0.99'
|
|
record: cluster_quantile:scheduler_binding_duration_seconds:histogram_quantile
|
|
- expr: histogram_quantile(0.9, sum(rate(scheduler_e2e_scheduling_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod))
|
|
labels:
|
|
quantile: '0.9'
|
|
record: cluster_quantile:scheduler_e2e_scheduling_duration_seconds:histogram_quantile
|
|
- expr: histogram_quantile(0.9, sum(rate(scheduler_scheduling_algorithm_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod))
|
|
labels:
|
|
quantile: '0.9'
|
|
record: cluster_quantile:scheduler_scheduling_algorithm_duration_seconds:histogram_quantile
|
|
- expr: histogram_quantile(0.9, sum(rate(scheduler_binding_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod))
|
|
labels:
|
|
quantile: '0.9'
|
|
record: cluster_quantile:scheduler_binding_duration_seconds:histogram_quantile
|
|
- expr: histogram_quantile(0.5, sum(rate(scheduler_e2e_scheduling_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod))
|
|
labels:
|
|
quantile: '0.5'
|
|
record: cluster_quantile:scheduler_e2e_scheduling_duration_seconds:histogram_quantile
|
|
- expr: histogram_quantile(0.5, sum(rate(scheduler_scheduling_algorithm_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod))
|
|
labels:
|
|
quantile: '0.5'
|
|
record: cluster_quantile:scheduler_scheduling_algorithm_duration_seconds:histogram_quantile
|
|
- expr: histogram_quantile(0.5, sum(rate(scheduler_binding_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod))
|
|
labels:
|
|
quantile: '0.5'
|
|
record: cluster_quantile:scheduler_binding_duration_seconds:histogram_quantile
|
|
---
|
|
# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/kube-state-metrics.yaml
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: PrometheusRule
|
|
metadata:
|
|
name: kube-prometheus-stack-kube-state-metrics
|
|
namespace: default
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack
|
|
app.kubernetes.io/name: kube-prometheus-stack #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
spec:
|
|
groups:
|
|
- name: kube-state-metrics
|
|
rules:
|
|
- alert: KubeStateMetricsListErrors
|
|
annotations:
|
|
description: kube-state-metrics is experiencing errors at an elevated rate in list operations. This is likely causing it to not be able to expose metrics about Kubernetes objects correctly or at all.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kube-state-metrics/kubestatemetricslisterrors
|
|
summary: kube-state-metrics is experiencing errors in list operations.
|
|
expr: |-
|
|
(sum(rate(kube_state_metrics_list_total{job="kube-state-metrics",result="error"}[5m])) by (cluster)
|
|
/
|
|
sum(rate(kube_state_metrics_list_total{job="kube-state-metrics"}[5m])) by (cluster))
|
|
> 0.01
|
|
for: 15m
|
|
labels:
|
|
severity: critical
|
|
- alert: KubeStateMetricsWatchErrors
|
|
annotations:
|
|
description: kube-state-metrics is experiencing errors at an elevated rate in watch operations. This is likely causing it to not be able to expose metrics about Kubernetes objects correctly or at all.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kube-state-metrics/kubestatemetricswatcherrors
|
|
summary: kube-state-metrics is experiencing errors in watch operations.
|
|
expr: |-
|
|
(sum(rate(kube_state_metrics_watch_total{job="kube-state-metrics",result="error"}[5m])) by (cluster)
|
|
/
|
|
sum(rate(kube_state_metrics_watch_total{job="kube-state-metrics"}[5m])) by (cluster))
|
|
> 0.01
|
|
for: 15m
|
|
labels:
|
|
severity: critical
|
|
- alert: KubeStateMetricsShardingMismatch
|
|
annotations:
|
|
description: kube-state-metrics pods are running with different --total-shards configuration, some Kubernetes objects may be exposed multiple times or not exposed at all.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kube-state-metrics/kubestatemetricsshardingmismatch
|
|
summary: kube-state-metrics sharding is misconfigured.
|
|
expr: stdvar (kube_state_metrics_total_shards{job="kube-state-metrics"}) by (cluster) != 0
|
|
for: 15m
|
|
labels:
|
|
severity: critical
|
|
- alert: KubeStateMetricsShardsMissing
|
|
annotations:
|
|
description: kube-state-metrics shards are missing, some Kubernetes objects are not being exposed.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kube-state-metrics/kubestatemetricsshardsmissing
|
|
summary: kube-state-metrics shards are missing.
|
|
expr: |-
|
|
2^max(kube_state_metrics_total_shards{job="kube-state-metrics"}) by (cluster) - 1
|
|
-
|
|
sum( 2 ^ max by (cluster, shard_ordinal) (kube_state_metrics_shard_ordinal{job="kube-state-metrics"}) ) by (cluster)
|
|
!= 0
|
|
for: 15m
|
|
labels:
|
|
severity: critical
|
|
---
|
|
# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/kubelet.rules.yaml
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: PrometheusRule
|
|
metadata:
|
|
name: kube-prometheus-stack-kubelet.rules
|
|
namespace: default
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack
|
|
app.kubernetes.io/name: kube-prometheus-stack #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
spec:
|
|
groups:
|
|
- name: kubelet.rules
|
|
rules:
|
|
- expr: histogram_quantile(0.99, sum(rate(kubelet_pleg_relist_duration_seconds_bucket{job="kubelet", metrics_path="/metrics"}[5m])) by (cluster, instance, le) * on (cluster, instance) group_left(node) kubelet_node_name{job="kubelet", metrics_path="/metrics"})
|
|
labels:
|
|
quantile: '0.99'
|
|
record: node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile
|
|
- expr: histogram_quantile(0.9, sum(rate(kubelet_pleg_relist_duration_seconds_bucket{job="kubelet", metrics_path="/metrics"}[5m])) by (cluster, instance, le) * on (cluster, instance) group_left(node) kubelet_node_name{job="kubelet", metrics_path="/metrics"})
|
|
labels:
|
|
quantile: '0.9'
|
|
record: node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile
|
|
- expr: histogram_quantile(0.5, sum(rate(kubelet_pleg_relist_duration_seconds_bucket{job="kubelet", metrics_path="/metrics"}[5m])) by (cluster, instance, le) * on (cluster, instance) group_left(node) kubelet_node_name{job="kubelet", metrics_path="/metrics"})
|
|
labels:
|
|
quantile: '0.5'
|
|
record: node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile
|
|
---
|
|
# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-apps.yaml
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: PrometheusRule
|
|
metadata:
|
|
name: kube-prometheus-stack-kubernetes-apps
|
|
namespace: default
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack
|
|
app.kubernetes.io/name: kube-prometheus-stack #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
spec:
|
|
groups:
|
|
- name: kubernetes-apps
|
|
rules:
|
|
- alert: KubePodCrashLooping
|
|
annotations:
|
|
description: 'Pod {{ $labels.namespace }}/{{ $labels.pod }} ({{ $labels.container }}) is in waiting state (reason: "CrashLoopBackOff").'
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubepodcrashlooping
|
|
summary: Pod is crash looping.
|
|
expr: max_over_time(kube_pod_container_status_waiting_reason{reason="CrashLoopBackOff", job="kube-state-metrics", namespace=~".*"}[5m]) >= 1
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
- alert: KubePodNotReady
|
|
annotations:
|
|
description: Pod {{ $labels.namespace }}/{{ $labels.pod }} has been in a non-ready state for longer than 15 minutes.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubepodnotready
|
|
summary: Pod has been in a non-ready state for more than 15 minutes.
|
|
expr: |-
|
|
sum by (namespace, pod, cluster) (
|
|
max by (namespace, pod, cluster) (
|
|
kube_pod_status_phase{job="kube-state-metrics", namespace=~".*", phase=~"Pending|Unknown|Failed"}
|
|
) * on (namespace, pod, cluster) group_left(owner_kind) topk by (namespace, pod, cluster) (
|
|
1, max by (namespace, pod, owner_kind, cluster) (kube_pod_owner{owner_kind!="Job"})
|
|
)
|
|
) > 0
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
- alert: KubeDeploymentGenerationMismatch
|
|
annotations:
|
|
description: Deployment generation for {{ $labels.namespace }}/{{ $labels.deployment }} does not match, this indicates that the Deployment has failed but has not been rolled back.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubedeploymentgenerationmismatch
|
|
summary: Deployment generation mismatch due to possible roll-back
|
|
expr: |-
|
|
kube_deployment_status_observed_generation{job="kube-state-metrics", namespace=~".*"}
|
|
!=
|
|
kube_deployment_metadata_generation{job="kube-state-metrics", namespace=~".*"}
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
- alert: KubeDeploymentReplicasMismatch
|
|
annotations:
|
|
description: Deployment {{ $labels.namespace }}/{{ $labels.deployment }} has not matched the expected number of replicas for longer than 15 minutes.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubedeploymentreplicasmismatch
|
|
summary: Deployment has not matched the expected number of replicas.
|
|
expr: |-
|
|
(
|
|
kube_deployment_spec_replicas{job="kube-state-metrics", namespace=~".*"}
|
|
>
|
|
kube_deployment_status_replicas_available{job="kube-state-metrics", namespace=~".*"}
|
|
) and (
|
|
changes(kube_deployment_status_replicas_updated{job="kube-state-metrics", namespace=~".*"}[10m])
|
|
==
|
|
0
|
|
)
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
- alert: KubeDeploymentRolloutStuck
|
|
annotations:
|
|
description: Rollout of deployment {{ $labels.namespace }}/{{ $labels.deployment }} is not progressing for longer than 15 minutes.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubedeploymentrolloutstuck
|
|
summary: Deployment rollout is not progressing.
|
|
expr: |-
|
|
kube_deployment_status_condition{condition="Progressing", status="false",job="kube-state-metrics", namespace=~".*"}
|
|
!= 0
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
- alert: KubeStatefulSetReplicasMismatch
|
|
annotations:
|
|
description: StatefulSet {{ $labels.namespace }}/{{ $labels.statefulset }} has not matched the expected number of replicas for longer than 15 minutes.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubestatefulsetreplicasmismatch
|
|
summary: StatefulSet has not matched the expected number of replicas.
|
|
expr: |-
|
|
(
|
|
kube_statefulset_status_replicas_ready{job="kube-state-metrics", namespace=~".*"}
|
|
!=
|
|
kube_statefulset_status_replicas{job="kube-state-metrics", namespace=~".*"}
|
|
) and (
|
|
changes(kube_statefulset_status_replicas_updated{job="kube-state-metrics", namespace=~".*"}[10m])
|
|
==
|
|
0
|
|
)
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
- alert: KubeStatefulSetGenerationMismatch
|
|
annotations:
|
|
description: StatefulSet generation for {{ $labels.namespace }}/{{ $labels.statefulset }} does not match, this indicates that the StatefulSet has failed but has not been rolled back.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubestatefulsetgenerationmismatch
|
|
summary: StatefulSet generation mismatch due to possible roll-back
|
|
expr: |-
|
|
kube_statefulset_status_observed_generation{job="kube-state-metrics", namespace=~".*"}
|
|
!=
|
|
kube_statefulset_metadata_generation{job="kube-state-metrics", namespace=~".*"}
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
- alert: KubeStatefulSetUpdateNotRolledOut
|
|
annotations:
|
|
description: StatefulSet {{ $labels.namespace }}/{{ $labels.statefulset }} update has not been rolled out.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubestatefulsetupdatenotrolledout
|
|
summary: StatefulSet update has not been rolled out.
|
|
expr: |-
|
|
(
|
|
max by (namespace, statefulset, job, cluster) (
|
|
kube_statefulset_status_current_revision{job="kube-state-metrics", namespace=~".*"}
|
|
unless
|
|
kube_statefulset_status_update_revision{job="kube-state-metrics", namespace=~".*"}
|
|
)
|
|
*
|
|
(
|
|
kube_statefulset_replicas{job="kube-state-metrics", namespace=~".*"}
|
|
!=
|
|
kube_statefulset_status_replicas_updated{job="kube-state-metrics", namespace=~".*"}
|
|
)
|
|
) and (
|
|
changes(kube_statefulset_status_replicas_updated{job="kube-state-metrics", namespace=~".*"}[5m])
|
|
==
|
|
0
|
|
)
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
- alert: KubeDaemonSetRolloutStuck
|
|
annotations:
|
|
description: DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} has not finished or progressed for at least 15m.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubedaemonsetrolloutstuck
|
|
summary: DaemonSet rollout is stuck.
|
|
expr: |-
|
|
(
|
|
(
|
|
kube_daemonset_status_current_number_scheduled{job="kube-state-metrics", namespace=~".*"}
|
|
!=
|
|
kube_daemonset_status_desired_number_scheduled{job="kube-state-metrics", namespace=~".*"}
|
|
) or (
|
|
kube_daemonset_status_number_misscheduled{job="kube-state-metrics", namespace=~".*"}
|
|
!=
|
|
0
|
|
) or (
|
|
kube_daemonset_status_updated_number_scheduled{job="kube-state-metrics", namespace=~".*"}
|
|
!=
|
|
kube_daemonset_status_desired_number_scheduled{job="kube-state-metrics", namespace=~".*"}
|
|
) or (
|
|
kube_daemonset_status_number_available{job="kube-state-metrics", namespace=~".*"}
|
|
!=
|
|
kube_daemonset_status_desired_number_scheduled{job="kube-state-metrics", namespace=~".*"}
|
|
)
|
|
) and (
|
|
changes(kube_daemonset_status_updated_number_scheduled{job="kube-state-metrics", namespace=~".*"}[5m])
|
|
==
|
|
0
|
|
)
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
- alert: KubeContainerWaiting
|
|
annotations:
|
|
description: 'pod/{{ $labels.pod }} in namespace {{ $labels.namespace }} on container {{ $labels.container}} has been in waiting state for longer than 1 hour. (reason: "{{ $labels.reason }}").'
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubecontainerwaiting
|
|
summary: Pod container waiting longer than 1 hour
|
|
expr: kube_pod_container_status_waiting_reason{reason!="CrashLoopBackOff", job="kube-state-metrics", namespace=~".*"} > 0
|
|
for: 1h
|
|
labels:
|
|
severity: warning
|
|
- alert: KubeDaemonSetNotScheduled
|
|
annotations:
|
|
description: '{{ $value }} Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} are not scheduled.'
