home/helm-charts
2
0
Fork 0
mirror of https://github.com/wahyd4/helm-charts.git synced 2026-08-09 04:26:02 +10:00
Code Issues Packages Projects Releases Wiki Activity

[kube-prometheus-stack] Sync rules and dashboards (#1075)

Browse Source 
prometheus-operator/kube-prometheus' default branch switched to main, so
we missed some updates.

Also we did not update the alertmanager, node-exporter and prometheus-operator rulesets,
which is fixed now as well.

Signed-off-by: Manuel Rüger <manuel@rueg.eu>
This commit is contained in:
Manuel Rüger
2021-06-15 14:16:47 +03:00
committed by GitHub
parent 3f82e4a9ab
commit 5477284197
51 changed files with 3087 additions and 2541 deletions
Download Patch File Download Diff File Expand all files Collapse all files
charts/kube-prometheus-stack/Chart.yaml
+1 -1
View File
@@ -18,7 +18,7 @@ name: kube-prometheus-stack
sources:
- https://github.com/prometheus-community/helm-charts
- https://github.com/prometheus-operator/kube-prometheus
version: 16.7.1
version: 16.8.0
appVersion: 0.48.1
kubeVersion: ">=1.16.0-0"
home: https://github.com/prometheus-operator/kube-prometheus
charts/kube-prometheus-stack/hack/sync_grafana_dashboards.py
+1 -1
View File
@@ -26,7 +26,7 @@ def change_style(style, representer):
# Source files list
charts = [
{
'source': 'https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/grafana-dashboardDefinitions.yaml',
'source': 'https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/grafana-dashboardDefinitions.yaml',
'destination': '../templates/grafana/dashboards-1.14',
'type': 'yaml',
'min_kubernetes': '1.14.0-0'
charts/kube-prometheus-stack/hack/sync_prometheus_rules.py
+31 -1
View File
@@ -25,7 +25,37 @@ def change_style(style, representer):
# Source files list
charts = [
{
'source': 'https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/kubernetes-prometheusRule.yaml',
'source': 'https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/alertmanager-prometheusRule.yaml',
'destination': '../templates/prometheus/rules-1.14',
'min_kubernetes': '1.14.0-0'
},
{
'source': 'https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/kube-prometheus-prometheusRule.yaml',
'destination': '../templates/prometheus/rules-1.14',
'min_kubernetes': '1.14.0-0'
},
{
'source': 'https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/kubernetes-prometheusRule.yaml',
'destination': '../templates/prometheus/rules-1.14',
'min_kubernetes': '1.14.0-0'
},
{
'source': 'https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/kube-state-metrics-prometheusRule.yaml',
'destination': '../templates/prometheus/rules-1.14',
'min_kubernetes': '1.14.0-0'
},
{
'source': 'https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/node-exporter-prometheusRule.yaml',
'destination': '../templates/prometheus/rules-1.14',
'min_kubernetes': '1.14.0-0'
},
{
'source': 'https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/prometheus-prometheusRule.yaml',
'destination': '../templates/prometheus/rules-1.14',
'min_kubernetes': '1.14.0-0'
},
{
'source': 'https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/prometheus-operator-prometheusRule.yaml',
'destination': '../templates/prometheus/rules-1.14',
'min_kubernetes': '1.14.0-0'
},
charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/alertmanager-overview.yaml
+610
View File
@@ -0,0 +1,610 @@
{{- /*
Generated from 'alertmanager-overview' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/grafana-dashboardDefinitions.yaml
Do not change in-place! In order to change this file first read following link:
https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack
*/ -}}
{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }}
{{- if and (or .Values.grafana.enabled .Values.grafana.forceDeployDashboards) (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.grafana.defaultDashboardsEnabled }}
apiVersion: v1
kind: ConfigMap
metadata:
namespace: {{ template "kube-prometheus-stack.namespace" . }}
name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" $) "alertmanager-overview" | trunc 63 | trimSuffix "-" }}
annotations:
{{ toYaml .Values.grafana.sidecar.dashboards.annotations | indent 4 }}
labels:
{{- if $.Values.grafana.sidecar.dashboards.label }}
{{ $.Values.grafana.sidecar.dashboards.label }}: "1"
{{- end }}
app: {{ template "kube-prometheus-stack.name" $ }}-grafana
{{ include "kube-prometheus-stack.labels" $ | indent 4 }}
data:
alertmanager-overview.json: |-
{
"__inputs": [
],
"__requires": [
],
"annotations": {
"list": [
]
},
"editable": false,
"gnetId": null,
"graphTooltip": 1,
"hideControls": false,
"id": null,
"links": [
],
"refresh": "30s",
"rows": [
{
"collapse": false,
"collapsed": false,
"panels": [
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
"id": 2,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": false,
"show": false,
"sideWidth": null,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 6,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sum(alertmanager_alerts{namespace=\"$namespace\",service=\"$service\"}) by (namespace,service,instance)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{`{{`}}instance{{`}}`}}",
"refId": "A"
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Alerts",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "none",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "none",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
"id": 3,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": false,
"show": false,
"sideWidth": null,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 6,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(alertmanager_alerts_received_total{namespace=\"$namespace\",service=\"$service\"}[5m])) by (namespace,service,instance)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{`{{`}}instance{{`}}`}} Received",
"refId": "A"
},
{
"expr": "sum(rate(alertmanager_alerts_invalid_total{namespace=\"$namespace\",service=\"$service\"}[5m])) by (namespace,service,instance)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{`{{`}}instance{{`}}`}} Invalid",
"refId": "B"
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Alerts receive rate",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "ops",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "ops",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Alerts",
"titleSize": "h6",
"type": "row"
},
{
"collapse": false,
"collapsed": false,
"panels": [
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
"id": 4,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": false,
"show": false,
"sideWidth": null,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": "integration",
"seriesOverrides": [
],
"spaceLength": 10,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(alertmanager_notifications_total{namespace=\"$namespace\",service=\"$service\", integration=\"$integration\"}[5m])) by (integration,namespace,service,instance)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{`{{`}}instance{{`}}`}} Total",
"refId": "A"
},
{
"expr": "sum(rate(alertmanager_notifications_failed_total{namespace=\"$namespace\",service=\"$service\", integration=\"$integration\"}[5m])) by (integration,namespace,service,instance)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{`{{`}}instance{{`}}`}} Failed",
"refId": "B"
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "$integration: Notifications Send Rate",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "ops",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "ops",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
"id": 5,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": false,
"show": false,
"sideWidth": null,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": "integration",
"seriesOverrides": [
],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "histogram_quantile(0.99,\n sum(rate(alertmanager_notification_latency_seconds_bucket{namespace=\"$namespace\",service=\"$service\", integration=\"$integration\"}[5m])) by (le,namespace,service,instance)\n) \n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{`{{`}}instance{{`}}`}} 99th Percentile",
"refId": "A"
},
{
"expr": "histogram_quantile(0.50,\n sum(rate(alertmanager_notification_latency_seconds_bucket{namespace=\"$namespace\",service=\"$service\", integration=\"$integration\"}[5m])) by (le,namespace,service,instance)\n) \n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{`{{`}}instance{{`}}`}} Median",
"refId": "B"
},
{
"expr": "sum(rate(alertmanager_notification_latency_seconds_sum{namespace=\"$namespace\",service=\"$service\", integration=\"$integration\"}[5m])) by (namespace,service,instance)\n/\nsum(rate(alertmanager_notification_latency_seconds_count{namespace=\"$namespace\",service=\"$service\", integration=\"$integration\"}[5m])) by (namespace,service,instance)\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{`{{`}}instance{{`}}`}} Average",
"refId": "C"
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "$integration: Notification Duration",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "s",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "s",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Notifications",
"titleSize": "h6",
"type": "row"
}
],
"schemaVersion": 14,
"style": "dark",
"tags": [
"alertmanager-mixin"
],
"templating": {
"list": [
{
"current": {
"text": "Prometheus",
"value": "Prometheus"
},
"hide": 0,
"label": null,
"name": "datasource",
"options": [
],
"query": "prometheus",
"refresh": 1,
"regex": "",
"type": "datasource"
},
{
"allValue": null,
"current": {
"text": "",
"value": ""
},
"datasource": "$datasource",
"hide": 0,
"includeAll": false,
"label": null,
"multi": false,
"name": "namespace",
"options": [
],
"query": "label_values(alertmanager_alerts, namespace)",
"refresh": 2,
"regex": "",
"sort": 1,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"allValue": null,
"current": {
"text": "",
"value": ""
},
"datasource": "$datasource",
"hide": 0,
