Compare commits
1 Commits
main
...
renovate/k
| Author | SHA1 | Date | |
|---|---|---|---|
| ccfd175417 |
@ -5,8 +5,8 @@ FROM docker.io/alpine:${ALPINE_VERSION}
|
||||
ARG ALPINE_VERSION
|
||||
ARG KUBE_VERSION=1.31
|
||||
|
||||
ARG SOPS_VERSION="3.9.4"
|
||||
ARG VALS_VERSION="0.39.1"
|
||||
ARG SOPS_VERSION="3.9.1"
|
||||
ARG VALS_VERSION="0.37.6"
|
||||
ARG HELM_SECRETS_VERSION="4.6.2"
|
||||
|
||||
RUN cd /etc/apk/keys && \
|
||||
|
||||
@ -49,6 +49,7 @@ function cert-manager-post() {
|
||||
wait_for "kubectl get deployment -n $namespace cert-manager-webhook"
|
||||
kubectl rollout status deployment -n $namespace cert-manager-webhook
|
||||
wait_for 'kubectl get validatingwebhookconfigurations -o yaml | grep "caBundle: LS0"'
|
||||
apply
|
||||
fi
|
||||
|
||||
wait_for "kubectl get ClusterIssuer -n $namespace kubezero-local-ca-issuer"
|
||||
@ -81,11 +82,11 @@ function metrics-pre() {
|
||||
get_kubezero_values $ARGOCD
|
||||
|
||||
# Always use embedded kubezero chart
|
||||
helm template $CHARTS/kubezero -f $WORKDIR/kubezero-values.yaml --kube-version $KUBE_VERSION --name-template kubezero --version ~$KUBE_VERSION --devel --output-dir $WORKDIR
|
||||
helm template $CHARTS/kubezero -f $WORKDIR/kubezero-values.yaml --kube-version $KUBE_VERSION --version ~$KUBE_VERSION --devel --output-dir $WORKDIR
|
||||
|
||||
# Root KubeZero apply directly and exit
|
||||
if [ ${ARTIFACTS[0]} == "kubezero" ]; then
|
||||
kubectl replace -f $WORKDIR/kubezero/templates
|
||||
kubectl apply -f $WORKDIR/kubezero/templates
|
||||
exit $?
|
||||
|
||||
# "catch all" apply all enabled modules
|
||||
|
||||
@ -7,8 +7,8 @@ pre_control_plane_upgrade_cluster() {
|
||||
kubectl label node $n 'node.kubernetes.io/kubezero.version=v1.30.6' || true
|
||||
done
|
||||
|
||||
# patch aws-iam-authenticator DS to NOT run pods on 1.31 controllers
|
||||
kubectl patch ds aws-iam-authenticator -n kube-system -p '{"spec": {"template": {"spec": {"nodeSelector": {"node.kubernetes.io/kubezero.version": "v1.30.6"}}}}}' || true
|
||||
# patch aws-iam-authentiator DS to NOT run pods on 1.31 controllers
|
||||
kubectl patch ds aws-iam-authentiator -p '{"spec": {"template": {"spec": {"nodeSelector": {"node.kubernetes.io/kubezero.version": "v1.30.6"}}}}}' || true
|
||||
}
|
||||
|
||||
|
||||
@ -20,28 +20,20 @@ post_control_plane_upgrade_cluster() {
|
||||
|
||||
# All things AFTER all contollers are on the new version
|
||||
pre_cluster_upgrade_final() {
|
||||
set +e
|
||||
|
||||
if [ "$PLATFORM" == "aws" ];then
|
||||
# cleanup aws-iam-authenticator
|
||||
kubectl delete clusterrolebinding aws-iam-authenticator
|
||||
kubectl delete clusterrole aws-iam-authenticator
|
||||
kubectl delete serviceaccount aws-iam-authenticator -n kube-system
|
||||
kubectl delete cm aws-iam-authenticator -n kube-system
|
||||
kubectl delete ds aws-iam-authenticator -n kube-system
|
||||
kubectl delete IAMIdentityMapping kubezero-worker-nodes
|
||||
kubectl delete IAMIdentityMapping kubernetes-admin
|
||||
kubectl delete crd iamidentitymappings.iamauthenticator.k8s.aws
|
||||
kubectl delete secret aws-iam-certs -n kube-system
|
||||
# cleanup aws-iam-authentiator
|
||||
kubectl delete clusterrolebinding aws-iam-authentiator || true
|
||||
kubectl delete clusterrole aws-iam-authentiator || true
|
||||
kubectl delete serviceaccount aws-iam-authentiator -n kube-system || true
|
||||
kubectl delete cm aws-iam-authentiator -n kube-system || true
|
||||
kubectl delete ds aws-iam-authentiator -n kube-system || true
|
||||
kubectl delete IAMIdentityMapping kubezero-worker-nodes || true
|
||||
kubectl delete IAMIdentityMapping kubernetes-admin || true
|
||||
kubectl delete crd iamidentitymappings.iamauthenticator.k8s.aws || true
|
||||
|
||||
kubectl delete secret aws-iam-certs -n kube-system || true
|
||||
fi
|
||||
|
||||
# Remove any helm hook related resources
|
||||
kubectl delete rolebinding argo-argocd-redis-secret-init -n argocd
|
||||
kubectl delete sa argo-argocd-redis-secret-init -n argocd
|
||||
kubectl delete role argo-argocd-redis-secret-init -n argocd
|
||||
kubectl delete job argo-argocd-redis-secret-init -n argocd
|
||||
|
||||
set -e
|
||||
}
|
||||
|
||||
|
||||
|
||||
@ -97,7 +97,6 @@ pre_kubeadm() {
|
||||
cp -r ${WORKDIR}/kubeadm/templates/apiserver ${HOSTFS}/etc/kubernetes
|
||||
|
||||
# copy patches to host to make --rootfs of kubeadm work
|
||||
rm -f ${HOSTFS}/etc/kubernetes/patches/*
|
||||
cp -r ${WORKDIR}/kubeadm/templates/patches ${HOSTFS}/etc/kubernetes
|
||||
}
|
||||
|
||||
@ -122,18 +121,23 @@ control_plane_upgrade() {
|
||||
get_kubezero_values $ARGOCD
|
||||
|
||||
# tumble new config through migrate.py
|
||||
migrate_argo_values.py < "$WORKDIR"/kubezero-values.yaml > "$WORKDIR"/new-kubezero-values.yaml \
|
||||
&& mv "$WORKDIR"/new-kubezero-values.yaml "$WORKDIR"/kubezero-values.yaml
|
||||
migrate_argo_values.py < "$WORKDIR"/kubezero-values.yaml > "$WORKDIR"/new-kubezero-values.yaml
|
||||
|
||||
update_kubezero_cm
|
||||
# Update kubezero-values CM
|
||||
kubectl get cm -n kubezero kubezero-values -o=yaml | \
|
||||
yq e '.data."values.yaml" |= load_str("/tmp/kubezero/new-kubezero-values.yaml")' | \
|
||||
kubectl apply --server-side --force-conflicts -f -
|
||||
|
||||
if [ "$ARGOCD" == "True" ]; then
|
||||
# update argo app
|
||||
export kubezero_chart_version=$(yq .version $CHARTS/kubezero/Chart.yaml)
|
||||
kubectl get application kubezero -n argocd -o yaml | \
|
||||
yq ".spec.source.helm.valuesObject |= load(\"$WORKDIR/kubezero-values.yaml\") | .spec.source.targetRevision = strenv(kubezero_chart_version)" \
|
||||
yq '.spec.source.helm.valuesObject |= load("/tmp/kubezero/new-kubezero-values.yaml") | .spec.source.targetRevision = strenv(kubezero_chart_version)' \
|
||||
> $WORKDIR/new-argocd-app.yaml
|
||||
kubectl replace -f $WORKDIR/new-argocd-app.yaml
|
||||
kubectl apply --server-side --force-conflicts -f $WORKDIR/new-argocd-app.yaml
|
||||
|
||||
# finally remove annotation to allow argo to sync again
|
||||
kubectl patch app kubezero -n argocd --type json -p='[{"op": "remove", "path": "/metadata/annotations"}]' || true
|
||||
fi
|
||||
|
||||
pre_kubeadm
|
||||
|
||||
@ -46,17 +46,13 @@ function get_kubezero_values() {
|
||||
}
|
||||
|
||||
|
||||
# Overwrite kubezero-values CM with file
|
||||
# Update kubezero-values CM
|
||||
function update_kubezero_cm() {
|
||||
kubectl get cm -n kubezero kubezero-values -o=yaml | \
|
||||
yq e ".data.\"values.yaml\" |= load_str(\"$WORKDIR/kubezero-values.yaml\")" | \
|
||||
kubectl replace -f -
|
||||
}
|
||||
kubectl get application kubezero -n argocd -o yaml | yq .spec.source.helm.valuesObject > ${WORKDIR}/kubezero-values.yaml
|
||||
|
||||
# sync kubezero-values CM from ArgoCD app
|
||||
function sync_kubezero_cm_from_argo() {
|
||||
get_kubezero_values True
|
||||
update_kubezero_cm
|
||||
kubectl get cm -n kubezero kubezero-values -o=yaml | \
|
||||
yq e '.data."values.yaml" |= load_str("/tmp/kubezero/kubezero-values.yaml")' | \
|
||||
kubectl apply --server-side --force-conflicts -f -
|
||||
}
|
||||
|
||||
|
||||
|
||||
@ -8,13 +8,6 @@ import yaml
|
||||
def migrate(values):
|
||||
"""Actual changes here"""
|
||||
|
||||
# remove syncOptions from root app
|
||||
try:
|
||||
if values["kubezero"]["syncPolicy"]:
|
||||
values["kubezero"].pop("syncPolicy")
|
||||
except KeyError:
|
||||
pass
|
||||
|
||||
return values
|
||||
|
||||
|
||||
|
||||
@ -14,6 +14,6 @@ maintainers:
|
||||
email: stefan@zero-downtime.net
|
||||
dependencies:
|
||||
- name: kubezero-lib
|
||||
version: 0.2.1
|
||||
version: ">= 0.1.6"
|
||||
repository: https://cdn.zero-downtime.net/charts/
|
||||
kubeVersion: ">= 1.26.0"
|
||||
|
||||
3
charts/envoy-ratelimit/.gitignore
vendored
3
charts/envoy-ratelimit/.gitignore
vendored
@ -1,3 +0,0 @@
|
||||
istioctl
|
||||
istio
|
||||
istio.zdt
|
||||
@ -1,32 +0,0 @@
|
||||
# Patterns to ignore when building packages.
|
||||
# This supports shell glob matching, relative path matching, and
|
||||
# negation (prefixed with !). Only one pattern per line.
|
||||
.DS_Store
|
||||
# Common VCS dirs
|
||||
.git/
|
||||
.gitignore
|
||||
.bzr/
|
||||
.bzrignore
|
||||
.hg/
|
||||
.hgignore
|
||||
.svn/
|
||||
# Common backup files
|
||||
*.swp
|
||||
*.bak
|
||||
*.tmp
|
||||
*.orig
|
||||
*~
|
||||
# Various IDEs
|
||||
.project
|
||||
.idea/
|
||||
*.tmproj
|
||||
.vscode/
|
||||
|
||||
README.md.gotmpl
|
||||
*.patch
|
||||
*.sh
|
||||
*.py
|
||||
|
||||
istioctl
|
||||
istio
|
||||
istio.zdt
|
||||
@ -1,19 +0,0 @@
|
||||
apiVersion: v2
|
||||
name: envoy-ratelimit
|
||||
description: Envoy gobal ratelimiting service - part of KubeZero
|
||||
type: application
|
||||
version: 0.1.2
|
||||
home: https://kubezero.com
|
||||
icon: https://cdn.zero-downtime.net/assets/kubezero/logo-small-64.png
|
||||
keywords:
|
||||
- kubezero
|
||||
- envoy
|
||||
- istio
|
||||
maintainers:
|
||||
- name: Stefan Reimer
|
||||
email: stefan@zero-downtime.net
|
||||
dependencies:
|
||||
- name: kubezero-lib
|
||||
version: 0.2.1
|
||||
repository: https://cdn.zero-downtime.net/charts/
|
||||
kubeVersion: ">= 1.31.0-0"
|
||||
@ -1,37 +0,0 @@
|
||||
# envoy-ratelimit
|
||||
|
||||
 
|
||||
|
||||
Envoy gobal ratelimiting service - part of KubeZero
|
||||
|
||||
**Homepage:** <https://kubezero.com>
|
||||
|
||||
## Maintainers
|
||||
|
||||
| Name | Email | Url |
|
||||
| ---- | ------ | --- |
|
||||
| Stefan Reimer | <stefan@zero-downtime.net> | |
|
||||
|
||||
## Requirements
|
||||
|
||||
Kubernetes: `>= 1.31.0-0`
|
||||
|
||||
| Repository | Name | Version |
|
||||
|------------|------|---------|
|
||||
| https://cdn.zero-downtime.net/charts/ | kubezero-lib | 0.2.1 |
|
||||
|
||||
## Values
|
||||
|
||||
| Key | Type | Default | Description |
|
||||
|-----|------|---------|-------------|
|
||||
| descriptors.ingress[0].key | string | `"remote_address"` | |
|
||||
| descriptors.ingress[0].rate_limit.requests_per_unit | int | `10` | |
|
||||
| descriptors.ingress[0].rate_limit.unit | string | `"second"` | |
|
||||
| descriptors.privateIngress[0].key | string | `"remote_address"` | |
|
||||
| descriptors.privateIngress[0].rate_limit.requests_per_unit | int | `10` | |
|
||||
| descriptors.privateIngress[0].rate_limit.unit | string | `"second"` | |
|
||||
| failureModeDeny | bool | `false` | |
|
||||
| localCacheSize | int | `1048576` | |
|
||||
| log.format | string | `"json"` | |
|
||||
| log.level | string | `"warn"` | |
|
||||
| metrics.enabled | bool | `true` | |
|
||||
@ -1,16 +0,0 @@
|
||||
{{ template "chart.header" . }}
|
||||
{{ template "chart.deprecationWarning" . }}
|
||||
|
||||
{{ template "chart.versionBadge" . }}{{ template "chart.typeBadge" . }}{{ template "chart.appVersionBadge" . }}
|
||||
|
||||
{{ template "chart.description" . }}
|
||||
|
||||
{{ template "chart.homepageLine" . }}
|
||||
|
||||
{{ template "chart.maintainersSection" . }}
|
||||
|
||||
{{ template "chart.sourcesSection" . }}
|
||||
|
||||
{{ template "chart.requirementsSection" . }}
|
||||
|
||||
{{ template "chart.valuesSection" . }}
|
||||
@ -1,63 +0,0 @@
|
||||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
metadata:
|
||||
name: ratelimit
|
||||
namespace: {{ .Release.Namespace }}
|
||||
spec:
|
||||
replicas: 1
|
||||
selector:
|
||||
matchLabels:
|
||||
app: ratelimit
|
||||
strategy:
|
||||
type: Recreate
|
||||
template:
|
||||
metadata:
|
||||
labels:
|
||||
app: ratelimit
|
||||
spec:
|
||||
containers:
|
||||
- image: {{ .Values.image.repository }}:{{ .Values.image.tag }}
|
||||
imagePullPolicy: IfNotPresent
|
||||
name: ratelimit
|
||||
command: ["/bin/ratelimit"]
|
||||
env:
|
||||
- name: LOG_LEVEL
|
||||
value: {{ default "WARN" .Values.log.level }}
|
||||
- name: LOG_FORMAT
|
||||
value: {{ default "text" .Values.log.format }}
|
||||
- name: REDIS_SOCKET_TYPE
|
||||
value: tcp
|
||||
- name: REDIS_URL
|
||||
value: ratelimit-valkey:6379
|
||||
- name: USE_PROMETHEUS
|
||||
value: "true"
|
||||
- name: USE_STATSD
|
||||
value: "false"
|
||||
- name: RUNTIME_ROOT
|
||||
value: /data
|
||||
- name: RUNTIME_SUBDIRECTORY
|
||||
value: ratelimit
|
||||
- name: RUNTIME_WATCH_ROOT
|
||||
value: "false"
|
||||
- name: RUNTIME_IGNOREDOTFILES
|
||||
value: "true"
|
||||
- name: LOCAL_CACHE_SIZE_IN_BYTES
|
||||
value: "{{ default 0 .Values.localCacheSize | int }}"
|
||||
ports:
|
||||
- containerPort: 8081
|
||||
#- containerPort: 8080
|
||||
#- containerPort: 6070
|
||||
volumeMounts:
|
||||
- name: ratelimit-config
|
||||
mountPath: /data/ratelimit/config
|
||||
resources:
|
||||
requests:
|
||||
cpu: 50m
|
||||
memory: 32Mi
|
||||
limits:
|
||||
cpu: 1
|
||||
memory: 256Mi
|
||||
volumes:
|
||||
- name: ratelimit-config
|
||||
configMap:
|
||||
name: ratelimit-config
|
||||
@ -1,27 +0,0 @@
|
||||
apiVersion: v1
|
||||
kind: Service
|
||||
metadata:
|
||||
name: ratelimit
|
||||
namespace: {{ .Release.Namespace }}
|
||||
labels:
|
||||
app: ratelimit
|
||||
spec:
|
||||
ports:
|
||||
#- name: http-port
|
||||
# port: 8080
|
||||
# targetPort: 8080
|
||||
# protocol: TCP
|
||||
- name: grpc-port
|
||||
port: 8081
|
||||
targetPort: 8081
|
||||
protocol: TCP
|
||||
#- name: http-debug
|
||||
# port: 6070
|
||||
# targetPort: 6070
|
||||
# protocol: TCP
|
||||
- name: http-monitoring
|
||||
port: 9090
|
||||
targetPort: 9090
|
||||
protocol: TCP
|
||||
selector:
|
||||
app: ratelimit
|
||||
@ -1,24 +0,0 @@
|
||||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
metadata:
|
||||
name: ratelimit-valkey
|
||||
namespace: {{ .Release.Namespace }}
|
||||
spec:
|
||||
replicas: 1
|
||||
selector:
|
||||
matchLabels:
|
||||
app: ratelimit-valkey
|
||||
template:
|
||||
metadata:
|
||||
labels:
|
||||
app: ratelimit-valkey
|
||||
spec:
|
||||
containers:
|
||||
- image: valkey/valkey:8.1-alpine3.21
|
||||
imagePullPolicy: IfNotPresent
|
||||
name: valkey
|
||||
ports:
|
||||
- name: valkey
|
||||
containerPort: 6379
|
||||
restartPolicy: Always
|
||||
serviceAccountName: ""
|
||||
@ -1,13 +0,0 @@
|
||||
apiVersion: v1
|
||||
kind: Service
|
||||
metadata:
|
||||
name: ratelimit-valkey
|
||||
namespace: {{ .Release.Namespace }}
|
||||
labels:
|
||||
app: ratelimit-valkey
|
||||
spec:
|
||||
ports:
|
||||
- name: valkey
|
||||
port: 6379
|
||||
selector:
|
||||
app: ratelimit-valkey
|
||||
@ -1,9 +0,0 @@
|
||||
#!/bin/bash
|
||||
set -ex
|
||||
|
||||
. ../../scripts/lib-update.sh
|
||||
|
||||
#login_ecr_public
|
||||
update_helm
|
||||
|
||||
update_docs
|
||||
@ -1,38 +0,0 @@
|
||||
image:
|
||||
repository: envoyproxy/ratelimit
|
||||
# see: https://hub.docker.com/r/envoyproxy/ratelimit/tags
|
||||
tag: 80b15778
|
||||
|
||||
log:
|
||||
level: warn
|
||||
format: json
|
||||
|
||||
# 1MB local cache for already reached limits to reduce calls to Redis
|
||||
localCacheSize: 1048576
|
||||
|
||||
# Wether to block requests if ratelimiting is down
|
||||
failureModeDeny: false
|
||||
|
||||
# rate limit descriptors for each domain
|
||||
# - slow: 1 req/s over a minute per sourceIP
|
||||
descriptors:
|
||||
ingress:
|
||||
- key: speed
|
||||
value: slow
|
||||
descriptors:
|
||||
- key: remote_address
|
||||
rate_limit:
|
||||
unit: minute
|
||||
requests_per_unit: 60
|
||||
|
||||
privateIngress:
|
||||
- key: speed
|
||||
value: slow
|
||||
descriptors:
|
||||
- key: remote_address
|
||||
rate_limit:
|
||||
unit: minute
|
||||
requests_per_unit: 60
|
||||
|
||||
metrics:
|
||||
enabled: false
|
||||
@ -2,7 +2,7 @@ apiVersion: v2
|
||||
name: kubeadm
|
||||
description: KubeZero Kubeadm cluster config
|
||||
type: application
|
||||
version: 1.31.6
|
||||
version: 1.31.5
|
||||
home: https://kubezero.com
|
||||
icon: https://cdn.zero-downtime.net/assets/kubezero/logo-small-64.png
|
||||
keywords:
|
||||
@ -11,4 +11,4 @@ keywords:
|
||||
maintainers:
|
||||
- name: Stefan Reimer
|
||||
email: stefan@zero-downtime.net
|
||||
kubeVersion: ">= 1.31.0-0"
|
||||
kubeVersion: ">= 1.26.0"
|
||||
|
||||
@ -14,7 +14,7 @@ KubeZero umbrella chart for various optional cluster addons
|
||||
|
||||
## Requirements
|
||||
|
||||
Kubernetes: `>= 1.30.0-0`
|
||||
Kubernetes: `>= 1.26.0`
|
||||
|
||||
| Repository | Name | Version |
|
||||
|------------|------|---------|
|
||||
@ -94,8 +94,9 @@ Device plugin for [AWS Neuron](https://aws.amazon.com/machine-learning/neuron/)
|
||||
| aws-node-termination-handler.managedTag | string | `"zdt:kubezero:nth:${ClusterName}"` | "zdt:kubezero:nth:${ClusterName}" |
|
||||
| aws-node-termination-handler.metadataTries | int | `0` | |
|
||||
| aws-node-termination-handler.nodeSelector."node-role.kubernetes.io/control-plane" | string | `""` | |
|
||||
| aws-node-termination-handler.podMonitor.create | bool | `false` | |
|
||||
| aws-node-termination-handler.queueURL | string | `""` | https://sqs.${AWS::Region}.amazonaws.com/${AWS::AccountId}/${ClusterName}_Nth |
|
||||
| aws-node-termination-handler.serviceMonitor.create | bool | `false` | |
|
||||
| aws-node-termination-handler.rbac.pspEnabled | bool | `false` | |
|
||||
| aws-node-termination-handler.taintNode | bool | `true` | |
|
||||
| aws-node-termination-handler.tolerations[0].effect | string | `"NoSchedule"` | |
|
||||
| aws-node-termination-handler.tolerations[0].key | string | `"node-role.kubernetes.io/control-plane"` | |
|
||||
@ -109,7 +110,7 @@ Device plugin for [AWS Neuron](https://aws.amazon.com/machine-learning/neuron/)
|
||||
| cluster-autoscaler.extraArgs.scan-interval | string | `"30s"` | |
|
||||
| cluster-autoscaler.extraArgs.skip-nodes-with-local-storage | bool | `false` | |
|
||||
| cluster-autoscaler.image.repository | string | `"registry.k8s.io/autoscaling/cluster-autoscaler"` | |
|
||||
| cluster-autoscaler.image.tag | string | `"v1.31.1"` | |
|
||||
| cluster-autoscaler.image.tag | string | `"v1.30.2"` | |
|
||||
| cluster-autoscaler.nodeSelector."node-role.kubernetes.io/control-plane" | string | `""` | |
|
||||
| cluster-autoscaler.podDisruptionBudget | bool | `false` | |
|
||||
| cluster-autoscaler.prometheusRule.enabled | bool | `false` | |
|
||||