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubedaemonsetnotscheduled
|
|
summary: DaemonSet pods are not scheduled.
|
|
expr: |-
|
|
kube_daemonset_status_desired_number_scheduled{job="kube-state-metrics", namespace=~".*"}
|
|
-
|
|
kube_daemonset_status_current_number_scheduled{job="kube-state-metrics", namespace=~".*"} > 0
|
|
for: 10m
|
|
labels:
|
|
severity: warning
|
|
- alert: KubeDaemonSetMisScheduled
|
|
annotations:
|
|
description: '{{ $value }} Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} are running where they are not supposed to run.'
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubedaemonsetmisscheduled
|
|
summary: DaemonSet pods are misscheduled.
|
|
expr: kube_daemonset_status_number_misscheduled{job="kube-state-metrics", namespace=~".*"} > 0
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
- alert: KubeJobNotCompleted
|
|
annotations:
|
|
description: Job {{ $labels.namespace }}/{{ $labels.job_name }} is taking more than {{ "43200" | humanizeDuration }} to complete.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubejobnotcompleted
|
|
summary: Job did not complete in time
|
|
expr: |-
|
|
time() - max by (namespace, job_name, cluster) (kube_job_status_start_time{job="kube-state-metrics", namespace=~".*"}
|
|
and
|
|
kube_job_status_active{job="kube-state-metrics", namespace=~".*"} > 0) > 43200
|
|
labels:
|
|
severity: warning
|
|
- alert: KubeJobFailed
|
|
annotations:
|
|
description: Job {{ $labels.namespace }}/{{ $labels.job_name }} failed to complete. Removing failed job after investigation should clear this alert.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubejobfailed
|
|
summary: Job failed to complete.
|
|
expr: kube_job_failed{job="kube-state-metrics", namespace=~".*"} > 0
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
- alert: KubeHpaReplicasMismatch
|
|
annotations:
|
|
description: HPA {{ $labels.namespace }}/{{ $labels.horizontalpodautoscaler }} has not matched the desired number of replicas for longer than 15 minutes.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubehpareplicasmismatch
|
|
summary: HPA has not matched desired number of replicas.
|
|
expr: |-
|
|
(kube_horizontalpodautoscaler_status_desired_replicas{job="kube-state-metrics", namespace=~".*"}
|
|
!=
|
|
kube_horizontalpodautoscaler_status_current_replicas{job="kube-state-metrics", namespace=~".*"})
|
|
and
|
|
(kube_horizontalpodautoscaler_status_current_replicas{job="kube-state-metrics", namespace=~".*"}
|
|
>
|
|
kube_horizontalpodautoscaler_spec_min_replicas{job="kube-state-metrics", namespace=~".*"})
|
|
and
|
|
(kube_horizontalpodautoscaler_status_current_replicas{job="kube-state-metrics", namespace=~".*"}
|
|
<
|
|
kube_horizontalpodautoscaler_spec_max_replicas{job="kube-state-metrics", namespace=~".*"})
|
|
and
|
|
changes(kube_horizontalpodautoscaler_status_current_replicas{job="kube-state-metrics", namespace=~".*"}[15m]) == 0
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
- alert: KubeHpaMaxedOut
|
|
annotations:
|
|
description: HPA {{ $labels.namespace }}/{{ $labels.horizontalpodautoscaler }} has been running at max replicas for longer than 15 minutes.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubehpamaxedout
|
|
summary: HPA is running at max replicas
|
|
expr: |-
|
|
kube_horizontalpodautoscaler_status_current_replicas{job="kube-state-metrics", namespace=~".*"}
|
|
==
|
|
kube_horizontalpodautoscaler_spec_max_replicas{job="kube-state-metrics", namespace=~".*"}
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
---
|
|
# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-resources.yaml
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: PrometheusRule
|
|
metadata:
|
|
name: kube-prometheus-stack-kubernetes-resources
|
|
namespace: default
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack
|
|
app.kubernetes.io/name: kube-prometheus-stack #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
spec:
|
|
groups:
|
|
- name: kubernetes-resources
|
|
rules:
|
|
- alert: KubeCPUOvercommit
|
|
annotations:
|
|
description: Cluster {{ $labels.cluster }} has overcommitted CPU resource requests for Pods by {{ $value }} CPU shares and cannot tolerate node failure.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubecpuovercommit
|
|
summary: Cluster has overcommitted CPU resource requests.
|
|
expr: |-
|
|
sum(namespace_cpu:kube_pod_container_resource_requests:sum{}) by (cluster) - (sum(kube_node_status_allocatable{job="kube-state-metrics",resource="cpu"}) by (cluster) - max(kube_node_status_allocatable{job="kube-state-metrics",resource="cpu"}) by (cluster)) > 0
|
|
and
|
|
(sum(kube_node_status_allocatable{job="kube-state-metrics",resource="cpu"}) by (cluster) - max(kube_node_status_allocatable{job="kube-state-metrics",resource="cpu"}) by (cluster)) > 0
|
|
for: 10m
|
|
labels:
|
|
severity: warning
|
|
- alert: KubeMemoryOvercommit
|
|
annotations:
|
|
description: Cluster {{ $labels.cluster }} has overcommitted memory resource requests for Pods by {{ $value | humanize }} bytes and cannot tolerate node failure.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubememoryovercommit
|
|
summary: Cluster has overcommitted memory resource requests.
|
|
expr: |-
|
|
sum(namespace_memory:kube_pod_container_resource_requests:sum{}) by (cluster) - (sum(kube_node_status_allocatable{resource="memory", job="kube-state-metrics"}) by (cluster) - max(kube_node_status_allocatable{resource="memory", job="kube-state-metrics"}) by (cluster)) > 0
|
|
and
|
|
(sum(kube_node_status_allocatable{resource="memory", job="kube-state-metrics"}) by (cluster) - max(kube_node_status_allocatable{resource="memory", job="kube-state-metrics"}) by (cluster)) > 0
|
|
for: 10m
|
|
labels:
|
|
severity: warning
|
|
- alert: KubeCPUQuotaOvercommit
|
|
annotations:
|
|
description: Cluster {{ $labels.cluster }} has overcommitted CPU resource requests for Namespaces.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubecpuquotaovercommit
|
|
summary: Cluster has overcommitted CPU resource requests.
|
|
expr: |-
|
|
sum(min without(resource) (kube_resourcequota{job="kube-state-metrics", type="hard", resource=~"(cpu|requests.cpu)"})) by (cluster)
|
|
/
|
|
sum(kube_node_status_allocatable{resource="cpu", job="kube-state-metrics"}) by (cluster)
|
|
> 1.5
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
- alert: KubeMemoryQuotaOvercommit
|
|
annotations:
|
|
description: Cluster {{ $labels.cluster }} has overcommitted memory resource requests for Namespaces.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubememoryquotaovercommit
|
|
summary: Cluster has overcommitted memory resource requests.
|
|
expr: |-
|
|
sum(min without(resource) (kube_resourcequota{job="kube-state-metrics", type="hard", resource=~"(memory|requests.memory)"})) by (cluster)
|
|
/
|
|
sum(kube_node_status_allocatable{resource="memory", job="kube-state-metrics"}) by (cluster)
|
|
> 1.5
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
- alert: KubeQuotaAlmostFull
|
|
annotations:
|
|
description: Namespace {{ $labels.namespace }} is using {{ $value | humanizePercentage }} of its {{ $labels.resource }} quota.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubequotaalmostfull
|
|
summary: Namespace quota is going to be full.
|
|
expr: |-
|
|
kube_resourcequota{job="kube-state-metrics", type="used"}
|
|
/ ignoring(instance, job, type)
|
|
(kube_resourcequota{job="kube-state-metrics", type="hard"} > 0)
|
|
> 0.9 < 1
|
|
for: 15m
|
|
labels:
|
|
severity: info
|
|
- alert: KubeQuotaFullyUsed
|
|
annotations:
|
|
description: Namespace {{ $labels.namespace }} is using {{ $value | humanizePercentage }} of its {{ $labels.resource }} quota.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubequotafullyused
|
|
summary: Namespace quota is fully used.
|
|
expr: |-
|
|
kube_resourcequota{job="kube-state-metrics", type="used"}
|
|
/ ignoring(instance, job, type)
|
|
(kube_resourcequota{job="kube-state-metrics", type="hard"} > 0)
|
|
== 1
|
|
for: 15m
|
|
labels:
|
|
severity: info
|
|
- alert: KubeQuotaExceeded
|
|
annotations:
|
|
description: Namespace {{ $labels.namespace }} is using {{ $value | humanizePercentage }} of its {{ $labels.resource }} quota.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubequotaexceeded
|
|
summary: Namespace quota has exceeded the limits.
|
|
expr: |-
|
|
kube_resourcequota{job="kube-state-metrics", type="used"}
|
|
/ ignoring(instance, job, type)
|
|
(kube_resourcequota{job="kube-state-metrics", type="hard"} > 0)
|
|
> 1
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
- alert: CPUThrottlingHigh
|
|
annotations:
|
|
description: '{{ $value | humanizePercentage }} throttling of CPU in namespace {{ $labels.namespace }} for container {{ $labels.container }} in pod {{ $labels.pod }}.'
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/cputhrottlinghigh
|
|
summary: Processes experience elevated CPU throttling.
|
|
expr: |-
|
|
sum(increase(container_cpu_cfs_throttled_periods_total{container!="", job="kubelet", metrics_path="/metrics/cadvisor", }[5m])) without (id, metrics_path, name, image, endpoint, job, node)
|
|
/
|
|
sum(increase(container_cpu_cfs_periods_total{job="kubelet", metrics_path="/metrics/cadvisor", }[5m])) without (id, metrics_path, name, image, endpoint, job, node)
|
|
> ( 25 / 100 )
|
|
for: 15m
|
|
labels:
|
|
severity: info
|
|
---
|
|
# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-storage.yaml
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: PrometheusRule
|
|
metadata:
|
|
name: kube-prometheus-stack-kubernetes-storage
|
|
namespace: default
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack
|
|
app.kubernetes.io/name: kube-prometheus-stack #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
spec:
|
|
groups:
|
|
- name: kubernetes-storage
|
|
rules:
|
|
- alert: KubePersistentVolumeFillingUp
|
|
annotations:
|
|
description: The PersistentVolume claimed by {{ $labels.persistentvolumeclaim }} in Namespace {{ $labels.namespace }} {{ with $labels.cluster -}} on Cluster {{ . }} {{- end }} is only {{ $value | humanizePercentage }} free.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubepersistentvolumefillingup
|
|
summary: PersistentVolume is filling up.
|
|
expr: |-
|
|
(
|
|
kubelet_volume_stats_available_bytes{job="kubelet", namespace=~".*", metrics_path="/metrics"}
|
|
/
|
|
kubelet_volume_stats_capacity_bytes{job="kubelet", namespace=~".*", metrics_path="/metrics"}
|
|
) < 0.03
|
|
and
|
|
kubelet_volume_stats_used_bytes{job="kubelet", namespace=~".*", metrics_path="/metrics"} > 0
|
|
unless on (cluster, namespace, persistentvolumeclaim)
|
|
kube_persistentvolumeclaim_access_mode{ access_mode="ReadOnlyMany"} == 1
|
|
unless on (cluster, namespace, persistentvolumeclaim)
|
|
kube_persistentvolumeclaim_labels{label_excluded_from_alerts="true"} == 1
|
|
for: 1m
|
|
labels:
|
|
severity: critical
|
|
- alert: KubePersistentVolumeFillingUp
|
|
annotations:
|
|
description: Based on recent sampling, the PersistentVolume claimed by {{ $labels.persistentvolumeclaim }} in Namespace {{ $labels.namespace }} {{ with $labels.cluster -}} on Cluster {{ . }} {{- end }} is expected to fill up within four days. Currently {{ $value | humanizePercentage }} is available.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubepersistentvolumefillingup
|
|
summary: PersistentVolume is filling up.
|
|
expr: |-
|
|
(
|
|
kubelet_volume_stats_available_bytes{job="kubelet", namespace=~".*", metrics_path="/metrics"}
|
|
/
|
|
kubelet_volume_stats_capacity_bytes{job="kubelet", namespace=~".*", metrics_path="/metrics"}
|
|
) < 0.15
|
|
and
|
|
kubelet_volume_stats_used_bytes{job="kubelet", namespace=~".*", metrics_path="/metrics"} > 0
|
|
and
|
|
predict_linear(kubelet_volume_stats_available_bytes{job="kubelet", namespace=~".*", metrics_path="/metrics"}[6h], 4 * 24 * 3600) < 0
|
|
unless on (cluster, namespace, persistentvolumeclaim)
|
|
kube_persistentvolumeclaim_access_mode{ access_mode="ReadOnlyMany"} == 1
|
|
unless on (cluster, namespace, persistentvolumeclaim)
|
|
kube_persistentvolumeclaim_labels{label_excluded_from_alerts="true"} == 1
|
|
for: 1h
|
|
labels:
|
|
severity: warning
|
|
- alert: KubePersistentVolumeInodesFillingUp
|
|
annotations:
|
|
description: The PersistentVolume claimed by {{ $labels.persistentvolumeclaim }} in Namespace {{ $labels.namespace }} {{ with $labels.cluster -}} on Cluster {{ . }} {{- end }} only has {{ $value | humanizePercentage }} free inodes.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubepersistentvolumeinodesfillingup
|
|
summary: PersistentVolumeInodes are filling up.
