mirror of https://git.rancher.io/charts
193 lines
9.4 KiB
YAML
193 lines
9.4 KiB
YAML
|
{{- /*
|
||
|
|
Generated from 'kubernetes-resources' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/kubernetesControlPlane-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
|
||
|
|
*/ -}}
|
||
|
|
{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }}
|
||
|
|
{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.defaultRules.create .Values.defaultRules.rules.kubernetesResources }}
|
||
|
|
apiVersion: monitoring.coreos.com/v1
|
||
|
|
kind: PrometheusRule
|
||
|
|
metadata:
|
||
|
|
name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "kubernetes-resources" | trunc 63 | trimSuffix "-" }}
|
||
|
|
namespace: {{ template "kube-prometheus-stack.namespace" . }}
|
||
|
|
labels:
|
||
|
|
app: {{ template "kube-prometheus-stack.name" . }}
|
||
|
|
{{ include "kube-prometheus-stack.labels" . | indent 4 }}
|
||
|
|
{{- if .Values.defaultRules.labels }}
|
||
|
|
{{ toYaml .Values.defaultRules.labels | indent 4 }}
|
||
|
|
{{- end }}
|
||
|
|
{{- if .Values.defaultRules.annotations }}
|
||
|
|
annotations:
|
||
|
|
{{ toYaml .Values.defaultRules.annotations | indent 4 }}
|
||
|
|
{{- end }}
|
||
|
|
spec:
|
||
|
|
groups:
|
||
|
|
- name: kubernetes-resources
|
||
|
|
rules:
|
||
|
|
{{- if not (.Values.defaultRules.disabled.KubeCPUOvercommit | default false) }}
|
||
|
|
- alert: KubeCPUOvercommit
|
||
|
|
annotations:
|
||
|
|
{{- if .Values.defaultRules.additionalRuleAnnotations }}
|
||
|
|
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
|
||
|
|
{{- end }}
|
||
|
|
description: Cluster has overcommitted CPU resource requests for Pods by {{`{{`}} $value {{`}}`}} CPU shares and cannot tolerate node failure.
|
||
|
|
runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/kubecpuovercommit
|
||
|
|
summary: Cluster has overcommitted CPU resource requests.
|
||
|
|
expr: |-
|
||
|
|
sum(namespace_cpu:kube_pod_container_resource_requests:sum{}) - (sum(kube_node_status_allocatable{resource="cpu"}) - max(kube_node_status_allocatable{resource="cpu"})) > 0
|
||
|
|
and
|
||
|
|
(sum(kube_node_status_allocatable{resource="cpu"}) - max(kube_node_status_allocatable{resource="cpu"})) > 0
|
||
|
|
for: 10m
|
||
|
|
labels:
|
||
|
|
severity: warning
|
||
|
|
{{- if .Values.defaultRules.additionalRuleLabels }}
|
||
|
|
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
|
||
|
|
{{- end }}
|
||
|
|
{{- end }}
|
||
|
|
{{- if not (.Values.defaultRules.disabled.KubeMemoryOvercommit | default false) }}
|
||
|
|
- alert: KubeMemoryOvercommit
|
||
|
|
annotations:
|
||
|
|
{{- if .Values.defaultRules.additionalRuleAnnotations }}
|
||
|
|
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
|
||
|
|
{{- end }}
|
||
|
|
description: Cluster has overcommitted memory resource requests for Pods by {{`{{`}} $value | humanize {{`}}`}} bytes and cannot tolerate node failure.
|
||
|
|
runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/kubememoryovercommit
|
||
|
|
summary: Cluster has overcommitted memory resource requests.