@ -158,9 +159,6 @@ Device plugin for [AWS Neuron](https://aws.amazon.com/machine-learning/neuron/)
|
||||
| neuron-helm-chart.enabled | bool | `false` | |
|
||||
| neuron-helm-chart.npd.enabled | bool | `false` | |
|
||||
| nvidia-device-plugin.cdi.nvidiaHookPath | string | `"/usr/bin"` | |
|
||||
| nvidia-device-plugin.config.default | string | `"default"` | |
|
||||
| nvidia-device-plugin.config.map.default | string | `"version: v1\nflags:\n migStrategy: none"` | |
|
||||
| nvidia-device-plugin.config.map.time-slice-4x | string | `"version: v1\nflags:\n migStrategy: none\nsharing:\n timeSlicing:\n resources:\n - name: nvidia.com/gpu\n replicas: 4"` | |
|
||||
| nvidia-device-plugin.deviceDiscoveryStrategy | string | `"nvml"` | |
|
||||
| nvidia-device-plugin.enabled | bool | `false` | |
|
||||
| nvidia-device-plugin.runtimeClassName | string | `"nvidia"` | |
|
||||
|
||||
@ -185,22 +185,6 @@ neuron-helm-chart:
|
||||
nvidia-device-plugin:
|
||||
enabled: false
|
||||
|
||||
config:
|
||||
default: "default"
|
||||
map:
|
||||
default: |-
|
||||
version: v1
|
||||
flags:
|
||||
migStrategy: none
|
||||
time-slice-4x: |-
|
||||
version: v1
|
||||
flags:
|
||||
migStrategy: none
|
||||
sharing:
|
||||
timeSlicing:
|
||||
resources:
|
||||
- name: nvidia.com/gpu
|
||||
replicas: 4
|
||||
cdi:
|
||||
nvidiaHookPath: /usr/bin
|
||||
deviceDiscoveryStrategy: nvml
|
||||
|
||||
@ -1,7 +1,7 @@
|
||||
apiVersion: v2
|
||||
description: KubeZero Argo - Events, Workflow, CD
|
||||
name: kubezero-argo
|
||||
version: 0.2.8
|
||||
version: 0.2.7
|
||||
home: https://kubezero.com
|
||||
icon: https://cdn.zero-downtime.net/assets/kubezero/logo-small-64.png
|
||||
keywords:
|
||||
@ -15,14 +15,14 @@ maintainers:
|
||||
# Url: https://github.com/argoproj/argo-helm/tree/main/charts
|
||||
dependencies:
|
||||
- name: kubezero-lib
|
||||
version: 0.2.1
|
||||
version: ">= 0.1.6"
|
||||
repository: https://cdn.zero-downtime.net/charts/
|
||||
- name: argo-events
|
||||
version: 2.4.13
|
||||
version: 2.4.9
|
||||
repository: https://argoproj.github.io/argo-helm
|
||||
condition: argo-events.enabled
|
||||
- name: argo-cd
|
||||
version: 7.8.2
|
||||
version: 7.7.7
|
||||
repository: https://argoproj.github.io/argo-helm
|
||||
condition: argo-cd.enabled
|
||||
- name: argocd-apps
|
||||
@ -30,7 +30,7 @@ dependencies:
|
||||
repository: https://argoproj.github.io/argo-helm
|
||||
condition: argo-cd.enabled
|
||||
- name: argocd-image-updater
|
||||
version: 0.12.0
|
||||
version: 0.11.2
|
||||
repository: https://argoproj.github.io/argo-helm
|
||||
condition: argocd-image-updater.enabled
|
||||
kubeVersion: ">= 1.26.0-0"
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
# kubezero-argo
|
||||
|
||||
|
||||
|
||||
|
||||
KubeZero Argo - Events, Workflow, CD
|
||||
|
||||
@ -18,17 +18,16 @@ Kubernetes: `>= 1.26.0-0`
|
||||
|
||||
| Repository | Name | Version |
|
||||
|------------|------|---------|
|
||||
| https://argoproj.github.io/argo-helm | argo-cd | 7.8.2 |
|
||||
| https://argoproj.github.io/argo-helm | argo-events | 2.4.13 |
|
||||
| https://argoproj.github.io/argo-helm | argo-cd | 7.7.7 |
|
||||
| https://argoproj.github.io/argo-helm | argo-events | 2.4.9 |
|
||||
| https://argoproj.github.io/argo-helm | argocd-apps | 2.0.2 |
|
||||
| https://argoproj.github.io/argo-helm | argocd-image-updater | 0.12.0 |
|
||||
| https://argoproj.github.io/argo-helm | argocd-image-updater | 0.11.2 |
|
||||
| https://cdn.zero-downtime.net/charts/ | kubezero-lib | >= 0.1.6 |
|
||||
|
||||
## Values
|
||||
|
||||
| Key | Type | Default | Description |
|
||||
|-----|------|---------|-------------|
|
||||
| argo-cd.configs.cm."application.instanceLabelKey" | string | `nil` | |
|
||||
| argo-cd.configs.cm."application.resourceTrackingMethod" | string | `"annotation"` | |
|
||||
| argo-cd.configs.cm."resource.customizations" | string | `"cert-manager.io/Certificate:\n # Lua script for customizing the health status assessment\n health.lua: |\n hs = {}\n if obj.status ~= nil then\n if obj.status.conditions ~= nil then\n for i, condition in ipairs(obj.status.conditions) do\n if condition.type == \"Ready\" and condition.status == \"False\" then\n hs.status = \"Degraded\"\n hs.message = condition.message\n return hs\n end\n if condition.type == \"Ready\" and condition.status == \"True\" then\n hs.status = \"Healthy\"\n hs.message = condition.message\n return hs\n end\n end\n end\n end\n hs.status = \"Progressing\"\n hs.message = \"Waiting for certificate\"\n return hs\n"` | |
|
||||
| argo-cd.configs.cm."timeout.reconciliation" | string | `"300s"` | |
|
||||
@ -36,7 +35,6 @@ Kubernetes: `>= 1.26.0-0`
|
||||
| argo-cd.configs.cm."ui.bannerpermanent" | string | `"true"` | |
|
||||
| argo-cd.configs.cm."ui.bannerposition" | string | `"bottom"` | |
|
||||
| argo-cd.configs.cm."ui.bannerurl" | string | `"https://kubezero.com/releases/v1.31"` | |
|
||||
| argo-cd.configs.cm.installationID | string | `"KubeZero-ArgoCD"` | |
|
||||
| argo-cd.configs.cm.url | string | `"https://argocd.example.com"` | |
|
||||
| argo-cd.configs.params."controller.diff.server.side" | string | `"true"` | |
|
||||
| argo-cd.configs.params."controller.operation.processors" | string | `"5"` | |
|
||||
@ -96,7 +94,7 @@ Kubernetes: `>= 1.26.0-0`
|
||||
| argo-events.configs.jetstream.streamConfig.maxMsgs | int | `1000000` | Maximum number of messages before expiring oldest message |
|
||||
| argo-events.configs.jetstream.streamConfig.replicas | int | `1` | Number of replicas, defaults to 3 and requires minimal 3 |
|
||||
| argo-events.configs.jetstream.versions[0].configReloaderImage | string | `"natsio/nats-server-config-reloader:0.14.1"` | |
|
||||
| argo-events.configs.jetstream.versions[0].metricsExporterImage | string | `"natsio/prometheus-nats-exporter:0.16.0"` | |
|
||||
| argo-events.configs.jetstream.versions[0].metricsExporterImage | string | `"natsio/prometheus-nats-exporter:0.14.0"` | |
|
||||
| argo-events.configs.jetstream.versions[0].natsImage | string | `"nats:2.10.11-scratch"` | |
|
||||
| argo-events.configs.jetstream.versions[0].startCommand | string | `"/nats-server"` | |
|
||||
| argo-events.configs.jetstream.versions[0].version | string | `"2.10.11"` | |
|
||||
|
||||
@ -45,7 +45,7 @@ argo-cd:
|
||||
format: json
|
||||
image:
|
||||
repository: public.ecr.aws/zero-downtime/zdt-argocd
|
||||
tag: v2.14.2
|
||||
tag: v2.13.1
|
||||
networkPolicy:
|
||||
create: true
|
||||
|
||||
@ -106,12 +106,9 @@ argo-cd:
|
||||
extraHosts: "git.zero-downtime.net ssh-rsa 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"
|
||||
|
||||
params:
|
||||
controller.status.processors: 8
|
||||
controller.operation.processors: 4
|
||||
controller.kubectl.parallelism.limit: 8
|
||||
controller.resource.health.persist: "false"
|
||||
controller.status.processors: "10"
|
||||
controller.operation.processors: "5"
|
||||
controller.diff.server.side: "true"
|
||||
controller.sync.timeout.seconds: 1800
|
||||
|
||||
server.insecure: true
|
||||
server.enable.gzip: true
|
||||
@ -180,9 +177,6 @@ argo-cd:
|
||||
serviceMonitor:
|
||||
enabled: true
|
||||
|
||||
redisSecretInit:
|
||||
enabled: false
|
||||
|
||||
# redis:
|
||||
# We might want to try to keep redis close to the controller
|
||||
# affinity:
|
||||
|
||||
@ -14,7 +14,7 @@ maintainers:
|
||||
email: stefan@zero-downtime.net
|
||||
dependencies:
|
||||
- name: kubezero-lib
|
||||
version: 0.2.1
|
||||
version: ">= 0.1.6"
|
||||
repository: https://cdn.zero-downtime.net/charts/
|
||||
- name: keycloak
|
||||
repository: "oci://registry-1.docker.io/bitnamicharts"
|
||||
|
||||
@ -14,7 +14,7 @@ maintainers:
|
||||
email: stefan@zero-downtime.net
|
||||
dependencies:
|
||||
- name: kubezero-lib
|
||||
version: 0.2.1
|
||||
version: ">= 0.2.1"
|
||||
repository: https://cdn.zero-downtime.net/charts/
|
||||
- name: redis
|
||||
version: 20.0.3
|
||||
|
||||
@ -2,7 +2,7 @@ apiVersion: v2
|
||||
name: kubezero-cert-manager
|
||||
description: KubeZero Umbrella Chart for cert-manager
|
||||
type: application
|
||||
version: 0.9.12
|
||||
version: 0.9.11
|
||||
home: https://kubezero.com
|
||||
icon: https://cdn.zero-downtime.net/assets/kubezero/logo-small-64.png
|
||||
keywords:
|
||||
@ -13,9 +13,9 @@ maintainers:
|
||||
email: stefan@zero-downtime.net
|
||||
dependencies:
|
||||
- name: kubezero-lib
|
||||
version: 0.2.1
|
||||
version: ">= 0.1.6"
|
||||
repository: https://cdn.zero-downtime.net/charts/
|
||||
- name: cert-manager
|
||||
version: v1.17.1
|
||||
version: v1.17.0
|
||||
repository: https://charts.jetstack.io
|
||||
kubeVersion: ">= 1.30.0-0"
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
# kubezero-cert-manager
|
||||
|
||||
 
|
||||
 
|
||||
|
||||
KubeZero Umbrella Chart for cert-manager
|
||||
|
||||
@ -14,12 +14,12 @@ KubeZero Umbrella Chart for cert-manager
|
||||
|
||||
## Requirements
|
||||
|
||||
Kubernetes: `>= 1.30.0-0`
|
||||
Kubernetes: `>= 1.26.0-0`
|
||||
|
||||
| Repository | Name | Version |
|
||||
|------------|------|---------|
|
||||
| https://cdn.zero-downtime.net/charts/ | kubezero-lib | >= 0.1.6 |
|
||||
| https://charts.jetstack.io | cert-manager | v1.17.1 |
|
||||
| https://charts.jetstack.io | cert-manager | v1.17.0 |
|
||||
|
||||
## AWS - OIDC IAM roles
|
||||
|
||||
|
||||
@ -18,7 +18,7 @@
|
||||
"subdir": "contrib/mixin"
|
||||
}
|
||||
},
|
||||
"version": "eb7607bd8b3665d14aa40d50435ae8c9002d620c",
|
||||
"version": "c0e7e8c873a6067f9ae9076c3c243a20fa713a58",
|
||||
"sum": "XmXkOCriQIZmXwlIIFhqlJMa0e6qGWdxZD+ZDYaN0Po="
|
||||
},
|
||||
{
|
||||
@ -78,7 +78,7 @@
|
||||
"subdir": "grafana-builder"
|
||||
}
|
||||
},
|
||||
"version": "ef841d571a704013b689368fe51e437810b6c935",
|
||||
"version": "d6c38bb26f576b128cadca4137d73a037afdd872",
|
||||
"sum": "yxqWcq/N3E/a/XreeU6EuE6X7kYPnG0AspAQFKOjASo="
|
||||
},
|
||||
{
|
||||
@ -118,8 +118,8 @@
|
||||
"subdir": ""
|
||||
}
|
||||
},
|
||||
"version": "4ff562d5e8145940cf355f62cf2308895c4dca81",
|
||||
"sum": "kiL19fTbXOtNglsmT62kOzIf/Xpu+YwoiMPAApDXhkE="
|
||||
"version": "e27267571be06c2bdc3d2fd8dbd70161cd709cb4",
|
||||
"sum": "je1RPCp2aFNefYs5Q57Q5wDm93p8pL4pdBtA5rC7jLA="
|
||||
},
|
||||
{
|
||||
"source": {
|
||||
@ -128,7 +128,7 @@
|
||||
"subdir": "jsonnet/kube-state-metrics"
|
||||
}
|
||||
},
|
||||
"version": "350a7c472e1801a2e13b9895ec8ef38876c96dd0",
|
||||
"version": "2a95d4649b2fea55799032fb9c0b571c4ba7f776",
|
||||
"sum": "3bioG7CfTfY9zeu5xU4yon6Zt3kYvNkyl492nOhQxnM="
|
||||
},
|
||||
{
|
||||
@ -138,7 +138,7 @@
|
||||
"subdir": "jsonnet/kube-state-metrics-mixin"
|
||||
}
|
||||
},
|
||||
"version": "350a7c472e1801a2e13b9895ec8ef38876c96dd0",
|
||||
"version": "2a95d4649b2fea55799032fb9c0b571c4ba7f776",
|
||||
"sum": "qclI7LwucTjBef3PkGBkKxF0mfZPbHnn4rlNWKGtR4c="
|
||||
},
|
||||
{
|
||||
@ -158,7 +158,7 @@
|
||||
"subdir": "jsonnet/mixin"
|
||||
}
|
||||
},
|
||||
"version": "7deab71d6d5921eeaf8c79e3ae8e31efe63783a9",
|
||||
"version": "4da36fdd2377362c285aee3a96f7b0516f6e41bf",
|
||||
"sum": "gi+knjdxs2T715iIQIntrimbHRgHnpM8IFBJDD1gYfs=",
|
||||
"name": "prometheus-operator-mixin"
|
||||
},
|
||||
@ -169,8 +169,8 @@
|
||||
"subdir": "jsonnet/prometheus-operator"
|
||||
}
|
||||
},
|
||||
"version": "7deab71d6d5921eeaf8c79e3ae8e31efe63783a9",
|
||||
"sum": "LctDdofQostvviE5y8vpRKWGGO1ZKO3dgJe7P9xifW0="
|
||||
"version": "4da36fdd2377362c285aee3a96f7b0516f6e41bf",
|
||||
"sum": "tb5PzIT75Hv4m3kbOHXvmrlcplg+EbS4++NfTttDNOk="
|
||||
},
|
||||
{
|
||||
"source": {
|
||||
@ -190,8 +190,8 @@
|
||||
"subdir": "docs/node-mixin"
|
||||
}
|
||||
},
|
||||
"version": "02afa5c53c36123611533f2defea6ccd4546a9bb",
|
||||
"sum": "8dNyJ4vpnKVBbCFN9YLsugp1IjlZjDCwdKMjKi0KTG4="
|
||||
"version": "11365f97bef6cb0e6259d536a7e21c49e3f5c065",
|
||||
"sum": "xYj6VYFT/eafsbleNlC+Z2VfLy1CndyYrJs9BcTmnX8="
|
||||
},
|
||||
{
|
||||
"source": {
|
||||
@ -200,7 +200,7 @@
|
||||
"subdir": "documentation/prometheus-mixin"
|
||||
}
|
||||
},
|
||||
"version": "a5ffa83be83be22e2ec9fd1d4765299d8d16119e",
|
||||
"version": "906f6a33b60cec2596018ac8cc97ac41b16b06b7",
|
||||
"sum": "2c+wttfee9TwuQJZIkNV7Tekem74Qgc7iZ842P28rNw=",
|
||||
"name": "prometheus"
|
||||
},
|
||||
|
||||
@ -2,7 +2,7 @@ apiVersion: v2
|
||||
name: kubezero-ci
|
||||
description: KubeZero umbrella chart for all things CI
|
||||
type: application
|
||||
version: 0.8.20
|
||||
version: 0.8.19
|
||||
home: https://kubezero.com
|
||||
icon: https://cdn.zero-downtime.net/assets/kubezero/logo-small-64.png
|
||||
keywords:
|
||||
@ -15,22 +15,22 @@ maintainers:
|
||||
email: stefan@zero-downtime.net
|
||||
dependencies:
|
||||
- name: kubezero-lib
|
||||
version: 0.2.1
|
||||
version: ">= 0.1.6"
|
||||
repository: https://cdn.zero-downtime.net/charts/
|
||||
- name: gitea
|
||||
version: 10.6.0
|
||||
repository: https://dl.gitea.io/charts/
|
||||
condition: gitea.enabled
|
||||
- name: jenkins
|
||||
version: 5.8.16
|
||||
version: 5.7.15
|
||||
repository: https://charts.jenkins.io
|
||||
condition: jenkins.enabled
|
||||
- name: trivy
|
||||
version: 0.11.1
|
||||
version: 0.9.0
|
||||
repository: https://aquasecurity.github.io/helm-charts/
|
||||
condition: trivy.enabled
|
||||
- name: renovate
|
||||
version: 39.180.2
|
||||
version: 39.33.1
|
||||
repository: https://docs.renovatebot.com/helm-charts
|
||||
condition: renovate.enabled
|
||||
kubeVersion: ">= 1.25.0"
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
# kubezero-ci
|
||||
|
||||
 
|
||||
 
|
||||
|
||||
KubeZero umbrella chart for all things CI
|
||||
|
||||
@ -18,11 +18,11 @@ Kubernetes: `>= 1.25.0`
|
||||
|
||||
| Repository | Name | Version |
|
||||
|------------|------|---------|
|
||||
| https://aquasecurity.github.io/helm-charts/ | trivy | 0.11.1 |
|
||||
| https://cdn.zero-downtime.net/charts/ | kubezero-lib | 0.1.6 |
|
||||
| https://charts.jenkins.io | jenkins | 5.8.16 |
|
||||
| https://aquasecurity.github.io/helm-charts/ | trivy | 0.9.0 |
|
||||
| https://cdn.zero-downtime.net/charts/ | kubezero-lib | >= 0.1.6 |
|
||||
| https://charts.jenkins.io | jenkins | 5.7.15 |
|
||||
| https://dl.gitea.io/charts/ | gitea | 10.6.0 |
|
||||
| https://docs.renovatebot.com/helm-charts | renovate | 39.180.2 |
|
||||
| https://docs.renovatebot.com/helm-charts | renovate | 39.33.1 |
|
||||
|
||||
# Jenkins
|
||||
- default build retention 10 builds, 32days
|
||||
@ -68,7 +68,7 @@ Kubernetes: `>= 1.25.0`
|
||||
| gitea.gitea.metrics.enabled | bool | `false` | |
|
||||
| gitea.gitea.metrics.serviceMonitor.enabled | bool | `true` | |
|
||||
| gitea.image.rootless | bool | `true` | |
|
||||
| gitea.image.tag | string | `"1.23.4"` | |
|
||||
| gitea.image.tag | string | `"1.22.3"` | |
|
||||
| gitea.istio.enabled | bool | `false` | |
|
||||
| gitea.istio.gateway | string | `"istio-ingress/private-ingressgateway"` | |
|
||||
| gitea.istio.url | string | `"git.example.com"` | |
|
||||
@ -90,7 +90,6 @@ Kubernetes: `>= 1.25.0`
|
||||
| jenkins.agent.containerCap | int | `2` | |
|
||||
| jenkins.agent.customJenkinsLabels[0] | string | `"podman-aws-trivy"` | |
|
||||
| jenkins.agent.defaultsProviderTemplate | string | `"podman-aws"` | |
|
||||
| jenkins.agent.garbageCollection.enabled | bool | `true` | |
|
||||
| jenkins.agent.idleMinutes | int | `30` | |
|
||||
| jenkins.agent.image.repository | string | `"public.ecr.aws/zero-downtime/jenkins-podman"` | |
|
||||
| jenkins.agent.image.tag | string | `"v0.7.0"` | |
|
||||
@ -161,8 +160,7 @@ Kubernetes: `>= 1.25.0`
|
||||
| renovate.cronjob.successfulJobsHistoryLimit | int | `1` | |
|
||||
| renovate.enabled | bool | `false` | |
|
||||
| renovate.env.LOG_FORMAT | string | `"json"` | |
|
||||
| renovate.renovate.config | string | `"{\n}\n"` | |
|
||||
| renovate.securityContext.fsGroupChangePolicy | string | `"OnRootMismatch"` | |
|
||||
| renovate.securityContext.fsGroup | int | `1000` | |
|
||||
| trivy.enabled | bool | `false` | |
|
||||
| trivy.persistence.enabled | bool | `true` | |
|
||||
| trivy.persistence.size | string | `"1Gi"` | |
|
||||
|
||||
@ -12,122 +12,6 @@ Use the following links to reference issues, PRs, and commits prior to v2.6.0.
|
||||
The changelog until v1.5.7 was auto-generated based on git commits.
|
||||
Those entries include a reference to the git commit to be able to get more details.
|
||||
|
||||
## 5.8.16
|
||||
|
||||
Update `docker.io/kiwigrid/k8s-sidecar` to version `1.30.1`
|
||||
|
||||
## 5.8.15
|
||||
|
||||
Update `kubernetes` to version `4313.va_9b_4fe2a_0e34`
|
||||
|
||||
## 5.8.14
|
||||
|
||||
Update `jenkins/inbound-agent` to version `3283.v92c105e0f819-9`
|
||||
|
||||
## 5.8.13
|
||||
|
||||
Fix `agentListenerPort` not being updated in `config.xml` when set via Helm values.
|
||||
|
||||
## 5.8.12
|
||||
|
||||
Update plugin count.
|
||||
|
||||
## 5.8.11
|
||||
|
||||
Update `jenkins/inbound-agent` to version `3283.v92c105e0f819-8`
|
||||
|
||||
## 5.8.10
|
||||
|
||||
Update `jenkins/jenkins` to version `2.492.1-jdk17`
|
||||
|
||||
## 5.8.9
|
||||
|
||||
Update `configuration-as-code` to version `1932.v75cb_b_f1b_698d`
|
||||
|
||||
## 5.8.8
|
||||
|
||||
Update `docker.io/kiwigrid/k8s-sidecar` to version `1.30.0`
|
||||
|
||||
## 5.8.7
|
||||
|
||||
Update `configuration-as-code` to version `1929.v036b_5a_e1f123`
|
||||
|
||||
## 5.8.6
|
||||
|
||||
Update `docker.io/kiwigrid/k8s-sidecar` to version `1.29.1`
|
||||
|
||||
## 5.8.5
|
||||
|
||||
Update `jenkins/inbound-agent` to version `3283.v92c105e0f819-7`
|
||||
|
||||
## 5.8.4
|
||||
|
||||
Allow setting [automountServiceAccountToken](https://kubernetes.io/docs/tasks/configure-pod-container/configure-service-account/#opt-out-of-api-credential-automounting)
|
||||
|
||||
## 5.8.3
|
||||
|
||||
Update `docker.io/kiwigrid/k8s-sidecar` to version `1.29.0`
|
||||
|
||||
## 5.8.2
|
||||
|
||||
Update `jenkins/jenkins` to version `2.479.3-jdk17`
|
||||
|
||||
## 5.8.1
|
||||
|
||||
Update `configuration-as-code` to version `1915.vcdd0a_d0d2625`
|
||||
|
||||
## 5.8.0
|
||||
|
||||
Add option to publish not-ready addresses in controller service.