|
|
expr: |-
|
|
(
|
|
kubelet_volume_stats_inodes_free{job="kubelet", namespace=~".*", metrics_path="/metrics"}
|
|
/
|
|
kubelet_volume_stats_inodes{job="kubelet", namespace=~".*", metrics_path="/metrics"}
|
|
) < 0.03
|
|
and
|
|
kubelet_volume_stats_inodes_used{job="kubelet", namespace=~".*", metrics_path="/metrics"} > 0
|
|
unless on (cluster, namespace, persistentvolumeclaim)
|
|
kube_persistentvolumeclaim_access_mode{ access_mode="ReadOnlyMany"} == 1
|
|
unless on (cluster, namespace, persistentvolumeclaim)
|
|
kube_persistentvolumeclaim_labels{label_excluded_from_alerts="true"} == 1
|
|
for: 1m
|
|
labels:
|
|
severity: critical
|
|
- alert: KubePersistentVolumeInodesFillingUp
|
|
annotations:
|
|
description: Based on recent sampling, the PersistentVolume claimed by {{ $labels.persistentvolumeclaim }} in Namespace {{ $labels.namespace }} {{ with $labels.cluster -}} on Cluster {{ . }} {{- end }} is expected to run out of inodes within four days. Currently {{ $value | humanizePercentage }} of its inodes are free.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubepersistentvolumeinodesfillingup
|
|
summary: PersistentVolumeInodes are filling up.
|
|
expr: |-
|
|
(
|
|
kubelet_volume_stats_inodes_free{job="kubelet", namespace=~".*", metrics_path="/metrics"}
|
|
/
|
|
kubelet_volume_stats_inodes{job="kubelet", namespace=~".*", metrics_path="/metrics"}
|
|
) < 0.15
|
|
and
|
|
kubelet_volume_stats_inodes_used{job="kubelet", namespace=~".*", metrics_path="/metrics"} > 0
|
|
and
|
|
predict_linear(kubelet_volume_stats_inodes_free{job="kubelet", namespace=~".*", metrics_path="/metrics"}[6h], 4 * 24 * 3600) < 0
|
|
unless on (cluster, namespace, persistentvolumeclaim)
|
|
kube_persistentvolumeclaim_access_mode{ access_mode="ReadOnlyMany"} == 1
|
|
unless on (cluster, namespace, persistentvolumeclaim)
|
|
kube_persistentvolumeclaim_labels{label_excluded_from_alerts="true"} == 1
|
|
for: 1h
|
|
labels:
|
|
severity: warning
|
|
- alert: KubePersistentVolumeErrors
|
|
annotations:
|
|
description: The persistent volume {{ $labels.persistentvolume }} {{ with $labels.cluster -}} on Cluster {{ . }} {{- end }} has status {{ $labels.phase }}.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubepersistentvolumeerrors
|
|
summary: PersistentVolume is having issues with provisioning.
|
|
expr: kube_persistentvolume_status_phase{phase=~"Failed|Pending",job="kube-state-metrics"} > 0
|
|
for: 5m
|
|
labels:
|
|
severity: critical
|
|
---
|
|
# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-system-apiserver.yaml
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: PrometheusRule
|
|
metadata:
|
|
name: kube-prometheus-stack-kubernetes-system-apiserver
|
|
namespace: default
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack
|
|
app.kubernetes.io/name: kube-prometheus-stack #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
spec:
|
|
groups:
|
|
- name: kubernetes-system-apiserver
|
|
rules:
|
|
- alert: KubeClientCertificateExpiration
|
|
annotations:
|
|
description: A client certificate used to authenticate to kubernetes apiserver is expiring in less than 7.0 days on cluster {{ $labels.cluster }}.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeclientcertificateexpiration
|
|
summary: Client certificate is about to expire.
|
|
expr: |-
|
|
histogram_quantile(0.01, sum without (namespace, service, endpoint) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="apiserver"}[5m]))) < 604800
|
|
and
|
|
on (job, cluster, instance) apiserver_client_certificate_expiration_seconds_count{job="apiserver"} > 0
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
- alert: KubeClientCertificateExpiration
|
|
annotations:
|
|
description: A client certificate used to authenticate to kubernetes apiserver is expiring in less than 24.0 hours on cluster {{ $labels.cluster }}.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeclientcertificateexpiration
|
|
summary: Client certificate is about to expire.
|
|
expr: |-
|
|
histogram_quantile(0.01, sum without (namespace, service, endpoint) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="apiserver"}[5m]))) < 86400
|
|
and
|
|
on (job, cluster, instance) apiserver_client_certificate_expiration_seconds_count{job="apiserver"} > 0
|
|
for: 5m
|
|
labels:
|
|
severity: critical
|
|
- alert: KubeAggregatedAPIErrors
|
|
annotations:
|
|
description: Kubernetes aggregated API {{ $labels.instance }}/{{ $labels.name }} has reported {{ $labels.reason }} errors on cluster {{ $labels.cluster }}.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeaggregatedapierrors
|
|
summary: Kubernetes aggregated API has reported errors.
|
|
expr: sum by (cluster, instance, name, reason)(increase(aggregator_unavailable_apiservice_total{job="apiserver"}[1m])) > 0
|
|
for: 10m
|
|
labels:
|
|
severity: warning
|
|
- alert: KubeAggregatedAPIDown
|
|
annotations:
|
|
description: Kubernetes aggregated API {{ $labels.name }}/{{ $labels.namespace }} has been only {{ $value | humanize }}% available over the last 10m.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeaggregatedapidown
|
|
summary: Kubernetes aggregated API is down.
|
|
expr: (1 - max by (name, namespace, cluster)(avg_over_time(aggregator_unavailable_apiservice{job="apiserver"}[10m]))) * 100 < 85
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
- alert: KubeAPIDown
|
|
annotations:
|
|
description: KubeAPI has disappeared from Prometheus target discovery.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeapidown
|
|
summary: Target disappeared from Prometheus target discovery.
|
|
expr: absent(up{job="apiserver"} == 1)
|
|
for: 15m
|
|
labels:
|
|
severity: critical
|
|
- alert: KubeAPITerminatedRequests
|
|
annotations:
|
|
description: The kubernetes apiserver has terminated {{ $value | humanizePercentage }} of its incoming requests.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeapiterminatedrequests
|
|
summary: The kubernetes apiserver has terminated {{ $value | humanizePercentage }} of its incoming requests.
|
|
expr: sum by (cluster) (rate(apiserver_request_terminations_total{job="apiserver"}[10m])) / ( sum by (cluster) (rate(apiserver_request_total{job="apiserver"}[10m])) + sum by (cluster) (rate(apiserver_request_terminations_total{job="apiserver"}[10m])) ) > 0.20
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
---
|
|
# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-system-controller-manager.yaml
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: PrometheusRule
|
|
metadata:
|
|
name: kube-prometheus-stack-kubernetes-system-controller-manager
|
|
namespace: default
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack
|
|
app.kubernetes.io/name: kube-prometheus-stack #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
spec:
|
|
groups:
|
|
- name: kubernetes-system-controller-manager
|
|
rules:
|
|
- alert: KubeControllerManagerDown
|
|
annotations:
|
|
description: KubeControllerManager has disappeared from Prometheus target discovery.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubecontrollermanagerdown
|
|
summary: Target disappeared from Prometheus target discovery.
|
|
expr: absent(up{job="kube-controller-manager"} == 1)
|
|
for: 15m
|
|
labels:
|
|
severity: critical
|
|
---
|
|
# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-system-kube-proxy.yaml
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: PrometheusRule
|
|
metadata:
|
|
name: kube-prometheus-stack-kubernetes-system-kube-proxy
|
|
namespace: default
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack
|
|
app.kubernetes.io/name: kube-prometheus-stack #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
spec:
|
|
groups:
|
|
- name: kubernetes-system-kube-proxy
|
|
rules:
|
|
- alert: KubeProxyDown
|
|
annotations:
|
|
description: KubeProxy has disappeared from Prometheus target discovery.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeproxydown
|
|
summary: Target disappeared from Prometheus target discovery.
|
|
expr: absent(up{job="kube-proxy"} == 1)
|
|
for: 15m
|
|
labels:
|
|
severity: critical
|
|
---
|
|
# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-system-kubelet.yaml
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: PrometheusRule
|
|
metadata:
|
|
name: kube-prometheus-stack-kubernetes-system-kubelet
|
|
namespace: default
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack
|
|
app.kubernetes.io/name: kube-prometheus-stack #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
spec:
|
|
groups:
|
|
- name: kubernetes-system-kubelet
|
|
rules:
|
|
- alert: KubeNodeNotReady
|
|
annotations:
|
|
description: '{{ $labels.node }} has been unready for more than 15 minutes.'
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubenodenotready
|
|
summary: Node is not ready.
|
|
expr: kube_node_status_condition{job="kube-state-metrics",condition="Ready",status="true"} == 0
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
- alert: KubeNodeUnreachable
|
|
annotations:
|
|
description: '{{ $labels.node }} is unreachable and some workloads may be rescheduled.'
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubenodeunreachable
|
|
summary: Node is unreachable.
|
|
expr: (kube_node_spec_taint{job="kube-state-metrics",key="node.kubernetes.io/unreachable",effect="NoSchedule"} unless ignoring(key,value) kube_node_spec_taint{job="kube-state-metrics",key=~"ToBeDeletedByClusterAutoscaler|cloud.google.com/impending-node-termination|aws-node-termination-handler/spot-itn"}) == 1
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
- alert: KubeletTooManyPods
|
|
annotations:
|
|
description: Kubelet '{{ $labels.node }}' is running at {{ $value | humanizePercentage }} of its Pod capacity.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubelettoomanypods
|
|
summary: Kubelet is running at capacity.
|
|
expr: |-
|
|
count by (cluster, node) (
|
|
(kube_pod_status_phase{job="kube-state-metrics",phase="Running"} == 1) * on (instance,pod,namespace,cluster) group_left(node) topk by (instance,pod,namespace,cluster) (1, kube_pod_info{job="kube-state-metrics"})
|
|
)
|
|
/
|
|
max by (cluster, node) (
|
|
kube_node_status_capacity{job="kube-state-metrics",resource="pods"} != 1
|
|
) > 0.95
|
|
for: 15m
|
|
labels:
|
|
severity: info
|
|
- alert: KubeNodeReadinessFlapping
|
|
annotations:
|
|
description: The readiness status of node {{ $labels.node }} has changed {{ $value }} times in the last 15 minutes.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubenodereadinessflapping
|
|
summary: Node readiness status is flapping.
|
|
expr: sum(changes(kube_node_status_condition{job="kube-state-metrics",status="true",condition="Ready"}[15m])) by (cluster, node) > 2
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
- alert: KubeletPlegDurationHigh
|
|
annotations:
|
|
description: The Kubelet Pod Lifecycle Event Generator has a 99th percentile duration of {{ $value }} seconds on node {{ $labels.node }}.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletplegdurationhigh
|
|
summary: Kubelet Pod Lifecycle Event Generator is taking too long to relist.
|
|
expr: node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile{quantile="0.99"} >= 10
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
- alert: KubeletPodStartUpLatencyHigh
|
|
annotations:
|
|
description: Kubelet Pod startup 99th percentile latency is {{ $value }} seconds on node {{ $labels.node }}.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletpodstartuplatencyhigh
|
|
summary: Kubelet Pod startup latency is too high.
|
|
expr: histogram_quantile(0.99, sum(rate(kubelet_pod_worker_duration_seconds_bucket{job="kubelet", metrics_path="/metrics"}[5m])) by (cluster, instance, le)) * on (cluster, instance) group_left(node) kubelet_node_name{job="kubelet", metrics_path="/metrics"} > 60
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
- alert: KubeletClientCertificateExpiration
|
|
annotations:
|
|
description: Client certificate for Kubelet on node {{ $labels.node }} expires in {{ $value | humanizeDuration }}.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletclientcertificateexpiration
|
|
summary: Kubelet client certificate is about to expire.
|
|
expr: kubelet_certificate_manager_client_ttl_seconds < 604800
|
|
labels:
|
|
severity: warning
|
|
- alert: KubeletClientCertificateExpiration
|
|
annotations:
|
|
description: Client certificate for Kubelet on node {{ $labels.node }} expires in {{ $value | humanizeDuration }}.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletclientcertificateexpiration
|
|
summary: Kubelet client certificate is about to expire.
|
|
expr: kubelet_certificate_manager_client_ttl_seconds < 86400
|
|
labels:
|
|
severity: critical
|
|
- alert: KubeletServerCertificateExpiration
|
|
annotations:
|
|
description: Server certificate for Kubelet on node {{ $labels.node }} expires in {{ $value | humanizeDuration }}.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletservercertificateexpiration
|
|
summary: Kubelet server certificate is about to expire.
|
|
expr: kubelet_certificate_manager_server_ttl_seconds < 604800
|
|
labels:
|
|
severity: warning
|
|
- alert: KubeletServerCertificateExpiration
|
|
annotations:
|
|
description: Server certificate for Kubelet on node {{ $labels.node }} expires in {{ $value | humanizeDuration }}.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletservercertificateexpiration
|
|
summary: Kubelet server certificate is about to expire.
|
|
expr: kubelet_certificate_manager_server_ttl_seconds < 86400
|
|
labels:
|
|
severity: critical
|
|
- alert: KubeletClientCertificateRenewalErrors
|
|
annotations:
|
|
description: Kubelet on node {{ $labels.node }} has failed to renew its client certificate ({{ $value | humanize }} errors in the last 5 minutes).
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletclientcertificaterenewalerrors
|
|
summary: Kubelet has failed to renew its client certificate.
|
|
expr: increase(kubelet_certificate_manager_client_expiration_renew_errors[5m]) > 0
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
- alert: KubeletServerCertificateRenewalErrors
|
|
annotations:
|
|
description: Kubelet on node {{ $labels.node }} has failed to renew its server certificate ({{ $value | humanize }} errors in the last 5 minutes).