|
||
|
|
expr: |-
|
||
|
|
sum(namespace_memory:kube_pod_container_resource_requests:sum{}) - (sum(kube_node_status_allocatable{resource="memory"}) - max(kube_node_status_allocatable{resource="memory"})) > 0
|
||
|
|
and
|
||
|
|
(sum(kube_node_status_allocatable{resource="memory"}) - max(kube_node_status_allocatable{resource="memory"})) > 0
|
||
|
|
for: 10m
|
||
|
|
labels:
|
||
|
|
severity: warning
|
||
|
|
{{- if .Values.defaultRules.additionalRuleLabels }}
|
||
|
|
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
|
||
|
|
{{- end }}
|
||
|
|
{{- end }}
|
||
|
|
{{- if not (.Values.defaultRules.disabled.KubeCPUQuotaOvercommit | default false) }}
|
||
|
|
- alert: KubeCPUQuotaOvercommit
|
||
|
|
annotations:
|
||
|
|
{{- if .Values.defaultRules.additionalRuleAnnotations }}
|
||
|
|
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
|
||
|
|
{{- end }}
|
||
|
|
description: Cluster has overcommitted CPU resource requests for Namespaces.
|
||
|
|
runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/kubecpuquotaovercommit
|
||
|
|
summary: Cluster has overcommitted CPU resource requests.
|
||
|
|
expr: |-
|
||
|
|
sum(min without(resource) (kube_resourcequota{job="kube-state-metrics", type="hard", resource=~"(cpu|requests.cpu)"}))
|
||
|
|
/
|
||
|
|
sum(kube_node_status_allocatable{resource="cpu", job="kube-state-metrics"})
|
||
|
|
> 1.5
|
||
|
|
for: 5m
|
||
|
|
labels:
|
||
|
|
severity: warning
|
||
|
|
{{- if .Values.defaultRules.additionalRuleLabels }}
|
||
|
|
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
|
||
|
|
{{- end }}
|
||
|
|
{{- end }}
|
||
|
|
{{- if not (.Values.defaultRules.disabled.KubeMemoryQuotaOvercommit | default false) }}
|
||
|
|
- alert: KubeMemoryQuotaOvercommit
|
||
|
|
annotations:
|
||
|
|
{{- if .Values.defaultRules.additionalRuleAnnotations }}
|
||
|
|
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
|
||
|
|
{{- end }}
|
||
|
|
description: Cluster has overcommitted memory resource requests for Namespaces.
|
||
|
|
runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/kubememoryquotaovercommit
|
||
|
|
summary: Cluster has overcommitted memory resource requests.
|
||
|
|
expr: |-
|
||
|
|
sum(min without(resource) (kube_resourcequota{job="kube-state-metrics", type="hard", resource=~"(memory|requests.memory)"}))
|
||
|
|
/
|
||
|
|
sum(kube_node_status_allocatable{resource="memory", job="kube-state-metrics"})
|
||
|
|
> 1.5
|
||
|
|
for: 5m
|
||
|
|
labels:
|
||
|
|
severity: warning
|
||
|
|
{{- if .Values.defaultRules.additionalRuleLabels }}
|
||
|
|
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
|
||
|
|
{{- end }}
|
||
|
|
{{- end }}
|
||
|
|
{{- if not (.Values.defaultRules.disabled.KubeQuotaAlmostFull | default false) }}
|
||
|
|
- alert: KubeQuotaAlmostFull
|
||
|
|
annotations:
|
||
|
|
{{- if .Values.defaultRules.additionalRuleAnnotations }}
|
||
|
|
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
|
||
|
|
{{- end }}
|
||
|
|
description: Namespace {{`{{`}} $labels.namespace {{`}}`}} is using {{`{{`}} $value | humanizePercentage {{`}}`}} of its {{`{{`}} $labels.resource {{`}}`}} quota.
|
||
|
|
runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/kubequotaalmostfull
|
||
|
|
summary: Namespace quota is going to be full.
|
||
|
|
expr: |-
|
||
|
|
kube_resourcequota{job="kube-state-metrics", type="used"}
|
||
|
|
/ ignoring(instance, job, type)
|
||
|
|
(kube_resourcequota{job="kube-state-metrics", type="hard"} > 0)
|
||
|
|
> 0.9 < 1
|
||
|
|
for: 15m
|
||
|
|
labels:
|
||
|
|
severity: info
|
||
|
|
{{- if .Values.defaultRules.additionalRuleLabels }}
|
||
|
|
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
|
||
|
|
{{- end }}
|
||
|
|
{{- end }}
|
||
|
|
{{- if not (.Values.defaultRules.disabled.KubeQuotaFullyUsed | default false) }}
|
||
|
|
- alert: KubeQuotaFullyUsed
|
||
|
|
annotations:
|
||
|
|
{{- if .Values.defaultRules.additionalRuleAnnotations }}
|
||
|
|
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
|
||
|
|
{{- end }}
|
||
|
|
description: Namespace {{`{{`}} $labels.namespace {{`}}`}} is using {{`{{`}} $value | humanizePercentage {{`}}`}} of its {{`{{`}} $labels.resource {{`}}`}} quota.