|
||||
|
||||
## 5.7.27
|
||||
|
||||
Update `git` to version `5.7.0`
|
||||
|
||||
## 5.7.26
|
||||
|
||||
Update `configuration-as-code` to version `1909.vb_b_f59a_27d013`
|
||||
|
||||
## 5.7.25
|
||||
|
||||
Update `kubernetes` to version `4306.vc91e951ea_eb_d`
|
||||
|
||||
## 5.7.24
|
||||
|
||||
Update `kubernetes` to version `4304.v1b_39d4f98210`
|
||||
|
||||
## 5.7.23
|
||||
|
||||
Update `docker.io/kiwigrid/k8s-sidecar` to version `1.28.4`
|
||||
|
||||
## 5.7.22
|
||||
|
||||
Update `docker.io/kiwigrid/k8s-sidecar` to version `1.28.3`
|
||||
|
||||
## 5.7.21
|
||||
|
||||
Update `docker.io/kiwigrid/k8s-sidecar` to version `1.28.1`
|
||||
|
||||
## 5.7.20
|
||||
|
||||
Update `kubernetes` to version `4302.va_756e4b_67715`
|
||||
|
||||
## 5.7.19
|
||||
|
||||
Update `configuration-as-code` to version `1903.v004d55388f30`
|
||||
|
||||
## 5.7.18
|
||||
|
||||
Update `kubernetes` to version `4300.vd82c5692b_3a_e`
|
||||
|
||||
## 5.7.17
|
||||
|
||||
Update `docker.io/bats/bats` to version `1.11.1`
|
||||
|
||||
## 5.7.16
|
||||
|
||||
Add tpl support for persistence.storageClassName in home-pvc.yaml and tpl support in controller.ingress parameters(ingressClassName, annotations, hostname) in jenkins-controller-ingress.yaml
|
||||
|
||||
## 5.7.15
|
||||
|
||||
Update `jenkins/jenkins` to version `2.479.2-jdk17`
|
||||
|
||||
@ -1,14 +1,14 @@
|
||||
annotations:
|
||||
artifacthub.io/category: integration-delivery
|
||||
artifacthub.io/changes: |
|
||||
- Update `docker.io/kiwigrid/k8s-sidecar` to version `1.30.1`
|
||||
- Update `jenkins/jenkins` to version `2.479.2-jdk17`
|
||||
artifacthub.io/images: |
|
||||
- name: jenkins
|
||||
image: docker.io/jenkins/jenkins:2.492.1-jdk17
|
||||
image: docker.io/jenkins/jenkins:2.479.2-jdk17
|
||||
- name: k8s-sidecar
|
||||
image: docker.io/kiwigrid/k8s-sidecar:1.30.1
|
||||
image: docker.io/kiwigrid/k8s-sidecar:1.28.0
|
||||
- name: inbound-agent
|
||||
image: jenkins/inbound-agent:3283.v92c105e0f819-9
|
||||
image: jenkins/inbound-agent:3273.v4cfe589b_fd83-1
|
||||
artifacthub.io/license: Apache-2.0
|
||||
artifacthub.io/links: |
|
||||
- name: Chart Source
|
||||
@ -18,9 +18,9 @@ annotations:
|
||||
- name: support
|
||||
url: https://github.com/jenkinsci/helm-charts/issues
|
||||
apiVersion: v2
|
||||
appVersion: 2.492.1
|
||||
appVersion: 2.479.2
|
||||
description: 'Jenkins - Build great things at any scale! As the leading open source
|
||||
automation server, Jenkins provides over 2000 plugins to support building, deploying
|
||||
automation server, Jenkins provides over 1800 plugins to support building, deploying
|
||||
and automating any project. '
|
||||
home: https://www.jenkins.io/
|
||||
icon: https://get.jenkins.io/art/jenkins-logo/logo.svg
|
||||
@ -46,4 +46,4 @@ sources:
|
||||
- https://github.com/maorfr/kube-tasks
|
||||
- https://github.com/jenkinsci/configuration-as-code-plugin
|
||||
type: application
|
||||
version: 5.8.16
|
||||
version: 5.7.15
|
||||
|
||||
@ -5,7 +5,7 @@
|
||||
[](https://github.com/jenkinsci/helm-charts/releases)
|
||||
[](https://app.gitter.im/#/room/#jenkins-ci:matrix.org)
|
||||
|
||||
[Jenkins](https://www.jenkins.io/) is the leading open source automation server, Jenkins provides over 2000 plugins to support building, deploying and automating any project.
|
||||
[Jenkins](https://www.jenkins.io/) is the leading open source automation server, Jenkins provides over 1800 plugins to support building, deploying and automating any project.
|
||||
|
||||
This chart installs a Jenkins server which spawns agents on [Kubernetes](http://kubernetes.io) utilizing the [Jenkins Kubernetes plugin](https://plugins.jenkins.io/kubernetes/).
|
||||
|
||||
|
||||
@ -8,164 +8,164 @@ The following tables list the configurable parameters of the Jenkins chart and t
|
||||
|
||||
| Key | Type | Description | Default |
|
||||
|:----|:-----|:---------|:------------|
|
||||
| [additionalAgents](./values.yaml#L1199) | object | Configure additional | `{}` |
|
||||
| [additionalClouds](./values.yaml#L1224) | object | | `{}` |
|
||||
| [agent.TTYEnabled](./values.yaml#L1105) | bool | Allocate pseudo tty to the side container | `false` |
|
||||
| [agent.additionalContainers](./values.yaml#L1152) | list | Add additional containers to the agents | `[]` |
|
||||
| [agent.alwaysPullImage](./values.yaml#L998) | bool | Always pull agent container image before build | `false` |
|
||||
| [agent.annotations](./values.yaml#L1148) | object | Annotations to apply to the pod | `{}` |
|
||||
| [agent.args](./values.yaml#L1099) | string | Arguments passed to command to execute | `"${computer.jnlpmac} ${computer.name}"` |
|
||||
| [agent.command](./values.yaml#L1097) | string | Command to execute when side container starts | `nil` |
|
||||
| [agent.componentName](./values.yaml#L966) | string | | `"jenkins-agent"` |
|
||||
| [agent.connectTimeout](./values.yaml#L1146) | int | Timeout in seconds for an agent to be online | `100` |
|
||||
| [agent.containerCap](./values.yaml#L1107) | int | Max number of agents to launch | `10` |
|
||||
| [agent.customJenkinsLabels](./values.yaml#L963) | list | Append Jenkins labels to the agent | `[]` |
|
||||
| [agent.defaultsProviderTemplate](./values.yaml#L917) | string | The name of the pod template to use for providing default values | `""` |
|
||||
| [agent.directConnection](./values.yaml#L969) | bool | | `false` |
|
||||
| [agent.disableDefaultAgent](./values.yaml#L1170) | bool | Disable the default Jenkins Agent configuration | `false` |
|
||||
| [agent.enabled](./values.yaml#L915) | bool | Enable Kubernetes plugin jnlp-agent podTemplate | `true` |
|
||||
| [agent.envVars](./values.yaml#L1080) | list | Environment variables for the agent Pod | `[]` |
|
||||
| [agent.garbageCollection.enabled](./values.yaml#L1114) | bool | When enabled, Jenkins will periodically check for orphan pods that have not been touched for the given timeout period and delete them. | `false` |
|
||||
| [agent.garbageCollection.namespaces](./values.yaml#L1116) | string | Namespaces to look at for garbage collection, in addition to the default namespace defined for the cloud. One namespace per line. | `""` |
|
||||
| [agent.garbageCollection.timeout](./values.yaml#L1121) | int | Timeout value for orphaned pods | `300` |
|
||||
| [agent.hostNetworking](./values.yaml#L977) | bool | Enables the agent to use the host network | `false` |
|
||||
| [agent.idleMinutes](./values.yaml#L1124) | int | Allows the Pod to remain active for reuse until the configured number of minutes has passed since the last step was executed on it | `0` |
|
||||
| [agent.image.repository](./values.yaml#L956) | string | Repository to pull the agent jnlp image from | `"jenkins/inbound-agent"` |
|
||||
| [agent.image.tag](./values.yaml#L958) | string | Tag of the image to pull | `"3283.v92c105e0f819-9"` |
|
||||
| [agent.imagePullSecretName](./values.yaml#L965) | string | Name of the secret to be used to pull the image | `nil` |
|
||||
| [agent.inheritYamlMergeStrategy](./values.yaml#L1144) | bool | Controls whether the defined yaml merge strategy will be inherited if another defined pod template is configured to inherit from the current one | `false` |
|
||||
| [agent.jenkinsTunnel](./values.yaml#L933) | string | Overrides the Kubernetes Jenkins tunnel | `nil` |
|
||||
| [agent.jenkinsUrl](./values.yaml#L929) | string | Overrides the Kubernetes Jenkins URL | `nil` |
|
||||
| [agent.jnlpregistry](./values.yaml#L953) | string | Custom registry used to pull the agent jnlp image from | `nil` |
|
||||
| [agent.kubernetesConnectTimeout](./values.yaml#L939) | int | The connection timeout in seconds for connections to Kubernetes API. The minimum value is 5 | `5` |
|
||||
| [agent.kubernetesReadTimeout](./values.yaml#L941) | int | The read timeout in seconds for connections to Kubernetes API. The minimum value is 15 | `15` |
|
||||
| [agent.livenessProbe](./values.yaml#L988) | object | | `{}` |
|
||||
| [agent.maxRequestsPerHostStr](./values.yaml#L943) | string | The maximum concurrent connections to Kubernetes API | `"32"` |
|
||||
| [agent.namespace](./values.yaml#L949) | string | Namespace in which the Kubernetes agents should be launched | `nil` |
|
||||
| [agent.nodeSelector](./values.yaml#L1091) | object | Node labels for pod assignment | `{}` |
|
||||
| [agent.nodeUsageMode](./values.yaml#L961) | string | | `"NORMAL"` |
|
||||
| [agent.podLabels](./values.yaml#L951) | object | Custom Pod labels (an object with `label-key: label-value` pairs) | `{}` |
|
||||
| [agent.podName](./values.yaml#L1109) | string | Agent Pod base name | `"default"` |
|
||||
| [agent.podRetention](./values.yaml#L1007) | string | | `"Never"` |
|
||||
| [agent.podTemplates](./values.yaml#L1180) | object | Configures extra pod templates for the default kubernetes cloud | `{}` |
|
||||
| [agent.privileged](./values.yaml#L971) | bool | Agent privileged container | `false` |
|
||||
| [agent.resources](./values.yaml#L979) | object | Resources allocation (Requests and Limits) | `{"limits":{"cpu":"512m","memory":"512Mi"},"requests":{"cpu":"512m","memory":"512Mi"}}` |
|
||||
| [agent.restrictedPssSecurityContext](./values.yaml#L1004) | bool | Set a restricted securityContext on jnlp containers | `false` |
|
||||
| [agent.retentionTimeout](./values.yaml#L945) | int | Time in minutes after which the Kubernetes cloud plugin will clean up an idle worker that has not already terminated | `5` |
|
||||
| [agent.runAsGroup](./values.yaml#L975) | string | Configure container group | `nil` |
|
||||
| [agent.runAsUser](./values.yaml#L973) | string | Configure container user | `nil` |
|
||||
| [agent.secretEnvVars](./values.yaml#L1084) | list | Mount a secret as environment variable | `[]` |
|
||||
| [agent.serviceAccount](./values.yaml#L925) | string | Override the default service account | `serviceAccountAgent.name` if `agent.useDefaultServiceAccount` is `true` |
|
||||
| [agent.showRawYaml](./values.yaml#L1011) | bool | | `true` |
|
||||
| [agent.sideContainerName](./values.yaml#L1101) | string | Side container name | `"jnlp"` |
|
||||
| [agent.skipTlsVerify](./values.yaml#L935) | bool | Disables the verification of the controller certificate on remote connection. This flag correspond to the "Disable https certificate check" flag in kubernetes plugin UI | `false` |
|
||||
| [agent.usageRestricted](./values.yaml#L937) | bool | Enable the possibility to restrict the usage of this agent to specific folder. This flag correspond to the "Restrict pipeline support to authorized folders" flag in kubernetes plugin UI | `false` |
|
||||
| [agent.useDefaultServiceAccount](./values.yaml#L921) | bool | Use `serviceAccountAgent.name` as the default value for defaults template `serviceAccount` | `true` |
|
||||
| [agent.volumes](./values.yaml#L1018) | list | Additional volumes | `[]` |
|
||||
| [agent.waitForPodSec](./values.yaml#L947) | int | Seconds to wait for pod to be running | `600` |
|
||||
| [agent.websocket](./values.yaml#L968) | bool | Enables agent communication via websockets | `false` |
|
||||
| [agent.workingDir](./values.yaml#L960) | string | Configure working directory for default agent | `"/home/jenkins/agent"` |
|
||||
| [agent.workspaceVolume](./values.yaml#L1053) | object | Workspace volume (defaults to EmptyDir) | `{}` |
|
||||
| [agent.yamlMergeStrategy](./values.yaml#L1142) | string | Defines how the raw yaml field gets merged with yaml definitions from inherited pod templates. Possible values: "merge" or "override" | `"override"` |
|
||||
| [agent.yamlTemplate](./values.yaml#L1131) | string | The raw yaml of a Pod API Object to merge into the agent spec | `""` |
|
||||
| [awsSecurityGroupPolicies.enabled](./values.yaml#L1356) | bool | | `false` |
|
||||
| [awsSecurityGroupPolicies.policies[0].name](./values.yaml#L1358) | string | | `""` |
|
||||
| [awsSecurityGroupPolicies.policies[0].podSelector](./values.yaml#L1360) | object | | `{}` |
|
||||
| [awsSecurityGroupPolicies.policies[0].securityGroupIds](./values.yaml#L1359) | list | | `[]` |
|
||||
| [checkDeprecation](./values.yaml#L1353) | bool | Checks if any deprecated values are used | `true` |
|
||||
| [additionalAgents](./values.yaml#L1195) | object | Configure additional | `{}` |
|
||||
| [additionalClouds](./values.yaml#L1220) | object | | `{}` |
|
||||
| [agent.TTYEnabled](./values.yaml#L1101) | bool | Allocate pseudo tty to the side container | `false` |
|
||||
| [agent.additionalContainers](./values.yaml#L1148) | list | Add additional containers to the agents | `[]` |
|
||||
| [agent.alwaysPullImage](./values.yaml#L994) | bool | Always pull agent container image before build | `false` |
|
||||
| [agent.annotations](./values.yaml#L1144) | object | Annotations to apply to the pod | `{}` |
|
||||
| [agent.args](./values.yaml#L1095) | string | Arguments passed to command to execute | `"${computer.jnlpmac} ${computer.name}"` |
|
||||
| [agent.command](./values.yaml#L1093) | string | Command to execute when side container starts | `nil` |
|
||||
| [agent.componentName](./values.yaml#L962) | string | | `"jenkins-agent"` |
|
||||
| [agent.connectTimeout](./values.yaml#L1142) | int | Timeout in seconds for an agent to be online | `100` |
|
||||
| [agent.containerCap](./values.yaml#L1103) | int | Max number of agents to launch | `10` |
|
||||
| [agent.customJenkinsLabels](./values.yaml#L959) | list | Append Jenkins labels to the agent | `[]` |
|
||||
| [agent.defaultsProviderTemplate](./values.yaml#L913) | string | The name of the pod template to use for providing default values | `""` |
|
||||
| [agent.directConnection](./values.yaml#L965) | bool | | `false` |
|
||||
| [agent.disableDefaultAgent](./values.yaml#L1166) | bool | Disable the default Jenkins Agent configuration | `false` |
|
||||
| [agent.enabled](./values.yaml#L911) | bool | Enable Kubernetes plugin jnlp-agent podTemplate | `true` |
|
||||
| [agent.envVars](./values.yaml#L1076) | list | Environment variables for the agent Pod | `[]` |
|
||||
| [agent.garbageCollection.enabled](./values.yaml#L1110) | bool | When enabled, Jenkins will periodically check for orphan pods that have not been touched for the given timeout period and delete them. | `false` |
|
||||
| [agent.garbageCollection.namespaces](./values.yaml#L1112) | string | Namespaces to look at for garbage collection, in addition to the default namespace defined for the cloud. One namespace per line. | `""` |
|
||||
| [agent.garbageCollection.timeout](./values.yaml#L1117) | int | Timeout value for orphaned pods | `300` |
|
||||
| [agent.hostNetworking](./values.yaml#L973) | bool | Enables the agent to use the host network | `false` |
|
||||
| [agent.idleMinutes](./values.yaml#L1120) | int | Allows the Pod to remain active for reuse until the configured number of minutes has passed since the last step was executed on it | `0` |
|
||||
| [agent.image.repository](./values.yaml#L952) | string | Repository to pull the agent jnlp image from | `"jenkins/inbound-agent"` |
|
||||
| [agent.image.tag](./values.yaml#L954) | string | Tag of the image to pull | `"3273.v4cfe589b_fd83-1"` |
|
||||
| [agent.imagePullSecretName](./values.yaml#L961) | string | Name of the secret to be used to pull the image | `nil` |
|
||||
| [agent.inheritYamlMergeStrategy](./values.yaml#L1140) | bool | Controls whether the defined yaml merge strategy will be inherited if another defined pod template is configured to inherit from the current one | `false` |
|
||||
| [agent.jenkinsTunnel](./values.yaml#L929) | string | Overrides the Kubernetes Jenkins tunnel | `nil` |
|
||||
| [agent.jenkinsUrl](./values.yaml#L925) | string | Overrides the Kubernetes Jenkins URL | `nil` |
|
||||
| [agent.jnlpregistry](./values.yaml#L949) | string | Custom registry used to pull the agent jnlp image from | `nil` |
|
||||
| [agent.kubernetesConnectTimeout](./values.yaml#L935) | int | The connection timeout in seconds for connections to Kubernetes API. The minimum value is 5 | `5` |
|
||||
| [agent.kubernetesReadTimeout](./values.yaml#L937) | int | The read timeout in seconds for connections to Kubernetes API. The minimum value is 15 | `15` |
|
||||
| [agent.livenessProbe](./values.yaml#L984) | object | | `{}` |
|
||||
| [agent.maxRequestsPerHostStr](./values.yaml#L939) | string | The maximum concurrent connections to Kubernetes API | `"32"` |
|
||||
| [agent.namespace](./values.yaml#L945) | string | Namespace in which the Kubernetes agents should be launched | `nil` |
|
||||
| [agent.nodeSelector](./values.yaml#L1087) | object | Node labels for pod assignment | `{}` |
|
||||
| [agent.nodeUsageMode](./values.yaml#L957) | string | | `"NORMAL"` |
|
||||
| [agent.podLabels](./values.yaml#L947) | object | Custom Pod labels (an object with `label-key: label-value` pairs) | `{}` |
|
||||
| [agent.podName](./values.yaml#L1105) | string | Agent Pod base name | `"default"` |
|
||||
| [agent.podRetention](./values.yaml#L1003) | string | | `"Never"` |
|
||||
| [agent.podTemplates](./values.yaml#L1176) | object | Configures extra pod templates for the default kubernetes cloud | `{}` |
|
||||
| [agent.privileged](./values.yaml#L967) | bool | Agent privileged container | `false` |
|
||||
| [agent.resources](./values.yaml#L975) | object | Resources allocation (Requests and Limits) | `{"limits":{"cpu":"512m","memory":"512Mi"},"requests":{"cpu":"512m","memory":"512Mi"}}` |
|
||||
| [agent.restrictedPssSecurityContext](./values.yaml#L1000) | bool | Set a restricted securityContext on jnlp containers | `false` |
|
||||
| [agent.retentionTimeout](./values.yaml#L941) | int | Time in minutes after which the Kubernetes cloud plugin will clean up an idle worker that has not already terminated | `5` |
|
||||
| [agent.runAsGroup](./values.yaml#L971) | string | Configure container group | `nil` |
|
||||
| [agent.runAsUser](./values.yaml#L969) | string | Configure container user | `nil` |
|
||||
| [agent.secretEnvVars](./values.yaml#L1080) | list | Mount a secret as environment variable | `[]` |
|
||||
| [agent.serviceAccount](./values.yaml#L921) | string | Override the default service account | `serviceAccountAgent.name` if `agent.useDefaultServiceAccount` is `true` |
|
||||
| [agent.showRawYaml](./values.yaml#L1007) | bool | | `true` |
|
||||
| [agent.sideContainerName](./values.yaml#L1097) | string | Side container name | `"jnlp"` |
|
||||
| [agent.skipTlsVerify](./values.yaml#L931) | bool | Disables the verification of the controller certificate on remote connection. This flag correspond to the "Disable https certificate check" flag in kubernetes plugin UI | `false` |
|
||||
| [agent.usageRestricted](./values.yaml#L933) | bool | Enable the possibility to restrict the usage of this agent to specific folder. This flag correspond to the "Restrict pipeline support to authorized folders" flag in kubernetes plugin UI | `false` |
|
||||
| [agent.useDefaultServiceAccount](./values.yaml#L917) | bool | Use `serviceAccountAgent.name` as the default value for defaults template `serviceAccount` | `true` |
|
||||
| [agent.volumes](./values.yaml#L1014) | list | Additional volumes | `[]` |
|
||||
| [agent.waitForPodSec](./values.yaml#L943) | int | Seconds to wait for pod to be running | `600` |
|
||||
| [agent.websocket](./values.yaml#L964) | bool | Enables agent communication via websockets | `false` |
|
||||
| [agent.workingDir](./values.yaml#L956) | string | Configure working directory for default agent | `"/home/jenkins/agent"` |
|
||||
| [agent.workspaceVolume](./values.yaml#L1049) | object | Workspace volume (defaults to EmptyDir) | `{}` |
|
||||
| [agent.yamlMergeStrategy](./values.yaml#L1138) | string | Defines how the raw yaml field gets merged with yaml definitions from inherited pod templates. Possible values: "merge" or "override" | `"override"` |
|
||||
| [agent.yamlTemplate](./values.yaml#L1127) | string | The raw yaml of a Pod API Object to merge into the agent spec | `""` |
|
||||
| [awsSecurityGroupPolicies.enabled](./values.yaml#L1348) | bool | | `false` |
|
||||
| [awsSecurityGroupPolicies.policies[0].name](./values.yaml#L1350) | string | | `""` |
|
||||
| [awsSecurityGroupPolicies.policies[0].podSelector](./values.yaml#L1352) | object | | `{}` |
|
||||
| [awsSecurityGroupPolicies.policies[0].securityGroupIds](./values.yaml#L1351) | list | | `[]` |
|
||||
| [checkDeprecation](./values.yaml#L1345) | bool | Checks if any deprecated values are used | `true` |
|
||||
| [clusterZone](./values.yaml#L21) | string | Override the cluster name for FQDN resolving | `"cluster.local"` |
|
||||
| [controller.JCasC.authorizationStrategy](./values.yaml#L543) | string | Jenkins Config as Code Authorization Strategy-section | `"loggedInUsersCanDoAnything:\n allowAnonymousRead: false"` |
|
||||
| [controller.JCasC.configMapAnnotations](./values.yaml#L548) | object | Annotations for the JCasC ConfigMap | `{}` |
|
||||
| [controller.JCasC.configScripts](./values.yaml#L517) | object | List of Jenkins Config as Code scripts | `{}` |
|
||||
| [controller.JCasC.configUrls](./values.yaml#L514) | list | Remote URLs for configuration files. | `[]` |
|
||||
| [controller.JCasC.defaultConfig](./values.yaml#L508) | bool | Enables default Jenkins configuration via configuration as code plugin | `true` |
|
||||
| [controller.JCasC.overwriteConfiguration](./values.yaml#L512) | bool | Whether Jenkins Config as Code should overwrite any existing configuration | `false` |
|
||||
| [controller.JCasC.security](./values.yaml#L524) | object | Jenkins Config as Code security-section | `{"apiToken":{"creationOfLegacyTokenEnabled":false,"tokenGenerationOnCreationEnabled":false,"usageStatisticsEnabled":true}}` |