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletservercertificaterenewalerrors
|
|
summary: Kubelet has failed to renew its server certificate.
|
|
expr: increase(kubelet_server_expiration_renew_errors[5m]) > 0
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
- alert: KubeletDown
|
|
annotations:
|
|
description: Kubelet has disappeared from Prometheus target discovery.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletdown
|
|
summary: Target disappeared from Prometheus target discovery.
|
|
expr: absent(up{job="kubelet", metrics_path="/metrics"} == 1)
|
|
for: 15m
|
|
labels:
|
|
severity: critical
|
|
---
|
|
# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-system-scheduler.yaml
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: PrometheusRule
|
|
metadata:
|
|
name: kube-prometheus-stack-kubernetes-system-scheduler
|
|
namespace: default
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack
|
|
app.kubernetes.io/name: kube-prometheus-stack #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
spec:
|
|
groups:
|
|
- name: kubernetes-system-scheduler
|
|
rules:
|
|
- alert: KubeSchedulerDown
|
|
annotations:
|
|
description: KubeScheduler has disappeared from Prometheus target discovery.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeschedulerdown
|
|
summary: Target disappeared from Prometheus target discovery.
|
|
expr: absent(up{job="kube-scheduler"} == 1)
|
|
for: 15m
|
|
labels:
|
|
severity: critical
|
|
---
|
|
# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-system.yaml
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: PrometheusRule
|
|
metadata:
|
|
name: kube-prometheus-stack-kubernetes-system
|
|
namespace: default
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack
|
|
app.kubernetes.io/name: kube-prometheus-stack #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
spec:
|
|
groups:
|
|
- name: kubernetes-system
|
|
rules:
|
|
- alert: KubeVersionMismatch
|
|
annotations:
|
|
description: There are {{ $value }} different semantic versions of Kubernetes components running.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeversionmismatch
|
|
summary: Different semantic versions of Kubernetes components running.
|
|
expr: count by (cluster) (count by (git_version, cluster) (label_replace(kubernetes_build_info{job!~"kube-dns|coredns"},"git_version","$1","git_version","(v[0-9]*.[0-9]*).*"))) > 1
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
- alert: KubeClientErrors
|
|
annotations:
|
|
description: Kubernetes API server client '{{ $labels.job }}/{{ $labels.instance }}' is experiencing {{ $value | humanizePercentage }} errors.'
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeclienterrors
|
|
summary: Kubernetes API server client is experiencing errors.
|
|
expr: |-
|
|
(sum(rate(rest_client_requests_total{job="apiserver",code=~"5.."}[5m])) by (cluster, instance, job, namespace)
|
|
/
|
|
sum(rate(rest_client_requests_total{job="apiserver"}[5m])) by (cluster, instance, job, namespace))
|
|
> 0.01
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
---
|
|
# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/node-exporter.rules.yaml
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: PrometheusRule
|
|
metadata:
|
|
name: kube-prometheus-stack-node-exporter.rules
|
|
namespace: default
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack
|
|
app.kubernetes.io/name: kube-prometheus-stack #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
spec:
|
|
groups:
|
|
- name: node-exporter.rules
|
|
rules:
|
|
- expr: |-
|
|
count without (cpu, mode) (
|
|
node_cpu_seconds_total{job="node-exporter",mode="idle"}
|
|
)
|
|
record: instance:node_num_cpu:sum
|
|
- expr: |-
|
|
1 - avg without (cpu) (
|
|
sum without (mode) (rate(node_cpu_seconds_total{job="node-exporter", mode=~"idle|iowait|steal"}[5m]))
|
|
)
|
|
record: instance:node_cpu_utilisation:rate5m
|
|
- expr: |-
|
|
(
|
|
node_load1{job="node-exporter"}
|
|
/
|
|
instance:node_num_cpu:sum{job="node-exporter"}
|
|
)
|
|
record: instance:node_load1_per_cpu:ratio
|
|
- expr: |-
|
|
1 - (
|
|
(
|
|
node_memory_MemAvailable_bytes{job="node-exporter"}
|
|
or
|
|
(
|
|
node_memory_Buffers_bytes{job="node-exporter"}
|
|
+
|
|
node_memory_Cached_bytes{job="node-exporter"}
|
|
+
|
|
node_memory_MemFree_bytes{job="node-exporter"}
|
|
+
|
|
node_memory_Slab_bytes{job="node-exporter"}
|
|
)
|
|
)
|
|
/
|
|
node_memory_MemTotal_bytes{job="node-exporter"}
|
|
)
|
|
record: instance:node_memory_utilisation:ratio
|
|
- expr: rate(node_vmstat_pgmajfault{job="node-exporter"}[5m])
|
|
record: instance:node_vmstat_pgmajfault:rate5m
|
|
- expr: rate(node_disk_io_time_seconds_total{job="node-exporter", device=~"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)"}[5m])
|
|
record: instance_device:node_disk_io_time_seconds:rate5m
|
|
- expr: rate(node_disk_io_time_weighted_seconds_total{job="node-exporter", device=~"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)"}[5m])
|
|
record: instance_device:node_disk_io_time_weighted_seconds:rate5m
|
|
- expr: |-
|
|
sum without (device) (
|
|
rate(node_network_receive_bytes_total{job="node-exporter", device!="lo"}[5m])
|
|
)
|
|
record: instance:node_network_receive_bytes_excluding_lo:rate5m
|
|
- expr: |-
|
|
sum without (device) (
|
|
rate(node_network_transmit_bytes_total{job="node-exporter", device!="lo"}[5m])
|
|
)
|
|
record: instance:node_network_transmit_bytes_excluding_lo:rate5m
|
|
- expr: |-
|
|
sum without (device) (
|
|
rate(node_network_receive_drop_total{job="node-exporter", device!="lo"}[5m])
|
|
)
|
|
record: instance:node_network_receive_drop_excluding_lo:rate5m
|
|
- expr: |-
|
|
sum without (device) (
|
|
rate(node_network_transmit_drop_total{job="node-exporter", device!="lo"}[5m])
|
|
)
|
|
record: instance:node_network_transmit_drop_excluding_lo:rate5m
|
|
---
|
|
# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/node-exporter.yaml
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: PrometheusRule
|
|
metadata:
|
|
name: kube-prometheus-stack-node-exporter
|
|
namespace: default
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack
|
|
app.kubernetes.io/name: kube-prometheus-stack #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
spec:
|
|
groups:
|
|
- name: node-exporter
|
|
rules:
|
|
- alert: NodeFilesystemSpaceFillingUp
|
|
annotations:
|
|
description: Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint }}, at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available space left and is filling up.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefilesystemspacefillingup
|
|
summary: Filesystem is predicted to run out of space within the next 24 hours.
|
|
expr: |-
|
|
(
|
|
node_filesystem_avail_bytes{job="node-exporter",fstype!="",mountpoint!=""} / node_filesystem_size_bytes{job="node-exporter",fstype!="",mountpoint!=""} * 100 < 15
|
|
and
|
|
predict_linear(node_filesystem_avail_bytes{job="node-exporter",fstype!="",mountpoint!=""}[6h], 24*60*60) < 0
|
|
and
|
|
node_filesystem_readonly{job="node-exporter",fstype!="",mountpoint!=""} == 0
|
|
)
|
|
for: 1h
|
|
labels:
|
|
severity: warning
|
|
- alert: NodeFilesystemSpaceFillingUp
|
|
annotations:
|
|
description: Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint }}, at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available space left and is filling up fast.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefilesystemspacefillingup
|
|
summary: Filesystem is predicted to run out of space within the next 4 hours.
|
|
expr: |-
|
|
(
|
|
node_filesystem_avail_bytes{job="node-exporter",fstype!="",mountpoint!=""} / node_filesystem_size_bytes{job="node-exporter",fstype!="",mountpoint!=""} * 100 < 10
|
|
and
|
|
predict_linear(node_filesystem_avail_bytes{job="node-exporter",fstype!="",mountpoint!=""}[6h], 4*60*60) < 0
|
|
and
|
|
node_filesystem_readonly{job="node-exporter",fstype!="",mountpoint!=""} == 0
|
|
)
|
|
for: 1h
|
|
labels:
|
|
severity: critical
|
|
- alert: NodeFilesystemAlmostOutOfSpace
|
|
annotations:
|
|
description: Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint }}, at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available space left.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefilesystemalmostoutofspace
|
|
summary: Filesystem has less than 5% space left.
|
|
expr: |-
|
|
(
|
|
node_filesystem_avail_bytes{job="node-exporter",fstype!="",mountpoint!=""} / node_filesystem_size_bytes{job="node-exporter",fstype!="",mountpoint!=""} * 100 < 5
|
|
and
|
|
node_filesystem_readonly{job="node-exporter",fstype!="",mountpoint!=""} == 0
|
|
)
|
|
for: 30m
|
|
labels:
|
|
severity: warning
|
|
- alert: NodeFilesystemAlmostOutOfSpace
|
|
annotations:
|
|
description: Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint }}, at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available space left.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefilesystemalmostoutofspace
|
|
summary: Filesystem has less than 3% space left.
|
|
expr: |-
|
|
(
|
|
node_filesystem_avail_bytes{job="node-exporter",fstype!="",mountpoint!=""} / node_filesystem_size_bytes{job="node-exporter",fstype!="",mountpoint!=""} * 100 < 3
|
|
and
|
|
node_filesystem_readonly{job="node-exporter",fstype!="",mountpoint!=""} == 0
|
|
)
|
|
for: 30m
|
|
labels:
|
|
severity: critical
|
|
- alert: NodeFilesystemFilesFillingUp
|
|
annotations:
|
|
description: Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint }}, at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available inodes left and is filling up.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefilesystemfilesfillingup
|
|
summary: Filesystem is predicted to run out of inodes within the next 24 hours.
|
|
expr: |-
|
|
(
|
|
node_filesystem_files_free{job="node-exporter",fstype!="",mountpoint!=""} / node_filesystem_files{job="node-exporter",fstype!="",mountpoint!=""} * 100 < 40
|
|
and
|
|
predict_linear(node_filesystem_files_free{job="node-exporter",fstype!="",mountpoint!=""}[6h], 24*60*60) < 0
|
|
and
|
|
node_filesystem_readonly{job="node-exporter",fstype!="",mountpoint!=""} == 0
|
|
)
|
|
for: 1h
|
|
labels:
|
|
severity: warning
|
|
- alert: NodeFilesystemFilesFillingUp
|
|
annotations:
|
|
description: Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint }}, at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available inodes left and is filling up fast.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefilesystemfilesfillingup
|
|
summary: Filesystem is predicted to run out of inodes within the next 4 hours.
|
|
expr: |-
|
|
(
|
|
node_filesystem_files_free{job="node-exporter",fstype!="",mountpoint!=""} / node_filesystem_files{job="node-exporter",fstype!="",mountpoint!=""} * 100 < 20
|
|
and
|
|
predict_linear(node_filesystem_files_free{job="node-exporter",fstype!="",mountpoint!=""}[6h], 4*60*60) < 0
|
|
and
|
|
node_filesystem_readonly{job="node-exporter",fstype!="",mountpoint!=""} == 0
|
|
)
|
|
for: 1h
|
|
labels:
|
|
severity: critical
|
|
- alert: NodeFilesystemAlmostOutOfFiles
|
|
annotations:
|
|
description: Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint }}, at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available inodes left.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefilesystemalmostoutoffiles
|
|
summary: Filesystem has less than 5% inodes left.
|
|
expr: |-
|
|
(
|
|
node_filesystem_files_free{job="node-exporter",fstype!="",mountpoint!=""} / node_filesystem_files{job="node-exporter",fstype!="",mountpoint!=""} * 100 < 5
|
|
and
|
|
node_filesystem_readonly{job="node-exporter",fstype!="",mountpoint!=""} == 0
|
|
)
|
|
for: 1h
|
|
labels:
|
|
severity: warning
|
|
- alert: NodeFilesystemAlmostOutOfFiles
|
|
annotations:
|
|
description: Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint }}, at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available inodes left.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefilesystemalmostoutoffiles
|
|
summary: Filesystem has less than 3% inodes left.
|
|
expr: |-
|
|
(
|
|
node_filesystem_files_free{job="node-exporter",fstype!="",mountpoint!=""} / node_filesystem_files{job="node-exporter",fstype!="",mountpoint!=""} * 100 < 3
|
|
and
|
|
node_filesystem_readonly{job="node-exporter",fstype!="",mountpoint!=""} == 0
|
|
)
|
|
for: 1h
|
|
labels:
|
|
severity: critical
|
|
- alert: NodeNetworkReceiveErrs
|
|
annotations:
|
|
description: '{{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf "%.0f" $value }} receive errors in the last two minutes.'
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodenetworkreceiveerrs
|
|
summary: Network interface is reporting many receive errors.
|
|
expr: rate(node_network_receive_errs_total{job="node-exporter"}[2m]) / rate(node_network_receive_packets_total{job="node-exporter"}[2m]) > 0.01
|
|
for: 1h
|
|
labels:
|
|
severity: warning
|
|
- alert: NodeNetworkTransmitErrs
|
|
annotations:
|
|
description: '{{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf "%.0f" $value }} transmit errors in the last two minutes.'
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodenetworktransmiterrs
|
|
summary: Network interface is reporting many transmit errors.
|
|
expr: rate(node_network_transmit_errs_total{job="node-exporter"}[2m]) / rate(node_network_transmit_packets_total{job="node-exporter"}[2m]) > 0.01
|
|
for: 1h
|
|
labels:
|
|
severity: warning
|
|
- alert: NodeHighNumberConntrackEntriesUsed
|
|
annotations:
|
|
description: '{{ $labels.instance }} {{ $value | humanizePercentage }} of conntrack entries are used.'
