mirror of https://git.rancher.io/charts
103 lines
4.6 KiB
YAML
103 lines
4.6 KiB
YAML
|
{{- /*
|
||
|
|
Generated from 'kubernetes-resources' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/prometheus-rules.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:
|
||
|
|
- alert: KubeCPUOvercommit
|
||
|
|
annotations:
|
||
|
|
message: Cluster has overcommitted CPU resource requests for Pods and cannot tolerate node failure.
|
||
|
|
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubecpuovercommit
|
||
|
|
expr: |-
|
||
|
|
sum(namespace:kube_pod_container_resource_requests_cpu_cores:sum{})
|
||
|
|
/
|
||
|
|
sum(kube_node_status_allocatable_cpu_cores)
|
||
|
|
>
|
||
|
|
(count(kube_node_status_allocatable_cpu_cores)-1) / count(kube_node_status_allocatable_cpu_cores)
|
||
|
|
for: 5m
|
||
|
|
labels:
|
||
|
|
severity: warning
|
||
|
|
- alert: KubeMemoryOvercommit
|
||
|
|
annotations:
|
||
|
|
message: Cluster has overcommitted memory resource requests for Pods and cannot tolerate node failure.
|
||
|
|
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubememoryovercommit
|
||
|
|
expr: |-
|
||
|
|
sum(namespace:kube_pod_container_resource_requests_memory_bytes:sum{})
|
||
|
|
/
|
||
|
|
sum(kube_node_status_allocatable_memory_bytes)
|
||
|
|
>
|
||
|
|
(count(kube_node_status_allocatable_memory_bytes)-1)
|
||
|
|
/
|
||
|
|
count(kube_node_status_allocatable_memory_bytes)
|
||
|
|
for: 5m
|
||
|
|
labels:
|
||
|
|
severity: warning
|
||
|
|
- alert: KubeCPUQuotaOvercommit
|
||
|
|
annotations:
|
||
|
|
message: Cluster has overcommitted CPU resource requests for Namespaces.
|
||
|
|
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubecpuquotaovercommit
|
||
|
|
expr: |-
|
||
|
|
sum(kube_resourcequota{job="kube-state-metrics", type="hard", resource="cpu"})
|
||
|
|
/
|
||
|
|
sum(kube_node_status_allocatable_cpu_cores)
|
||
|
|
> 1.5
|
||
|
|
for: 5m
|
||
|
|
labels:
|
||
|
|
severity: warning
|
||
|
|
- alert: KubeMemoryQuotaOvercommit
|
||
|
|
annotations:
|
||
|
|
message: Cluster has overcommitted memory resource requests for Namespaces.
|
||
|
|
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubememoryquotaovercommit
|
||
|
|
expr: |-
|
||
|
|
sum(kube_resourcequota{job="kube-state-metrics", type="hard", resource="memory"})
|
||
|
|
/
|
||
|
|
sum(kube_node_status_allocatable_memory_bytes{job="node-exporter"})
|
||
|
|
> 1.5
|
||
|
|
for: 5m
|
||
|
|
labels:
|
||
|
|
severity: warning
|
||
|
|
- alert: KubeQuotaFullyUsed
|
||
|
|
annotations:
|
||
|
|
message: Namespace {{`{{`}} $labels.namespace {{`}}`}} is using {{`{{`}} $value | humanizePercentage {{`}}`}} of its {{`{{`}} $labels.resource {{`}}`}} quota.
|
||
|
|
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubequotafullyused
|
||
|
|
expr: |-
|
||
|
|
kube_resourcequota{job="kube-state-metrics", type="used"}
|
||
|
|
/ ignoring(instance, job, type)
|
||
|
|
(kube_resourcequota{job="kube-state-metrics", type="hard"} > 0)
|
||
|
|
>= 1
|
||
|
|
for: 15m
|
||
|
|
labels:
|
||
|
|
severity: info
|
||
|
|
- alert: CPUThrottlingHigh
|
||
|
|
annotations:
|
||
|
|
message: '{{`{{`}} $value | humanizePercentage {{`}}`}} throttling of CPU in namespace {{`{{`}} $labels.namespace {{`}}`}} for container {{`{{`}} $labels.container {{`}}`}} in pod {{`{{`}} $labels.pod {{`}}`}}.'
|
||
|
|
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-cputhrottlinghigh
|
||
|
|
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
|
||
|
|
{{- end }}
|