"includeAll": false,
"label": null,
"multi": false,
"name": "service",
"options": [
],
"query": "label_values(alertmanager_alerts, service)",
"refresh": 2,
"regex": "",
"sort": 1,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"allValue": null,
"current": {
"text": "all",
"value": "$__all"
},
"datasource": "$datasource",
"hide": 2,
"includeAll": true,
"label": null,
"multi": false,
"name": "integration",
"options": [
],
"query": "label_values(alertmanager_notifications_total{integration=~\".*\"}, integration)",
"refresh": 2,
"regex": "",
"sort": 1,
"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": "Alertmanager / Overview",
"uid": "alertmanager-overview",
"version": 0
}
{{- end }}
charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/apiserver.yaml
+1 -1
View File
@@ -1,5 +1,5 @@
{{- /*
Generated from 'apiserver' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/grafana-dashboardDefinitions.yaml
Generated from 'apiserver' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/grafana-dashboardDefinitions.yaml
Do not change in-place! In order to change this file first read following link:
https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack
*/ -}}
charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/cluster-total.yaml
+1 -1
View File
@@ -1,5 +1,5 @@
{{- /*
Generated from 'cluster-total' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/grafana-dashboardDefinitions.yaml
Generated from 'cluster-total' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/grafana-dashboardDefinitions.yaml
Do not change in-place! In order to change this file first read following link:
https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack
*/ -}}
charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/controller-manager.yaml
+7 -7
View File
@@ -1,5 +1,5 @@
{{- /*
Generated from 'controller-manager' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/grafana-dashboardDefinitions.yaml
Generated from 'controller-manager' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/grafana-dashboardDefinitions.yaml
Do not change in-place! In order to change this file first read following link:
https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack
*/ -}}
@@ -176,10 +176,10 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(workqueue_adds_total{cluster=\"$cluster\", job=\"kube-controller-manager\", instance=~\"$instance\"}[5m])) by (instance, name)",
"expr": "sum(rate(workqueue_adds_total{cluster=\"$cluster\", job=\"kube-controller-manager\", instance=~\"$instance\"}[5m])) by (cluster, instance, name)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{`{{`}}instance{{`}}`}} {{`{{`}}name{{`}}`}}",
"legendFormat": "{{`{{`}}cluster{{`}}`}} {{`{{`}}instance{{`}}`}} {{`{{`}}name{{`}}`}}",
"refId": "A"
}
],
@@ -282,10 +282,10 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(workqueue_depth{cluster=\"$cluster\", job=\"kube-controller-manager\", instance=~\"$instance\"}[5m])) by (instance, name)",
"expr": "sum(rate(workqueue_depth{cluster=\"$cluster\", job=\"kube-controller-manager\", instance=~\"$instance\"}[5m])) by (cluster, instance, name)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{`{{`}}instance{{`}}`}} {{`{{`}}name{{`}}`}}",
"legendFormat": "{{`{{`}}cluster{{`}}`}} {{`{{`}}instance{{`}}`}} {{`{{`}}name{{`}}`}}",
"refId": "A"
}
],
@@ -388,10 +388,10 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "histogram_quantile(0.99, sum(rate(workqueue_queue_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-controller-manager\", instance=~\"$instance\"}[5m])) by (instance, name, le))",
"expr": "histogram_quantile(0.99, sum(rate(workqueue_queue_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-controller-manager\", instance=~\"$instance\"}[5m])) by (cluster, instance, name, le))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{`{{`}}instance{{`}}`}} {{`{{`}}name{{`}}`}}",
"legendFormat": "{{`{{`}}cluster{{`}}`}} {{`{{`}}instance{{`}}`}} {{`{{`}}name{{`}}`}}",
"refId": "A"
}
],
charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-resources-cluster.yaml
+5 -5
View File
@@ -1,5 +1,5 @@
{{- /*
Generated from 'k8s-resources-cluster' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/grafana-dashboardDefinitions.yaml
Generated from 'k8s-resources-cluster' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/grafana-dashboardDefinitions.yaml
Do not change in-place! In order to change this file first read following link:
https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack
*/ -}}
@@ -594,7 +594,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\"}) by (namespace)",
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\"}) by (namespace)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{`{{`}}namespace{{`}}`}}",
@@ -885,7 +885,7 @@ data:
"step": 10
},
{
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\"}) by (namespace)",
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\"}) by (namespace)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -903,7 +903,7 @@ data:
"step": 10
},
{
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\"}) by (namespace) / sum(kube_pod_container_resource_requests{cluster=\"$cluster\", resource=\"cpu\"}) by (namespace)",
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\"}) by (namespace) / sum(kube_pod_container_resource_requests{cluster=\"$cluster\", resource=\"cpu\"}) by (namespace)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -921,7 +921,7 @@ data:
"step": 10
},
{
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\"}) by (namespace) / sum(kube_pod_container_resource_limits{cluster=\"$cluster\", resource=\"cpu\"}) by (namespace)",
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\"}) by (namespace) / sum(kube_pod_container_resource_limits{cluster=\"$cluster\", resource=\"cpu\"}) by (namespace)",
"format": "table",
"instant": true,
"intervalFactor": 2,
charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-resources-namespace.yaml
+7 -7
View File
@@ -1,5 +1,5 @@
{{- /*
Generated from 'k8s-resources-namespace' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/grafana-dashboardDefinitions.yaml
Generated from 'k8s-resources-namespace' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/grafana-dashboardDefinitions.yaml
Do not change in-place! In order to change this file first read following link:
https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack
*/ -}}
@@ -78,7 +78,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}) / sum(kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"})",
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}) / sum(kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"})",
"format": "time_series",
"instant": true,
"intervalFactor": 2,
@@ -162,7 +162,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}) / sum(kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"})",
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}) / sum(kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"})",
"format": "time_series",
"instant": true,
"intervalFactor": 2,
@@ -446,7 +446,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)",
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{`{{`}}pod{{`}}`}}",
@@ -697,7 +697,7 @@ data:
],
"targets": [
{
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)",
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -715,7 +715,7 @@ data:
"step": 10
},
{
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod) / sum(kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}) by (pod)",
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod) / sum(kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -733,7 +733,7 @@ data:
"step": 10
},
{
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod) / sum(kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}) by (pod)",
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod) / sum(kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-resources-node.yaml
+5 -5
View File
@@ -1,5 +1,5 @@
{{- /*
Generated from 'k8s-resources-node' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/grafana-dashboardDefinitions.yaml
Generated from 'k8s-resources-node' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/grafana-dashboardDefinitions.yaml
Do not change in-place! In order to change this file first read following link:
https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack
*/ -}}
@@ -77,7 +77,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", node=~\"$node\"}) by (pod)",
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", node=~\"$node\"}) by (pod)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{`{{`}}pod{{`}}`}}",
@@ -312,7 +312,7 @@ data:
],
"targets": [
{
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", node=~\"$node\"}) by (pod)",
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", node=~\"$node\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -330,7 +330,7 @@ data:
"step": 10
},
{
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", node=~\"$node\"}) by (pod) / sum(kube_pod_container_resource_requests{cluster=\"$cluster\", node=~\"$node\", resource=\"cpu\"}) by (pod)",
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", node=~\"$node\"}) by (pod) / sum(kube_pod_container_resource_requests{cluster=\"$cluster\", node=~\"$node\", resource=\"cpu\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -348,7 +348,7 @@ data:
"step": 10
},
{
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", node=~\"$node\"}) by (pod) / sum(kube_pod_container_resource_limits{cluster=\"$cluster\", node=~\"$node\", resource=\"cpu\"}) by (pod)",
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", node=~\"$node\"}) by (pod) / sum(kube_pod_container_resource_limits{cluster=\"$cluster\", node=~\"$node\", resource=\"cpu\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-resources-pod.yaml
+5 -5
View File
@@ -1,5 +1,5 @@
{{- /*
Generated from 'k8s-resources-pod' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/grafana-dashboardDefinitions.yaml