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodehighnumberconntrackentriesused
|
|
summary: Number of conntrack are getting close to the limit.
|
|
expr: (node_nf_conntrack_entries{job="node-exporter"} / node_nf_conntrack_entries_limit) > 0.75
|
|
labels:
|
|
severity: warning
|
|
- alert: NodeTextFileCollectorScrapeError
|
|
annotations:
|
|
description: Node Exporter text file collector on {{ $labels.instance }} failed to scrape.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodetextfilecollectorscrapeerror
|
|
summary: Node Exporter text file collector failed to scrape.
|
|
expr: node_textfile_scrape_error{job="node-exporter"} == 1
|
|
labels:
|
|
severity: warning
|
|
- alert: NodeClockSkewDetected
|
|
annotations:
|
|
description: Clock at {{ $labels.instance }} is out of sync by more than 0.05s. Ensure NTP is configured correctly on this host.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodeclockskewdetected
|
|
summary: Clock skew detected.
|
|
expr: |-
|
|
(
|
|
node_timex_offset_seconds{job="node-exporter"} > 0.05
|
|
and
|
|
deriv(node_timex_offset_seconds{job="node-exporter"}[5m]) >= 0
|
|
)
|
|
or
|
|
(
|
|
node_timex_offset_seconds{job="node-exporter"} < -0.05
|
|
and
|
|
deriv(node_timex_offset_seconds{job="node-exporter"}[5m]) <= 0
|
|
)
|
|
for: 10m
|
|
labels:
|
|
severity: warning
|
|
- alert: NodeClockNotSynchronising
|
|
annotations:
|
|
description: Clock at {{ $labels.instance }} is not synchronising. Ensure NTP is configured on this host.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodeclocknotsynchronising
|
|
summary: Clock not synchronising.
|
|
expr: |-
|
|
min_over_time(node_timex_sync_status{job="node-exporter"}[5m]) == 0
|
|
and
|
|
node_timex_maxerror_seconds{job="node-exporter"} >= 16
|
|
for: 10m
|
|
labels:
|
|
severity: warning
|
|
- alert: NodeRAIDDegraded
|
|
annotations:
|
|
description: RAID array '{{ $labels.device }}' at {{ $labels.instance }} is in degraded state due to one or more disks failures. Number of spare drives is insufficient to fix issue automatically.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/noderaiddegraded
|
|
summary: RAID Array is degraded.
|
|
expr: node_md_disks_required{job="node-exporter",device=~"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)"} - ignoring (state) (node_md_disks{state="active",job="node-exporter",device=~"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)"}) > 0
|
|
for: 15m
|
|
labels:
|
|
severity: critical
|
|
- alert: NodeRAIDDiskFailure
|
|
annotations:
|
|
description: At least one device in RAID array at {{ $labels.instance }} failed. Array '{{ $labels.device }}' needs attention and possibly a disk swap.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/noderaiddiskfailure
|
|
summary: Failed device in RAID array.
|
|
expr: node_md_disks{state="failed",job="node-exporter",device=~"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)"} > 0
|
|
labels:
|
|
severity: warning
|
|
- alert: NodeFileDescriptorLimit
|
|
annotations:
|
|
description: File descriptors limit at {{ $labels.instance }} is currently at {{ printf "%.2f" $value }}%.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefiledescriptorlimit
|
|
summary: Kernel is predicted to exhaust file descriptors limit soon.
|
|
expr: |-
|
|
(
|
|
node_filefd_allocated{job="node-exporter"} * 100 / node_filefd_maximum{job="node-exporter"} > 70
|
|
)
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
- alert: NodeFileDescriptorLimit
|
|
annotations:
|
|
description: File descriptors limit at {{ $labels.instance }} is currently at {{ printf "%.2f" $value }}%.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefiledescriptorlimit
|
|
summary: Kernel is predicted to exhaust file descriptors limit soon.
|
|
expr: |-
|
|
(
|
|
node_filefd_allocated{job="node-exporter"} * 100 / node_filefd_maximum{job="node-exporter"} > 90
|
|
)
|
|
for: 15m
|
|
labels:
|
|
severity: critical
|
|
- alert: NodeCPUHighUsage
|
|
annotations:
|
|
description: 'CPU usage at {{ $labels.instance }} has been above 90% for the last 15 minutes, is currently at {{ printf "%.2f" $value }}%.
|
|
|
|
'
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodecpuhighusage
|
|
summary: High CPU usage.
|
|
expr: sum without(mode) (avg without (cpu) (rate(node_cpu_seconds_total{job="node-exporter", mode!~"idle|iowait"}[2m]))) * 100 > 90
|
|
for: 15m
|
|
labels:
|
|
severity: info
|
|
- alert: NodeSystemSaturation
|
|
annotations:
|
|
description: 'System load per core at {{ $labels.instance }} has been above 2 for the last 15 minutes, is currently at {{ printf "%.2f" $value }}.
|
|
|
|
This might indicate this instance resources saturation and can cause it becoming unresponsive.
|
|
|
|
'
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodesystemsaturation
|
|
summary: System saturated, load per core is very high.
|
|
expr: |-
|
|
node_load1{job="node-exporter"}
|
|
/ count without (cpu, mode) (node_cpu_seconds_total{job="node-exporter", mode="idle"}) > 2
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
- alert: NodeMemoryMajorPagesFaults
|
|
annotations:
|
|
description: 'Memory major pages are occurring at very high rate at {{ $labels.instance }}, 500 major page faults per second for the last 15 minutes, is currently at {{ printf "%.2f" $value }}.
|
|
|
|
Please check that there is enough memory available at this instance.
|
|
|
|
'
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodememorymajorpagesfaults
|
|
summary: Memory major page faults are occurring at very high rate.
|
|
expr: rate(node_vmstat_pgmajfault{job="node-exporter"}[5m]) > 500
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
- alert: NodeMemoryHighUtilization
|
|
annotations:
|
|
description: 'Memory is filling up at {{ $labels.instance }}, has been above 90% for the last 15 minutes, is currently at {{ printf "%.2f" $value }}%.
|
|
|
|
'
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodememoryhighutilization
|
|
summary: Host is running out of memory.
|
|
expr: 100 - (node_memory_MemAvailable_bytes{job="node-exporter"} / node_memory_MemTotal_bytes{job="node-exporter"} * 100) > 90
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
- alert: NodeDiskIOSaturation
|
|
annotations:
|
|
description: 'Disk IO queue (aqu-sq) is high on {{ $labels.device }} at {{ $labels.instance }}, has been above 10 for the last 30 minutes, is currently at {{ printf "%.2f" $value }}.
|
|
|
|
This symptom might indicate disk saturation.
|
|
|
|
'
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodediskiosaturation
|
|
summary: Disk IO queue is high.
|
|
expr: rate(node_disk_io_time_weighted_seconds_total{job="node-exporter", device=~"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)"}[5m]) > 10
|
|
for: 30m
|
|
labels:
|
|
severity: warning
|
|
- alert: NodeSystemdServiceFailed
|
|
annotations:
|
|
description: Systemd service {{ $labels.name }} has entered failed state at {{ $labels.instance }}
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodesystemdservicefailed
|
|
summary: Systemd service has entered failed state.
|
|
expr: node_systemd_unit_state{job="node-exporter", state="failed"} == 1
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
- alert: NodeBondingDegraded
|
|
annotations:
|
|
description: Bonding interface {{ $labels.master }} on {{ $labels.instance }} is in degraded state due to one or more slave failures.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodebondingdegraded
|
|
summary: Bonding interface is degraded
|
|
expr: (node_bonding_slaves - node_bonding_active) != 0
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
---
|
|
# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/node-network.yaml
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: PrometheusRule
|
|
metadata:
|
|
name: kube-prometheus-stack-node-network
|
|
namespace: default
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack
|
|
app.kubernetes.io/name: kube-prometheus-stack #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
spec:
|
|
groups:
|
|
- name: node-network
|
|
rules:
|
|
- alert: NodeNetworkInterfaceFlapping
|
|
annotations:
|
|
description: Network interface "{{ $labels.device }}" changing its up status often on node-exporter {{ $labels.namespace }}/{{ $labels.pod }}
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/general/nodenetworkinterfaceflapping
|
|
summary: Network interface is often changing its status
|
|
expr: changes(node_network_up{job="node-exporter",device!~"veth.+"}[2m]) > 2
|
|
for: 2m
|
|
labels:
|
|
severity: warning
|
|
---
|
|
# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/node.rules.yaml
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: PrometheusRule
|
|
metadata:
|
|
name: kube-prometheus-stack-node.rules
|
|
namespace: default
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack
|
|
app.kubernetes.io/name: kube-prometheus-stack #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
spec:
|
|
groups:
|
|
- name: node.rules
|
|
rules:
|
|
- expr: |-
|
|
topk by (cluster, namespace, pod) (1,
|
|
max by (cluster, node, namespace, pod) (
|
|
label_replace(kube_pod_info{job="kube-state-metrics",node!=""}, "pod", "$1", "pod", "(.*)")
|
|
))
|
|
record: 'node_namespace_pod:kube_pod_info:'
|
|
- expr: |-
|
|
count by (cluster, node) (
|
|
node_cpu_seconds_total{mode="idle",job="node-exporter"}
|
|
* on (cluster, namespace, pod) group_left(node)
|
|
topk by (cluster, namespace, pod) (1, node_namespace_pod:kube_pod_info:)
|
|
)
|
|
record: node:node_num_cpu:sum
|
|
- expr: |-
|
|
sum(
|
|
node_memory_MemAvailable_bytes{job="node-exporter"} or
|
|
(
|
|
node_memory_Buffers_bytes{job="node-exporter"} +
|
|
node_memory_Cached_bytes{job="node-exporter"} +
|
|
node_memory_MemFree_bytes{job="node-exporter"} +
|
|
node_memory_Slab_bytes{job="node-exporter"}
|
|
)
|
|
) by (cluster)
|
|
record: :node_memory_MemAvailable_bytes:sum
|
|
- expr: |-
|
|
avg by (cluster, node) (
|
|
sum without (mode) (
|
|
rate(node_cpu_seconds_total{mode!="idle",mode!="iowait",mode!="steal",job="node-exporter"}[5m])
|
|
)
|
|
)
|
|
record: node:node_cpu_utilization:ratio_rate5m
|
|
- expr: |-
|
|
avg by (cluster) (
|
|
node:node_cpu_utilization:ratio_rate5m
|
|
)
|
|
record: cluster:node_cpu:ratio_rate5m
|
|
---
|
|
# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/prometheus-operator.yaml
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: PrometheusRule
|
|
metadata:
|
|
name: kube-prometheus-stack-prometheus-operator
|
|
namespace: default
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack
|
|
app.kubernetes.io/name: kube-prometheus-stack #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
spec:
|
|
groups:
|
|
- name: prometheus-operator
|
|
rules:
|
|
- alert: PrometheusOperatorListErrors
|
|
annotations:
|
|
description: Errors while performing List operations in controller {{$labels.controller}} in {{$labels.namespace}} namespace.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus-operator/prometheusoperatorlisterrors
|
|
summary: Errors while performing list operations in controller.
|
|
expr: (sum by (cluster,controller,namespace) (rate(prometheus_operator_list_operations_failed_total{job="kube-prometheus-stack-operator",namespace="default"}[10m])) / sum by (cluster,controller,namespace) (rate(prometheus_operator_list_operations_total{job="kube-prometheus-stack-operator",namespace="default"}[10m]))) > 0.4
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
- alert: PrometheusOperatorWatchErrors
|
|
annotations:
|
|
description: Errors while performing watch operations in controller {{$labels.controller}} in {{$labels.namespace}} namespace.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus-operator/prometheusoperatorwatcherrors
|
|
summary: Errors while performing watch operations in controller.
|
|
expr: (sum by (cluster,controller,namespace) (rate(prometheus_operator_watch_operations_failed_total{job="kube-prometheus-stack-operator",namespace="default"}[5m])) / sum by (cluster,controller,namespace) (rate(prometheus_operator_watch_operations_total{job="kube-prometheus-stack-operator",namespace="default"}[5m]))) > 0.4
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
- alert: PrometheusOperatorSyncFailed
|
|
annotations:
|
|
description: Controller {{ $labels.controller }} in {{ $labels.namespace }} namespace fails to reconcile {{ $value }} objects.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus-operator/prometheusoperatorsyncfailed
|
|
summary: Last controller reconciliation failed
|
|
expr: min_over_time(prometheus_operator_syncs{status="failed",job="kube-prometheus-stack-operator",namespace="default"}[5m]) > 0
|
|
for: 10m
|
|
labels:
|
|
severity: warning
|
|
- alert: PrometheusOperatorReconcileErrors
|
|
annotations:
|
|
description: '{{ $value | humanizePercentage }} of reconciling operations failed for {{ $labels.controller }} controller in {{ $labels.namespace }} namespace.'
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus-operator/prometheusoperatorreconcileerrors
|
|
summary: Errors while reconciling objects.
|
|
expr: (sum by (cluster,controller,namespace) (rate(prometheus_operator_reconcile_errors_total{job="kube-prometheus-stack-operator",namespace="default"}[5m]))) / (sum by (cluster,controller,namespace) (rate(prometheus_operator_reconcile_operations_total{job="kube-prometheus-stack-operator",namespace="default"}[5m]))) > 0.1
|
|
for: 10m
|
|
labels:
|
|
severity: warning
|
|
- alert: PrometheusOperatorStatusUpdateErrors
|
|
annotations:
|
|
description: '{{ $value | humanizePercentage }} of status update operations failed for {{ $labels.controller }} controller in {{ $labels.namespace }} namespace.'