|
||
|
|
runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/kubequotafullyused
|
||
|
|
summary: Namespace quota is fully used.
|
||
|
|
expr: |-
|
||
|
|
kube_resourcequota{job="kube-state-metrics", type="used"}
|
||
|
|
/ ignoring(instance, job, type)
|
||
|
|
(kube_resourcequota{job="kube-state-metrics", type="hard"} > 0)
|
||
|
|
== 1
|
||
|
|
for: 15m
|
||
|
|
labels:
|
||
|
|
severity: info
|
||
|
|
{{- if .Values.defaultRules.additionalRuleLabels }}
|
||
|
|
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
|
||
|
|
{{- end }}
|
||
|
|
{{- end }}
|
||
|
|
{{- if not (.Values.defaultRules.disabled.KubeQuotaExceeded | default false) }}
|
||
|
|
- alert: KubeQuotaExceeded
|
||
|
|
annotations:
|
||
|
|
{{- if .Values.defaultRules.additionalRuleAnnotations }}
|
||
|
|
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
|
||
|
|
{{- end }}
|
||
|
|
description: Namespace {{`{{`}} $labels.namespace {{`}}`}} is using {{`{{`}} $value | humanizePercentage {{`}}`}} of its {{`{{`}} $labels.resource {{`}}`}} quota.
|
||
|
|
runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/kubequotaexceeded
|
||
|
|
summary: Namespace quota has exceeded the limits.
|
||
|
|
expr: |-
|
||
|
|
kube_resourcequota{job="kube-state-metrics", type="used"}
|
||
|
|
/ ignoring(instance, job, type)
|
||
|
|
(kube_resourcequota{job="kube-state-metrics", type="hard"} > 0)
|
||
|
|
> 1
|
||
|
|
for: 15m
|
||
|
|
labels:
|
||
|
|
severity: warning
|
||
|
|
{{- if .Values.defaultRules.additionalRuleLabels }}
|
||
|
|
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
|
||
|
|
{{- end }}
|
||
|
|
{{- end }}
|
||
|
|
{{- if not (.Values.defaultRules.disabled.CPUThrottlingHigh | default false) }}
|
||
|
|
- alert: CPUThrottlingHigh
|
||
|
|
annotations:
|
||
|
|
{{- if .Values.defaultRules.additionalRuleAnnotations }}
|
||
|
|
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
|
||
|
|
{{- end }}
|
||
|
|
description: '{{`{{`}} $value | humanizePercentage {{`}}`}} throttling of CPU in namespace {{`{{`}} $labels.namespace {{`}}`}} for container {{`{{`}} $labels.container {{`}}`}} in pod {{`{{`}} $labels.pod {{`}}`}}.'
|
||
|
|
runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/cputhrottlinghigh
|
||
|
|
summary: Processes experience elevated CPU throttling.
|
||
|
|
expr: |-
|
||
|
|
sum(increase(container_cpu_cfs_throttled_periods_total{container!="", }[5m])) by (container, pod, namespace)
|
||
|
|
/
|
||
|
|
sum(increase(container_cpu_cfs_periods_total{}[5m])) by (container, pod, namespace)
|
||
|
|
> ( 25 / 100 )
|
||
|
|
for: 15m
|
||
|
|
labels:
|
||
|
|
severity: info
|
||
|
|
{{- if .Values.defaultRules.additionalRuleLabels }}
|
||
|
|
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
|
||
|
|
{{- end }}
|
||
|
|
{{- end }}
|
||
|
|
{{- end }}
|