Generated from 'k8s-resources-pod' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/grafana-dashboardDefinitions.yaml
Do not change in-place! In order to change this file first read following link:
https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack
*/ -}}
@@ -94,7 +94,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{namespace=\"$namespace\", pod=\"$pod\", cluster=\"$cluster\"}) by (container)",
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{namespace=\"$namespace\", pod=\"$pod\", cluster=\"$cluster\"}) by (container)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{`{{`}}container{{`}}`}}",
@@ -450,7 +450,7 @@ data:
],
"targets": [
{
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)",
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -468,7 +468,7 @@ data:
"step": 10
},
{
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container) / sum(kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"cpu\"}) by (container)",
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container) / sum(kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"cpu\"}) by (container)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -486,7 +486,7 @@ data:
"step": 10
},
{
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container) / sum(kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"cpu\"}) by (container)",
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container) / sum(kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"cpu\"}) by (container)",
"format": "table",
"instant": true,
"intervalFactor": 2,
charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-resources-workload.yaml
+5 -5
View File
@@ -1,5 +1,5 @@
{{- /*
Generated from 'k8s-resources-workload' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/grafana-dashboardDefinitions.yaml
Generated from 'k8s-resources-workload' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/grafana-dashboardDefinitions.yaml
Do not change in-place! In order to change this file first read following link:
https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack
*/ -}}
@@ -77,7 +77,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{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",
"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": "time_series",
"intervalFactor": 2,
"legendFormat": "{{`{{`}}pod{{`}}`}}",
@@ -312,7 +312,7 @@ data:
],
"targets": [
{
"expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{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",
"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,
"intervalFactor": 2,
@@ -330,7 +330,7 @@ data:
"step": 10
},
{
"expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
"expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -348,7 +348,7 @@ data:
"step": 10
},
{
"expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
"expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-resources-workloads-namespace.yaml
+5 -5
View File
@@ -1,5 +1,5 @@
{{- /*
Generated from 'k8s-resources-workloads-namespace' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/grafana-dashboardDefinitions.yaml
Generated from 'k8s-resources-workloads-namespace' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/grafana-dashboardDefinitions.yaml
Do not change in-place! In order to change this file first read following link:
https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack
*/ -}}
@@ -98,7 +98,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{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=\"$type\"}\n) by (workload, workload_type)\n",
"expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$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": "time_series",
"intervalFactor": 2,
"legendFormat": "{{`{{`}}workload{{`}}`}} - {{`{{`}}workload_type{{`}}`}}",
@@ -396,7 +396,7 @@ data:
"step": 10
},
{
"expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{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=\"$type\"}\n) by (workload, workload_type)\n",
"expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$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,
"intervalFactor": 2,
@@ -414,7 +414,7 @@ data:
"step": 10
},
{
"expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
"expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -432,7 +432,7 @@ data:
"step": 10
},
{
"expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
"expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/kubelet.yaml
+2091 -2376
View File
File diff suppressed because it is too large Load Diff
charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/namespace-by-pod.yaml
+1 -1
View File
@@ -1,5 +1,5 @@
{{- /*
Generated from 'namespace-by-pod' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/grafana-dashboardDefinitions.yaml
Generated from 'namespace-by-pod' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/grafana-dashboardDefinitions.yaml
Do not change in-place! In order to change this file first read following link:
https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack
*/ -}}
charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/namespace-by-workload.yaml
+1 -1
View File
@@ -1,5 +1,5 @@
{{- /*
Generated from 'namespace-by-workload' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/grafana-dashboardDefinitions.yaml
Generated from 'namespace-by-workload' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/grafana-dashboardDefinitions.yaml
Do not change in-place! In order to change this file first read following link:
https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack
*/ -}}
charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/node-cluster-rsrc-use.yaml
+1 -1
View File
@@ -1,5 +1,5 @@
{{- /*
Generated from 'node-cluster-rsrc-use' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/grafana-dashboardDefinitions.yaml
Generated from 'node-cluster-rsrc-use' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/grafana-dashboardDefinitions.yaml
Do not change in-place! In order to change this file first read following link:
https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack
*/ -}}
charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/node-rsrc-use.yaml
+1 -1
View File
@@ -1,5 +1,5 @@
{{- /*
Generated from 'node-rsrc-use' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/grafana-dashboardDefinitions.yaml
Generated from 'node-rsrc-use' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/grafana-dashboardDefinitions.yaml
Do not change in-place! In order to change this file first read following link:
https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack
*/ -}}
charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/nodes.yaml
+1 -1
View File
@@ -1,5 +1,5 @@
{{- /*
Generated from 'nodes' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/grafana-dashboardDefinitions.yaml
Generated from 'nodes' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/grafana-dashboardDefinitions.yaml
Do not change in-place! In order to change this file first read following link:
https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack
*/ -}}
charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/persistentvolumesusage.yaml
+1 -1
View File
@@ -1,5 +1,5 @@
{{- /*
Generated from 'persistentvolumesusage' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/grafana-dashboardDefinitions.yaml
Generated from 'persistentvolumesusage' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/grafana-dashboardDefinitions.yaml
Do not change in-place! In order to change this file first read following link:
https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack
*/ -}}
charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/pod-total.yaml
+1 -1
View File
@@ -1,5 +1,5 @@
{{- /*
Generated from 'pod-total' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/grafana-dashboardDefinitions.yaml
Generated from 'pod-total' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/grafana-dashboardDefinitions.yaml
Do not change in-place! In order to change this file first read following link:
https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack
*/ -}}
charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/prometheus-remote-write.yaml
+1 -1
View File
@@ -1,5 +1,5 @@
{{- /*
Generated from 'prometheus-remote-write' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/grafana-dashboardDefinitions.yaml
Generated from 'prometheus-remote-write' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/grafana-dashboardDefinitions.yaml
Do not change in-place! In order to change this file first read following link:
https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack
*/ -}}
charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/prometheus.yaml
+1 -1
View File
@@ -1,5 +1,5 @@
{{- /*
Generated from 'prometheus' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/grafana-dashboardDefinitions.yaml
Generated from 'prometheus' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/grafana-dashboardDefinitions.yaml
Do not change in-place! In order to change this file first read following link:
https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack
*/ -}}
charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/proxy.yaml
+1 -1
View File
@@ -1,5 +1,5 @@
{{- /*
Generated from 'proxy' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/grafana-dashboardDefinitions.yaml
Generated from 'proxy' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/grafana-dashboardDefinitions.yaml
Do not change in-place! In order to change this file first read following link:
https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack
*/ -}}
charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/scheduler.yaml
+17 -17
View File
@@ -1,5 +1,5 @@
{{- /*
Generated from 'scheduler' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/grafana-dashboardDefinitions.yaml
Generated from 'scheduler' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/grafana-dashboardDefinitions.yaml