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus-operator/prometheusoperatorstatusupdateerrors
|
|
summary: Errors while updating objects status.
|
|
expr: (sum by (cluster,controller,namespace) (rate(prometheus_operator_status_update_errors_total{job="kube-prometheus-stack-operator",namespace="default"}[5m]))) / (sum by (cluster,controller,namespace) (rate(prometheus_operator_status_update_operations_total{job="kube-prometheus-stack-operator",namespace="default"}[5m]))) > 0.1
|
|
for: 10m
|
|
labels:
|
|
severity: warning
|
|
- alert: PrometheusOperatorNodeLookupErrors
|
|
annotations:
|
|
description: Errors while reconciling Prometheus in {{ $labels.namespace }} Namespace.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus-operator/prometheusoperatornodelookuperrors
|
|
summary: Errors while reconciling Prometheus.
|
|
expr: rate(prometheus_operator_node_address_lookup_errors_total{job="kube-prometheus-stack-operator",namespace="default"}[5m]) > 0.1
|
|
for: 10m
|
|
labels:
|
|
severity: warning
|
|
- alert: PrometheusOperatorNotReady
|
|
annotations:
|
|
description: Prometheus operator in {{ $labels.namespace }} namespace isn't ready to reconcile {{ $labels.controller }} resources.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus-operator/prometheusoperatornotready
|
|
summary: Prometheus operator not ready
|
|
expr: min by (cluster,controller,namespace) (max_over_time(prometheus_operator_ready{job="kube-prometheus-stack-operator",namespace="default"}[5m]) == 0)
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
- alert: PrometheusOperatorRejectedResources
|
|
annotations:
|
|
description: Prometheus operator in {{ $labels.namespace }} namespace rejected {{ printf "%0.0f" $value }} {{ $labels.controller }}/{{ $labels.resource }} resources.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus-operator/prometheusoperatorrejectedresources
|
|
summary: Resources rejected by Prometheus operator
|
|
expr: min_over_time(prometheus_operator_managed_resources{state="rejected",job="kube-prometheus-stack-operator",namespace="default"}[5m]) > 0
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
---
|
|
# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/prometheus.yaml
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: PrometheusRule
|
|
metadata:
|
|
name: kube-prometheus-stack-prometheus
|
|
namespace: default
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack
|
|
app.kubernetes.io/name: kube-prometheus-stack #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
spec:
|
|
groups:
|
|
- name: prometheus
|
|
rules:
|
|
- alert: PrometheusBadConfig
|
|
annotations:
|
|
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has failed to reload its configuration.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusbadconfig
|
|
summary: Failed Prometheus configuration reload.
|
|
expr: |-
|
|
# Without max_over_time, failed scrapes could create false negatives, see
|
|
# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.
|
|
max_over_time(prometheus_config_last_reload_successful{job="kube-prometheus-stack-prometheus",namespace="default"}[5m]) == 0
|
|
for: 10m
|
|
labels:
|
|
severity: critical
|
|
- alert: PrometheusSDRefreshFailure
|
|
annotations:
|
|
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has failed to refresh SD with mechanism {{$labels.mechanism}}.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheussdrefreshfailure
|
|
summary: Failed Prometheus SD refresh.
|
|
expr: increase(prometheus_sd_refresh_failures_total{job="kube-prometheus-stack-prometheus",namespace="default"}[10m]) > 0
|
|
for: 20m
|
|
labels:
|
|
severity: warning
|
|
- alert: PrometheusKubernetesListWatchFailures
|
|
annotations:
|
|
description: Kubernetes service discovery of Prometheus {{$labels.namespace}}/{{$labels.pod}} is experiencing {{ printf "%.0f" $value }} failures with LIST/WATCH requests to the Kubernetes API in the last 5 minutes.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheuskuberneteslistwatchfailures
|
|
summary: Requests in Kubernetes SD are failing.
|
|
expr: increase(prometheus_sd_kubernetes_failures_total{job="kube-prometheus-stack-prometheus",namespace="default"}[5m]) > 0
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
- alert: PrometheusNotificationQueueRunningFull
|
|
annotations:
|
|
description: Alert notification queue of Prometheus {{$labels.namespace}}/{{$labels.pod}} is running full.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusnotificationqueuerunningfull
|
|
summary: Prometheus alert notification queue predicted to run full in less than 30m.
|
|
expr: |-
|
|
# Without min_over_time, failed scrapes could create false negatives, see
|
|
# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.
|
|
(
|
|
predict_linear(prometheus_notifications_queue_length{job="kube-prometheus-stack-prometheus",namespace="default"}[5m], 60 * 30)
|
|
>
|
|
min_over_time(prometheus_notifications_queue_capacity{job="kube-prometheus-stack-prometheus",namespace="default"}[5m])
|
|
)
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
- alert: PrometheusErrorSendingAlertsToSomeAlertmanagers
|
|
annotations:
|
|
description: '{{ printf "%.1f" $value }}% of alerts sent by Prometheus {{$labels.namespace}}/{{$labels.pod}} to Alertmanager {{$labels.alertmanager}} were affected by errors.'
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheuserrorsendingalertstosomealertmanagers
|
|
summary: More than 1% of alerts sent by Prometheus to a specific Alertmanager were affected by errors.
|
|
expr: |-
|
|
(
|
|
rate(prometheus_notifications_errors_total{job="kube-prometheus-stack-prometheus",namespace="default"}[5m])
|
|
/
|
|
rate(prometheus_notifications_sent_total{job="kube-prometheus-stack-prometheus",namespace="default"}[5m])
|
|
)
|
|
* 100
|
|
> 1
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
- alert: PrometheusNotConnectedToAlertmanagers
|
|
annotations:
|
|
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} is not connected to any Alertmanagers.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusnotconnectedtoalertmanagers
|
|
summary: Prometheus is not connected to any Alertmanagers.
|
|
expr: |-
|
|
# Without max_over_time, failed scrapes could create false negatives, see
|
|
# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.
|
|
max_over_time(prometheus_notifications_alertmanagers_discovered{job="kube-prometheus-stack-prometheus",namespace="default"}[5m]) < 1
|
|
for: 10m
|
|
labels:
|
|
severity: warning
|
|
- alert: PrometheusTSDBReloadsFailing
|
|
annotations:
|
|
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has detected {{$value | humanize}} reload failures over the last 3h.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheustsdbreloadsfailing
|
|
summary: Prometheus has issues reloading blocks from disk.
|
|
expr: increase(prometheus_tsdb_reloads_failures_total{job="kube-prometheus-stack-prometheus",namespace="default"}[3h]) > 0
|
|
for: 4h
|
|
labels:
|
|
severity: warning
|
|
- alert: PrometheusTSDBCompactionsFailing
|
|
annotations:
|
|
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has detected {{$value | humanize}} compaction failures over the last 3h.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheustsdbcompactionsfailing
|
|
summary: Prometheus has issues compacting blocks.
|
|
expr: increase(prometheus_tsdb_compactions_failed_total{job="kube-prometheus-stack-prometheus",namespace="default"}[3h]) > 0
|
|
for: 4h
|
|
labels:
|
|
severity: warning
|
|
- alert: PrometheusNotIngestingSamples
|
|
annotations:
|
|
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} is not ingesting samples.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusnotingestingsamples
|
|
summary: Prometheus is not ingesting samples.
|
|
expr: |-
|
|
(
|
|
sum without(type) (rate(prometheus_tsdb_head_samples_appended_total{job="kube-prometheus-stack-prometheus",namespace="default"}[5m])) <= 0
|
|
and
|
|
(
|
|
sum without(scrape_job) (prometheus_target_metadata_cache_entries{job="kube-prometheus-stack-prometheus",namespace="default"}) > 0
|
|
or
|
|
sum without(rule_group) (prometheus_rule_group_rules{job="kube-prometheus-stack-prometheus",namespace="default"}) > 0
|
|
)
|
|
)
|
|
for: 10m
|
|
labels:
|
|
severity: warning
|
|
- alert: PrometheusDuplicateTimestamps
|
|
annotations:
|
|
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} is dropping {{ printf "%.4g" $value }} samples/s with different values but duplicated timestamp.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusduplicatetimestamps
|
|
summary: Prometheus is dropping samples with duplicate timestamps.
|
|
expr: rate(prometheus_target_scrapes_sample_duplicate_timestamp_total{job="kube-prometheus-stack-prometheus",namespace="default"}[5m]) > 0
|
|
for: 10m
|
|
labels:
|
|
severity: warning
|
|
- alert: PrometheusOutOfOrderTimestamps
|
|
annotations:
|
|
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} is dropping {{ printf "%.4g" $value }} samples/s with timestamps arriving out of order.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusoutofordertimestamps
|
|
summary: Prometheus drops samples with out-of-order timestamps.
|
|
expr: rate(prometheus_target_scrapes_sample_out_of_order_total{job="kube-prometheus-stack-prometheus",namespace="default"}[5m]) > 0
|
|
for: 10m
|
|
labels:
|
|
severity: warning
|
|
- alert: PrometheusRemoteStorageFailures
|
|
annotations:
|
|
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} failed to send {{ printf "%.1f" $value }}% of the samples to {{ $labels.remote_name}}:{{ $labels.url }}
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusremotestoragefailures
|
|
summary: Prometheus fails to send samples to remote storage.
|
|
expr: |-
|
|
(
|
|
(rate(prometheus_remote_storage_failed_samples_total{job="kube-prometheus-stack-prometheus",namespace="default"}[5m]) or rate(prometheus_remote_storage_samples_failed_total{job="kube-prometheus-stack-prometheus",namespace="default"}[5m]))
|
|
/
|
|
(
|
|
(rate(prometheus_remote_storage_failed_samples_total{job="kube-prometheus-stack-prometheus",namespace="default"}[5m]) or rate(prometheus_remote_storage_samples_failed_total{job="kube-prometheus-stack-prometheus",namespace="default"}[5m]))
|
|
+
|
|
(rate(prometheus_remote_storage_succeeded_samples_total{job="kube-prometheus-stack-prometheus",namespace="default"}[5m]) or rate(prometheus_remote_storage_samples_total{job="kube-prometheus-stack-prometheus",namespace="default"}[5m]))
|
|
)
|
|
)
|
|
* 100
|
|
> 1
|
|
for: 15m
|
|
labels:
|
|
severity: critical
|
|
- alert: PrometheusRemoteWriteBehind
|
|
annotations:
|
|
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} remote write is {{ printf "%.1f" $value }}s behind for {{ $labels.remote_name}}:{{ $labels.url }}.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusremotewritebehind
|
|
summary: Prometheus remote write is behind.
|
|
expr: |-
|
|
# Without max_over_time, failed scrapes could create false negatives, see
|
|
# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.
|
|
(
|
|
max_over_time(prometheus_remote_storage_highest_timestamp_in_seconds{job="kube-prometheus-stack-prometheus",namespace="default"}[5m])
|
|
- ignoring(remote_name, url) group_right
|
|
max_over_time(prometheus_remote_storage_queue_highest_sent_timestamp_seconds{job="kube-prometheus-stack-prometheus",namespace="default"}[5m])
|
|
)
|
|
> 120
|
|
for: 15m
|
|
labels:
|
|
severity: critical
|
|
- alert: PrometheusRemoteWriteDesiredShards
|
|
annotations:
|
|
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} remote write desired shards calculation wants to run {{ $value }} shards for queue {{ $labels.remote_name}}:{{ $labels.url }}, which is more than the max of {{ printf `prometheus_remote_storage_shards_max{instance="%s",job="kube-prometheus-stack-prometheus",namespace="default"}` $labels.instance | query | first | value }}.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusremotewritedesiredshards
|
|
summary: Prometheus remote write desired shards calculation wants to run more than configured max shards.
|
|
expr: |-
|
|
# Without max_over_time, failed scrapes could create false negatives, see
|
|
# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.
|
|
(
|
|
max_over_time(prometheus_remote_storage_shards_desired{job="kube-prometheus-stack-prometheus",namespace="default"}[5m])
|
|
>
|
|
max_over_time(prometheus_remote_storage_shards_max{job="kube-prometheus-stack-prometheus",namespace="default"}[5m])
|
|
)
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
- alert: PrometheusRuleFailures
|
|
annotations:
|
|
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has failed to evaluate {{ printf "%.0f" $value }} rules in the last 5m.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusrulefailures
|
|
summary: Prometheus is failing rule evaluations.
|
|
expr: increase(prometheus_rule_evaluation_failures_total{job="kube-prometheus-stack-prometheus",namespace="default"}[5m]) > 0
|
|
for: 15m
|
|
labels:
|
|
severity: critical
|
|
- alert: PrometheusMissingRuleEvaluations
|
|
annotations:
|
|
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has missed {{ printf "%.0f" $value }} rule group evaluations in the last 5m.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusmissingruleevaluations
|
|
summary: Prometheus is missing rule evaluations due to slow rule group evaluation.
|
|
expr: increase(prometheus_rule_group_iterations_missed_total{job="kube-prometheus-stack-prometheus",namespace="default"}[5m]) > 0
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
- alert: PrometheusTargetLimitHit
|
|
annotations:
|
|
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has dropped {{ printf "%.0f" $value }} targets because the number of targets exceeded the configured target_limit.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheustargetlimithit
|
|
summary: Prometheus has dropped targets because some scrape configs have exceeded the targets limit.
|
|
expr: increase(prometheus_target_scrape_pool_exceeded_target_limit_total{job="kube-prometheus-stack-prometheus",namespace="default"}[5m]) > 0
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
- alert: PrometheusLabelLimitHit
|
|
annotations:
|
|
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has dropped {{ printf "%.0f" $value }} targets because some samples exceeded the configured label_limit, label_name_length_limit or label_value_length_limit.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheuslabellimithit
|
|
summary: Prometheus has dropped targets because some scrape configs have exceeded the labels limit.
|
|
expr: increase(prometheus_target_scrape_pool_exceeded_label_limits_total{job="kube-prometheus-stack-prometheus",namespace="default"}[5m]) > 0
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
- alert: PrometheusScrapeBodySizeLimitHit
|
|
annotations:
|
|
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has failed {{ printf "%.0f" $value }} scrapes in the last 5m because some targets exceeded the configured body_size_limit.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusscrapebodysizelimithit
|
|
summary: Prometheus has dropped some targets that exceeded body size limit.
|
|
expr: increase(prometheus_target_scrapes_exceeded_body_size_limit_total{job="kube-prometheus-stack-prometheus",namespace="default"}[5m]) > 0
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
- alert: PrometheusScrapeSampleLimitHit
|
|
annotations:
|
|
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has failed {{ printf "%.0f" $value }} scrapes in the last 5m because some targets exceeded the configured sample_limit.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusscrapesamplelimithit
|
|
summary: Prometheus has failed scrapes that have exceeded the configured sample limit.
|
|
expr: increase(prometheus_target_scrapes_exceeded_sample_limit_total{job="kube-prometheus-stack-prometheus",namespace="default"}[5m]) > 0
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
- alert: PrometheusTargetSyncFailure
|
|
annotations:
|
|
description: '{{ printf "%.0f" $value }} targets in Prometheus {{$labels.namespace}}/{{$labels.pod}} have failed to sync because invalid configuration was supplied.'
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheustargetsyncfailure
|
|
summary: Prometheus has failed to sync targets.
|
|
expr: increase(prometheus_target_sync_failed_total{job="kube-prometheus-stack-prometheus",namespace="default"}[30m]) > 0
|
|
for: 5m
|
|
labels:
|
|
severity: critical
|
|
- alert: PrometheusHighQueryLoad
|
|
annotations:
|
|
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} query API has less than 20% available capacity in its query engine for the last 15 minutes.