|
||||
| [controller.JCasC.securityRealm](./values.yaml#L532) | string | Jenkins Config as Code Security Realm-section | `"local:\n allowsSignup: false\n enableCaptcha: false\n users:\n - id: \"${chart-admin-username}\"\n name: \"Jenkins Admin\"\n password: \"${chart-admin-password}\""` |
|
||||
| [controller.additionalExistingSecrets](./values.yaml#L469) | list | List of additional existing secrets to mount | `[]` |
|
||||
| [controller.additionalPlugins](./values.yaml#L419) | list | List of plugins to install in addition to those listed in controller.installPlugins | `[]` |
|
||||
| [controller.additionalSecrets](./values.yaml#L478) | list | List of additional secrets to create and mount | `[]` |
|
||||
| [controller.JCasC.authorizationStrategy](./values.yaml#L539) | string | Jenkins Config as Code Authorization Strategy-section | `"loggedInUsersCanDoAnything:\n allowAnonymousRead: false"` |
|
||||
| [controller.JCasC.configMapAnnotations](./values.yaml#L544) | object | Annotations for the JCasC ConfigMap | `{}` |
|
||||
| [controller.JCasC.configScripts](./values.yaml#L513) | object | List of Jenkins Config as Code scripts | `{}` |
|
||||
| [controller.JCasC.configUrls](./values.yaml#L510) | list | Remote URLs for configuration files. | `[]` |
|
||||
| [controller.JCasC.defaultConfig](./values.yaml#L504) | bool | Enables default Jenkins configuration via configuration as code plugin | `true` |
|
||||
| [controller.JCasC.overwriteConfiguration](./values.yaml#L508) | bool | Whether Jenkins Config as Code should overwrite any existing configuration | `false` |
|
||||
| [controller.JCasC.security](./values.yaml#L520) | object | Jenkins Config as Code security-section | `{"apiToken":{"creationOfLegacyTokenEnabled":false,"tokenGenerationOnCreationEnabled":false,"usageStatisticsEnabled":true}}` |
|
||||
| [controller.JCasC.securityRealm](./values.yaml#L528) | string | Jenkins Config as Code Security Realm-section | `"local:\n allowsSignup: false\n enableCaptcha: false\n users:\n - id: \"${chart-admin-username}\"\n name: \"Jenkins Admin\"\n password: \"${chart-admin-password}\""` |
|
||||
| [controller.additionalExistingSecrets](./values.yaml#L465) | list | List of additional existing secrets to mount | `[]` |
|
||||
| [controller.additionalPlugins](./values.yaml#L415) | list | List of plugins to install in addition to those listed in controller.installPlugins | `[]` |
|
||||
| [controller.additionalSecrets](./values.yaml#L474) | list | List of additional secrets to create and mount | `[]` |
|
||||
| [controller.admin.createSecret](./values.yaml#L91) | bool | Create secret for admin user | `true` |
|
||||
| [controller.admin.existingSecret](./values.yaml#L94) | string | The name of an existing secret containing the admin credentials | `""` |
|
||||
| [controller.admin.password](./values.yaml#L81) | string | Admin password created as a secret if `controller.admin.createSecret` is true | `<random password>` |
|
||||
| [controller.admin.passwordKey](./values.yaml#L86) | string | The key in the existing admin secret containing the password | `"jenkins-admin-password"` |
|
||||
| [controller.admin.userKey](./values.yaml#L84) | string | The key in the existing admin secret containing the username | `"jenkins-admin-user"` |
|
||||
| [controller.admin.username](./values.yaml#L78) | string | Admin username created as a secret if `controller.admin.createSecret` is true | `"admin"` |
|
||||
| [controller.affinity](./values.yaml#L670) | object | Affinity settings | `{}` |
|
||||
| [controller.agentListenerEnabled](./values.yaml#L328) | bool | Create Agent listener service | `true` |
|
||||
| [controller.agentListenerExternalTrafficPolicy](./values.yaml#L338) | string | Traffic Policy of for the agentListener service | `nil` |
|
||||
| [controller.agentListenerHostPort](./values.yaml#L332) | string | Host port to listen for agents | `nil` |
|
||||
| [controller.agentListenerLoadBalancerIP](./values.yaml#L368) | string | Static IP for the agentListener LoadBalancer | `nil` |
|
||||
| [controller.agentListenerLoadBalancerSourceRanges](./values.yaml#L340) | list | Allowed inbound IP for the agentListener service | `["0.0.0.0/0"]` |
|
||||
| [controller.agentListenerNodePort](./values.yaml#L334) | string | Node port to listen for agents | `nil` |
|
||||
| [controller.agentListenerPort](./values.yaml#L330) | int | Listening port for agents | `50000` |
|
||||
| [controller.agentListenerServiceAnnotations](./values.yaml#L363) | object | Annotations for the agentListener service | `{}` |
|
||||
| [controller.agentListenerServiceType](./values.yaml#L360) | string | Defines how to expose the agentListener service | `"ClusterIP"` |
|
||||
| [controller.backendconfig.annotations](./values.yaml#L773) | object | backendconfig annotations | `{}` |
|
||||
| [controller.backendconfig.apiVersion](./values.yaml#L767) | string | backendconfig API version | `"extensions/v1beta1"` |
|
||||
| [controller.backendconfig.enabled](./values.yaml#L765) | bool | Enables backendconfig | `false` |
|
||||
| [controller.backendconfig.labels](./values.yaml#L771) | object | backendconfig labels | `{}` |
|
||||
| [controller.backendconfig.name](./values.yaml#L769) | string | backendconfig name | `nil` |
|
||||
| [controller.backendconfig.spec](./values.yaml#L775) | object | backendconfig spec | `{}` |
|
||||
| [controller.cloudName](./values.yaml#L497) | string | Name of default cloud configuration. | `"kubernetes"` |
|
||||
| [controller.affinity](./values.yaml#L666) | object | Affinity settings | `{}` |
|
||||
| [controller.agentListenerEnabled](./values.yaml#L324) | bool | Create Agent listener service | `true` |
|
||||
| [controller.agentListenerExternalTrafficPolicy](./values.yaml#L334) | string | Traffic Policy of for the agentListener service | `nil` |
|
||||
| [controller.agentListenerHostPort](./values.yaml#L328) | string | Host port to listen for agents | `nil` |
|
||||
| [controller.agentListenerLoadBalancerIP](./values.yaml#L364) | string | Static IP for the agentListener LoadBalancer | `nil` |
|
||||
| [controller.agentListenerLoadBalancerSourceRanges](./values.yaml#L336) | list | Allowed inbound IP for the agentListener service | `["0.0.0.0/0"]` |
|
||||
| [controller.agentListenerNodePort](./values.yaml#L330) | string | Node port to listen for agents | `nil` |
|
||||
| [controller.agentListenerPort](./values.yaml#L326) | int | Listening port for agents | `50000` |
|
||||
| [controller.agentListenerServiceAnnotations](./values.yaml#L359) | object | Annotations for the agentListener service | `{}` |
|
||||
| [controller.agentListenerServiceType](./values.yaml#L356) | string | Defines how to expose the agentListener service | `"ClusterIP"` |
|
||||
| [controller.backendconfig.annotations](./values.yaml#L769) | object | backendconfig annotations | `{}` |
|
||||
| [controller.backendconfig.apiVersion](./values.yaml#L763) | string | backendconfig API version | `"extensions/v1beta1"` |
|
||||
| [controller.backendconfig.enabled](./values.yaml#L761) | bool | Enables backendconfig | `false` |
|
||||
| [controller.backendconfig.labels](./values.yaml#L767) | object | backendconfig labels | `{}` |
|
||||
| [controller.backendconfig.name](./values.yaml#L765) | string | backendconfig name | `nil` |
|
||||
| [controller.backendconfig.spec](./values.yaml#L771) | object | backendconfig spec | `{}` |
|
||||
| [controller.cloudName](./values.yaml#L493) | string | Name of default cloud configuration. | `"kubernetes"` |
|
||||
| [controller.clusterIp](./values.yaml#L223) | string | k8s service clusterIP. Only used if serviceType is ClusterIP | `nil` |
|
||||
| [controller.componentName](./values.yaml#L34) | string | Used for label app.kubernetes.io/component | `"jenkins-controller"` |
|
||||
| [controller.containerEnv](./values.yaml#L156) | list | Environment variables for Jenkins Container | `[]` |
|
||||
| [controller.containerEnvFrom](./values.yaml#L153) | list | Environment variable sources for Jenkins Container | `[]` |
|
||||
| [controller.containerSecurityContext](./values.yaml#L211) | object | Allow controlling the securityContext for the jenkins container | `{"allowPrivilegeEscalation":false,"readOnlyRootFilesystem":true,"runAsGroup":1000,"runAsUser":1000}` |
|
||||
| [controller.csrf.defaultCrumbIssuer.enabled](./values.yaml#L349) | bool | Enable the default CSRF Crumb issuer | `true` |
|
||||
| [controller.csrf.defaultCrumbIssuer.proxyCompatability](./values.yaml#L351) | bool | Enable proxy compatibility | `true` |
|
||||
| [controller.customInitContainers](./values.yaml#L551) | list | Custom init-container specification in raw-yaml format | `[]` |
|
||||
| [controller.csrf.defaultCrumbIssuer.enabled](./values.yaml#L345) | bool | Enable the default CSRF Crumb issuer | `true` |
|
||||
| [controller.csrf.defaultCrumbIssuer.proxyCompatability](./values.yaml#L347) | bool | Enable proxy compatibility | `true` |
|
||||
| [controller.customInitContainers](./values.yaml#L547) | list | Custom init-container specification in raw-yaml format | `[]` |
|
||||
| [controller.customJenkinsLabels](./values.yaml#L68) | list | Append Jenkins labels to the controller | `[]` |
|
||||
| [controller.disableRememberMe](./values.yaml#L59) | bool | Disable use of remember me | `false` |
|
||||
| [controller.disabledAgentProtocols](./values.yaml#L343) | list | Disabled agent protocols | `["JNLP-connect","JNLP2-connect"]` |
|
||||
| [controller.enableRawHtmlMarkupFormatter](./values.yaml#L439) | bool | Enable HTML parsing using OWASP Markup Formatter Plugin (antisamy-markup-formatter) | `false` |
|
||||
| [controller.disabledAgentProtocols](./values.yaml#L339) | list | Disabled agent protocols | `["JNLP-connect","JNLP2-connect"]` |
|
||||
| [controller.enableRawHtmlMarkupFormatter](./values.yaml#L435) | bool | Enable HTML parsing using OWASP Markup Formatter Plugin (antisamy-markup-formatter) | `false` |
|
||||
| [controller.enableServiceLinks](./values.yaml#L130) | bool | | `false` |
|
||||
| [controller.executorMode](./values.yaml#L65) | string | Sets the executor mode of the Jenkins node. Possible values are "NORMAL" or "EXCLUSIVE" | `"NORMAL"` |
|
||||
| [controller.existingSecret](./values.yaml#L466) | string | | `nil` |
|
||||
| [controller.extraPorts](./values.yaml#L398) | list | Optionally configure other ports to expose in the controller container | `[]` |
|
||||
| [controller.existingSecret](./values.yaml#L462) | string | | `nil` |
|
||||
| [controller.extraPorts](./values.yaml#L394) | list | Optionally configure other ports to expose in the controller container | `[]` |
|
||||
| [controller.fsGroup](./values.yaml#L192) | int | Deprecated in favor of `controller.podSecurityContextOverride`. uid that will be used for persistent volume. | `1000` |
|
||||
| [controller.googlePodMonitor.enabled](./values.yaml#L836) | bool | | `false` |
|
||||
| [controller.googlePodMonitor.scrapeEndpoint](./values.yaml#L841) | string | | `"/prometheus"` |
|
||||
| [controller.googlePodMonitor.scrapeInterval](./values.yaml#L839) | string | | `"60s"` |
|
||||
| [controller.healthProbes](./values.yaml#L258) | bool | Enable Kubernetes Probes configuration configured in `controller.probes` | `true` |
|
||||
| [controller.hostAliases](./values.yaml#L789) | list | Allows for adding entries to Pod /etc/hosts | `[]` |
|
||||
| [controller.googlePodMonitor.enabled](./values.yaml#L832) | bool | | `false` |
|
||||
| [controller.googlePodMonitor.scrapeEndpoint](./values.yaml#L837) | string | | `"/prometheus"` |
|
||||
| [controller.googlePodMonitor.scrapeInterval](./values.yaml#L835) | string | | `"60s"` |
|
||||
| [controller.healthProbes](./values.yaml#L254) | bool | Enable Kubernetes Probes configuration configured in `controller.probes` | `true` |
|
||||
| [controller.hostAliases](./values.yaml#L785) | list | Allows for adding entries to Pod /etc/hosts | `[]` |
|
||||
| [controller.hostNetworking](./values.yaml#L70) | bool | | `false` |
|
||||
| [controller.httpsKeyStore.disableSecretMount](./values.yaml#L857) | bool | | `false` |
|
||||
| [controller.httpsKeyStore.enable](./values.yaml#L848) | bool | Enables HTTPS keystore on jenkins controller | `false` |
|
||||
| [controller.httpsKeyStore.fileName](./values.yaml#L865) | string | Jenkins keystore filename which will appear under controller.httpsKeyStore.path | `"keystore.jks"` |
|
||||
| [controller.httpsKeyStore.httpPort](./values.yaml#L861) | int | HTTP Port that Jenkins should listen to along with HTTPS, it also serves as the liveness and readiness probes port. | `8081` |
|
||||
| [controller.httpsKeyStore.jenkinsHttpsJksPasswordSecretKey](./values.yaml#L856) | string | Name of the key in the secret that contains the JKS password | `"https-jks-password"` |
|
||||
| [controller.httpsKeyStore.jenkinsHttpsJksPasswordSecretName](./values.yaml#L854) | string | Name of the secret that contains the JKS password, if it is not in the same secret as the JKS file | `""` |
|
||||
| [controller.httpsKeyStore.jenkinsHttpsJksSecretKey](./values.yaml#L852) | string | Name of the key in the secret that already has ssl keystore | `"jenkins-jks-file"` |
|
||||
| [controller.httpsKeyStore.jenkinsHttpsJksSecretName](./values.yaml#L850) | string | Name of the secret that already has ssl keystore | `""` |
|
||||
| [controller.httpsKeyStore.jenkinsKeyStoreBase64Encoded](./values.yaml#L870) | string | Base64 encoded Keystore content. Keystore must be converted to base64 then being pasted here | `nil` |
|
||||
| [controller.httpsKeyStore.password](./values.yaml#L867) | string | Jenkins keystore password | `"password"` |
|
||||
| [controller.httpsKeyStore.path](./values.yaml#L863) | string | Path of HTTPS keystore file | `"/var/jenkins_keystore"` |
|
||||
| [controller.httpsKeyStore.disableSecretMount](./values.yaml#L853) | bool | | `false` |
|
||||
| [controller.httpsKeyStore.enable](./values.yaml#L844) | bool | Enables HTTPS keystore on jenkins controller | `false` |
|
||||
| [controller.httpsKeyStore.fileName](./values.yaml#L861) | string | Jenkins keystore filename which will appear under controller.httpsKeyStore.path | `"keystore.jks"` |
|
||||
| [controller.httpsKeyStore.httpPort](./values.yaml#L857) | int | HTTP Port that Jenkins should listen to along with HTTPS, it also serves as the liveness and readiness probes port. | `8081` |
|
||||
| [controller.httpsKeyStore.jenkinsHttpsJksPasswordSecretKey](./values.yaml#L852) | string | Name of the key in the secret that contains the JKS password | `"https-jks-password"` |
|
||||
| [controller.httpsKeyStore.jenkinsHttpsJksPasswordSecretName](./values.yaml#L850) | string | Name of the secret that contains the JKS password, if it is not in the same secret as the JKS file | `""` |
|
||||
| [controller.httpsKeyStore.jenkinsHttpsJksSecretKey](./values.yaml#L848) | string | Name of the key in the secret that already has ssl keystore | `"jenkins-jks-file"` |
|
||||
| [controller.httpsKeyStore.jenkinsHttpsJksSecretName](./values.yaml#L846) | string | Name of the secret that already has ssl keystore | `""` |
|
||||
| [controller.httpsKeyStore.jenkinsKeyStoreBase64Encoded](./values.yaml#L866) | string | Base64 encoded Keystore content. Keystore must be converted to base64 then being pasted here | `nil` |
|
||||
| [controller.httpsKeyStore.password](./values.yaml#L863) | string | Jenkins keystore password | `"password"` |
|
||||
| [controller.httpsKeyStore.path](./values.yaml#L859) | string | Path of HTTPS keystore file | `"/var/jenkins_keystore"` |
|
||||
| [controller.image.pullPolicy](./values.yaml#L47) | string | Controller image pull policy | `"Always"` |
|
||||
| [controller.image.registry](./values.yaml#L37) | string | Controller image registry | `"docker.io"` |
|
||||
| [controller.image.repository](./values.yaml#L39) | string | Controller image repository | `"jenkins/jenkins"` |
|
||||
| [controller.image.tag](./values.yaml#L42) | string | Controller image tag override; i.e., tag: "2.440.1-jdk17" | `nil` |
|
||||
| [controller.image.tagLabel](./values.yaml#L45) | string | Controller image tag label | `"jdk17"` |
|
||||
| [controller.imagePullSecretName](./values.yaml#L49) | string | Controller image pull secret | `nil` |
|
||||
| [controller.ingress.annotations](./values.yaml#L712) | object | Ingress annotations | `{}` |
|
||||
| [controller.ingress.apiVersion](./values.yaml#L708) | string | Ingress API version | `"extensions/v1beta1"` |
|
||||
| [controller.ingress.enabled](./values.yaml#L691) | bool | Enables ingress | `false` |
|
||||
| [controller.ingress.hostName](./values.yaml#L725) | string | Ingress hostname | `nil` |
|
||||
| [controller.ingress.labels](./values.yaml#L710) | object | Ingress labels | `{}` |
|
||||
| [controller.ingress.path](./values.yaml#L721) | string | Ingress path | `nil` |
|
||||
| [controller.ingress.paths](./values.yaml#L695) | list | Override for the default Ingress paths | `[]` |
|
||||
| [controller.ingress.resourceRootUrl](./values.yaml#L727) | string | Hostname to serve assets from | `nil` |
|
||||
| [controller.ingress.tls](./values.yaml#L729) | list | Ingress TLS configuration | `[]` |
|
||||
| [controller.initConfigMap](./values.yaml#L456) | string | Name of the existing ConfigMap that contains init scripts | `nil` |
|
||||
| [controller.ingress.annotations](./values.yaml#L708) | object | Ingress annotations | `{}` |
|
||||
| [controller.ingress.apiVersion](./values.yaml#L704) | string | Ingress API version | `"extensions/v1beta1"` |
|
||||
| [controller.ingress.enabled](./values.yaml#L687) | bool | Enables ingress | `false` |
|
||||
| [controller.ingress.hostName](./values.yaml#L721) | string | Ingress hostname | `nil` |
|
||||
| [controller.ingress.labels](./values.yaml#L706) | object | Ingress labels | `{}` |
|
||||
| [controller.ingress.path](./values.yaml#L717) | string | Ingress path | `nil` |
|
||||
| [controller.ingress.paths](./values.yaml#L691) | list | Override for the default Ingress paths | `[]` |
|
||||
| [controller.ingress.resourceRootUrl](./values.yaml#L723) | string | Hostname to serve assets from | `nil` |
|
||||
| [controller.ingress.tls](./values.yaml#L725) | list | Ingress TLS configuration | `[]` |
|
||||
| [controller.initConfigMap](./values.yaml#L452) | string | Name of the existing ConfigMap that contains init scripts | `nil` |
|
||||
| [controller.initContainerEnv](./values.yaml#L147) | list | Environment variables for Init Container | `[]` |
|
||||
| [controller.initContainerEnvFrom](./values.yaml#L143) | list | Environment variable sources for Init Container | `[]` |
|
||||
| [controller.initContainerResources](./values.yaml#L134) | object | Resources allocation (Requests and Limits) for Init Container | `{}` |
|
||||
| [controller.initScripts](./values.yaml#L452) | object | Map of groovy init scripts to be executed during Jenkins controller start | `{}` |
|
||||
| [controller.initializeOnce](./values.yaml#L424) | bool | Initialize only on first installation. Ensures plugins do not get updated inadvertently. Requires `persistence.enabled` to be set to `true` | `false` |
|
||||
| [controller.installLatestPlugins](./values.yaml#L413) | bool | Download the minimum required version or latest version of all dependencies | `true` |
|
||||
| [controller.installLatestSpecifiedPlugins](./values.yaml#L416) | bool | Set to true to download the latest version of any plugin that is requested to have the latest version | `false` |
|
||||
| [controller.installPlugins](./values.yaml#L405) | list | List of Jenkins plugins to install. If you don't want to install plugins, set it to `false` | `["kubernetes:4313.va_9b_4fe2a_0e34","workflow-aggregator:600.vb_57cdd26fdd7","git:5.7.0","configuration-as-code:1932.v75cb_b_f1b_698d"]` |
|
||||
| [controller.initScripts](./values.yaml#L448) | object | Map of groovy init scripts to be executed during Jenkins controller start | `{}` |
|
||||
| [controller.initializeOnce](./values.yaml#L420) | bool | Initialize only on first installation. Ensures plugins do not get updated inadvertently. Requires `persistence.enabled` to be set to `true` | `false` |
|
||||
| [controller.installLatestPlugins](./values.yaml#L409) | bool | Download the minimum required version or latest version of all dependencies | `true` |
|
||||
| [controller.installLatestSpecifiedPlugins](./values.yaml#L412) | bool | Set to true to download the latest version of any plugin that is requested to have the latest version | `false` |
|
||||
| [controller.installPlugins](./values.yaml#L401) | list | List of Jenkins plugins to install. If you don't want to install plugins, set it to `false` | `["kubernetes:4296.v20a_7e4d77cf6","workflow-aggregator:600.vb_57cdd26fdd7","git:5.6.0","configuration-as-code:1897.v79281e066ea_7"]` |
|
||||
| [controller.javaOpts](./values.yaml#L162) | string | Append to `JAVA_OPTS` env var | `nil` |
|
||||
| [controller.jenkinsAdminEmail](./values.yaml#L96) | string | Email address for the administrator of the Jenkins instance | `nil` |
|
||||
| [controller.jenkinsHome](./values.yaml#L101) | string | Custom Jenkins home path | `"/var/jenkins_home"` |
|
||||
@ -175,147 +175,144 @@ The following tables list the configurable parameters of the Jenkins chart and t
|
||||
| [controller.jenkinsUrl](./values.yaml#L174) | string | Set Jenkins URL if you are not using the ingress definitions provided by the chart | `nil` |
|
||||
| [controller.jenkinsUrlProtocol](./values.yaml#L171) | string | Set protocol for Jenkins URL; `https` if `controller.ingress.tls`, `http` otherwise | `nil` |
|
||||
| [controller.jenkinsWar](./values.yaml#L109) | string | | `"/usr/share/jenkins/jenkins.war"` |