Do not change in-place! In order to change this file first read following link:
https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack
*/ -}}
@@ -176,31 +176,31 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(scheduler_e2e_scheduling_duration_seconds_count{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[5m])) by (instance)",
"expr": "sum(rate(scheduler_e2e_scheduling_duration_seconds_count{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[5m])) by (cluster, instance)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{`{{`}}instance{{`}}`}} e2e",
"legendFormat": "{{`{{`}}cluster{{`}}`}} {{`{{`}}instance{{`}}`}} e2e",
"refId": "A"
},
{
"expr": "sum(rate(scheduler_binding_duration_seconds_count{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[5m])) by (instance)",
"expr": "sum(rate(scheduler_binding_duration_seconds_count{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[5m])) by (cluster, instance)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{`{{`}}instance{{`}}`}} binding",
"legendFormat": "{{`{{`}}cluster{{`}}`}} {{`{{`}}instance{{`}}`}} binding",
"refId": "B"
},
{
"expr": "sum(rate(scheduler_scheduling_algorithm_duration_seconds_count{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[5m])) by (instance)",
"expr": "sum(rate(scheduler_scheduling_algorithm_duration_seconds_count{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[5m])) by (cluster, instance)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{`{{`}}instance{{`}}`}} scheduling algorithm",
"legendFormat": "{{`{{`}}cluster{{`}}`}} {{`{{`}}instance{{`}}`}} scheduling algorithm",
"refId": "C"
},
{
"expr": "sum(rate(scheduler_volume_scheduling_duration_seconds_count{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[5m])) by (instance)",
"expr": "sum(rate(scheduler_volume_scheduling_duration_seconds_count{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[5m])) by (cluster, instance)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{`{{`}}instance{{`}}`}} volume",
"legendFormat": "{{`{{`}}cluster{{`}}`}} {{`{{`}}instance{{`}}`}} volume",
"refId": "D"
}
],
@@ -290,31 +290,31 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "histogram_quantile(0.99, sum(rate(scheduler_e2e_scheduling_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\",instance=~\"$instance\"}[5m])) by (instance, le))",
"expr": "histogram_quantile(0.99, sum(rate(scheduler_e2e_scheduling_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\",instance=~\"$instance\"}[5m])) by (cluster, instance, le))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{`{{`}}instance{{`}}`}} e2e",
"legendFormat": "{{`{{`}}cluster{{`}}`}} {{`{{`}}instance{{`}}`}} e2e",
"refId": "A"
},
{
"expr": "histogram_quantile(0.99, sum(rate(scheduler_binding_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\",instance=~\"$instance\"}[5m])) by (instance, le))",
"expr": "histogram_quantile(0.99, sum(rate(scheduler_binding_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\",instance=~\"$instance\"}[5m])) by (cluster, instance, le))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{`{{`}}instance{{`}}`}} binding",
"legendFormat": "{{`{{`}}cluster{{`}}`}} {{`{{`}}instance{{`}}`}} binding",
"refId": "B"
},
{
"expr": "histogram_quantile(0.99, sum(rate(scheduler_scheduling_algorithm_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\",instance=~\"$instance\"}[5m])) by (instance, le))",
"expr": "histogram_quantile(0.99, sum(rate(scheduler_scheduling_algorithm_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\",instance=~\"$instance\"}[5m])) by (cluster, instance, le))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{`{{`}}instance{{`}}`}} scheduling algorithm",
"legendFormat": "{{`{{`}}cluster{{`}}`}} {{`{{`}}instance{{`}}`}} scheduling algorithm",
"refId": "C"
},
{
"expr": "histogram_quantile(0.99, sum(rate(scheduler_volume_scheduling_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\",instance=~\"$instance\"}[5m])) by (instance, le))",
"expr": "histogram_quantile(0.99, sum(rate(scheduler_volume_scheduling_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\",instance=~\"$instance\"}[5m])) by (cluster, instance, le))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{`{{`}}instance{{`}}`}} volume",
"legendFormat": "{{`{{`}}cluster{{`}}`}} {{`{{`}}instance{{`}}`}} volume",
"refId": "D"
}
],
charts/kube-prometheus-stack/templates/grafana/dashboards-1.14/workload-total.yaml
+1 -1
View File
@@ -1,5 +1,5 @@
{{- /*
Generated from 'workload-total' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/grafana-dashboardDefinitions.yaml
Generated from 'workload-total' from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/grafana-dashboardDefinitions.yaml
Do not change in-place! In order to change this file first read following link:
https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack
*/ -}}
charts/kube-prometheus-stack/templates/prometheus/rules-1.14/alertmanager.rules.yaml
+126 -21
View File
@@ -1,5 +1,5 @@
{{- /*
Generated from 'alertmanager.rules' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/prometheus-rules.yaml
Generated from 'alertmanager.rules' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/alertmanager-prometheusRule.yaml
Do not change in-place! In order to change this file first read following link:
https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack
*/ -}}
@@ -26,41 +26,146 @@ spec:
groups:
- name: alertmanager.rules
rules:
- alert: AlertmanagerConfigInconsistent
- alert: AlertmanagerFailedReload
annotations:
message: 'The configuration of the instances of the Alertmanager cluster `{{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.service {{`}}`}}` are out of sync.
{{`{{`}} range printf "alertmanager_config_hash{namespace=\"%s\",service=\"%s\"}" $labels.namespace $labels.service | query {{`}}`}}
Configuration hash for pod {{`{{`}} .Labels.pod {{`}}`}} is "{{`{{`}} printf "%.f" .Value {{`}}`}}"
{{`{{`}} end {{`}}`}}
'
expr: count by(namespace,service) (count_values by(namespace,service) ("config_hash", alertmanager_config_hash{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}"})) != 1
description: Configuration has failed to load for {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.pod{{`}}`}}.
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-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="{{ $alertmanagerJob }}",namespace="{{ $namespace }}"}[5m]) == 0
for: 10m
labels:
severity: critical
{{- if .Values.defaultRules.additionalRuleLabels }}
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
{{- end }}
- alert: AlertmanagerMembersInconsistent
annotations:
description: Alertmanager {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.pod{{`}}`}} has only found {{`{{`}} $value {{`}}`}} members of the {{`{{`}}$labels.job{{`}}`}} cluster.
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-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="{{ $alertmanagerJob }}",namespace="{{ $namespace }}"}[5m])
< on (namespace,service) group_left
count by (namespace,service) (max_over_time(alertmanager_cluster_members{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}"}[5m]))
for: 10m
labels:
severity: critical
{{- if .Values.defaultRules.additionalRuleLabels }}
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
{{- end }}
- alert: AlertmanagerFailedToSendAlerts
annotations:
description: Alertmanager {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.pod{{`}}`}} failed to send {{`{{`}} $value | humanizePercentage {{`}}`}} of notifications to {{`{{`}} $labels.integration {{`}}`}}.
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-alertmanagerfailedtosendalerts
summary: An Alertmanager instance failed to send notifications.
expr: |-
(
rate(alertmanager_notifications_failed_total{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}"}[5m])
/
rate(alertmanager_notifications_total{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}"}[5m])
)
> 0.01
for: 5m
labels:
severity: warning
{{- if .Values.defaultRules.additionalRuleLabels }}
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
{{- end }}
- 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: {{ .Values.defaultRules.runbookUrl }}alert-name-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="{{ $alertmanagerJob }}",namespace="{{ $namespace }}", integration=~`.*`}[5m])
/
rate(alertmanager_notifications_total{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}", integration=~`.*`}[5m])
)
> 0.01
for: 5m
labels:
severity: critical
{{- if .Values.defaultRules.additionalRuleLabels }}
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
{{- end }}
- alert: AlertmanagerFailedReload
- alert: AlertmanagerClusterFailedToSendAlerts
annotations:
message: Reloading Alertmanager's configuration has failed for {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.pod{{`}}`}}.
expr: alertmanager_config_last_reload_successful{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}"} == 0
for: 10m
description: The minimum notification failure rate to {{`{{`}} $labels.integration {{`}}`}} sent from any instance in the {{`{{`}}$labels.job{{`}}`}} cluster is {{`{{`}} $value | humanizePercentage {{`}}`}}.
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-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="{{ $alertmanagerJob }}",namespace="{{ $namespace }}", integration!~`.*`}[5m])
/
rate(alertmanager_notifications_total{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}", integration!~`.*`}[5m])
)
> 0.01
for: 5m
labels:
severity: warning
{{- if .Values.defaultRules.additionalRuleLabels }}
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
{{- end }}
- alert: AlertmanagerMembersInconsistent
- alert: AlertmanagerConfigInconsistent
annotations:
message: Alertmanager has not found all other members of the cluster.
description: Alertmanager instances within the {{`{{`}}$labels.job{{`}}`}} cluster have different configurations.