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheushighqueryload
|
|
summary: Prometheus is reaching its maximum capacity serving concurrent requests.
|
|
expr: avg_over_time(prometheus_engine_queries{job="kube-prometheus-stack-prometheus",namespace="default"}[5m]) / max_over_time(prometheus_engine_queries_concurrent_max{job="kube-prometheus-stack-prometheus",namespace="default"}[5m]) > 0.8
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
- alert: PrometheusErrorSendingAlertsToAnyAlertmanager
|
|
annotations:
|
|
description: '{{ printf "%.1f" $value }}% minimum errors while sending alerts from Prometheus {{$labels.namespace}}/{{$labels.pod}} to any Alertmanager.'
|
|
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheuserrorsendingalertstoanyalertmanager
|
|
summary: Prometheus encounters more than 3% errors sending alerts to any Alertmanager.
|
|
expr: |-
|
|
min without (alertmanager) (
|
|
rate(prometheus_notifications_errors_total{job="kube-prometheus-stack-prometheus",namespace="default",alertmanager!~``}[5m])
|
|
/
|
|
rate(prometheus_notifications_sent_total{job="kube-prometheus-stack-prometheus",namespace="default",alertmanager!~``}[5m])
|
|
)
|
|
* 100
|
|
> 3
|
|
for: 15m
|
|
labels:
|
|
severity: critical
|
|
---
|
|
# Source: kube-prometheus-stack/charts/grafana/templates/servicemonitor.yaml
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: ServiceMonitor
|
|
metadata:
|
|
name: kube-prometheus-stack-grafana
|
|
namespace: default
|
|
labels:
|
|
|
|
helm.sh/chart: grafana-8.8.2
|
|
app.kubernetes.io/name: grafana
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "11.4.0"
|
|
spec:
|
|
endpoints:
|
|
- port: http-web
|
|
scrapeTimeout: 30s
|
|
honorLabels: true
|
|
path: /metrics
|
|
scheme: http
|
|
jobLabel: "kube-prometheus-stack"
|
|
selector:
|
|
matchLabels:
|
|
app.kubernetes.io/name: grafana
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
namespaceSelector:
|
|
matchNames:
|
|
- default
|
|
---
|
|
# Source: kube-prometheus-stack/charts/kube-state-metrics/templates/servicemonitor.yaml
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: ServiceMonitor
|
|
metadata:
|
|
name: kube-prometheus-stack-kube-state-metrics
|
|
namespace: default
|
|
labels:
|
|
helm.sh/chart: kube-state-metrics-5.28.0
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/component: metrics
|
|
app.kubernetes.io/part-of: kube-state-metrics
|
|
app.kubernetes.io/name: kube-state-metrics
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "2.14.0"
|
|
#TBR: release: kube-prometheus-stack
|
|
spec:
|
|
jobLabel: app.kubernetes.io/name
|
|
selector:
|
|
matchLabels:
|
|
app.kubernetes.io/name: kube-state-metrics
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
endpoints:
|
|
- port: http
|
|
honorLabels: true
|
|
---
|
|
# Source: kube-prometheus-stack/charts/prometheus-node-exporter/templates/servicemonitor.yaml
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: ServiceMonitor
|
|
metadata:
|
|
name: kube-prometheus-stack-prometheus-node-exporter
|
|
namespace: default
|
|
labels:
|
|
helm.sh/chart: prometheus-node-exporter-4.43.1
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/component: metrics
|
|
app.kubernetes.io/part-of: prometheus-node-exporter
|
|
app.kubernetes.io/name: prometheus-node-exporter
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "1.8.2"
|
|
#TBR: release: kube-prometheus-stack
|
|
spec:
|
|
jobLabel: jobLabel
|
|
|
|
selector:
|
|
matchLabels:
|
|
app.kubernetes.io/name: prometheus-node-exporter
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
attachMetadata:
|
|
node: false
|
|
endpoints:
|
|
- port: http-metrics
|
|
scheme: http
|
|
---
|
|
# Source: kube-prometheus-stack/templates/alertmanager/servicemonitor.yaml
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: ServiceMonitor
|
|
metadata:
|
|
name: kube-prometheus-stack-alertmanager
|
|
namespace: default
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack
|
|
app.kubernetes.io/name: kube-prometheus-stack #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
spec:
|
|
|
|
selector:
|
|
matchLabels:
|
|
#TBR: app: kube-prometheus-stack-alertmanager
|
|
app.kubernetes.io/name: kube-prometheus-stack-alertmanager #ADDED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
self-monitor: "true"
|
|
namespaceSelector:
|
|
matchNames:
|
|
- "default"
|
|
endpoints:
|
|
- port: http-web
|
|
enableHttp2: true
|
|
path: "/metrics"
|
|
- port: reloader-web
|
|
path: "/metrics"
|
|
---
|
|
# Source: kube-prometheus-stack/templates/exporters/core-dns/servicemonitor.yaml
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: ServiceMonitor
|
|
metadata:
|
|
name: kube-prometheus-stack-coredns
|
|
namespace: default
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack-coredns
|
|
app.kubernetes.io/name: kube-prometheus-stack-coredns #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
spec:
|
|
jobLabel: jobLabel
|
|
|
|
selector:
|
|
matchLabels:
|
|
#TBR: app: kube-prometheus-stack-coredns
|
|
app.kubernetes.io/name: kube-prometheus-stack-coredns #ADDED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
namespaceSelector:
|
|
matchNames:
|
|
- "kube-system"
|
|
endpoints:
|
|
- port: http-metrics
|
|
bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
|
|
---
|
|
# Source: kube-prometheus-stack/templates/exporters/kube-api-server/servicemonitor.yaml
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: ServiceMonitor
|
|
metadata:
|
|
name: kube-prometheus-stack-apiserver
|
|
namespace: default
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack-apiserver
|
|
app.kubernetes.io/name: kube-prometheus-stack-apiserver #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
spec:
|
|
|
|
endpoints:
|
|
- bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
|
|
port: https
|
|
scheme: https
|
|
metricRelabelings:
|
|
- action: drop
|
|
regex: apiserver_request_duration_seconds_bucket;(0.15|0.2|0.3|0.35|0.4|0.45|0.6|0.7|0.8|0.9|1.25|1.5|1.75|2|3|3.5|4|4.5|6|7|8|9|15|25|40|50)
|
|
sourceLabels:
|
|
- __name__
|
|
- le
|
|
tlsConfig:
|
|
caFile: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
|
|
serverName: kubernetes
|
|
insecureSkipVerify: false
|
|
jobLabel: component
|
|
namespaceSelector:
|
|
matchNames:
|
|
- default
|
|
selector:
|
|
matchLabels:
|
|
component: apiserver
|
|
provider: kubernetes
|
|
---
|
|
# Source: kube-prometheus-stack/templates/exporters/kube-controller-manager/servicemonitor.yaml
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: ServiceMonitor
|
|
metadata:
|
|
name: kube-prometheus-stack-kube-controller-manager
|
|
namespace: default
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack-kube-controller-manager
|
|
app.kubernetes.io/name: kube-prometheus-stack-kube-controller-manager #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
spec:
|
|
jobLabel: jobLabel
|
|
|
|
selector:
|
|
matchLabels:
|
|
#TBR: app: kube-prometheus-stack-kube-controller-manager
|
|
app.kubernetes.io/name: kube-prometheus-stack-kube-controller-manager #ADDED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
namespaceSelector:
|
|
matchNames:
|
|
- "kube-system"
|
|
endpoints:
|
|
- port: http-metrics
|
|
bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
|
|
scheme: https
|
|
tlsConfig:
|
|
caFile: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
|
|
insecureSkipVerify: true
|
|
---
|
|
# Source: kube-prometheus-stack/templates/exporters/kube-etcd/servicemonitor.yaml
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: ServiceMonitor
|
|
metadata:
|
|
name: kube-prometheus-stack-kube-etcd
|
|
namespace: default
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack-kube-etcd
|
|
app.kubernetes.io/name: kube-prometheus-stack-kube-etcd #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
spec:
|
|
jobLabel: jobLabel
|
|
|
|
selector:
|
|
matchLabels:
|
|
#TBR: app: kube-prometheus-stack-kube-etcd
|
|
app.kubernetes.io/name: kube-prometheus-stack-kube-etcd #ADDED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
namespaceSelector:
|
|
matchNames:
|
|
- "kube-system"
|
|
endpoints:
|
|
- port: http-metrics
|
|
bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
|
|
---
|
|
# Source: kube-prometheus-stack/templates/exporters/kube-proxy/servicemonitor.yaml
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: ServiceMonitor
|
|
metadata:
|
|
name: kube-prometheus-stack-kube-proxy
|
|
namespace: default
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack-kube-proxy
|
|
app.kubernetes.io/name: kube-prometheus-stack-kube-proxy #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
spec:
|
|
jobLabel: jobLabel
|
|
|
|
selector:
|
|
matchLabels:
|
|
#TBR: app: kube-prometheus-stack-kube-proxy
|
|
app.kubernetes.io/name: kube-prometheus-stack-kube-proxy #ADDED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
namespaceSelector:
|
|
matchNames:
|
|
- "kube-system"
|
|
endpoints:
|
|
- port: http-metrics
|
|
bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
|
|
---
|
|
# Source: kube-prometheus-stack/templates/exporters/kube-scheduler/servicemonitor.yaml
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: ServiceMonitor
|
|
metadata:
|
|
name: kube-prometheus-stack-kube-scheduler
|
|
namespace: default
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack-kube-scheduler
|
|
app.kubernetes.io/name: kube-prometheus-stack-kube-scheduler #ADDED
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
spec:
|
|
jobLabel: jobLabel
|
|
|
|
selector:
|
|
matchLabels:
|
|
#TBR: app: kube-prometheus-stack-kube-scheduler
|
|
app.kubernetes.io/name: kube-prometheus-stack-kube-scheduler #ADDED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
namespaceSelector:
|
|
matchNames:
|
|
- "kube-system"
|
|
endpoints:
|
|
- port: http-metrics
|
|
bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
|
|
scheme: https
|
|
tlsConfig:
|
|
caFile: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
|
|
insecureSkipVerify: true
|
|
---
|
|
# Source: kube-prometheus-stack/templates/exporters/kubelet/servicemonitor.yaml
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: ServiceMonitor
|
|
metadata:
|
|
name: kube-prometheus-stack-kubelet
|
|
namespace: default
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack-kube-kubelet
|
|
app.kubernetes.io/name: kube-prometheus-stack-kube-kubelet #ADDED
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
spec:
|
|
|
|
attachMetadata:
|
|
node: false
|
|
jobLabel: k8s-app
|
|
namespaceSelector:
|
|
matchNames:
|
|
- kube-system
|
|
selector:
|
|
matchLabels:
|
|
app.kubernetes.io/name: kubelet
|
|
k8s-app: kubelet
|
|
endpoints:
|
|
- port: https-metrics
|
|
scheme: https
|
|
tlsConfig:
|
|
caFile: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
|
|
insecureSkipVerify: true
|
|
bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
|
|
honorLabels: true
|
|
honorTimestamps: true
|
|
relabelings:
|
|
- action: replace
|
|
sourceLabels:
|
|
- __metrics_path__
|
|
targetLabel: metrics_path
|
|
- port: https-metrics
|
|
scheme: https
|
|
path: /metrics/cadvisor
|
|
interval: 10s
|
|
honorLabels: true
|
|
honorTimestamps: true
|
|
trackTimestampsStaleness: true
|
|
tlsConfig:
|
|
caFile: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
|
|
insecureSkipVerify: true
|
|
bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
|
|
metricRelabelings:
|
|
- action: drop
|
|
regex: container_cpu_(cfs_throttled_seconds_total|load_average_10s|system_seconds_total|user_seconds_total)
|
|
sourceLabels:
|
|
- __name__
|
|
- action: drop
|
|
regex: container_fs_(io_current|io_time_seconds_total|io_time_weighted_seconds_total|reads_merged_total|sector_reads_total|sector_writes_total|writes_merged_total)
|
|
sourceLabels:
|
|
- __name__
|
|
- action: drop
|
|
regex: container_memory_(mapped_file|swap)
|
|
sourceLabels:
|
|
- __name__
|
|
- action: drop
|
|
regex: container_(file_descriptors|tasks_state|threads_max)
|
|
sourceLabels:
|
|
- __name__
|
|
- action: drop
|
|
regex: container_spec.*
|
|
sourceLabels:
|
|
- __name__
|
|
- action: drop
|
|
regex: .+;
|
|
sourceLabels:
|
|
- id
|
|
- pod
|
|
relabelings:
|
|
- action: replace
|
|
sourceLabels:
|
|
- __metrics_path__
|
|
targetLabel: metrics_path
|
|
- port: https-metrics
|
|
scheme: https
|
|
path: /metrics/probes
|
|
honorLabels: true
|
|
honorTimestamps: true
|
|
tlsConfig:
|
|
caFile: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
|
|
insecureSkipVerify: true
|
|
bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
|
|
relabelings:
|
|
- action: replace
|
|
sourceLabels:
|
|
- __metrics_path__
|
|
targetLabel: metrics_path
|
|
---
|
|