|
||||
| [controller.jmxPort](./values.yaml#L395) | string | Open a port, for JMX stats | `nil` |
|
||||
| [controller.legacyRemotingSecurityEnabled](./values.yaml#L371) | bool | Whether legacy remoting security should be enabled | `false` |
|
||||
| [controller.jmxPort](./values.yaml#L391) | string | Open a port, for JMX stats | `nil` |
|
||||
| [controller.legacyRemotingSecurityEnabled](./values.yaml#L367) | bool | Whether legacy remoting security should be enabled | `false` |
|
||||
| [controller.lifecycle](./values.yaml#L51) | object | Lifecycle specification for controller-container | `{}` |
|
||||
| [controller.loadBalancerIP](./values.yaml#L386) | string | Optionally assign a known public LB IP | `nil` |
|
||||
| [controller.loadBalancerSourceRanges](./values.yaml#L382) | list | Allowed inbound IP addresses | `["0.0.0.0/0"]` |
|
||||
| [controller.markupFormatter](./values.yaml#L443) | string | Yaml of the markup formatter to use | `"plainText"` |
|
||||
| [controller.loadBalancerIP](./values.yaml#L382) | string | Optionally assign a known public LB IP | `nil` |
|
||||
| [controller.loadBalancerSourceRanges](./values.yaml#L378) | list | Allowed inbound IP addresses | `["0.0.0.0/0"]` |
|
||||
| [controller.markupFormatter](./values.yaml#L439) | string | Yaml of the markup formatter to use | `"plainText"` |
|
||||
| [controller.nodePort](./values.yaml#L229) | string | k8s node port. Only used if serviceType is NodePort | `nil` |
|
||||
| [controller.nodeSelector](./values.yaml#L657) | object | Node labels for pod assignment | `{}` |
|
||||
| [controller.nodeSelector](./values.yaml#L653) | object | Node labels for pod assignment | `{}` |
|
||||
| [controller.numExecutors](./values.yaml#L62) | int | Set Number of executors | `0` |
|
||||
| [controller.overwritePlugins](./values.yaml#L428) | bool | Overwrite installed plugins on start | `false` |
|
||||
| [controller.overwritePluginsFromImage](./values.yaml#L432) | bool | Overwrite plugins that are already installed in the controller image | `true` |
|
||||
| [controller.podAnnotations](./values.yaml#L678) | object | Annotations for controller pod | `{}` |
|
||||
| [controller.podDisruptionBudget.annotations](./values.yaml#L322) | object | | `{}` |
|
||||
| [controller.podDisruptionBudget.apiVersion](./values.yaml#L320) | string | Policy API version | `"policy/v1beta1"` |
|
||||
| [controller.podDisruptionBudget.enabled](./values.yaml#L315) | bool | Enable Kubernetes Pod Disruption Budget configuration | `false` |
|
||||
| [controller.podDisruptionBudget.labels](./values.yaml#L323) | object | | `{}` |
|
||||
| [controller.podDisruptionBudget.maxUnavailable](./values.yaml#L325) | string | Number of pods that can be unavailable. Either an absolute number or a percentage | `"0"` |
|
||||
| [controller.podLabels](./values.yaml#L251) | object | Custom Pod labels (an object with `label-key: label-value` pairs) | `{}` |
|
||||
| [controller.overwritePlugins](./values.yaml#L424) | bool | Overwrite installed plugins on start | `false` |
|
||||
| [controller.overwritePluginsFromImage](./values.yaml#L428) | bool | Overwrite plugins that are already installed in the controller image | `true` |
|
||||
| [controller.podAnnotations](./values.yaml#L674) | object | Annotations for controller pod | `{}` |
|
||||
| [controller.podDisruptionBudget.annotations](./values.yaml#L318) | object | | `{}` |
|
||||
| [controller.podDisruptionBudget.apiVersion](./values.yaml#L316) | string | Policy API version | `"policy/v1beta1"` |
|
||||
| [controller.podDisruptionBudget.enabled](./values.yaml#L311) | bool | Enable Kubernetes Pod Disruption Budget configuration | `false` |
|
||||
| [controller.podDisruptionBudget.labels](./values.yaml#L319) | object | | `{}` |
|
||||
| [controller.podDisruptionBudget.maxUnavailable](./values.yaml#L321) | string | Number of pods that can be unavailable. Either an absolute number or a percentage | `"0"` |
|
||||
| [controller.podLabels](./values.yaml#L247) | object | Custom Pod labels (an object with `label-key: label-value` pairs) | `{}` |
|
||||
| [controller.podSecurityContextOverride](./values.yaml#L208) | string | Completely overwrites the contents of the pod security context, ignoring the values provided for `runAsUser`, `fsGroup`, and `securityContextCapabilities` | `nil` |
|
||||
| [controller.priorityClassName](./values.yaml#L675) | string | The name of a `priorityClass` to apply to the controller pod | `nil` |
|
||||
| [controller.probes.livenessProbe.failureThreshold](./values.yaml#L276) | int | Set the failure threshold for the liveness probe | `5` |
|
||||
| [controller.probes.livenessProbe.httpGet.path](./values.yaml#L279) | string | Set the Pod's HTTP path for the liveness probe | `"{{ default \"\" .Values.controller.jenkinsUriPrefix }}/login"` |
|
||||
| [controller.probes.livenessProbe.httpGet.port](./values.yaml#L281) | string | Set the Pod's HTTP port to use for the liveness probe | `"http"` |
|
||||
| [controller.probes.livenessProbe.initialDelaySeconds](./values.yaml#L290) | string | Set the initial delay for the liveness probe in seconds | `nil` |
|
||||
| [controller.probes.livenessProbe.periodSeconds](./values.yaml#L283) | int | Set the time interval between two liveness probes executions in seconds | `10` |
|
||||
| [controller.probes.livenessProbe.timeoutSeconds](./values.yaml#L285) | int | Set the timeout for the liveness probe in seconds | `5` |
|
||||
| [controller.probes.readinessProbe.failureThreshold](./values.yaml#L294) | int | Set the failure threshold for the readiness probe | `3` |
|
||||
| [controller.probes.readinessProbe.httpGet.path](./values.yaml#L297) | string | Set the Pod's HTTP path for the liveness probe | `"{{ default \"\" .Values.controller.jenkinsUriPrefix }}/login"` |
|
||||
| [controller.probes.readinessProbe.httpGet.port](./values.yaml#L299) | string | Set the Pod's HTTP port to use for the readiness probe | `"http"` |
|
||||
| [controller.probes.readinessProbe.initialDelaySeconds](./values.yaml#L308) | string | Set the initial delay for the readiness probe in seconds | `nil` |
|
||||
| [controller.probes.readinessProbe.periodSeconds](./values.yaml#L301) | int | Set the time interval between two readiness probes executions in seconds | `10` |
|
||||
| [controller.probes.readinessProbe.timeoutSeconds](./values.yaml#L303) | int | Set the timeout for the readiness probe in seconds | `5` |
|
||||
| [controller.probes.startupProbe.failureThreshold](./values.yaml#L263) | int | Set the failure threshold for the startup probe | `12` |
|
||||
| [controller.probes.startupProbe.httpGet.path](./values.yaml#L266) | string | Set the Pod's HTTP path for the startup probe | `"{{ default \"\" .Values.controller.jenkinsUriPrefix }}/login"` |
|
||||
| [controller.probes.startupProbe.httpGet.port](./values.yaml#L268) | string | Set the Pod's HTTP port to use for the startup probe | `"http"` |
|
||||
| [controller.probes.startupProbe.periodSeconds](./values.yaml#L270) | int | Set the time interval between two startup probes executions in seconds | `10` |
|
||||
| [controller.probes.startupProbe.timeoutSeconds](./values.yaml#L272) | int | Set the timeout for the startup probe in seconds | `5` |
|
||||
| [controller.projectNamingStrategy](./values.yaml#L435) | string | | `"standard"` |
|
||||
| [controller.prometheus.alertingRulesAdditionalLabels](./values.yaml#L822) | object | Additional labels to add to the PrometheusRule object | `{}` |
|
||||
| [controller.prometheus.alertingrules](./values.yaml#L820) | list | Array of prometheus alerting rules | `[]` |
|
||||
| [controller.prometheus.enabled](./values.yaml#L805) | bool | Enables prometheus service monitor | `false` |
|
||||
| [controller.prometheus.metricRelabelings](./values.yaml#L832) | list | | `[]` |
|
||||
| [controller.prometheus.prometheusRuleNamespace](./values.yaml#L824) | string | Set a custom namespace where to deploy PrometheusRule resource | `""` |
|
||||
| [controller.prometheus.relabelings](./values.yaml#L830) | list | | `[]` |
|
||||
| [controller.prometheus.scrapeEndpoint](./values.yaml#L815) | string | The endpoint prometheus should get metrics from | `"/prometheus"` |
|
||||
| [controller.prometheus.scrapeInterval](./values.yaml#L811) | string | How often prometheus should scrape metrics | `"60s"` |
|
||||
| [controller.prometheus.serviceMonitorAdditionalLabels](./values.yaml#L807) | object | Additional labels to add to the service monitor object | `{}` |
|
||||
| [controller.prometheus.serviceMonitorNamespace](./values.yaml#L809) | string | Set a custom namespace where to deploy ServiceMonitor resource | `nil` |
|
||||
| [controller.publishNotReadyAddresses](./values.yaml#L237) | string | | `nil` |
|
||||
| [controller.priorityClassName](./values.yaml#L671) | string | The name of a `priorityClass` to apply to the controller pod | `nil` |
|
||||
| [controller.probes.livenessProbe.failureThreshold](./values.yaml#L272) | int | Set the failure threshold for the liveness probe | `5` |
|
||||
| [controller.probes.livenessProbe.httpGet.path](./values.yaml#L275) | string | Set the Pod's HTTP path for the liveness probe | `"{{ default \"\" .Values.controller.jenkinsUriPrefix }}/login"` |
|
||||
| [controller.probes.livenessProbe.httpGet.port](./values.yaml#L277) | string | Set the Pod's HTTP port to use for the liveness probe | `"http"` |
|
||||
| [controller.probes.livenessProbe.initialDelaySeconds](./values.yaml#L286) | string | Set the initial delay for the liveness probe in seconds | `nil` |
|
||||
| [controller.probes.livenessProbe.periodSeconds](./values.yaml#L279) | int | Set the time interval between two liveness probes executions in seconds | `10` |
|
||||
| [controller.probes.livenessProbe.timeoutSeconds](./values.yaml#L281) | int | Set the timeout for the liveness probe in seconds | `5` |
|
||||
| [controller.probes.readinessProbe.failureThreshold](./values.yaml#L290) | int | Set the failure threshold for the readiness probe | `3` |
|
||||
| [controller.probes.readinessProbe.httpGet.path](./values.yaml#L293) | string | Set the Pod's HTTP path for the liveness probe | `"{{ default \"\" .Values.controller.jenkinsUriPrefix }}/login"` |
|
||||
| [controller.probes.readinessProbe.httpGet.port](./values.yaml#L295) | string | Set the Pod's HTTP port to use for the readiness probe | `"http"` |
|
||||
| [controller.probes.readinessProbe.initialDelaySeconds](./values.yaml#L304) | string | Set the initial delay for the readiness probe in seconds | `nil` |
|
||||
| [controller.probes.readinessProbe.periodSeconds](./values.yaml#L297) | int | Set the time interval between two readiness probes executions in seconds | `10` |
|
||||
| [controller.probes.readinessProbe.timeoutSeconds](./values.yaml#L299) | int | Set the timeout for the readiness probe in seconds | `5` |
|
||||
| [controller.probes.startupProbe.failureThreshold](./values.yaml#L259) | int | Set the failure threshold for the startup probe | `12` |
|
||||
| [controller.probes.startupProbe.httpGet.path](./values.yaml#L262) | string | Set the Pod's HTTP path for the startup probe | `"{{ default \"\" .Values.controller.jenkinsUriPrefix }}/login"` |
|
||||
| [controller.probes.startupProbe.httpGet.port](./values.yaml#L264) | string | Set the Pod's HTTP port to use for the startup probe | `"http"` |
|
||||
| [controller.probes.startupProbe.periodSeconds](./values.yaml#L266) | int | Set the time interval between two startup probes executions in seconds | `10` |
|
||||
| [controller.probes.startupProbe.timeoutSeconds](./values.yaml#L268) | int | Set the timeout for the startup probe in seconds | `5` |
|
||||
| [controller.projectNamingStrategy](./values.yaml#L431) | string | | `"standard"` |
|
||||
| [controller.prometheus.alertingRulesAdditionalLabels](./values.yaml#L818) | object | Additional labels to add to the PrometheusRule object | `{}` |
|
||||
| [controller.prometheus.alertingrules](./values.yaml#L816) | list | Array of prometheus alerting rules | `[]` |
|
||||
| [controller.prometheus.enabled](./values.yaml#L801) | bool | Enables prometheus service monitor | `false` |
|
||||
| [controller.prometheus.metricRelabelings](./values.yaml#L828) | list | | `[]` |
|
||||
| [controller.prometheus.prometheusRuleNamespace](./values.yaml#L820) | string | Set a custom namespace where to deploy PrometheusRule resource | `""` |
|
||||
| [controller.prometheus.relabelings](./values.yaml#L826) | list | | `[]` |
|
||||
| [controller.prometheus.scrapeEndpoint](./values.yaml#L811) | string | The endpoint prometheus should get metrics from | `"/prometheus"` |
|
||||
| [controller.prometheus.scrapeInterval](./values.yaml#L807) | string | How often prometheus should scrape metrics | `"60s"` |
|
||||
| [controller.prometheus.serviceMonitorAdditionalLabels](./values.yaml#L803) | object | Additional labels to add to the service monitor object | `{}` |
|
||||
| [controller.prometheus.serviceMonitorNamespace](./values.yaml#L805) | string | Set a custom namespace where to deploy ServiceMonitor resource | `nil` |
|
||||
| [controller.resources](./values.yaml#L115) | object | Resource allocation (Requests and Limits) | `{"limits":{"cpu":"2000m","memory":"4096Mi"},"requests":{"cpu":"50m","memory":"256Mi"}}` |
|
||||
| [controller.route.annotations](./values.yaml#L784) | object | Route annotations | `{}` |
|
||||
| [controller.route.enabled](./values.yaml#L780) | bool | Enables openshift route | `false` |
|
||||
| [controller.route.labels](./values.yaml#L782) | object | Route labels | `{}` |
|
||||
| [controller.route.path](./values.yaml#L786) | string | Route path | `nil` |
|
||||
| [controller.route.annotations](./values.yaml#L780) | object | Route annotations | `{}` |
|
||||
| [controller.route.enabled](./values.yaml#L776) | bool | Enables openshift route | `false` |
|
||||
| [controller.route.labels](./values.yaml#L778) | object | Route labels | `{}` |
|
||||
| [controller.route.path](./values.yaml#L782) | string | Route path | `nil` |
|
||||
| [controller.runAsUser](./values.yaml#L189) | int | Deprecated in favor of `controller.podSecurityContextOverride`. uid that jenkins runs with. | `1000` |
|
||||
| [controller.schedulerName](./values.yaml#L653) | string | Name of the Kubernetes scheduler to use | `""` |
|
||||
| [controller.scriptApproval](./values.yaml#L447) | list | List of groovy functions to approve | `[]` |
|
||||
| [controller.secondaryingress.annotations](./values.yaml#L747) | object | | `{}` |
|
||||
| [controller.secondaryingress.apiVersion](./values.yaml#L745) | string | | `"extensions/v1beta1"` |
|
||||
| [controller.secondaryingress.enabled](./values.yaml#L739) | bool | | `false` |
|
||||
| [controller.secondaryingress.hostName](./values.yaml#L754) | string | | `nil` |
|
||||
| [controller.secondaryingress.labels](./values.yaml#L746) | object | | `{}` |
|
||||
| [controller.secondaryingress.paths](./values.yaml#L742) | list | | `[]` |
|
||||
| [controller.secondaryingress.tls](./values.yaml#L755) | string | | `nil` |
|
||||
| [controller.secretClaims](./values.yaml#L490) | list | List of `SecretClaim` resources to create | `[]` |
|
||||
| [controller.schedulerName](./values.yaml#L649) | string | Name of the Kubernetes scheduler to use | `""` |
|
||||
| [controller.scriptApproval](./values.yaml#L443) | list | List of groovy functions to approve | `[]` |
|
||||
| [controller.secondaryingress.annotations](./values.yaml#L743) | object | | `{}` |
|
||||
| [controller.secondaryingress.apiVersion](./values.yaml#L741) | string | | `"extensions/v1beta1"` |
|
||||
| [controller.secondaryingress.enabled](./values.yaml#L735) | bool | | `false` |
|
||||
| [controller.secondaryingress.hostName](./values.yaml#L750) | string | | `nil` |
|
||||
| [controller.secondaryingress.labels](./values.yaml#L742) | object | | `{}` |
|
||||
| [controller.secondaryingress.paths](./values.yaml#L738) | list | | `[]` |
|
||||
| [controller.secondaryingress.tls](./values.yaml#L751) | string | | `nil` |
|
||||
| [controller.secretClaims](./values.yaml#L486) | list | List of `SecretClaim` resources to create | `[]` |
|
||||
| [controller.securityContextCapabilities](./values.yaml#L198) | object | | `{}` |
|
||||
| [controller.serviceAnnotations](./values.yaml#L240) | object | Jenkins controller service annotations | `{}` |
|
||||
| [controller.serviceAnnotations](./values.yaml#L236) | object | Jenkins controller service annotations | `{}` |
|
||||
| [controller.serviceExternalTrafficPolicy](./values.yaml#L233) | string | | `nil` |
|
||||
| [controller.serviceLabels](./values.yaml#L246) | object | Labels for the Jenkins controller-service | `{}` |
|
||||
| [controller.serviceLabels](./values.yaml#L242) | object | Labels for the Jenkins controller-service | `{}` |
|
||||
| [controller.servicePort](./values.yaml#L225) | int | k8s service port | `8080` |
|
||||
| [controller.serviceType](./values.yaml#L220) | string | k8s service type | `"ClusterIP"` |
|
||||
| [controller.shareProcessNamespace](./values.yaml#L124) | bool | | `false` |
|
||||
| [controller.sidecars.additionalSidecarContainers](./values.yaml#L635) | list | Configures additional sidecar container(s) for the Jenkins controller | `[]` |
|
||||
| [controller.sidecars.configAutoReload.additionalVolumeMounts](./values.yaml#L581) | list | Enables additional volume mounts for the config auto-reload container | `[]` |
|
||||
| [controller.sidecars.configAutoReload.containerSecurityContext](./values.yaml#L630) | object | Enable container security context | `{"allowPrivilegeEscalation":false,"readOnlyRootFilesystem":true}` |
|
||||
| [controller.sidecars.configAutoReload.enabled](./values.yaml#L564) | bool | Enables Jenkins Config as Code auto-reload | `true` |
|
||||
| [controller.sidecars.configAutoReload.env](./values.yaml#L612) | object | Environment variables for the Jenkins Config as Code auto-reload container | `{}` |
|
||||
| [controller.sidecars.configAutoReload.envFrom](./values.yaml#L610) | list | Environment variable sources for the Jenkins Config as Code auto-reload container | `[]` |
|
||||
| [controller.sidecars.configAutoReload.folder](./values.yaml#L623) | string | | `"/var/jenkins_home/casc_configs"` |
|
||||
| [controller.sidecars.configAutoReload.image.registry](./values.yaml#L567) | string | Registry for the image that triggers the reload | `"docker.io"` |
|
||||
| [controller.sidecars.configAutoReload.image.repository](./values.yaml#L569) | string | Repository of the image that triggers the reload | `"kiwigrid/k8s-sidecar"` |
|
||||
| [controller.sidecars.configAutoReload.image.tag](./values.yaml#L571) | string | Tag for the image that triggers the reload | `"1.30.1"` |
|
||||
| [controller.sidecars.configAutoReload.imagePullPolicy](./values.yaml#L572) | string | | `"IfNotPresent"` |
|
||||
| [controller.sidecars.configAutoReload.logging](./values.yaml#L587) | object | Config auto-reload logging settings | `{"configuration":{"backupCount":3,"formatter":"JSON","logLevel":"INFO","logToConsole":true,"logToFile":false,"maxBytes":1024,"override":false}}` |
|
||||
| [controller.sidecars.configAutoReload.logging.configuration.override](./values.yaml#L591) | bool | Enables custom log config utilizing using the settings below. | `false` |
|
||||
| [controller.sidecars.configAutoReload.reqRetryConnect](./values.yaml#L605) | int | How many connection-related errors to retry on | `10` |
|
||||
| [controller.sidecars.configAutoReload.resources](./values.yaml#L573) | object | | `{}` |
|
||||
| [controller.sidecars.configAutoReload.scheme](./values.yaml#L600) | string | The scheme to use when connecting to the Jenkins configuration as code endpoint | `"http"` |
|
||||
| [controller.sidecars.configAutoReload.skipTlsVerify](./values.yaml#L602) | bool | Skip TLS verification when connecting to the Jenkins configuration as code endpoint | `false` |
|
||||
| [controller.sidecars.configAutoReload.sleepTime](./values.yaml#L607) | string | How many seconds to wait before updating config-maps/secrets (sets METHOD=SLEEP on the sidecar) | `nil` |
|
||||
| [controller.sidecars.configAutoReload.sshTcpPort](./values.yaml#L621) | int | | `1044` |
|
||||
| [controller.statefulSetAnnotations](./values.yaml#L680) | object | Annotations for controller StatefulSet | `{}` |
|
||||
| [controller.statefulSetLabels](./values.yaml#L242) | object | Jenkins controller custom labels for the StatefulSet | `{}` |
|
||||
| [controller.sidecars.additionalSidecarContainers](./values.yaml#L631) | list | Configures additional sidecar container(s) for the Jenkins controller | `[]` |
|
||||
| [controller.sidecars.configAutoReload.additionalVolumeMounts](./values.yaml#L577) | list | Enables additional volume mounts for the config auto-reload container | `[]` |
|
||||
| [controller.sidecars.configAutoReload.containerSecurityContext](./values.yaml#L626) | object | Enable container security context | `{"allowPrivilegeEscalation":false,"readOnlyRootFilesystem":true}` |
|
||||
| [controller.sidecars.configAutoReload.enabled](./values.yaml#L560) | bool | Enables Jenkins Config as Code auto-reload | `true` |
|
||||
| [controller.sidecars.configAutoReload.env](./values.yaml#L608) | object | Environment variables for the Jenkins Config as Code auto-reload container | `{}` |
|
||||
| [controller.sidecars.configAutoReload.envFrom](./values.yaml#L606) | list | Environment variable sources for the Jenkins Config as Code auto-reload container | `[]` |
|
||||
| [controller.sidecars.configAutoReload.folder](./values.yaml#L619) | string | | `"/var/jenkins_home/casc_configs"` |
|
||||