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-alertmanagerconfiginconsistent
summary: Alertmanager instances within the same cluster have different configurations.
expr: |-
alertmanager_cluster_members{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}"}
!= on (service) GROUP_LEFT()
count by (service) (alertmanager_cluster_members{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}"})
count by (namespace,service) (
count_values by (namespace,service) ("config_hash", alertmanager_config_hash{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}"})
)
!= 1
for: 20m
labels:
severity: critical
{{- if .Values.defaultRules.additionalRuleLabels }}
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
{{- end }}
- 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: {{ .Values.defaultRules.runbookUrl }}alert-name-alertmanagerclusterdown
summary: Half or more of the Alertmanager instances within the same cluster are down.
expr: |-
(
count by (namespace,service) (
avg_over_time(up{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}"}[5m]) < 0.5
)
/
count by (namespace,service) (
up{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}"}
)
)
>= 0.5
for: 5m
labels:
severity: critical
{{- if .Values.defaultRules.additionalRuleLabels }}
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
{{- end }}
- 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: {{ .Values.defaultRules.runbookUrl }}alert-name-alertmanagerclustercrashlooping
summary: Half or more of the Alertmanager instances within the same cluster are crashlooping.
expr: |-
(
count by (namespace,service) (
changes(process_start_time_seconds{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}"}[10m]) > 4
)
/
count by (namespace,service) (
up{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}"}
)
)
>= 0.5
for: 5m
labels:
severity: critical
charts/kube-prometheus-stack/templates/prometheus/rules-1.14/general.rules.yaml
+7 -3
View File
@@ -1,5 +1,5 @@
{{- /*
Generated from 'general.rules' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/prometheus-rules.yaml
Generated from 'general.rules' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/kube-prometheus-prometheusRule.yaml
Do not change in-place! In order to change this file first read following link:
https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack
*/ -}}
@@ -26,7 +26,9 @@ spec:
rules:
- alert: TargetDown
annotations:
message: '{{`{{`}} printf "%.4g" $value {{`}}`}}% of the {{`{{`}} $labels.job {{`}}`}}/{{`{{`}} $labels.service {{`}}`}} targets in {{`{{`}} $labels.namespace {{`}}`}} namespace are down.'
description: '{{`{{`}} printf "%.4g" $value {{`}}`}}% of the {{`{{`}} $labels.job {{`}}`}}/{{`{{`}} $labels.service {{`}}`}} targets in {{`{{`}} $labels.namespace {{`}}`}} namespace are down.'
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-targetdown
summary: One or more targets are unreachable.
expr: 100 * (count(up == 0) BY (job, namespace, service) / count(up) BY (job, namespace, service)) > 10
for: 10m
labels:
@@ -36,7 +38,7 @@ spec:
{{- end }}
- alert: Watchdog
annotations:
message: 'This is an alert meant to ensure that the entire alerting pipeline is functional.
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
@@ -47,6 +49,8 @@ spec:
"DeadMansSnitch" integration in PagerDuty.
'
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-watchdog
summary: An alert that should always be firing to certify that Alertmanager is working properly.
expr: vector(1)
labels:
severity: none
charts/kube-prometheus-stack/templates/prometheus/rules-1.14/k8s.rules.yaml
+3 -3
View File
@@ -1,5 +1,5 @@
{{- /*
Generated from 'k8s.rules' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/kubernetes-prometheusRule.yaml
Generated from 'k8s.rules' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/kubernetes-prometheusRule.yaml
Do not change in-place! In order to change this file first read following link:
https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack
*/ -}}
@@ -26,11 +26,11 @@ spec:
rules:
- expr: |-
sum by (cluster, namespace, pod, container) (
rate(container_cpu_usage_seconds_total{job="kubelet", metrics_path="/metrics/cadvisor", image!=""}[5m])
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_rate
record: node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate
- expr: |-
container_memory_working_set_bytes{job="kubelet", metrics_path="/metrics/cadvisor", image!=""}
* on (namespace, pod) group_left(node) topk by(namespace, pod) (1,
charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kube-apiserver-availability.rules.yaml
+1 -1
View File
@@ -1,5 +1,5 @@
{{- /*
Generated from 'kube-apiserver-availability.rules' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/kubernetes-prometheusRule.yaml
Generated from 'kube-apiserver-availability.rules' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/kubernetes-prometheusRule.yaml
Do not change in-place! In order to change this file first read following link:
https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack
*/ -}}
charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kube-apiserver-slos.yaml
+1 -1
View File
@@ -1,5 +1,5 @@
{{- /*
Generated from 'kube-apiserver-slos' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/kubernetes-prometheusRule.yaml
Generated from 'kube-apiserver-slos' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/kubernetes-prometheusRule.yaml
Do not change in-place! In order to change this file first read following link:
https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack
*/ -}}
charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kube-apiserver.rules.yaml
+1 -1
View File
@@ -1,5 +1,5 @@
{{- /*
Generated from 'kube-apiserver.rules' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/kubernetes-prometheusRule.yaml
Generated from 'kube-apiserver.rules' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/kubernetes-prometheusRule.yaml
Do not change in-place! In order to change this file first read following link:
https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack
*/ -}}
charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kube-prometheus-general.rules.yaml
+1 -1
View File
@@ -1,5 +1,5 @@
{{- /*
Generated from 'kube-prometheus-general.rules' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/prometheus-rules.yaml
Generated from 'kube-prometheus-general.rules' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/kube-prometheus-prometheusRule.yaml
Do not change in-place! In order to change this file first read following link:
https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack
*/ -}}
charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kube-prometheus-node-recording.rules.yaml
+1 -1
View File
@@ -1,5 +1,5 @@
{{- /*
Generated from 'kube-prometheus-node-recording.rules' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/prometheus-rules.yaml
Generated from 'kube-prometheus-node-recording.rules' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/kube-prometheus-prometheusRule.yaml
Do not change in-place! In order to change this file first read following link:
https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack
*/ -}}
charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kube-scheduler.rules.yaml
+1 -1
View File
@@ -1,5 +1,5 @@
{{- /*
Generated from 'kube-scheduler.rules' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/kubernetes-prometheusRule.yaml
Generated from 'kube-scheduler.rules' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/kubernetes-prometheusRule.yaml
Do not change in-place! In order to change this file first read following link:
https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack
*/ -}}
charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kube-state-metrics.yaml
+29 -1
View File
@@ -1,5 +1,5 @@
{{- /*
Generated from 'kube-state-metrics' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/prometheus-rules.yaml
Generated from 'kube-state-metrics' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/kube-state-metrics-prometheusRule.yaml
Do not change in-place! In order to change this file first read following link:
https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack
*/ -}}
@@ -55,5 +55,33 @@ spec:
severity: critical
{{- if .Values.defaultRules.additionalRuleLabels }}
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
{{- end }}
- 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: {{ .Values.defaultRules.runbookUrl }}alert-name-kubestatemetricsshardingmismatch
summary: kube-state-metrics sharding is misconfigured.
expr: stdvar (kube_state_metrics_total_shards{job="kube-state-metrics"}) != 0
for: 15m
labels:
severity: critical
{{- if .Values.defaultRules.additionalRuleLabels }}
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
{{- end }}
- alert: KubeStateMetricsShardsMissing
annotations:
description: kube-state-metrics shards are missing, some Kubernetes objects are not being exposed.
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubestatemetricsshardsmissing
summary: kube-state-metrics shards are missing.
expr: |-
2^max(kube_state_metrics_total_shards{job="kube-state-metrics"}) - 1
-
sum( 2 ^ max by (shard_ordinal) (kube_state_metrics_shard_ordinal{job="kube-state-metrics"}) )
!= 0
for: 15m
labels:
severity: critical
{{- if .Values.defaultRules.additionalRuleLabels }}
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
{{- end }}
{{- end }}
charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kubelet.rules.yaml
+1 -1
View File
@@ -1,5 +1,5 @@
{{- /*
Generated from 'kubelet.rules' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/kubernetes-prometheusRule.yaml
Generated from 'kubelet.rules' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/kubernetes-prometheusRule.yaml
Do not change in-place! In order to change this file first read following link:
https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack
*/ -}}
charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-apps.yaml
+2 -2
View File
@@ -1,5 +1,5 @@
{{- /*
Generated from 'kubernetes-apps' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/kubernetes-prometheusRule.yaml
Generated from 'kubernetes-apps' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/kubernetes-prometheusRule.yaml
Do not change in-place! In order to change this file first read following link:
https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack
*/ -}}
@@ -30,7 +30,7 @@ spec:
description: Pod {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.pod {{`}}`}} ({{`{{`}} $labels.container {{`}}`}}) is restarting {{`{{`}} printf "%.2f" $value {{`}}`}} times / 10 minutes.
