mirror of https://git.rancher.io/charts
103 lines
4.5 KiB
YAML
103 lines
4.5 KiB
YAML
{{- /*
|
|
Generated from 'kubernetes-resources' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/release-0.1/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 ">=1.10.0-0" $kubeTargetVersion) (semverCompare "<1.14.0-0" $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_name:kube_pod_container_resource_requests_cpu_cores:sum)
|
|
/
|
|
sum(node:node_num_cpu:sum)
|
|
>
|
|
(count(node:node_num_cpu:sum)-1) / count(node:node_num_cpu:sum)
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
- alert: KubeMemOvercommit
|
|
annotations:
|
|
message: Cluster has overcommitted memory resource requests for Pods and cannot tolerate node failure.
|
|
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubememovercommit
|
|
expr: |-
|
|
sum(namespace_name:kube_pod_container_resource_requests_memory_bytes:sum)
|
|
/
|
|
sum(node_memory_MemTotal_bytes)
|
|
>
|
|
(count(node:node_num_cpu:sum)-1)
|
|
/
|
|
count(node:node_num_cpu:sum)
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
- alert: KubeCPUOvercommit
|
|
annotations:
|
|
message: Cluster has overcommitted CPU resource requests for Namespaces.
|
|
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubecpuovercommit
|
|
expr: |-
|
|
sum(kube_resourcequota{job="kube-state-metrics", type="hard", resource="cpu"})
|
|
/
|
|
sum(node:node_num_cpu:sum)
|
|
> 1.5
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
- alert: KubeMemOvercommit
|
|
annotations:
|
|
message: Cluster has overcommitted memory resource requests for Namespaces.
|
|
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubememovercommit
|
|
expr: |-
|
|
sum(kube_resourcequota{job="kube-state-metrics", type="hard", resource="memory"})
|
|
/
|
|
sum(node_memory_MemTotal_bytes{job="node-exporter"})
|
|
> 1.5
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
- alert: KubeQuotaExceeded
|
|
annotations:
|
|
message: Namespace {{`{{`}} $labels.namespace {{`}}`}} is using {{`{{`}} printf "%0.0f" $value {{`}}`}}% of its {{`{{`}} $labels.resource {{`}}`}} quota.
|
|
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-kubequotaexceeded
|
|
expr: |-
|
|
100 * kube_resourcequota{job="kube-state-metrics", type="used"}
|
|
/ ignoring(instance, job, type)
|
|
(kube_resourcequota{job="kube-state-metrics", type="hard"} > 0)
|
|
> 90
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
- alert: CPUThrottlingHigh
|
|
annotations:
|
|
message: '{{`{{`}} printf "%0.0f" $value {{`}}`}}% throttling of CPU in namespace {{`{{`}} $labels.namespace {{`}}`}} for container {{`{{`}} $labels.container_name {{`}}`}} in pod {{`{{`}} $labels.pod_name {{`}}`}}.'
|
|
runbook_url: {{ .Values.defaultRules.runbookUrl }}alert-name-cputhrottlinghigh
|
|
expr: |-
|
|
100 * sum(increase(container_cpu_cfs_throttled_periods_total{container_name!="", }[5m])) by (container_name, pod_name, namespace)
|
|
/
|
|
sum(increase(container_cpu_cfs_periods_total{}[5m])) by (container_name, pod_name, namespace)
|
|
> 25
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
{{- end }} |