| [controller.sidecars.configAutoReload.image.registry](./values.yaml#L563) | string | Registry for the image that triggers the reload | `"docker.io"` |
|
||||
| [controller.sidecars.configAutoReload.image.repository](./values.yaml#L565) | string | Repository of the image that triggers the reload | `"kiwigrid/k8s-sidecar"` |
|
||||
| [controller.sidecars.configAutoReload.image.tag](./values.yaml#L567) | string | Tag for the image that triggers the reload | `"1.28.0"` |
|
||||
| [controller.sidecars.configAutoReload.imagePullPolicy](./values.yaml#L568) | string | | `"IfNotPresent"` |
|
||||
| [controller.sidecars.configAutoReload.logging](./values.yaml#L583) | object | Config auto-reload logging settings | `{"configuration":{"backupCount":3,"formatter":"JSON","logLevel":"INFO","logToConsole":true,"logToFile":false,"maxBytes":1024,"override":false}}` |
|
||||
| [controller.sidecars.configAutoReload.logging.configuration.override](./values.yaml#L587) | bool | Enables custom log config utilizing using the settings below. | `false` |
|
||||
| [controller.sidecars.configAutoReload.reqRetryConnect](./values.yaml#L601) | int | How many connection-related errors to retry on | `10` |
|
||||
| [controller.sidecars.configAutoReload.resources](./values.yaml#L569) | object | | `{}` |
|
||||
| [controller.sidecars.configAutoReload.scheme](./values.yaml#L596) | string | The scheme to use when connecting to the Jenkins configuration as code endpoint | `"http"` |
|
||||
| [controller.sidecars.configAutoReload.skipTlsVerify](./values.yaml#L598) | bool | Skip TLS verification when connecting to the Jenkins configuration as code endpoint | `false` |
|
||||
| [controller.sidecars.configAutoReload.sleepTime](./values.yaml#L603) | string | How many seconds to wait before updating config-maps/secrets (sets METHOD=SLEEP on the sidecar) | `nil` |
|
||||
| [controller.sidecars.configAutoReload.sshTcpPort](./values.yaml#L617) | int | | `1044` |
|
||||
| [controller.statefulSetAnnotations](./values.yaml#L676) | object | Annotations for controller StatefulSet | `{}` |
|
||||
| [controller.statefulSetLabels](./values.yaml#L238) | object | Jenkins controller custom labels for the StatefulSet | `{}` |
|
||||
| [controller.targetPort](./values.yaml#L227) | int | k8s target port | `8080` |
|
||||
| [controller.terminationGracePeriodSeconds](./values.yaml#L663) | string | Set TerminationGracePeriodSeconds | `nil` |
|
||||
| [controller.terminationMessagePath](./values.yaml#L665) | string | Set the termination message path | `nil` |
|
||||
| [controller.terminationMessagePolicy](./values.yaml#L667) | string | Set the termination message policy | `nil` |
|
||||
| [controller.testEnabled](./values.yaml#L844) | bool | Can be used to disable rendering controller test resources when using helm template | `true` |
|
||||
| [controller.tolerations](./values.yaml#L661) | list | Toleration labels for pod assignment | `[]` |
|
||||
| [controller.topologySpreadConstraints](./values.yaml#L687) | object | Topology spread constraints | `{}` |
|
||||
| [controller.updateStrategy](./values.yaml#L684) | object | Update strategy for StatefulSet | `{}` |
|
||||
| [controller.terminationGracePeriodSeconds](./values.yaml#L659) | string | Set TerminationGracePeriodSeconds | `nil` |
|
||||
| [controller.terminationMessagePath](./values.yaml#L661) | string | Set the termination message path | `nil` |
|
||||
| [controller.terminationMessagePolicy](./values.yaml#L663) | string | Set the termination message policy | `nil` |
|
||||
| [controller.testEnabled](./values.yaml#L840) | bool | Can be used to disable rendering controller test resources when using helm template | `true` |
|
||||
| [controller.tolerations](./values.yaml#L657) | list | Toleration labels for pod assignment | `[]` |
|
||||
| [controller.topologySpreadConstraints](./values.yaml#L683) | object | Topology spread constraints | `{}` |
|
||||
| [controller.updateStrategy](./values.yaml#L680) | object | Update strategy for StatefulSet | `{}` |
|
||||
| [controller.usePodSecurityContext](./values.yaml#L182) | bool | Enable pod security context (must be `true` if podSecurityContextOverride, runAsUser or fsGroup are set) | `true` |
|
||||
| [credentialsId](./values.yaml#L27) | string | The Jenkins credentials to access the Kubernetes API server. For the default cluster it is not needed. | `nil` |
|
||||
| [fullnameOverride](./values.yaml#L13) | string | Override the full resource names | `jenkins-(release-name)` or `jenkins` if the release-name is `jenkins` |
|
||||
| [helmtest.bats.image.registry](./values.yaml#L1369) | string | Registry of the image used to test the framework | `"docker.io"` |
|
||||
| [helmtest.bats.image.repository](./values.yaml#L1371) | string | Repository of the image used to test the framework | `"bats/bats"` |
|
||||
| [helmtest.bats.image.tag](./values.yaml#L1373) | string | Tag of the image to test the framework | `"1.11.1"` |
|
||||
| [helmtest.bats.image.registry](./values.yaml#L1361) | string | Registry of the image used to test the framework | `"docker.io"` |
|
||||
| [helmtest.bats.image.repository](./values.yaml#L1363) | string | Repository of the image used to test the framework | `"bats/bats"` |
|
||||
| [helmtest.bats.image.tag](./values.yaml#L1365) | string | Tag of the image to test the framework | `"1.11.0"` |
|
||||
| [kubernetesURL](./values.yaml#L24) | string | The URL of the Kubernetes API server | `"https://kubernetes.default"` |
|
||||
| [nameOverride](./values.yaml#L10) | string | Override the resource name prefix | `Chart.Name` |
|
||||
| [namespaceOverride](./values.yaml#L16) | string | Override the deployment namespace | `Release.Namespace` |
|
||||
| [networkPolicy.apiVersion](./values.yaml#L1293) | string | NetworkPolicy ApiVersion | `"networking.k8s.io/v1"` |
|
||||
| [networkPolicy.enabled](./values.yaml#L1288) | bool | Enable the creation of NetworkPolicy resources | `false` |
|
||||
| [networkPolicy.externalAgents.except](./values.yaml#L1307) | list | A list of IP sub-ranges to be excluded from the allowlisted IP range | `[]` |
|
||||
| [networkPolicy.externalAgents.ipCIDR](./values.yaml#L1305) | string | The IP range from which external agents are allowed to connect to controller, i.e., 172.17.0.0/16 | `nil` |
|
||||
| [networkPolicy.internalAgents.allowed](./values.yaml#L1297) | bool | Allow internal agents (from the same cluster) to connect to controller. Agent pods will be filtered based on PodLabels | `true` |
|
||||
| [networkPolicy.internalAgents.namespaceLabels](./values.yaml#L1301) | object | A map of labels (keys/values) that agents namespaces must have to be able to connect to controller | `{}` |
|
||||
| [networkPolicy.internalAgents.podLabels](./values.yaml#L1299) | object | A map of labels (keys/values) that agent pods must have to be able to connect to controller | `{}` |
|
||||
| [persistence.accessMode](./values.yaml#L1263) | string | The PVC access mode | `"ReadWriteOnce"` |
|
||||
| [persistence.annotations](./values.yaml#L1259) | object | Annotations for the PVC | `{}` |
|
||||
| [persistence.dataSource](./values.yaml#L1269) | object | Existing data source to clone PVC from | `{}` |
|
||||
| [persistence.enabled](./values.yaml#L1243) | bool | Enable the use of a Jenkins PVC | `true` |
|
||||
| [persistence.existingClaim](./values.yaml#L1249) | string | Provide the name of a PVC | `nil` |
|
||||
| [persistence.labels](./values.yaml#L1261) | object | Labels for the PVC | `{}` |
|
||||
| [persistence.mounts](./values.yaml#L1281) | list | Additional mounts | `[]` |
|
||||
| [persistence.size](./values.yaml#L1265) | string | The size of the PVC | `"8Gi"` |
|
||||
| [persistence.storageClass](./values.yaml#L1257) | string | Storage class for the PVC | `nil` |
|
||||
| [persistence.subPath](./values.yaml#L1274) | string | SubPath for jenkins-home mount | `nil` |
|
||||
| [persistence.volumes](./values.yaml#L1276) | list | Additional volumes | `[]` |
|
||||
| [rbac.create](./values.yaml#L1313) | bool | Whether RBAC resources are created | `true` |
|
||||
| [rbac.readSecrets](./values.yaml#L1315) | bool | Whether the Jenkins service account should be able to read Kubernetes secrets | `false` |
|
||||
| [rbac.useOpenShiftNonRootSCC](./values.yaml#L1317) | bool | Whether the Jenkins service account should be able to use the OpenShift "nonroot" Security Context Constraints | `false` |
|
||||
| [networkPolicy.apiVersion](./values.yaml#L1289) | string | NetworkPolicy ApiVersion | `"networking.k8s.io/v1"` |
|
||||
| [networkPolicy.enabled](./values.yaml#L1284) | bool | Enable the creation of NetworkPolicy resources | `false` |
|
||||
| [networkPolicy.externalAgents.except](./values.yaml#L1303) | list | A list of IP sub-ranges to be excluded from the allowlisted IP range | `[]` |
|
||||
| [networkPolicy.externalAgents.ipCIDR](./values.yaml#L1301) | string | The IP range from which external agents are allowed to connect to controller, i.e., 172.17.0.0/16 | `nil` |
|
||||
| [networkPolicy.internalAgents.allowed](./values.yaml#L1293) | bool | Allow internal agents (from the same cluster) to connect to controller. Agent pods will be filtered based on PodLabels | `true` |
|
||||
| [networkPolicy.internalAgents.namespaceLabels](./values.yaml#L1297) | object | A map of labels (keys/values) that agents namespaces must have to be able to connect to controller | `{}` |
|
||||
| [networkPolicy.internalAgents.podLabels](./values.yaml#L1295) | object | A map of labels (keys/values) that agent pods must have to be able to connect to controller | `{}` |
|
||||
| [persistence.accessMode](./values.yaml#L1259) | string | The PVC access mode | `"ReadWriteOnce"` |
|
||||
| [persistence.annotations](./values.yaml#L1255) | object | Annotations for the PVC | `{}` |
|
||||
| [persistence.dataSource](./values.yaml#L1265) | object | Existing data source to clone PVC from | `{}` |
|
||||
| [persistence.enabled](./values.yaml#L1239) | bool | Enable the use of a Jenkins PVC | `true` |
|
||||
| [persistence.existingClaim](./values.yaml#L1245) | string | Provide the name of a PVC | `nil` |
|
||||
| [persistence.labels](./values.yaml#L1257) | object | Labels for the PVC | `{}` |
|
||||
| [persistence.mounts](./values.yaml#L1277) | list | Additional mounts | `[]` |
|
||||
| [persistence.size](./values.yaml#L1261) | string | The size of the PVC | `"8Gi"` |
|
||||
| [persistence.storageClass](./values.yaml#L1253) | string | Storage class for the PVC | `nil` |
|
||||
| [persistence.subPath](./values.yaml#L1270) | string | SubPath for jenkins-home mount | `nil` |
|
||||
| [persistence.volumes](./values.yaml#L1272) | list | Additional volumes | `[]` |
|
||||
| [rbac.create](./values.yaml#L1309) | bool | Whether RBAC resources are created | `true` |
|
||||
| [rbac.readSecrets](./values.yaml#L1311) | bool | Whether the Jenkins service account should be able to read Kubernetes secrets | `false` |
|
||||
| [rbac.useOpenShiftNonRootSCC](./values.yaml#L1313) | bool | Whether the Jenkins service account should be able to use the OpenShift "nonroot" Security Context Constraints | `false` |
|
||||
| [renderHelmLabels](./values.yaml#L30) | bool | Enables rendering of the helm.sh/chart label to the annotations | `true` |
|
||||
| [serviceAccount.annotations](./values.yaml#L1327) | object | Configures annotations for the ServiceAccount | `{}` |
|
||||
| [serviceAccount.automountServiceAccountToken](./values.yaml#L1333) | bool | Auto-mount ServiceAccount token | `true` |
|
||||
| [serviceAccount.create](./values.yaml#L1321) | bool | Configures if a ServiceAccount with this name should be created | `true` |
|
||||
| [serviceAccount.extraLabels](./values.yaml#L1329) | object | Configures extra labels for the ServiceAccount | `{}` |
|
||||
| [serviceAccount.imagePullSecretName](./values.yaml#L1331) | string | Controller ServiceAccount image pull secret | `nil` |
|
||||
| [serviceAccount.name](./values.yaml#L1325) | string | | `nil` |
|
||||
| [serviceAccountAgent.annotations](./values.yaml#L1344) | object | Configures annotations for the agent ServiceAccount | `{}` |
|
||||
| [serviceAccountAgent.automountServiceAccountToken](./values.yaml#L1350) | bool | Auto-mount ServiceAccount token | `true` |
|
||||
| [serviceAccountAgent.create](./values.yaml#L1338) | bool | Configures if an agent ServiceAccount should be created | `false` |
|
||||
| [serviceAccountAgent.extraLabels](./values.yaml#L1346) | object | Configures extra labels for the agent ServiceAccount | `{}` |
|
||||
| [serviceAccountAgent.imagePullSecretName](./values.yaml#L1348) | string | Agent ServiceAccount image pull secret | `nil` |
|
||||
| [serviceAccountAgent.name](./values.yaml#L1342) | string | The name of the agent ServiceAccount to be used by access-controlled resources | `nil` |
|
||||
| [serviceAccount.annotations](./values.yaml#L1323) | object | Configures annotations for the ServiceAccount | `{}` |
|
||||
| [serviceAccount.create](./values.yaml#L1317) | bool | Configures if a ServiceAccount with this name should be created | `true` |
|
||||
| [serviceAccount.extraLabels](./values.yaml#L1325) | object | Configures extra labels for the ServiceAccount | `{}` |
|
||||
| [serviceAccount.imagePullSecretName](./values.yaml#L1327) | string | Controller ServiceAccount image pull secret | `nil` |
|
||||
| [serviceAccount.name](./values.yaml#L1321) | string | | `nil` |
|
||||
| [serviceAccountAgent.annotations](./values.yaml#L1338) | object | Configures annotations for the agent ServiceAccount | `{}` |
|
||||
| [serviceAccountAgent.create](./values.yaml#L1332) | bool | Configures if an agent ServiceAccount should be created | `false` |
|
||||
| [serviceAccountAgent.extraLabels](./values.yaml#L1340) | object | Configures extra labels for the agent ServiceAccount | `{}` |
|
||||
| [serviceAccountAgent.imagePullSecretName](./values.yaml#L1342) | string | Agent ServiceAccount image pull secret | `nil` |
|
||||
| [serviceAccountAgent.name](./values.yaml#L1336) | string | The name of the agent ServiceAccount to be used by access-controlled resources | `nil` |
|
||||
|
||||
@ -309,7 +309,6 @@ jenkins:
|
||||
{{- /* restore root */}}
|
||||
{{- $_ := set $ "Values" $oldRoot.Values }}
|
||||
{{- end }}
|
||||
slaveAgentPort: {{ .Values.controller.agentListenerPort }}
|
||||
{{- if .Values.controller.csrf.defaultCrumbIssuer.enabled }}
|
||||
crumbIssuer:
|
||||
standard:
|
||||
|
||||
@ -34,7 +34,7 @@ spec:
|
||||
{{- if (eq "-" .Values.persistence.storageClass) }}
|
||||
storageClassName: ""
|
||||
{{- else }}
|
||||
storageClassName: "{{ tpl .Values.persistence.storageClass . }}"
|
||||
storageClassName: "{{ .Values.persistence.storageClass }}"
|
||||
{{- end }}
|
||||
{{- end }}
|
||||
{{- end }}
|
||||
|
||||
@ -23,12 +23,12 @@ metadata:
|
||||
{{- end }}
|
||||
{{- if .Values.controller.ingress.annotations }}
|
||||
annotations:
|
||||
{{ tpl (toYaml .Values.controller.ingress.annotations) . | indent 4 }}
|
||||
{{ toYaml .Values.controller.ingress.annotations | indent 4 }}
|
||||
{{- end }}
|
||||
name: {{ template "jenkins.fullname" . }}
|
||||
spec:
|
||||
{{- if .Values.controller.ingress.ingressClassName }}
|
||||
ingressClassName: {{ tpl .Values.controller.ingress.ingressClassName . | quote }}
|
||||
ingressClassName: {{ .Values.controller.ingress.ingressClassName | quote }}
|
||||
{{- end }}
|
||||
rules:
|
||||
- http:
|
||||
|
||||
@ -107,7 +107,6 @@ spec:
|
||||
{{- end }}
|
||||
{{- end }}
|
||||
serviceAccountName: "{{ template "jenkins.serviceAccountName" . }}"
|
||||
automountServiceAccountToken: {{ .Values.serviceAccount.automountServiceAccountToken }}
|
||||
{{- if .Values.controller.hostNetworking }}
|
||||
hostNetwork: true
|
||||
dnsPolicy: ClusterFirstWithHostNet
|
||||
|
||||
@ -41,9 +41,6 @@ spec:
|
||||
targetPort: {{ $port.port }}
|
||||
{{- end -}}
|
||||
{{- end }}
|
||||
{{- if .Values.controller.publishNotReadyAddresses }}
|
||||
publishNotReadyAddresses: true
|
||||
{{- end }}
|
||||
selector:
|
||||
"app.kubernetes.io/component": "{{ .Values.controller.componentName }}"
|
||||
"app.kubernetes.io/instance": "{{ .Release.Name }}"
|
||||
|
||||
@ -1,7 +1,6 @@
|
||||
{{ if .Values.serviceAccountAgent.create }}
|
||||
apiVersion: v1
|
||||
kind: ServiceAccount
|
||||
automountServiceAccountToken: {{ .Values.serviceAccountAgent.automountServiceAccountToken }}
|
||||
metadata:
|
||||
name: {{ include "jenkins.serviceAccountAgentName" . }}
|
||||
namespace: {{ template "jenkins.agent.namespace" . }}
|
||||
|
||||
@ -1,7 +1,6 @@
|
||||
{{ if .Values.serviceAccount.create }}
|
||||
apiVersion: v1
|
||||
kind: ServiceAccount
|
||||
automountServiceAccountToken: {{ .Values.serviceAccount.automountServiceAccountToken }}
|
||||
metadata:
|
||||
name: {{ include "jenkins.serviceAccountName" . }}
|
||||
namespace: {{ template "jenkins.namespace" . }}
|
||||
|
||||
@ -232,10 +232,6 @@ controller:
|
||||
# but risks potentially imbalanced traffic spreading.
|
||||
serviceExternalTrafficPolicy:
|
||||
|
||||
# If enabled, the controller is available through its service before its pods reports ready. Makes startup screen and
|
||||
# auto-reload on restart feature possible.
|
||||
publishNotReadyAddresses:
|
||||
|
||||
# -- Jenkins controller service annotations
|
||||
serviceAnnotations: {}
|
||||
# -- Jenkins controller custom labels for the StatefulSet
|
||||
@ -403,10 +399,10 @@ controller:
|
||||
# Plugins will be installed during Jenkins controller start
|
||||
# -- List of Jenkins plugins to install. If you don't want to install plugins, set it to `false`
|
||||
installPlugins:
|
||||
- kubernetes:4313.va_9b_4fe2a_0e34
|
||||
- kubernetes:4296.v20a_7e4d77cf6
|
||||
- workflow-aggregator:600.vb_57cdd26fdd7
|
||||
- git:5.7.0
|
||||
- configuration-as-code:1932.v75cb_b_f1b_698d
|
||||
- git:5.6.0
|
||||
- configuration-as-code:1897.v79281e066ea_7
|
||||
|
||||
# If set to false, Jenkins will download the minimum required version of all dependencies.
|
||||
# -- Download the minimum required version or latest version of all dependencies
|
||||
@ -568,7 +564,7 @@ controller:
|
||||
# -- Repository of the image that triggers the reload
|
||||
repository: kiwigrid/k8s-sidecar
|
||||
# -- Tag for the image that triggers the reload
|
||||
tag: 1.30.1
|
||||
tag: 1.28.0
|
||||
imagePullPolicy: IfNotPresent
|
||||
resources: {}
|
||||
# limits:
|
||||
@ -955,7 +951,7 @@ agent:
|
||||
# -- Repository to pull the agent jnlp image from
|
||||
repository: "jenkins/inbound-agent"
|
||||
# -- Tag of the image to pull
|
||||
tag: "3283.v92c105e0f819-9"
|
||||
tag: "3273.v4cfe589b_fd83-1"
|
||||
# -- Configure working directory for default agent
|
||||
workingDir: "/home/jenkins/agent"
|
||||
nodeUsageMode: "NORMAL"
|
||||
@ -1329,8 +1325,6 @@ serviceAccount:
|
||||
extraLabels: {}
|
||||
# -- Controller ServiceAccount image pull secret
|
||||
imagePullSecretName:
|
||||
# -- Auto-mount ServiceAccount token
|
||||
automountServiceAccountToken: true
|
||||
|
||||
|
||||
serviceAccountAgent:
|
||||
@ -1346,8 +1340,6 @@ serviceAccountAgent:
|
||||
extraLabels: {}
|
||||
# -- Agent ServiceAccount image pull secret
|
||||
imagePullSecretName:
|
||||
# -- Auto-mount ServiceAccount token
|
||||
automountServiceAccountToken: true
|
||||
|
||||
# -- Checks if any deprecated values are used
|
||||
checkDeprecation: true
|
||||
@ -1370,4 +1362,4 @@ helmtest:
|
||||
# -- Repository of the image used to test the framework
|
||||
repository: "bats/bats"
|
||||
# -- Tag of the image to test the framework
|
||||
tag: "1.11.1"
|
||||
tag: "1.11.0"
|
||||
|
||||
@ -2,7 +2,7 @@ gitea:
|
||||
enabled: false
|
||||
|
||||
image:
|
||||
tag: 1.23.4
|
||||
tag: 1.22.6
|
||||
rootless: true
|
||||
|
||||
repliaCount: 1
|
||||
@ -16,10 +16,6 @@ gitea:
|
||||
claimName: data-gitea-0
|
||||
size: 4Gi
|
||||
|
||||
service:
|
||||
http:
|
||||
port: 80
|
||||
|
||||
securityContext:
|
||||
allowPrivilegeEscalation: false
|
||||
capabilities:
|
||||
@ -293,18 +289,12 @@ trivy:
|
||||
renovate:
|
||||
enabled: false
|
||||
|
||||
renovate:
|
||||
config: |
|
||||
{
|
||||
}
|
||||
|
||||
env:
|
||||
LOG_FORMAT: json
|
||||
cronjob:
|
||||
concurrencyPolicy: Forbid
|
||||
jobBackoffLimit: 2
|
||||
jobBackoffLimit: 3
|
||||
schedule: "0 3 * * *"
|
||||
successfulJobsHistoryLimit: 1
|
||||
|
||||
securityContext:
|
||||
fsGroupChangePolicy: OnRootMismatch
|
||||
fsGroup: 1000
|
||||
|
||||
@ -13,7 +13,7 @@ maintainers:
|
||||
email: stefan@zero-downtime.net
|
||||
dependencies:
|
||||
- name: kubezero-lib
|
||||
version: 0.2.1
|
||||
version: ">= 0.1.6"
|
||||
repository: https://cdn.zero-downtime.net/charts/
|
||||
- name: falco
|
||||
version: 4.2.5
|
||||
|
||||
@ -13,7 +13,7 @@ maintainers:
|
||||
email: stefan@zero-downtime.net
|
||||
dependencies:
|
||||
- name: kubezero-lib
|
||||
version: 0.2.1
|
||||
version: ">= 0.2.1"
|
||||
repository: https://cdn.zero-downtime.net/charts/
|
||||
- name: neo4j
|
||||
version: 5.26.0
|
||||
|
||||
@ -2,7 +2,7 @@ apiVersion: v2
|
||||
name: kubezero-istio-gateway
|
||||
description: KubeZero Umbrella Chart for Istio gateways
|
||||
type: application
|
||||
version: 0.24.3
|
||||
version: 0.24.2
|
||||
home: https://kubezero.com
|
||||
icon: https://cdn.zero-downtime.net/assets/kubezero/logo-small-64.png
|
||||
keywords:
|
||||
@ -14,9 +14,9 @@ maintainers:
|
||||
email: stefan@zero-downtime.net
|
||||
dependencies:
|
||||
- name: kubezero-lib
|
||||
version: 0.2.1
|
||||
version: ">= 0.1.6"
|
||||
repository: https://cdn.zero-downtime.net/charts/
|
||||
- name: gateway
|
||||
version: 1.24.3
|
||||
version: 1.24.2
|
||||
repository: https://istio-release.storage.googleapis.com/charts
|
||||
kubeVersion: ">= 1.30.0-0"