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubepodcrashlooping
summary: Pod is crash looping.
expr: rate(kube_pod_container_status_restarts_total{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"}[10m]) * 60 * 5 > 0
expr: increase(kube_pod_container_status_restarts_total{job="kube-state-metrics", namespace=~"{{ $targetNamespace }}"}[10m]) > 0
for: 15m
labels:
severity: warning
charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-resources.yaml
+1 -1
View File
@@ -1,5 +1,5 @@
{{- /*
Generated from 'kubernetes-resources' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/kubernetes-prometheusRule.yaml
Generated from 'kubernetes-resources' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/kubernetes-prometheusRule.yaml
Do not change in-place! In order to change this file first read following link:
https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack
*/ -}}
charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-storage.yaml
+1 -1
View File
@@ -1,5 +1,5 @@
{{- /*
Generated from 'kubernetes-storage' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/kubernetes-prometheusRule.yaml
Generated from 'kubernetes-storage' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/kubernetes-prometheusRule.yaml
Do not change in-place! In order to change this file first read following link:
https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack
*/ -}}
charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-system-apiserver.yaml
+1 -1
View File
@@ -1,5 +1,5 @@
{{- /*
Generated from 'kubernetes-system-apiserver' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/kubernetes-prometheusRule.yaml
Generated from 'kubernetes-system-apiserver' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/kubernetes-prometheusRule.yaml
Do not change in-place! In order to change this file first read following link:
https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack
*/ -}}
charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-system-controller-manager.yaml
+1 -1
View File
@@ -1,5 +1,5 @@
{{- /*
Generated from 'kubernetes-system-controller-manager' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/kubernetes-prometheusRule.yaml
Generated from 'kubernetes-system-controller-manager' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/kubernetes-prometheusRule.yaml
Do not change in-place! In order to change this file first read following link:
https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack
*/ -}}
charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-system-kubelet.yaml
+1 -1
View File
@@ -1,5 +1,5 @@
{{- /*
Generated from 'kubernetes-system-kubelet' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/kubernetes-prometheusRule.yaml
Generated from 'kubernetes-system-kubelet' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/kubernetes-prometheusRule.yaml
Do not change in-place! In order to change this file first read following link:
https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack
*/ -}}
charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-system-scheduler.yaml
+1 -1
View File
@@ -1,5 +1,5 @@
{{- /*
Generated from 'kubernetes-system-scheduler' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/kubernetes-prometheusRule.yaml
Generated from 'kubernetes-system-scheduler' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/kubernetes-prometheusRule.yaml
Do not change in-place! In order to change this file first read following link:
https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack
*/ -}}
charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-system.yaml
+1 -1
View File
@@ -1,5 +1,5 @@
{{- /*
Generated from 'kubernetes-system' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/kubernetes-prometheusRule.yaml
Generated from 'kubernetes-system' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/kubernetes-prometheusRule.yaml
Do not change in-place! In order to change this file first read following link:
https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack
*/ -}}
charts/kube-prometheus-stack/templates/prometheus/rules-1.14/node-exporter.rules.yaml
+17 -17
View File
@@ -1,5 +1,5 @@
{{- /*
Generated from 'node-exporter.rules' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/node-exporter-prometheusRule.yaml
Generated from 'node-exporter.rules' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/node-exporter-prometheusRule.yaml
Do not change in-place! In order to change this file first read following link:
https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack
*/ -}}
@@ -33,9 +33,9 @@ spec:
record: instance:node_num_cpu:sum
- expr: |-
1 - avg without (cpu, mode) (
rate(node_cpu_seconds_total{job="node-exporter", mode="idle"}[1m])
rate(node_cpu_seconds_total{job="node-exporter", mode="idle"}[5m])
)
record: instance:node_cpu_utilisation:rate1m
record: instance:node_cpu_utilisation:rate5m
- expr: |-
(
node_load1{job="node-exporter"}
@@ -50,30 +50,30 @@ spec:
node_memory_MemTotal_bytes{job="node-exporter"}
)
record: instance:node_memory_utilisation:ratio
- expr: rate(node_vmstat_pgmajfault{job="node-exporter"}[1m])
record: instance:node_vmstat_pgmajfault:rate1m
- expr: rate(node_disk_io_time_seconds_total{job="node-exporter", device=~"mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+"}[1m])
record: instance_device:node_disk_io_time_seconds:rate1m
- expr: rate(node_disk_io_time_weighted_seconds_total{job="node-exporter", device=~"mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+"}[1m])
record: instance_device:node_disk_io_time_weighted_seconds:rate1m
- 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=~"mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+"}[5m])
record: instance_device:node_disk_io_time_seconds:rate5m
- expr: rate(node_disk_io_time_weighted_seconds_total{job="node-exporter", device=~"mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|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"}[1m])
rate(node_network_receive_bytes_total{job="node-exporter", device!="lo"}[5m])
)
record: instance:node_network_receive_bytes_excluding_lo:rate1m
record: instance:node_network_receive_bytes_excluding_lo:rate5m
- expr: |-
sum without (device) (
rate(node_network_transmit_bytes_total{job="node-exporter", device!="lo"}[1m])
rate(node_network_transmit_bytes_total{job="node-exporter", device!="lo"}[5m])
)
record: instance:node_network_transmit_bytes_excluding_lo:rate1m
record: instance:node_network_transmit_bytes_excluding_lo:rate5m
- expr: |-
sum without (device) (
rate(node_network_receive_drop_total{job="node-exporter", device!="lo"}[1m])
rate(node_network_receive_drop_total{job="node-exporter", device!="lo"}[5m])
)
record: instance:node_network_receive_drop_excluding_lo:rate1m
record: instance:node_network_receive_drop_excluding_lo:rate5m
- expr: |-
sum without (device) (
rate(node_network_transmit_drop_total{job="node-exporter", device!="lo"}[1m])
rate(node_network_transmit_drop_total{job="node-exporter", device!="lo"}[5m])
)
record: instance:node_network_transmit_drop_excluding_lo:rate1m
record: instance:node_network_transmit_drop_excluding_lo:rate5m
{{- end }}
charts/kube-prometheus-stack/templates/prometheus/rules-1.14/node-exporter.yaml
+20 -4
View File
@@ -1,5 +1,5 @@
{{- /*
Generated from 'node-exporter' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/node-exporter-prometheusRule.yaml
Generated from 'node-exporter' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/node-exporter-prometheusRule.yaml
Do not change in-place! In order to change this file first read following link:
https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack
*/ -}}
@@ -27,6 +27,7 @@ spec:
- alert: NodeFilesystemSpaceFillingUp
annotations:
description: Filesystem on {{`{{`}} $labels.device {{`}}`}} at {{`{{`}} $labels.instance {{`}}`}} has only {{`{{`}} printf "%.2f" $value {{`}}`}}% available space left and is filling up.
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-nodefilesystemspacefillingup
summary: Filesystem is predicted to run out of space within the next 24 hours.
expr: |-
(
@@ -45,6 +46,7 @@ spec:
- alert: NodeFilesystemSpaceFillingUp
annotations:
description: Filesystem on {{`{{`}} $labels.device {{`}}`}} at {{`{{`}} $labels.instance {{`}}`}} has only {{`{{`}} printf "%.2f" $value {{`}}`}}% available space left and is filling up fast.
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-nodefilesystemspacefillingup
summary: Filesystem is predicted to run out of space within the next 4 hours.
expr: |-
(
@@ -63,6 +65,7 @@ spec:
- alert: NodeFilesystemAlmostOutOfSpace
annotations:
description: Filesystem on {{`{{`}} $labels.device {{`}}`}} at {{`{{`}} $labels.instance {{`}}`}} has only {{`{{`}} printf "%.2f" $value {{`}}`}}% available space left.
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-nodefilesystemalmostoutofspace
summary: Filesystem has less than 5% space left.
expr: |-
(
@@ -79,6 +82,7 @@ spec:
- alert: NodeFilesystemAlmostOutOfSpace
annotations:
description: Filesystem on {{`{{`}} $labels.device {{`}}`}} at {{`{{`}} $labels.instance {{`}}`}} has only {{`{{`}} printf "%.2f" $value {{`}}`}}% available space left.