# Source: kube-prometheus-stack/templates/prometheus-operator/servicemonitor.yaml
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: ServiceMonitor
|
|
metadata:
|
|
name: kube-prometheus-stack-operator
|
|
namespace: default
|
|
labels:
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
#TBR: app: kube-prometheus-stack-operator
|
|
app.kubernetes.io/name: kube-prometheus-stack-prometheus-operator
|
|
app.kubernetes.io/component: prometheus-operator
|
|
spec:
|
|
|
|
endpoints:
|
|
- port: https
|
|
scheme: https
|
|
tlsConfig:
|
|
serverName: kube-prometheus-stack-operator
|
|
ca:
|
|
secret:
|
|
name: kube-prometheus-stack-admission
|
|
key: ca
|
|
optional: false
|
|
honorLabels: true
|
|
selector:
|
|
matchLabels:
|
|
#TBR: app: kube-prometheus-stack-operator
|
|
app.kubernetes.io/name: kube-prometheus-stack-prometheus-operator
|
|
#TBR: release: "kube-prometheus-stack"
|
|
namespaceSelector:
|
|
matchNames:
|
|
- "default"
|
|
---
|
|
# Source: kube-prometheus-stack/templates/prometheus/servicemonitor.yaml
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: ServiceMonitor
|
|
metadata:
|
|
name: kube-prometheus-stack-prometheus
|
|
namespace: default
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack-prometheus
|
|
app.kubernetes.io/name: kube-prometheus-stack-prometheus
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
spec:
|
|
|
|
selector:
|
|
matchLabels:
|
|
#TBR: app: kube-prometheus-stack-prometheus
|
|
app.kubernetes.io/name: kube-prometheus-stack-prometheus-prometheus
|
|
#TBR: release: "kube-prometheus-stack"
|
|
self-monitor: "true"
|
|
namespaceSelector:
|
|
matchNames:
|
|
- "default"
|
|
endpoints:
|
|
- port: http-web
|
|
path: "/metrics"
|
|
- port: reloader-web
|
|
path: "/metrics"
|
|
---
|
|
# Source: kube-prometheus-stack/templates/prometheus-operator/admission-webhooks/validatingWebhookConfiguration.yaml
|
|
apiVersion: admissionregistration.k8s.io/v1
|
|
kind: ValidatingWebhookConfiguration
|
|
metadata:
|
|
name: kube-prometheus-stack-admission
|
|
annotations:
|
|
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack-admission
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
app.kubernetes.io/name: kube-prometheus-stack-prometheus-operator
|
|
app.kubernetes.io/component: prometheus-operator-webhook
|
|
webhooks:
|
|
- name: prometheusrulemutate.monitoring.coreos.com
|
|
failurePolicy: Ignore
|
|
rules:
|
|
- apiGroups:
|
|
- monitoring.coreos.com
|
|
apiVersions:
|
|
- "*"
|
|
resources:
|
|
- prometheusrules
|
|
operations:
|
|
- CREATE
|
|
- UPDATE
|
|
clientConfig:
|
|
service:
|
|
namespace: default
|
|
name: kube-prometheus-stack-operator
|
|
path: /admission-prometheusrules/validate
|
|
timeoutSeconds: 10
|
|
admissionReviewVersions: ["v1", "v1beta1"]
|
|
sideEffects: None
|
|
---
|
|
# Source: kube-prometheus-stack/charts/grafana/templates/tests/test-serviceaccount.yaml
|
|
apiVersion: v1
|
|
kind: ServiceAccount
|
|
metadata:
|
|
labels:
|
|
|
|
helm.sh/chart: grafana-8.8.2
|
|
app.kubernetes.io/name: grafana
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "11.4.0"
|
|
name: kube-prometheus-stack-grafana-test
|
|
namespace: default
|
|
annotations:
|
|
"helm.sh/hook": test
|
|
"helm.sh/hook-delete-policy": "before-hook-creation,hook-succeeded"
|
|
---
|
|
# Source: kube-prometheus-stack/templates/prometheus-operator/admission-webhooks/job-patch/serviceaccount.yaml
|
|
apiVersion: v1
|
|
kind: ServiceAccount
|
|
metadata:
|
|
name: kube-prometheus-stack-admission
|
|
namespace: default
|
|
annotations:
|
|
"helm.sh/hook": pre-install,pre-upgrade,post-install,post-upgrade
|
|
"helm.sh/hook-delete-policy": before-hook-creation,hook-succeeded
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack-admission
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
app.kubernetes.io/name: kube-prometheus-stack-prometheus-operator
|
|
app.kubernetes.io/component: prometheus-operator-webhook
|
|
automountServiceAccountToken: true
|
|
---
|
|
# Source: kube-prometheus-stack/charts/grafana/templates/tests/test-configmap.yaml
|
|
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
name: kube-prometheus-stack-grafana-test
|
|
namespace: default
|
|
annotations:
|
|
"helm.sh/hook": test
|
|
"helm.sh/hook-delete-policy": "before-hook-creation,hook-succeeded"
|
|
labels:
|
|
|
|
helm.sh/chart: grafana-8.8.2
|
|
app.kubernetes.io/name: grafana
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "11.4.0"
|
|
data:
|
|
run.sh: |-
|
|
@test "Test Health" {
|
|
url="http://kube-prometheus-stack-grafana/api/health"
|
|
|
|
code=$(wget --server-response --spider --timeout 90 --tries 10 ${url} 2>&1 | awk '/^ HTTP/{print $2}')
|
|
[ "$code" == "200" ]
|
|
}
|
|
---
|
|
# Source: kube-prometheus-stack/templates/prometheus-operator/admission-webhooks/job-patch/clusterrole.yaml
|
|
apiVersion: rbac.authorization.k8s.io/v1
|
|
kind: ClusterRole
|
|
metadata:
|
|
name: kube-prometheus-stack-admission
|
|
annotations:
|
|
"helm.sh/hook": pre-install,pre-upgrade,post-install,post-upgrade
|
|
"helm.sh/hook-delete-policy": before-hook-creation,hook-succeeded
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack-admission
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
app.kubernetes.io/name: kube-prometheus-stack-prometheus-operator
|
|
app.kubernetes.io/component: prometheus-operator-webhook
|
|
rules:
|
|
- apiGroups:
|
|
- admissionregistration.k8s.io
|
|
resources:
|
|
- validatingwebhookconfigurations
|
|
- mutatingwebhookconfigurations
|
|
verbs:
|
|
- get
|
|
- update
|
|
---
|
|
# Source: kube-prometheus-stack/templates/prometheus-operator/admission-webhooks/job-patch/clusterrolebinding.yaml
|
|
apiVersion: rbac.authorization.k8s.io/v1
|
|
kind: ClusterRoleBinding
|
|
metadata:
|
|
name: kube-prometheus-stack-admission
|
|
annotations:
|
|
"helm.sh/hook": pre-install,pre-upgrade,post-install,post-upgrade
|
|
"helm.sh/hook-delete-policy": before-hook-creation,hook-succeeded
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack-admission
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
app.kubernetes.io/name: kube-prometheus-stack-prometheus-operator
|
|
app.kubernetes.io/component: prometheus-operator-webhook
|
|
roleRef:
|
|
apiGroup: rbac.authorization.k8s.io
|
|
kind: ClusterRole
|
|
name: kube-prometheus-stack-admission
|
|
subjects:
|
|
- kind: ServiceAccount
|
|
name: kube-prometheus-stack-admission
|
|
namespace: default
|
|
---
|
|
# Source: kube-prometheus-stack/templates/prometheus-operator/admission-webhooks/job-patch/role.yaml
|
|
apiVersion: rbac.authorization.k8s.io/v1
|
|
kind: Role
|
|
metadata:
|
|
name: kube-prometheus-stack-admission
|
|
namespace: default
|
|
annotations:
|
|
"helm.sh/hook": pre-install,pre-upgrade,post-install,post-upgrade
|
|
"helm.sh/hook-delete-policy": before-hook-creation,hook-succeeded
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack-admission
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
app.kubernetes.io/name: kube-prometheus-stack-prometheus-operator
|
|
app.kubernetes.io/component: prometheus-operator-webhook
|
|
rules:
|
|
- apiGroups:
|
|
- ""
|
|
resources:
|
|
- secrets
|
|
verbs:
|
|
- get
|
|
- create
|
|
---
|
|
# Source: kube-prometheus-stack/templates/prometheus-operator/admission-webhooks/job-patch/rolebinding.yaml
|
|
apiVersion: rbac.authorization.k8s.io/v1
|
|
kind: RoleBinding
|
|
metadata:
|
|
name: kube-prometheus-stack-admission
|
|
namespace: default
|
|
annotations:
|
|
"helm.sh/hook": pre-install,pre-upgrade,post-install,post-upgrade
|
|
"helm.sh/hook-delete-policy": before-hook-creation,hook-succeeded
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack-admission
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
app.kubernetes.io/name: kube-prometheus-stack-prometheus-operator
|
|
app.kubernetes.io/component: prometheus-operator-webhook
|
|
roleRef:
|
|
apiGroup: rbac.authorization.k8s.io
|
|
kind: Role
|
|
name: kube-prometheus-stack-admission
|
|
subjects:
|
|
- kind: ServiceAccount
|
|
name: kube-prometheus-stack-admission
|
|
namespace: default
|
|
---
|
|
# Source: kube-prometheus-stack/charts/grafana/templates/tests/test.yaml
|
|
apiVersion: v1
|
|
kind: Pod
|
|
metadata:
|
|
name: kube-prometheus-stack-grafana-test
|
|
labels:
|
|
|
|
helm.sh/chart: grafana-8.8.2
|
|
app.kubernetes.io/name: grafana
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "11.4.0"
|
|
annotations:
|
|
"helm.sh/hook": test
|
|
"helm.sh/hook-delete-policy": "before-hook-creation,hook-succeeded"
|
|
namespace: default
|
|
spec:
|
|
serviceAccountName: kube-prometheus-stack-grafana-test
|
|
containers:
|
|
- name: kube-prometheus-stack-test
|
|
image: "docker.io/bats/bats:v1.4.1"
|
|
imagePullPolicy: "IfNotPresent"
|
|
command: ["/opt/bats/bin/bats", "-t", "/tests/run.sh"]
|
|
volumeMounts:
|
|
- mountPath: /tests
|
|
name: tests
|
|
readOnly: true
|
|
volumes:
|
|
- name: tests
|
|
configMap:
|
|
name: kube-prometheus-stack-grafana-test
|
|
restartPolicy: Never
|
|
---
|
|
# Source: kube-prometheus-stack/templates/prometheus-operator/admission-webhooks/job-patch/job-createSecret.yaml
|
|
apiVersion: batch/v1
|
|
kind: Job
|
|
metadata:
|
|
name: kube-prometheus-stack-admission-create
|
|
namespace: default
|
|
annotations:
|
|
"helm.sh/hook": pre-install,pre-upgrade
|
|
"helm.sh/hook-delete-policy": before-hook-creation,hook-succeeded
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack-admission-create
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
app.kubernetes.io/name: kube-prometheus-stack-prometheus-operator
|
|
app.kubernetes.io/component: prometheus-operator-webhook
|
|
spec:
|
|
ttlSecondsAfterFinished: 60
|
|
template:
|
|
metadata:
|
|
name: kube-prometheus-stack-admission-create
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack-admission-create
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
app.kubernetes.io/name: kube-prometheus-stack-prometheus-operator
|
|
app.kubernetes.io/component: prometheus-operator-webhook
|
|
spec:
|
|
containers:
|
|
- name: create
|
|
image: registry.k8s.io/ingress-nginx/kube-webhook-certgen:v20221220-controller-v1.5.1-58-g787ea74b6
|
|
imagePullPolicy: IfNotPresent
|
|
args:
|
|
- create
|
|
- --host=kube-prometheus-stack-operator,kube-prometheus-stack-operator.default.svc
|
|
- --namespace=default
|
|
- --secret-name=kube-prometheus-stack-admission
|
|
securityContext:
|
|
|
|
allowPrivilegeEscalation: false
|
|
capabilities:
|
|
drop:
|
|
- ALL
|
|
readOnlyRootFilesystem: true
|
|
resources:
|
|
{}
|
|
restartPolicy: OnFailure
|
|
serviceAccountName: kube-prometheus-stack-admission
|
|
securityContext:
|
|
runAsGroup: 2000
|
|
runAsNonRoot: true
|
|
runAsUser: 2000
|
|
seccompProfile:
|
|
type: RuntimeDefault
|
|
---
|
|
# Source: kube-prometheus-stack/templates/prometheus-operator/admission-webhooks/job-patch/job-patchWebhook.yaml
|
|
apiVersion: batch/v1
|
|
kind: Job
|
|
metadata:
|
|
name: kube-prometheus-stack-admission-patch
|
|
namespace: default
|
|
annotations:
|
|
"helm.sh/hook": post-install,post-upgrade
|
|
"helm.sh/hook-delete-policy": before-hook-creation,hook-succeeded
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack-admission-patch
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
app.kubernetes.io/name: kube-prometheus-stack-prometheus-operator
|
|
app.kubernetes.io/component: prometheus-operator-webhook
|
|
spec:
|
|
ttlSecondsAfterFinished: 60
|
|
template:
|
|
metadata:
|
|
name: kube-prometheus-stack-admission-patch
|
|
labels:
|
|
#TBR: app: kube-prometheus-stack-admission-patch
|
|
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/instance: kube-prometheus-stack
|
|
app.kubernetes.io/version: "67.7.0"
|
|
app.kubernetes.io/part-of: kube-prometheus-stack
|
|
helm.sh/chart: kube-prometheus-stack-67.7.0 #UPDATED
|
|
#TBR: release: "kube-prometheus-stack"
|
|
heritage: "Helm"
|
|
app.kubernetes.io/name: kube-prometheus-stack-prometheus-operator
|
|
app.kubernetes.io/component: prometheus-operator-webhook
|
|
spec:
|
|
containers:
|
|
- name: patch
|
|
image: registry.k8s.io/ingress-nginx/kube-webhook-certgen:v20221220-controller-v1.5.1-58-g787ea74b6
|
|
imagePullPolicy: IfNotPresent
|
|
args:
|
|
- patch
|
|
- --webhook-name=kube-prometheus-stack-admission
|
|
- --namespace=default
|
|
- --secret-name=kube-prometheus-stack-admission
|
|
- --patch-failure-policy=
|
|
securityContext:
|
|
|
|
allowPrivilegeEscalation: false
|
|
capabilities:
|
|
drop:
|
|
- ALL
|
|
readOnlyRootFilesystem: true
|
|
resources:
|
|
{}
|
|
restartPolicy: OnFailure
|
|
serviceAccountName: kube-prometheus-stack-admission
|
|
securityContext:
|
|
runAsGroup: 2000
|
|
runAsNonRoot: true
|
|
runAsUser: 2000
|
|
seccompProfile:
|
|
type: RuntimeDefault
|