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
# kubezero-istio-gateway
|
||||
|
||||
 
|
||||
 
|
||||
|
||||
KubeZero Umbrella Chart for Istio gateways
|
||||
|
||||
@ -20,8 +20,8 @@ Kubernetes: `>= 1.30.0-0`
|
||||
|
||||
| Repository | Name | Version |
|
||||
|------------|------|---------|
|
||||
| https://cdn.zero-downtime.net/charts/ | kubezero-lib | 0.2.1 |
|
||||
| https://istio-release.storage.googleapis.com/charts | gateway | 1.24.3 |
|
||||
| https://cdn.zero-downtime.net/charts/ | kubezero-lib | >= 0.1.6 |
|
||||
| https://istio-release.storage.googleapis.com/charts | gateway | 1.24.2 |
|
||||
|
||||
## Values
|
||||
|
||||
@ -32,8 +32,8 @@ Kubernetes: `>= 1.30.0-0`
|
||||
| gateway.autoscaling.maxReplicas | int | `4` | |
|
||||
| gateway.autoscaling.minReplicas | int | `1` | |
|
||||
| gateway.autoscaling.targetCPUUtilizationPercentage | int | `80` | |
|
||||
| gateway.minReadySeconds | int | `10` | |
|
||||
| gateway.podAnnotations."proxy.istio.io/config" | string | `"{ \"terminationDrainDuration\": \"90s\" }"` | |
|
||||
| gateway.minReadySeconds | int | `120` | |
|
||||
| gateway.podAnnotations."proxy.istio.io/config" | string | `"{ \"terminationDrainDuration\": \"20s\" }"` | |
|
||||
| gateway.replicaCount | int | `1` | |
|
||||
| gateway.resources.limits.memory | string | `"512Mi"` | |
|
||||
| gateway.resources.requests.cpu | string | `"50m"` | |
|
||||
|
||||
@ -1,5 +1,5 @@
|
||||
apiVersion: v2
|
||||
appVersion: 1.24.3
|
||||
appVersion: 1.24.2
|
||||
description: Helm chart for deploying Istio gateways
|
||||
icon: https://istio.io/latest/favicons/android-192x192.png
|
||||
keywords:
|
||||
@ -9,4 +9,4 @@ name: gateway
|
||||
sources:
|
||||
- https://github.com/istio/istio
|
||||
type: application
|
||||
version: 1.24.3
|
||||
version: 1.24.2
|
||||
|
||||
@ -77,7 +77,7 @@ spec:
|
||||
allowPrivilegeEscalation: false
|
||||
privileged: false
|
||||
readOnlyRootFilesystem: true
|
||||
{{- if not (eq (.Values.platform | default "") "openshift") }}
|
||||
{{- if not (eq .Values.platform "openshift") }}
|
||||
runAsUser: 1337
|
||||
runAsGroup: 1337
|
||||
{{- end }}
|
||||
|
||||
@ -49,7 +49,7 @@ Finally, we can set all of that under .Values so the chart behaves without aware
|
||||
{{- $a := mustMergeOverwrite $defaults $profile }}
|
||||
{{- end }}
|
||||
# Flatten globals, if defined on a per-chart basis
|
||||
{{- if true }}
|
||||
{{- if false }}
|
||||
{{- $a := mustMergeOverwrite $defaults ($profile.global) ($.Values.global | default dict) }}
|
||||
{{- end }}
|
||||
{{- $b := set $ "Values" (mustMergeOverwrite $defaults $.Values) }}
|
||||
|
||||
@ -2,7 +2,7 @@ apiVersion: v2
|
||||
name: kubezero-istio
|
||||
description: KubeZero Umbrella Chart for Istio
|
||||
type: application
|
||||
version: 0.24.3
|
||||
version: 0.24.2
|
||||
home: https://kubezero.com
|
||||
icon: https://cdn.zero-downtime.net/assets/kubezero/logo-small-64.png
|
||||
keywords:
|
||||
@ -13,20 +13,16 @@ maintainers:
|
||||
email: stefan@zero-downtime.net
|
||||
dependencies:
|
||||
- name: kubezero-lib
|
||||
version: 0.2.1
|
||||
version: ">= 0.1.6"
|
||||
repository: https://cdn.zero-downtime.net/charts/
|
||||
- name: envoy-ratelimit
|
||||
version: 0.1.2
|
||||
repository: https://cdn.zero-downtime.net/charts/
|
||||
condition: envoy-ratelimit.enabled
|
||||
- name: base
|
||||
version: 1.24.3
|
||||
version: 1.24.2
|
||||
repository: https://istio-release.storage.googleapis.com/charts
|
||||
- name: istiod
|
||||
version: 1.24.3
|
||||
version: 1.24.2
|
||||
repository: https://istio-release.storage.googleapis.com/charts
|
||||
- name: kiali-server
|
||||
version: "2.6.0"
|
||||
version: "1.89.7"
|
||||
repository: https://kiali.org/helm-charts
|
||||
condition: kiali-server.enabled
|
||||
kubeVersion: ">= 1.30.0-0"
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
# kubezero-istio
|
||||
|
||||
 
|
||||
 
|
||||
|
||||
KubeZero Umbrella Chart for Istio
|
||||
|
||||
@ -20,27 +20,15 @@ Kubernetes: `>= 1.30.0-0`
|
||||
|
||||
| Repository | Name | Version |
|
||||
|------------|------|---------|
|
||||
| https://cdn.zero-downtime.net/charts/ | envoy-ratelimit | 0.1.2 |
|
||||
| https://cdn.zero-downtime.net/charts/ | kubezero-lib | 0.2.1 |
|
||||
| https://istio-release.storage.googleapis.com/charts | base | 1.24.3 |
|
||||
| https://istio-release.storage.googleapis.com/charts | istiod | 1.24.3 |
|
||||
| https://kiali.org/helm-charts | kiali-server | 2.6.0 |
|
||||
| https://cdn.zero-downtime.net/charts/ | kubezero-lib | >= 0.1.6 |
|
||||
| https://istio-release.storage.googleapis.com/charts | base | 1.24.2 |
|
||||
| https://istio-release.storage.googleapis.com/charts | istiod | 1.24.2 |
|
||||
| https://kiali.org/helm-charts | kiali-server | 1.89.7 |
|
||||
|
||||
## Values
|
||||
|
||||
| Key | Type | Default | Description |
|
||||
|-----|------|---------|-------------|
|
||||
| envoy-ratelimit.descriptors.ingress[0].key | string | `"remote_address"` | |
|
||||
| envoy-ratelimit.descriptors.ingress[0].rate_limit.requests_per_unit | int | `10` | |
|
||||
| envoy-ratelimit.descriptors.ingress[0].rate_limit.unit | string | `"second"` | |
|
||||
| envoy-ratelimit.descriptors.privateIngress[0].key | string | `"remote_address"` | |
|
||||
| envoy-ratelimit.descriptors.privateIngress[0].rate_limit.requests_per_unit | int | `10` | |
|
||||
| envoy-ratelimit.descriptors.privateIngress[0].rate_limit.unit | string | `"second"` | |
|
||||
| envoy-ratelimit.enabled | bool | `false` | |
|
||||
| envoy-ratelimit.failureModeDeny | bool | `false` | |
|
||||
| envoy-ratelimit.localCacheSize | int | `1048576` | |
|
||||
| envoy-ratelimit.log.format | string | `"json"` | |
|
||||
| envoy-ratelimit.log.level | string | `"warn"` | |
|
||||
| global.defaultPodDisruptionBudget.enabled | bool | `false` | |
|
||||
| global.logAsJson | bool | `true` | |
|
||||
| global.variant | string | `"distroless"` | |
|
||||
@ -62,6 +50,17 @@ Kubernetes: `>= 1.30.0-0`
|
||||
| kiali-server.istio.enabled | bool | `false` | |
|
||||
| kiali-server.istio.gateway | string | `"istio-ingress/private-ingressgateway"` | |
|
||||
| kiali-server.server.metrics_enabled | bool | `false` | |
|
||||
| rateLimiting.descriptors.ingress[0].key | string | `"remote_address"` | |
|
||||
| rateLimiting.descriptors.ingress[0].rate_limit.requests_per_unit | int | `10` | |
|
||||
| rateLimiting.descriptors.ingress[0].rate_limit.unit | string | `"second"` | |
|
||||
| rateLimiting.descriptors.privateIngress[0].key | string | `"remote_address"` | |
|
||||
| rateLimiting.descriptors.privateIngress[0].rate_limit.requests_per_unit | int | `10` | |
|
||||
| rateLimiting.descriptors.privateIngress[0].rate_limit.unit | string | `"second"` | |
|
||||
| rateLimiting.enabled | bool | `false` | |
|
||||
| rateLimiting.failureModeDeny | bool | `false` | |
|
||||
| rateLimiting.localCacheSize | int | `1048576` | |
|
||||
| rateLimiting.log.format | string | `"json"` | |
|
||||
| rateLimiting.log.level | string | `"warn"` | |
|
||||
|
||||
## Resources
|
||||
|
||||
|
||||
@ -5,22 +5,22 @@ folder: Istio
|
||||
condition: '.Values.istiod.telemetry.enabled'
|
||||
dashboards:
|
||||
- name: istio-control-plane
|
||||
url: https://grafana.com/api/dashboards/7645/revisions/239/download
|
||||
url: https://grafana.com/api/dashboards/7645/revisions/229/download
|
||||
tags:
|
||||
- Istio
|
||||
- name: istio-mesh
|
||||
url: https://grafana.com/api/dashboards/7639/revisions/239/download
|
||||
url: https://grafana.com/api/dashboards/7639/revisions/229/download
|
||||
tags:
|
||||
- Istio
|
||||
- name: istio-service
|
||||
url: https://grafana.com/api/dashboards/7636/revisions/239/download
|
||||
url: https://grafana.com/api/dashboards/7636/revisions/229/download
|
||||
tags:
|
||||
- Istio
|
||||
- name: istio-workload
|
||||
url: https://grafana.com/api/dashboards/7630/revisions/239/download
|
||||
url: https://grafana.com/api/dashboards/7630/revisions/229/download
|
||||
tags:
|
||||
- Istio
|
||||
- name: istio-performance
|
||||
url: https://grafana.com/api/dashboards/11829/revisions/239/download
|
||||
url: https://grafana.com/api/dashboards/11829/revisions/229/download
|
||||
tags:
|
||||
- Istio
|
||||
|
||||
File diff suppressed because one or more lines are too long
@ -0,0 +1,106 @@
|
||||
{{- if .Values.rateLimiting.enabled }}
|
||||
apiVersion: v1
|
||||
kind: ConfigMap
|
||||
metadata:
|
||||
name: ratelimit-statsd-exporter-config
|
||||
namespace: {{ .Release.Namespace }}
|
||||
labels:
|
||||
{{- include "kubezero-lib.labels" . | nindent 4 }}
|
||||
data:
|
||||
config.yaml: |
|
||||
defaults:
|
||||
ttl: 1m # Resets the metrics every minute
|
||||
mappings:
|
||||
- match:
|
||||
"ratelimit.service.rate_limit.*.*.near_limit"
|
||||
name: "ratelimit_service_rate_limit_near_limit"
|
||||
timer_type: "histogram"
|
||||
labels:
|
||||
domain: "$1"
|
||||
key1: "$2"
|
||||
- match:
|
||||
"ratelimit.service.rate_limit.*.*.over_limit"
|
||||
name: "ratelimit_service_rate_limit_over_limit"
|
||||
timer_type: "histogram"
|
||||
labels:
|
||||
domain: "$1"
|
||||
key1: "$2"
|
||||
- match:
|
||||
"ratelimit.service.rate_limit.*.*.total_hits"
|
||||
name: "ratelimit_service_rate_limit_total_hits"
|
||||
timer_type: "histogram"
|
||||
labels:
|
||||
domain: "$1"
|
||||
key1: "$2"
|
||||
- match:
|
||||
"ratelimit.service.rate_limit.*.*.within_limit"
|
||||
name: "ratelimit_service_rate_limit_within_limit"
|
||||
timer_type: "histogram"
|
||||
labels:
|
||||
domain: "$1"
|
||||
key1: "$2"
|
||||
- match:
|
||||
"ratelimit.service.rate_limit.*.*.*.near_limit"
|
||||
name: "ratelimit_service_rate_limit_near_limit"
|
||||
timer_type: "histogram"
|
||||
labels:
|
||||
domain: "$1"
|
||||
key1: "$2"
|
||||
key2: "$3"
|
||||
- match:
|
||||
"ratelimit.service.rate_limit.*.*.*.over_limit"
|
||||
name: "ratelimit_service_rate_limit_over_limit"
|
||||
timer_type: "histogram"
|
||||
labels:
|
||||
domain: "$1"
|
||||
key1: "$2"
|
||||
key2: "$3"
|
||||
- match:
|
||||
"ratelimit.service.rate_limit.*.*.*.total_hits"
|
||||
name: "ratelimit_service_rate_limit_total_hits"
|
||||
timer_type: "histogram"
|
||||
labels:
|
||||
domain: "$1"
|
||||
key1: "$2"
|
||||
key2: "$3"
|
||||
- match:
|
||||
"ratelimit.service.rate_limit.*.*.*.within_limit"
|
||||
name: "ratelimit_service_rate_limit_within_limit"
|
||||
timer_type: "histogram"
|
||||
labels:
|
||||
domain: "$1"
|
||||
key1: "$2"
|
||||
key2: "$3"
|
||||
- match:
|
||||
"ratelimit.service.call.should_rate_limit.*"
|
||||
name: "ratelimit_service_should_rate_limit_error"
|
||||
match_metric_type: counter
|
||||
labels:
|
||||
err_type: "$1"
|
||||
- match:
|
||||
"ratelimit_server.*.total_requests"
|
||||
name: "ratelimit_service_total_requests"
|
||||
match_metric_type: counter
|
||||
labels:
|
||||
grpc_method: "$1"
|
||||
- match:
|
||||
"ratelimit_server.*.response_time"
|
||||
name: "ratelimit_service_response_time_seconds"
|
||||
timer_type: histogram
|
||||
labels:
|
||||
grpc_method: "$1"
|
||||
- match:
|
||||
"ratelimit.service.config_load_success"
|
||||
name: "ratelimit_service_config_load_success"
|
||||
match_metric_type: counter
|
||||
ttl: 3m
|
||||
- match:
|
||||
"ratelimit.service.config_load_error"
|
||||
name: "ratelimit_service_config_load_error"
|
||||
match_metric_type: counter
|
||||
ttl: 3m
|
||||
- match: "."
|
||||
match_type: "regex"
|
||||
action: "drop"
|
||||
name: "dropped"
|
||||
{{- end }}
|
||||
@ -1,3 +1,4 @@
|
||||
{{- if .Values.rateLimiting.enabled }}
|
||||
apiVersion: v1
|
||||
kind: ConfigMap
|
||||
metadata:
|
||||
@ -9,9 +10,10 @@ data:
|
||||
ingress.yaml: |
|
||||
domain: ingress
|
||||
descriptors:
|
||||
{{- toYaml .Values.descriptors.ingress | nindent 4 }}
|
||||
{{- toYaml .Values.rateLimiting.descriptors.ingress | nindent 4 }}
|
||||
|
||||
private-ingress.yaml: |
|
||||
domain: private-ingress
|
||||
descriptors:
|
||||
{{- toYaml .Values.descriptors.privateIngress | nindent 4 }}
|
||||
{{- toYaml .Values.rateLimiting.descriptors.privateIngress | nindent 4 }}
|
||||
{{- end }}
|
||||
@ -1,3 +1,4 @@
|
||||
{{- if .Values.rateLimiting.enabled }}
|
||||
apiVersion: networking.istio.io/v1alpha3
|
||||
kind: EnvoyFilter
|
||||
metadata:
|
||||
@ -26,7 +27,7 @@ spec:
|
||||
typed_config:
|
||||
"@type": type.googleapis.com/envoy.extensions.filters.http.ratelimit.v3.RateLimit
|
||||
domain: ingress
|
||||
failure_mode_deny: {{ .Values.failureModeDeny }}
|
||||
failure_mode_deny: {{ .Values.rateLimiting.failureModeDeny }}
|
||||
timeout: 0.5s
|
||||
rate_limit_service:
|
||||
grpc_service:
|
||||
@ -84,7 +85,7 @@ spec:
|
||||
typed_config:
|
||||
"@type": type.googleapis.com/envoy.extensions.filters.http.ratelimit.v3.RateLimit
|
||||
domain: private-ingress
|
||||
failure_mode_deny: {{ .Values.failureModeDeny }}
|
||||
failure_mode_deny: {{ .Values.rateLimiting.failureModeDeny }}
|
||||
timeout: 0.5s
|
||||
rate_limit_service:
|
||||
grpc_service:
|
||||
@ -112,3 +113,4 @@ spec:
|
||||
socket_address:
|
||||
address: ratelimit.istio-system
|
||||
port_value: 8081
|
||||
{{- end }}
|
||||
@ -0,0 +1,154 @@
|
||||
{{- if .Values.rateLimiting.enabled }}
|
||||
apiVersion: v1
|
||||
kind: Service
|
||||
metadata:
|
||||
name: ratelimit-redis
|
||||
namespace: {{ .Release.Namespace }}
|
||||
labels:
|
||||
app: ratelimit-redis
|
||||
spec:
|
||||
ports:
|
||||
- name: redis
|
||||
port: 6379
|
||||
selector:
|
||||
app: ratelimit-redis
|
||||
---
|
||||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
metadata:
|
||||
name: ratelimit-redis
|
||||
namespace: {{ .Release.Namespace }}
|
||||
spec:
|
||||
replicas: 1
|
||||
selector:
|
||||
matchLabels:
|
||||
app: ratelimit-redis
|
||||
template:
|
||||
metadata:
|
||||
labels:
|
||||
app: ratelimit-redis
|
||||
spec:
|
||||
containers:
|
||||
- image: redis:6-alpine
|
||||
imagePullPolicy: IfNotPresent
|
||||
name: redis
|
||||
ports:
|
||||
- name: redis
|
||||
containerPort: 6379
|
||||
restartPolicy: Always
|
||||
serviceAccountName: ""
|
||||
---
|
||||
apiVersion: v1
|
||||
kind: Service
|
||||
metadata:
|
||||
name: ratelimit
|
||||
namespace: {{ .Release.Namespace }}
|
||||
labels:
|
||||
app: ratelimit
|
||||
spec:
|
||||
ports:
|
||||
#- name: http-port
|
||||
# port: 8080
|
||||
# targetPort: 8080
|
||||
# protocol: TCP
|
||||
- name: grpc-port
|
||||
port: 8081
|
||||
targetPort: 8081
|
||||
protocol: TCP
|
||||
#- name: http-debug
|
||||
# port: 6070
|
||||
# targetPort: 6070
|
||||
# protocol: TCP
|
||||
- name: http-monitoring
|
||||
port: 9102
|
||||
targetPort: 9102
|
||||
protocol: TCP
|
||||
selector:
|
||||
app: ratelimit
|
||||
---
|
||||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
metadata:
|
||||
name: ratelimit
|
||||
namespace: {{ .Release.Namespace }}
|
||||
spec:
|
||||
replicas: 1
|
||||
selector:
|
||||
matchLabels:
|
||||
app: ratelimit
|
||||
strategy:
|
||||
type: Recreate
|
||||
template:
|
||||
metadata:
|
||||
labels:
|
||||
app: ratelimit
|
||||
spec:
|
||||
containers:
|
||||
- image: envoyproxy/ratelimit:b42701cb # 2021/08/12
|
||||
imagePullPolicy: IfNotPresent
|
||||
name: ratelimit
|
||||
command: ["/bin/ratelimit"]
|
||||
env:
|
||||
- name: LOG_LEVEL
|
||||
value: {{ default "WARN" .Values.rateLimiting.log.level }}
|
||||
- name: LOG_FORMAT
|
||||
value: {{ default "text" .Values.rateLimiting.log.format }}
|
||||
- name: REDIS_SOCKET_TYPE
|
||||
value: tcp
|
||||
- name: REDIS_URL
|
||||
value: ratelimit-redis:6379
|
||||
- name: USE_STATSD
|
||||
value: "true"
|
||||
- name: STATSD_HOST
|
||||
value: "localhost"
|
||||
- name: STATSD_PORT
|
||||
value: "9125"
|
||||
- name: RUNTIME_ROOT
|
||||
value: /data
|
||||
- name: RUNTIME_SUBDIRECTORY
|
||||
value: ratelimit
|
||||
- name: RUNTIME_WATCH_ROOT
|
||||
value: "false"
|
||||
- name: RUNTIME_IGNOREDOTFILES
|
||||
value: "true"
|
||||
- name: LOCAL_CACHE_SIZE_IN_BYTES
|
||||
value: "{{ default 0 .Values.rateLimiting.localCacheSize | int }}"
|
||||
ports:
|
||||
#- containerPort: 8080
|
||||
- containerPort: 8081
|
||||
#- containerPort: 6070
|
||||
volumeMounts:
|
||||
- name: ratelimit-config
|
||||
mountPath: /data/ratelimit/config
|
||||
resources:
|
||||
requests:
|
||||
cpu: 50m
|
||||
memory: 32Mi
|
||||
limits:
|
||||
cpu: 1
|
||||
memory: 256Mi
|
||||
- name: statsd-exporter
|
||||
image: docker.io/prom/statsd-exporter:v0.21.0
|
||||
imagePullPolicy: Always
|
||||
args: ["--statsd.mapping-config=/etc/statsd-exporter/config.yaml"]
|
||||
ports:
|
||||
- containerPort: 9125
|
||||
# - containerPort: 9102
|
||||
resources:
|
||||
requests:
|
||||
cpu: 50m
|
||||
memory: 32Mi
|
||||
limits:
|
||||
cpu: 200m
|
||||
memory: 64Mi
|
||||
volumeMounts:
|
||||
- name: statsd-exporter-config
|
||||
mountPath: /etc/statsd-exporter
|
||||
volumes:
|
||||
- name: ratelimit-config
|
||||
configMap:
|
||||
name: ratelimit-config
|
||||
- name: statsd-exporter-config
|
||||
configMap:
|
||||
name: ratelimit-statsd-exporter-config
|
||||
{{- end }}
|
||||
@ -1,4 +1,4 @@
|
||||
{{- if and .Values.metrics.enabled }}
|
||||
{{- if and .Values.istiod.telemetry.enabled .Values.rateLimiting.enabled }}
|
||||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: ServiceMonitor
|
||||
metadata:
|
||||
@ -56,7 +56,29 @@ kiali-server:
|
||||
#url: "kiali.example.com"
|
||||
|
||||
|
||||
# for available options see envoy-ratelimit chart
|
||||
envoy-ratelimit:
|
||||
rateLimiting:
|
||||
enabled: false
|
||||
|
||||
log:
|
||||
level: warn
|
||||
format: json
|
||||
|
||||
# 1MB local cache for already reached limits to reduce calls to Redis
|
||||
localCacheSize: 1048576
|
||||
|
||||
# Wether to block requests if ratelimiting is down
|
||||
failureModeDeny: false
|
||||
|
||||
# rate limit descriptors for each domain, examples 10 req/s per sourceIP
|
||||
descriptors:
|
||||
ingress:
|
||||
- key: remote_address
|
||||
rate_limit:
|
||||
unit: second
|
||||
requests_per_unit: 10
|
||||
|
||||
privateIngress:
|
||||
- key: remote_address
|
||||
rate_limit:
|
||||
unit: second
|
||||
requests_per_unit: 10
|
||||
|
||||
@ -10,4 +10,4 @@ keywords:
|
||||
maintainers:
|
||||
- name: Stefan Reimer
|
||||
email: stefan@zero-downtime.net
|
||||
kubeVersion: ">= 1.30.0-0"
|
||||
kubeVersion: ">= 1.30.0"
|
||||
|
||||
@ -2,7 +2,7 @@ apiVersion: v2
|
||||
name: kubezero-logging
|
||||
description: KubeZero Umbrella Chart for complete EFK stack
|
||||
type: application
|
||||
version: 0.8.13
|
||||
version: 0.8.14
|
||||
appVersion: 1.6.0
|
||||
home: https://kubezero.com
|
||||
icon: https://cdn.zero-downtime.net/assets/kubezero/logo-small-64.png
|
||||
@ -17,14 +17,14 @@ maintainers:
|
||||
email: stefan@zero-downtime.net
|
||||
dependencies:
|
||||
- name: kubezero-lib
|
||||
version: 0.2.1
|
||||
version: ">= 0.1.6"
|
||||
repository: https://cdn.zero-downtime.net/charts/
|
||||
- name: fluentd
|
||||
version: 0.5.2
|
||||
repository: https://fluent.github.io/helm-charts
|
||||
condition: fluentd.enabled
|
||||
- name: fluent-bit
|
||||
version: 0.47.10
|
||||
version: 0.48.6
|
||||
repository: https://fluent.github.io/helm-charts
|
||||
condition: fluent-bit.enabled
|
||||
kubeVersion: ">= 1.26.0"
|
||||
|
||||
@ -2,7 +2,7 @@ apiVersion: v2
|
||||
name: kubezero-metrics
|
||||
description: KubeZero Umbrella Chart for Prometheus, Grafana and Alertmanager as well as all Kubernetes integrations.
|
||||
type: application
|
||||
version: 0.11.0
|
||||
version: 0.10.3
|
||||
home: https://kubezero.com
|
||||
icon: https://cdn.zero-downtime.net/assets/kubezero/logo-small-64.png
|
||||
keywords:
|
||||
@ -16,17 +16,17 @@ maintainers:
|
||||
# https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack
|
||||
dependencies:
|
||||
- name: kubezero-lib
|
||||
version: 0.2.1
|
||||
version: ">= 0.1.6"
|
||||
repository: https://cdn.zero-downtime.net/charts/
|
||||
- name: kube-prometheus-stack
|
||||
version: 69.2.3
|
||||
version: 66.7.1
|
||||
repository: https://prometheus-community.github.io/helm-charts
|
||||
- name: prometheus-adapter
|
||||
version: 4.11.0
|
||||
repository: https://prometheus-community.github.io/helm-charts
|
||||
condition: prometheus-adapter.enabled
|
||||
- name: prometheus-pushgateway
|
||||
version: 3.0.0
|
||||
version: 2.17.0
|
||||
repository: https://prometheus-community.github.io/helm-charts
|
||||
condition: prometheus-pushgateway.enabled
|
||||
kubeVersion: ">= 1.30.0-0"
|
||||
kubeVersion: ">= 1.26.0"
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
# kubezero-metrics
|
||||
|
||||
 
|
||||
 
|
||||
|
||||
KubeZero Umbrella Chart for Prometheus, Grafana and Alertmanager as well as all Kubernetes integrations.
|
||||
|
||||
@ -14,14 +14,14 @@ KubeZero Umbrella Chart for Prometheus, Grafana and Alertmanager as well as all
|
||||
|
||||
## Requirements
|
||||
|
||||
Kubernetes: `>= 1.30.0-0`
|
||||
Kubernetes: `>= 1.26.0`
|
||||
|
||||
| Repository | Name | Version |
|
||||
|------------|------|---------|
|
||||
| https://cdn.zero-downtime.net/charts/ | kubezero-lib | >= 0.1.6 |
|
||||
| https://prometheus-community.github.io/helm-charts | kube-prometheus-stack | 69.2.3 |
|
||||
| https://prometheus-community.github.io/helm-charts | kube-prometheus-stack | 66.1.1 |
|
||||
| https://prometheus-community.github.io/helm-charts | prometheus-adapter | 4.11.0 |
|
||||
| https://prometheus-community.github.io/helm-charts | prometheus-pushgateway | 3.0.0 |
|
||||
| https://prometheus-community.github.io/helm-charts | prometheus-pushgateway | 2.15.0 |
|
||||
|
||||
## Values
|
||||
|
||||
|
||||
@ -30,7 +30,7 @@
|
||||
"options": {
|
||||
"content": "The SLO (service level objective) and other metrics displayed on this dashboard are for informational purposes only."