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-nodefilesystemalmostoutofspace
summary: Filesystem has less than 3% space left.
expr: |-
(
@@ -95,6 +99,7 @@ spec:
- alert: NodeFilesystemFilesFillingUp
annotations:
description: Filesystem on {{`{{`}} $labels.device {{`}}`}} at {{`{{`}} $labels.instance {{`}}`}} has only {{`{{`}} printf "%.2f" $value {{`}}`}}% available inodes left and is filling up.
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-nodefilesystemfilesfillingup
summary: Filesystem is predicted to run out of inodes within the next 24 hours.
expr: |-
(
@@ -113,6 +118,7 @@ spec:
- alert: NodeFilesystemFilesFillingUp
annotations:
description: Filesystem on {{`{{`}} $labels.device {{`}}`}} at {{`{{`}} $labels.instance {{`}}`}} has only {{`{{`}} printf "%.2f" $value {{`}}`}}% available inodes left and is filling up fast.
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-nodefilesystemfilesfillingup
summary: Filesystem is predicted to run out of inodes within the next 4 hours.
expr: |-
(
@@ -131,6 +137,7 @@ spec:
- alert: NodeFilesystemAlmostOutOfFiles
annotations:
description: Filesystem on {{`{{`}} $labels.device {{`}}`}} at {{`{{`}} $labels.instance {{`}}`}} has only {{`{{`}} printf "%.2f" $value {{`}}`}}% available inodes left.
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-nodefilesystemalmostoutoffiles
summary: Filesystem has less than 5% inodes left.
expr: |-
(
@@ -147,6 +154,7 @@ spec:
- alert: NodeFilesystemAlmostOutOfFiles
annotations:
description: Filesystem on {{`{{`}} $labels.device {{`}}`}} at {{`{{`}} $labels.instance {{`}}`}} has only {{`{{`}} printf "%.2f" $value {{`}}`}}% available inodes left.
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-nodefilesystemalmostoutoffiles
summary: Filesystem has less than 3% inodes left.
expr: |-
(
@@ -163,6 +171,7 @@ spec:
- alert: NodeNetworkReceiveErrs
annotations:
description: '{{`{{`}} $labels.instance {{`}}`}} interface {{`{{`}} $labels.device {{`}}`}} has encountered {{`{{`}} printf "%.0f" $value {{`}}`}} receive errors in the last two minutes.'
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-nodenetworkreceiveerrs
summary: Network interface is reporting many receive errors.
expr: rate(node_network_receive_errs_total[2m]) / rate(node_network_receive_packets_total[2m]) > 0.01
for: 1h
@@ -174,6 +183,7 @@ spec:
- alert: NodeNetworkTransmitErrs
annotations:
description: '{{`{{`}} $labels.instance {{`}}`}} interface {{`{{`}} $labels.device {{`}}`}} has encountered {{`{{`}} printf "%.0f" $value {{`}}`}} transmit errors in the last two minutes.'
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-nodenetworktransmiterrs
summary: Network interface is reporting many transmit errors.
expr: rate(node_network_transmit_errs_total[2m]) / rate(node_network_transmit_packets_total[2m]) > 0.01
for: 1h
@@ -185,6 +195,7 @@ spec:
- alert: NodeHighNumberConntrackEntriesUsed
annotations:
description: '{{`{{`}} $value | humanizePercentage {{`}}`}} of conntrack entries are used.'
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-nodehighnumberconntrackentriesused
summary: Number of conntrack are getting close to the limit.
expr: (node_nf_conntrack_entries / node_nf_conntrack_entries_limit) > 0.75
labels:
@@ -195,6 +206,7 @@ spec:
- alert: NodeTextFileCollectorScrapeError
annotations:
description: Node Exporter text file collector failed to scrape.
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-nodetextfilecollectorscrapeerror
summary: Node Exporter text file collector failed to scrape.
expr: node_textfile_scrape_error{job="node-exporter"} == 1
labels:
@@ -204,7 +216,8 @@ spec:
{{- end }}
- alert: NodeClockSkewDetected
annotations:
message: Clock on {{`{{`}} $labels.instance {{`}}`}} is out of sync by more than 300s. Ensure NTP is configured correctly on this host.
description: Clock on {{`{{`}} $labels.instance {{`}}`}} is out of sync by more than 300s. Ensure NTP is configured correctly on this host.
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-nodeclockskewdetected
summary: Clock skew detected.
expr: |-
(
@@ -226,7 +239,8 @@ spec:
{{- end }}
- alert: NodeClockNotSynchronising
annotations:
message: Clock on {{`{{`}} $labels.instance {{`}}`}} is not synchronising. Ensure NTP is configured on this host.
description: Clock on {{`{{`}} $labels.instance {{`}}`}} is not synchronising. Ensure NTP is configured on this host.
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-nodeclocknotsynchronising
summary: Clock not synchronising.
expr: |-
min_over_time(node_timex_sync_status[5m]) == 0
@@ -241,6 +255,7 @@ spec:
- alert: NodeRAIDDegraded
annotations:
description: RAID array '{{`{{`}} $labels.device {{`}}`}}' on {{`{{`}} $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: {{ .Values.defaultRules.runbookUrl }}alert-name-noderaiddegraded
summary: RAID Array is degraded
expr: node_md_disks_required - ignoring (state) (node_md_disks{state="active"}) > 0
for: 15m
@@ -252,8 +267,9 @@ spec:
- alert: NodeRAIDDiskFailure
annotations:
description: At least one device in RAID array on {{`{{`}} $labels.instance {{`}}`}} failed. Array '{{`{{`}} $labels.device {{`}}`}}' needs attention and possibly a disk swap.
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-noderaiddiskfailure
summary: Failed device in RAID array
expr: node_md_disks{state="fail"} > 0
expr: node_md_disks{state="failed"} > 0
labels:
severity: warning
{{- if .Values.defaultRules.additionalRuleLabels }}
charts/kube-prometheus-stack/templates/prometheus/rules-1.14/node-network.yaml
+3 -2
View File
@@ -1,5 +1,5 @@
{{- /*
Generated from 'node-network' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/prometheus-rules.yaml
Generated from 'node-network' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/kube-prometheus-prometheusRule.yaml
Do not change in-place! In order to change this file first read following link:
https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack
*/ -}}
@@ -26,7 +26,8 @@ spec:
rules:
- alert: NodeNetworkInterfaceFlapping
annotations:
message: Network interface "{{`{{`}} $labels.device {{`}}`}}" changing it's up status often on node-exporter {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.pod {{`}}`}}"
message: Network interface "{{`{{`}} $labels.device {{`}}`}}" changing it's up status often on node-exporter {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.pod {{`}}`}}
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-nodenetworkinterfaceflapping
expr: changes(node_network_up{job="node-exporter",device!~"veth.+"}[2m]) > 2
for: 2m
labels:
charts/kube-prometheus-stack/templates/prometheus/rules-1.14/node.rules.yaml
+1 -1
View File
@@ -1,5 +1,5 @@
{{- /*
Generated from 'node.rules' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/kubernetes-prometheusRule.yaml
Generated from 'node.rules' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/kubernetes-prometheusRule.yaml
Do not change in-place! In order to change this file first read following link:
https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack
*/ -}}
charts/kube-prometheus-stack/templates/prometheus/rules-1.14/prometheus-operator.yaml
+1 -1
View File
@@ -1,5 +1,5 @@
{{- /*
Generated from 'prometheus-operator' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/prometheus-rules.yaml
Generated from 'prometheus-operator' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/prometheus-operator-prometheusRule.yaml
Do not change in-place! In order to change this file first read following link:
https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack
*/ -}}
charts/kube-prometheus-stack/templates/prometheus/rules-1.14/prometheus.yaml
+61 -24
View File
@@ -1,5 +1,5 @@
{{- /*
Generated from 'prometheus' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/prometheus-rules.yaml
Generated from 'prometheus' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/prometheus-prometheusRule.yaml
Do not change in-place! In order to change this file first read following link:
https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack
*/ -}}
@@ -29,6 +29,7 @@ spec:
- alert: PrometheusBadConfig
annotations:
description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} has failed to reload its configuration.
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-prometheusbadconfig
summary: Failed Prometheus configuration reload.
expr: |-
# Without max_over_time, failed scrapes could create false negatives, see
@@ -43,6 +44,7 @@ spec:
- alert: PrometheusNotificationQueueRunningFull
annotations:
description: Alert notification queue of Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} is running full.
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-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
@@ -61,6 +63,7 @@ spec:
- alert: PrometheusErrorSendingAlertsToSomeAlertmanagers
annotations:
description: '{{`{{`}} printf "%.1f" $value {{`}}`}}% errors while sending alerts from Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} to Alertmanager {{`{{`}}$labels.alertmanager{{`}}`}}.'
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-prometheuserrorsendingalertstosomealertmanagers
summary: Prometheus has encountered more than 1% errors sending alerts to a specific Alertmanager.
expr: |-
(
@@ -75,28 +78,11 @@ spec:
severity: warning
{{- if .Values.defaultRules.additionalRuleLabels }}
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
{{- end }}
- alert: PrometheusErrorSendingAlertsToAnyAlertmanager
annotations:
description: '{{`{{`}} printf "%.1f" $value {{`}}`}}% minimum errors while sending alerts from Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} to any Alertmanager.'
summary: Prometheus encounters more than 3% errors sending alerts to any Alertmanager.
expr: |-
min without(alertmanager) (
rate(prometheus_notifications_errors_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m])
/
rate(prometheus_notifications_sent_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m])
)
* 100
> 3
for: 15m
labels:
severity: critical
{{- if .Values.defaultRules.additionalRuleLabels }}
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
{{- end }}
- alert: PrometheusNotConnectedToAlertmanagers
annotations:
description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} is not connected to any Alertmanagers.
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-prometheusnotconnectedtoalertmanagers
summary: Prometheus is not connected to any Alertmanagers.
expr: |-
# Without max_over_time, failed scrapes could create false negatives, see
@@ -111,6 +97,7 @@ spec:
- alert: PrometheusTSDBReloadsFailing
annotations:
description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} has detected {{`{{`}}$value | humanize{{`}}`}} reload failures over the last 3h.
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-prometheustsdbreloadsfailing
summary: Prometheus has issues reloading blocks from disk.
expr: increase(prometheus_tsdb_reloads_failures_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[3h]) > 0
for: 4h
@@ -122,6 +109,7 @@ spec:
- alert: PrometheusTSDBCompactionsFailing
annotations:
description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} has detected {{`{{`}}$value | humanize{{`}}`}} compaction failures over the last 3h.
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-prometheustsdbcompactionsfailing
summary: Prometheus has issues compacting blocks.
expr: increase(prometheus_tsdb_compactions_failed_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[3h]) > 0
for: 4h
@@ -133,8 +121,18 @@ spec:
- alert: PrometheusNotIngestingSamples
annotations:
description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} is not ingesting samples.
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-prometheusnotingestingsamples
summary: Prometheus is not ingesting samples.
expr: rate(prometheus_tsdb_head_samples_appended_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) <= 0
expr: |-
(
rate(prometheus_tsdb_head_samples_appended_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) <= 0
and
(
sum without(scrape_job) (prometheus_target_metadata_cache_entries{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}) > 0
or
sum without(rule_group) (prometheus_rule_group_rules{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}) > 0
)
)
for: 10m
labels:
severity: warning
@@ -144,6 +142,7 @@ spec:
- alert: PrometheusDuplicateTimestamps
annotations:
description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} is dropping {{`{{`}} printf "%.4g" $value {{`}}`}} samples/s with different values but duplicated timestamp.
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-prometheusduplicatetimestamps
summary: Prometheus is dropping samples with duplicate timestamps.
expr: rate(prometheus_target_scrapes_sample_duplicate_timestamp_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) > 0
for: 10m
@@ -155,6 +154,7 @@ spec:
- alert: PrometheusOutOfOrderTimestamps
annotations:
description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} is dropping {{`{{`}} printf "%.4g" $value {{`}}`}} samples/s with timestamps arriving out of order.
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-prometheusoutofordertimestamps
summary: Prometheus drops samples with out-of-order timestamps.
expr: rate(prometheus_target_scrapes_sample_out_of_order_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) > 0
for: 10m
@@ -166,15 +166,16 @@ spec:
- alert: PrometheusRemoteStorageFailures
annotations:
description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} failed to send {{`{{`}} printf "%.1f" $value {{`}}`}}% of the samples to {{`{{`}} $labels.remote_name{{`}}`}}:{{`{{`}} $labels.url {{`}}`}}
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-prometheusremotestoragefailures
summary: Prometheus fails to send samples to remote storage.
expr: |-
(
rate(prometheus_remote_storage_failed_samples_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m])
(rate(prometheus_remote_storage_failed_samples_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) or rate(prometheus_remote_storage_samples_failed_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]))
/
(
rate(prometheus_remote_storage_failed_samples_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m])
(rate(prometheus_remote_storage_failed_samples_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) or rate(prometheus_remote_storage_samples_failed_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]))
+
rate(prometheus_remote_storage_succeeded_samples_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m])
(rate(prometheus_remote_storage_succeeded_samples_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) or rate(prometheus_remote_storage_samples_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]))
)
)
* 100
@@ -188,13 +189,14 @@ spec:
- alert: PrometheusRemoteWriteBehind
annotations:
description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} remote write is {{`{{`}} printf "%.1f" $value {{`}}`}}s behind for {{`{{`}} $labels.remote_name{{`}}`}}:{{`{{`}} $labels.url {{`}}`}}.
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-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="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m])
- on(job, instance) group_right
- ignoring(remote_name, url) group_right
max_over_time(prometheus_remote_storage_queue_highest_sent_timestamp_seconds{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m])
)
> 120
@@ -207,6 +209,7 @@ spec:
- alert: PrometheusRemoteWriteDesiredShards
annotations:
description: Prometheus {{`{{`}}$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="{{ $prometheusJob }}",namespace="{{ $namespace }}"}` $labels.instance | query | first | value {{`}}`}}.
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-prometheusremotewritedesiredshards
summary: Prometheus remote write desired shards calculation wants to run more than configured max shards.
expr: |-
# Without max_over_time, failed scrapes could create false negatives, see
@@ -225,6 +228,7 @@ spec:
- alert: PrometheusRuleFailures
annotations:
description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} has failed to evaluate {{`{{`}} printf "%.0f" $value {{`}}`}} rules in the last 5m.
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-prometheusrulefailures
summary: Prometheus is failing rule evaluations.
expr: increase(prometheus_rule_evaluation_failures_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) > 0
for: 15m
@@ -236,6 +240,7 @@ spec:
- alert: PrometheusMissingRuleEvaluations
annotations:
description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} has missed {{`{{`}} printf "%.0f" $value {{`}}`}} rule group evaluations in the last 5m.
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-prometheusmissingruleevaluations
summary: Prometheus is missing rule evaluations due to slow rule group evaluation.
expr: increase(prometheus_rule_group_iterations_missed_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) > 0
for: 15m
@@ -247,6 +252,7 @@ spec:
- alert: PrometheusTargetLimitHit
annotations:
description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} has dropped {{`{{`}} printf "%.0f" $value {{`}}`}} targets because the number of targets exceeded the configured target_limit.
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-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="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) > 0
for: 15m
@@ -254,5 +260,36 @@ spec:
severity: warning
{{- if .Values.defaultRules.additionalRuleLabels }}
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
{{- end }}
- alert: PrometheusLabelLimitHit
annotations:
description: Prometheus {{`{{`}}$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: {{ .Values.defaultRules.runbookUrl }}alert-name-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="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) > 0
for: 15m
labels:
severity: warning
{{- if .Values.defaultRules.additionalRuleLabels }}
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
{{- end }}
- alert: PrometheusErrorSendingAlertsToAnyAlertmanager
annotations:
description: '{{`{{`}} printf "%.1f" $value {{`}}`}}% minimum errors while sending alerts from Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} to any Alertmanager.'
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-prometheuserrorsendingalertstoanyalertmanager
summary: Prometheus encounters more than 3% errors sending alerts to any Alertmanager.
expr: |-
min without (alertmanager) (
rate(prometheus_notifications_errors_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}",alertmanager!~``}[5m])
/
rate(prometheus_notifications_sent_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}",alertmanager!~``}[5m])
)
* 100
> 3
for: 15m
labels:
severity: critical
{{- if .Values.defaultRules.additionalRuleLabels }}
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
{{- end }}
{{- end }}