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"title": "Notice",
|
||||
"type": "text"
|
||||
},
|
||||
@ -54,7 +54,7 @@
|
||||
},
|
||||
"id": 2,
|
||||
"interval": "1m",
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -100,7 +100,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -134,7 +134,7 @@
|
||||
},
|
||||
"id": 4,
|
||||
"interval": "1m",
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -232,7 +232,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -276,7 +276,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -319,7 +319,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -353,7 +353,7 @@
|
||||
},
|
||||
"id": 8,
|
||||
"interval": "1m",
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -451,7 +451,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -495,7 +495,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -538,7 +538,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -581,7 +581,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -624,7 +624,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -670,7 +670,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -712,7 +712,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -755,7 +755,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -797,7 +797,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
|
||||
@ -46,7 +46,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -92,7 +92,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -163,7 +163,7 @@
|
||||
"y": 9
|
||||
},
|
||||
"id": 3,
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -328,7 +328,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -374,7 +374,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -420,7 +420,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -466,7 +466,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -512,7 +512,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -558,7 +558,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -604,7 +604,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -650,7 +650,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -696,7 +696,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -742,7 +742,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
|
||||
@ -35,7 +35,7 @@
|
||||
"options": {
|
||||
"colorMode": "none"
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -86,7 +86,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -137,7 +137,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -188,7 +188,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -239,7 +239,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -314,15 +314,15 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-controller-manager\", instance=~\"$instance\", verb=\"POST\"}[$__rate_interval])) by (verb, le))",
|
||||
"legendFormat": "{{verb}}"
|
||||
"expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-controller-manager\", instance=~\"$instance\", verb=\"POST\"}[$__rate_interval])) by (verb, url, le))",
|
||||
"legendFormat": "{{verb}} {{url}}"
|
||||
}
|
||||
],
|
||||
"title": "Post Request Latency 99th Quantile",
|
||||
@ -365,15 +365,15 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-controller-manager\", instance=~\"$instance\", verb=\"GET\"}[$__rate_interval])) by (verb, le))",
|
||||
"legendFormat": "{{verb}}"
|
||||
"expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-controller-manager\", instance=~\"$instance\", verb=\"GET\"}[$__rate_interval])) by (verb, url, le))",
|
||||
"legendFormat": "{{verb}} {{url}}"
|
||||
}
|
||||
],
|
||||
"title": "Get Request Latency 99th Quantile",
|
||||
@ -416,7 +416,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -467,7 +467,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -518,7 +518,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
|
||||
@ -35,7 +35,7 @@
|
||||
"options": {
|
||||
"colorMode": "none"
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -70,7 +70,7 @@
|
||||
"options": {
|
||||
"colorMode": "none"
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -105,7 +105,7 @@
|
||||
"options": {
|
||||
"colorMode": "none"
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -140,7 +140,7 @@
|
||||
"options": {
|
||||
"colorMode": "none"
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -175,7 +175,7 @@
|
||||
"options": {
|
||||
"colorMode": "none"
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -210,7 +210,7 @@
|
||||
"options": {
|
||||
"colorMode": "none"
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -260,7 +260,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -319,7 +319,7 @@
|
||||
"y": 12
|
||||
},
|
||||
"id": 8,
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -476,7 +476,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -571,7 +571,7 @@
|
||||
"y": 24
|
||||
},
|
||||
"id": 10,
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -748,7 +748,7 @@
|
||||
"y": 30
|
||||
},
|
||||
"id": 11,
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -892,7 +892,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -943,7 +943,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -994,7 +994,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -1045,7 +1045,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -1096,7 +1096,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -1147,7 +1147,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -1198,7 +1198,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -1249,7 +1249,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -1300,7 +1300,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -1351,7 +1351,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -1422,7 +1422,7 @@
|
||||
"y": 96
|
||||
},
|
||||
"id": 22,
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
|
||||
@ -35,7 +35,7 @@
|
||||
"options": {
|
||||
"colorMode": "none"
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -70,7 +70,7 @@
|
||||
"options": {
|
||||
"colorMode": "none"
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -105,7 +105,7 @@
|
||||
"options": {
|
||||
"colorMode": "none"
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -140,7 +140,7 @@
|
||||
"options": {
|
||||
"colorMode": "none"
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -242,7 +242,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -317,7 +317,7 @@
|
||||
"y": 14
|
||||
},
|
||||
"id": 6,
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -500,7 +500,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -578,7 +578,7 @@
|
||||
"y": 28
|
||||
},
|
||||
"id": 8,
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -768,7 +768,7 @@
|
||||
"y": 35
|
||||
},
|
||||
"id": 9,
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -912,7 +912,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -963,7 +963,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -1014,7 +1014,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -1065,7 +1065,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -1116,7 +1116,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -1167,7 +1167,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -1218,7 +1218,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -1269,7 +1269,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -1340,7 +1340,7 @@
|
||||
"y": 70
|
||||
},
|
||||
"id": 18,
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
|
||||
@ -94,7 +94,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -161,7 +161,7 @@
|
||||
"y": 6
|
||||
},
|
||||
"id": 2,
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -323,7 +323,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -342,109 +342,6 @@
|
||||
"legendFormat": "{{pod}}"
|
||||
}
|
||||
],
|
||||
"title": "Memory Usage (w/cache)",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"custom": {
|
||||
"fillOpacity": 10,
|
||||
"showPoints": "never",
|
||||
"spanNulls": true,
|
||||
"stacking": {
|
||||
"mode": "normal"
|
||||
}
|
||||
},
|
||||
"unit": "bytes"
|
||||
},
|
||||
"overrides": [
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "max capacity"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "color",
|
||||
"value": {
|
||||
"fixedColor": "red",
|
||||
"mode": "fixed"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "custom.stacking",
|
||||
"value": {
|
||||
"mode": "none"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "custom.hideFrom",
|
||||
"value": {
|
||||
"legend": false,
|
||||
"tooltip": true,
|
||||
"viz": false
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "custom.lineStyle",
|
||||
"value": {
|
||||
"dash": [
|
||||
10,
|
||||
10
|
||||
],
|
||||
"fill": "dash"
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 6,
|
||||
"w": 24,
|
||||
"x": 0,
|
||||
"y": 18
|
||||
},
|
||||
"id": 4,
|
||||
"interval": "1m",
|
||||
"options": {
|
||||
"legend": {
|
||||
"asTable": true,
|
||||
"calcs": [
|
||||
"lastNotNull"
|
||||
],
|
||||
"displayMode": "table",
|
||||
"placement": "right",
|
||||
"showLegend": true
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "sum(kube_node_status_capacity{cluster=\"$cluster\", job=\"kube-state-metrics\", node=~\"$node\", resource=\"memory\"})",
|
||||
"legendFormat": "max capacity"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "sum(node_namespace_pod_container:container_memory_rss{cluster=\"$cluster\", node=~\"$node\", container!=\"\"}) by (pod)",
|
||||
"legendFormat": "{{pod}}"
|
||||
}
|
||||
],
|
||||
"title": "Memory Usage (w/o cache)",
|
||||
"type": "timeseries"
|
||||
},
|
||||
@ -493,10 +390,10 @@
|
||||
"h": 6,
|
||||
"w": 24,
|
||||
"x": 0,
|
||||
"y": 24
|
||||
"y": 18
|
||||
},
|
||||
"id": 5,
|
||||
"pluginVersion": "v11.4.0",
|
||||
"id": 4,
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
|
||||
@ -102,7 +102,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -208,7 +208,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -250,7 +250,7 @@
|
||||
"y": 14
|
||||
},
|
||||
"id": 3,
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -433,7 +433,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -494,7 +494,7 @@
|
||||
"y": 28
|
||||
},
|
||||
"id": 5,
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -664,7 +664,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -715,7 +715,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -766,7 +766,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -817,7 +817,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -868,7 +868,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -919,7 +919,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -970,7 +970,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -1029,7 +1029,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -1088,7 +1088,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -1139,7 +1139,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -1193,7 +1193,7 @@
|
||||
"y": 70
|
||||
},
|
||||
"id": 16,
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
|
||||
@ -1,675 +0,0 @@
|
||||
{
|
||||
"editable": false,
|
||||
"panels": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "none"
|
||||
}
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 3,
|
||||
"w": 4,
|
||||
"x": 0,
|
||||
"y": 0
|
||||
},
|
||||
"id": 1,
|
||||
"interval": "1m",
|
||||
"options": {
|
||||
"colorMode": "none"
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "1 - avg(rate(windows_cpu_time_total{cluster=\"$cluster\", job=\"kubernetes-windows-exporter\", mode=\"idle\"}[$__rate_interval]))",
|
||||
"instant": true
|
||||
}
|
||||
],
|
||||
"title": "CPU Utilisation",
|
||||
"type": "stat"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "percentunit"
|
||||
}
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 3,
|
||||
"w": 4,
|
||||
"x": 4,
|
||||
"y": 0
|
||||
},
|
||||
"id": 2,
|
||||
"interval": "1m",
|
||||
"options": {
|
||||
"colorMode": "none"
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "sum(kube_pod_windows_container_resource_cpu_cores_request{cluster=\"$cluster\"}) / sum(node:windows_node_num_cpu:sum{cluster=\"$cluster\"})",
|
||||
"instant": true
|
||||
}
|
||||
],
|
||||
"title": "CPU Requests Commitment",
|
||||
"type": "stat"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "percentunit"
|
||||
}
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 3,
|
||||
"w": 4,
|
||||
"x": 8,
|
||||
"y": 0
|
||||
},
|
||||
"id": 3,
|
||||
"interval": "1m",
|
||||
"options": {
|
||||
"colorMode": "none"
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "sum(kube_pod_windows_container_resource_cpu_cores_limit{cluster=\"$cluster\"}) / sum(node:windows_node_num_cpu:sum{cluster=\"$cluster\"})",
|
||||
"instant": true
|
||||
}
|
||||
],
|
||||
"title": "CPU Limits Commitment",
|
||||
"type": "stat"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "percentunit"
|
||||
}
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 3,
|
||||
"w": 4,
|
||||
"x": 12,
|
||||
"y": 0
|
||||
},
|
||||
"id": 4,
|
||||
"interval": "1m",
|
||||
"options": {
|
||||
"colorMode": "none"
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "1 - sum(:windows_node_memory_MemFreeCached_bytes:sum{cluster=\"$cluster\"}) / sum(:windows_node_memory_MemTotal_bytes:sum{cluster=\"$cluster\"})",
|
||||
"instant": true
|
||||
}
|
||||
],
|
||||
"title": "Memory Utilisation",
|
||||
"type": "stat"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "percentunit"
|
||||
}
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 3,
|
||||
"w": 4,
|
||||
"x": 16,
|
||||
"y": 0
|
||||
},
|
||||
"id": 5,
|
||||
"interval": "1m",
|
||||
"options": {
|
||||
"colorMode": "none"
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "sum(kube_pod_windows_container_resource_memory_request{cluster=\"$cluster\"}) / sum(:windows_node_memory_MemTotal_bytes:sum{cluster=\"$cluster\"})",
|
||||
"instant": true
|
||||
}
|
||||
],
|
||||
"title": "Memory Requests Commitment",
|
||||
"type": "stat"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "percentunit"
|
||||
}
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 3,
|
||||
"w": 4,
|
||||
"x": 20,
|
||||
"y": 0
|
||||
},
|
||||
"id": 6,
|
||||
"interval": "1m",
|
||||
"options": {
|
||||
"colorMode": "none"
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "sum(kube_pod_windows_container_resource_memory_limit{cluster=\"$cluster\"}) / sum(:windows_node_memory_MemTotal_bytes:sum{cluster=\"$cluster\"})",
|
||||
"instant": true
|
||||
}
|
||||
],
|
||||
"title": "Memory Limits Commitment",
|
||||
"type": "stat"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"custom": {
|
||||
"fillOpacity": 10,
|
||||
"showPoints": "never",
|
||||
"spanNulls": true
|
||||
}
|
||||
}
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 7,
|
||||
"w": 24,
|
||||
"x": 0,
|
||||
"y": 7
|
||||
},
|
||||
"id": 7,
|
||||
"interval": "1m",
|
||||
"options": {
|
||||
"legend": {
|
||||
"asTable": true,
|
||||
"calcs": [
|
||||
"lastNotNull"
|
||||
],
|
||||
"displayMode": "table",
|
||||
"placement": "right",
|
||||
"showLegend": true
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "sum(namespace_pod_container:windows_container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\"}) by (namespace)",
|
||||
"legendFormat": "__auto"
|
||||
}
|
||||
],
|
||||
"title": "CPU Usage",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"overrides": [
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byRegexp",
|
||||
"options": "/%/"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "unit",
|
||||
"value": "percentunit"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "Namespace"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "links",
|
||||
"value": [
|
||||
{
|
||||
"title": "Drill down to pods",
|
||||
"url": "/d/490b402361724ab1d4c45666c1fa9b6f/k8s-resources-windows-namespace?${datasource:queryparam}&var-cluster=$cluster&var-namespace=${__data.fields.Namespace}"
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 7,
|
||||
"w": 24,
|
||||
"x": 0,
|
||||
"y": 14
|
||||
},
|
||||
"id": 8,
|
||||
"pluginVersion": "v11.4.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "sum(namespace_pod_container:windows_container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\"}) by (namespace)",
|
||||
"format": "table",
|
||||
"instant": true
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "sum(kube_pod_windows_container_resource_cpu_cores_request{cluster=\"$cluster\"}) by (namespace)",
|
||||
"format": "table",
|
||||
"instant": true
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "sum(namespace_pod_container:windows_container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\"}) by (namespace) / sum(kube_pod_windows_container_resource_cpu_cores_request{cluster=\"$cluster\"}) by (namespace)",
|
||||
"format": "table",
|
||||
"instant": true
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "sum(kube_pod_windows_container_resource_cpu_cores_limit{cluster=\"$cluster\"}) by (namespace)",
|
||||
"format": "table",
|
||||
"instant": true
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "sum(namespace_pod_container:windows_container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\"}) by (namespace) / sum(kube_pod_windows_container_resource_cpu_cores_limit{cluster=\"$cluster\"}) by (namespace)",
|
||||
"format": "table",
|
||||
"instant": true
|
||||
}
|
||||
],
|
||||
"title": "CPU Quota",
|
||||
"transformations": [
|
||||
{
|
||||
"id": "joinByField",
|
||||
"options": {
|
||||
"byField": "namespace",
|
||||
"mode": "outer"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "organize",
|
||||
"options": {
|
||||
"excludeByName": {
|
||||
"Time": true,
|
||||
"Time 1": true,
|
||||
"Time 2": true,
|
||||
"Time 3": true,
|
||||
"Time 4": true,
|
||||
"Time 5": true
|
||||
},
|
||||
"indexByName": {
|
||||
"Time 1": 0,
|
||||
"Time 2": 1,
|
||||
"Time 3": 2,
|
||||
"Time 4": 3,
|
||||
"Time 5": 4,
|
||||
"Value #A": 6,
|
||||
"Value #B": 7,
|
||||
"Value #C": 8,
|
||||
"Value #D": 9,
|
||||
"Value #E": 10,
|
||||
"namespace": 5
|
||||
},
|
||||
"renameByName": {
|
||||
"Value #A": "CPU Usage",
|
||||
"Value #B": "CPU Requests",
|
||||
"Value #C": "CPU Requests %",
|
||||
"Value #D": "CPU Limits",
|
||||
"Value #E": "CPU Limits %",
|
||||
"namespace": "Namespace"
|
||||
}
|
||||
}
|
||||
}
|
||||
],
|
||||
"type": "table"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"custom": {
|
||||
"fillOpacity": 10,
|
||||
"showPoints": "never",
|
||||
"spanNulls": true
|
||||
},
|
||||
"unit": "decbytes"
|
||||
}
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 7,
|
||||
"w": 24,
|
||||
"x": 0,
|
||||
"y": 21
|
||||
},
|
||||
"id": 9,
|
||||
"interval": "1m",
|
||||
"options": {
|
||||
"legend": {
|
||||
"asTable": true,
|
||||
"calcs": [
|
||||
"lastNotNull"
|
||||
],
|
||||
"displayMode": "table",
|
||||
"placement": "right",
|
||||
"showLegend": true
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "sum(windows_container_private_working_set_usage{cluster=\"$cluster\"}) by (namespace)",
|
||||
"legendFormat": "__auto"
|
||||
}
|
||||
],
|
||||
"title": "Memory Usage (Private Working Set)",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "bytes"
|
||||
},
|
||||
"overrides": [
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byRegexp",
|
||||
"options": "/%/"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "unit",
|
||||
"value": "percentunit"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "Memory Usage"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "unit",
|
||||
"value": "decbytes"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "Memory Requests"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "unit",
|
||||
"value": "decbytes"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "Memory Limits"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "unit",
|
||||
"value": "decbytes"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "Namespace"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "links",
|
||||
"value": [
|
||||
{
|
||||
"title": "Drill down to pods",
|
||||
"url": "/d/490b402361724ab1d4c45666c1fa9b6f/k8s-resources-windows-namespace?${datasource:queryparam}&var-cluster=$cluster&var-namespace=${__data.fields.Namespace}"
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 7,
|
||||
"w": 24,
|
||||
"x": 0,
|
||||
"y": 28
|
||||
},
|
||||
"id": 10,
|
||||
"pluginVersion": "v11.4.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "sum(windows_container_private_working_set_usage{cluster=\"$cluster\"}) by (namespace)",
|
||||
"format": "table",
|
||||
"instant": true
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "sum(kube_pod_windows_container_resource_memory_request{cluster=\"$cluster\"}) by (namespace)",
|
||||
"format": "table",
|
||||
"instant": true
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "sum(windows_container_private_working_set_usage{cluster=\"$cluster\"}) by (namespace) / sum(kube_pod_windows_container_resource_memory_request{cluster=\"$cluster\"}) by (namespace)",
|
||||
"format": "table",
|
||||
"instant": true
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "sum(kube_pod_windows_container_resource_memory_limit{cluster=\"$cluster\"}) by (namespace)",
|
||||
"format": "table",
|
||||
"instant": true
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "sum(windows_container_private_working_set_usage{cluster=\"$cluster\"}) by (namespace) / sum(kube_pod_windows_container_resource_memory_limit{cluster=\"$cluster\"}) by (namespace)",
|
||||
"format": "table",
|
||||
"instant": true
|
||||
}
|
||||
],
|
||||
"title": "Memory Requests by Namespace",
|
||||
"transformations": [
|
||||
{
|
||||
"id": "joinByField",
|
||||
"options": {
|
||||
"byField": "namespace",
|
||||
"mode": "outer"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "organize",
|
||||
"options": {
|
||||
"excludeByName": {
|
||||
"Time": true,
|
||||
"Time 1": true,
|
||||
"Time 2": true,
|
||||
"Time 3": true,
|
||||
"Time 4": true,
|
||||
"Time 5": true
|
||||
},
|
||||
"indexByName": {
|
||||
"Time 1": 0,
|
||||
"Time 2": 1,
|
||||
"Time 3": 2,
|
||||
"Time 4": 3,
|
||||
"Time 5": 4,
|
||||
"Value #A": 6,
|
||||
"Value #B": 7,
|
||||
"Value #C": 8,
|
||||
"Value #D": 9,
|
||||
"Value #E": 10,
|
||||
"namespace": 5
|
||||
},
|
||||
"renameByName": {
|
||||
"Value #A": "Memory Usage",
|
||||
"Value #B": "Memory Requests",
|
||||
"Value #C": "Memory Requests %",
|
||||
"Value #D": "Memory Limits",
|
||||
"Value #E": "Memory Limits %",
|
||||
"namespace": "Namespace"
|
||||
}
|
||||
}
|
||||
}
|
||||
],
|
||||
"type": "table"
|
||||
}
|
||||
],
|
||||
"refresh": "10s",
|
||||
"schemaVersion": 39,
|
||||
"tags": [
|
||||
"kubernetes"
|
||||
],
|
||||
"templating": {
|
||||
"list": [
|
||||
{
|
||||
"current": {
|
||||
"selected": true,
|
||||
"text": "default",
|
||||
"value": "default"
|
||||
},
|
||||
"hide": 0,
|
||||
"label": "Data source",
|
||||
"name": "datasource",
|
||||
"query": "prometheus",
|
||||
"regex": "",
|
||||
"type": "datasource"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"hide": 2,
|
||||
"label": "cluster",
|
||||
"name": "cluster",
|
||||
"query": "label_values(up{job=\"kubernetes-windows-exporter\"}, cluster)",
|
||||
"refresh": 2,
|
||||
"sort": 1,
|
||||
"type": "query"
|
||||
}
|
||||
]
|
||||
},
|
||||
"time": {
|
||||
"from": "now-1h",
|
||||
"to": "now"
|
||||
},
|
||||
"timezone": "utc",
|
||||
"title": "Compute Resources / Cluster(Windows)",
|
||||
"uid": "4d08557fd9391b100730f2494bccac68"
|
||||
}
|
||||
@ -1,442 +0,0 @@
|
||||
{
|
||||
"editable": false,
|
||||
"panels": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"custom": {
|
||||
"fillOpacity": 10,
|
||||
"showPoints": "never",
|
||||
"spanNulls": true
|
||||
}
|
||||
}
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 7,
|
||||
"w": 24,
|
||||
"x": 0,
|
||||
"y": 0
|
||||
},
|
||||
"id": 1,
|
||||
"interval": "1m",
|
||||
"options": {
|
||||
"legend": {
|
||||
"asTable": true,
|
||||
"calcs": [
|
||||
"lastNotNull"
|
||||
],
|
||||
"displayMode": "table",
|
||||
"placement": "right",
|
||||
"showLegend": true
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "sum(namespace_pod_container:windows_container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)",
|
||||
"legendFormat": "__auto"
|
||||
}
|
||||
],
|
||||
"title": "CPU Usage",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"overrides": [
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byRegexp",
|
||||
"options": "/%/"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "unit",
|
||||
"value": "percentunit"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "Pod"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "links",
|
||||
"value": [
|
||||
{
|
||||
"title": "Drill down to pods",
|
||||
"url": "/d/40597a704a610e936dc6ed374a7ce023/k8s-resources-windows-pod?${datasource:queryparam}&var-cluster=$cluster&var-namespace=$namespace&var-pod=${__data.fields.Pod}"
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 7,
|
||||
"w": 24,
|
||||
"x": 0,
|
||||
"y": 7
|
||||
},
|
||||
"id": 2,
|
||||
"pluginVersion": "v11.4.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "sum(namespace_pod_container:windows_container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)",
|
||||
"format": "table",
|
||||
"instant": true
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "sum(kube_pod_windows_container_resource_cpu_cores_request{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)",
|
||||
"format": "table",
|
||||
"instant": true
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "sum(namespace_pod_container:windows_container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod) / sum(kube_pod_windows_container_resource_cpu_cores_request{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)",
|
||||
"format": "table",
|
||||
"instant": true
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "sum(kube_pod_windows_container_resource_cpu_cores_limit{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)",
|
||||
"format": "table",
|
||||
"instant": true
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "sum(namespace_pod_container:windows_container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod) / sum(kube_pod_windows_container_resource_cpu_cores_limit{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)",
|
||||
"format": "table",
|
||||
"instant": true
|
||||
}
|
||||
],
|
||||
"title": "CPU Quota",
|
||||
"transformations": [
|
||||
{
|
||||
"id": "joinByField",
|
||||
"options": {
|
||||
"byField": "pod",
|
||||
"mode": "outer"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "organize",
|
||||
"options": {
|
||||
"excludeByName": {
|
||||
"Time": true,
|
||||
"Time 1": true,
|
||||
"Time 2": true,
|
||||
"Time 3": true,
|
||||
"Time 4": true,
|
||||
"Time 5": true
|
||||
},
|
||||
"indexByName": {
|
||||
"Time 1": 0,
|
||||
"Time 2": 1,
|
||||
"Time 3": 2,
|
||||
"Time 4": 3,
|
||||
"Time 5": 4,
|
||||
"Value #A": 6,
|
||||
"Value #B": 7,
|
||||
"Value #C": 8,
|
||||
"Value #D": 9,
|
||||
"Value #E": 10,
|
||||
"pod": 5
|
||||
},
|
||||
"renameByName": {
|
||||
"Value #A": "CPU Usage",
|
||||
"Value #B": "CPU Requests",
|
||||
"Value #C": "CPU Requests %",
|
||||
"Value #D": "CPU Limits",
|
||||
"Value #E": "CPU Limits %",
|
||||
"pod": "Pod"
|
||||
}
|
||||
}
|
||||
}
|
||||
],
|
||||
"type": "table"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"custom": {
|
||||
"fillOpacity": 10,
|
||||
"showPoints": "never",
|
||||
"spanNulls": true
|
||||
},
|
||||
"unit": "decbytes"
|
||||
}
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 7,
|
||||
"w": 24,
|
||||
"x": 0,
|
||||
"y": 14
|
||||
},
|
||||
"id": 3,
|
||||
"interval": "1m",
|
||||
"options": {
|
||||
"legend": {
|
||||
"asTable": true,
|
||||
"calcs": [
|
||||
"lastNotNull"
|
||||
],
|
||||
"displayMode": "table",
|
||||
"placement": "right",
|
||||
"showLegend": true
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "sum(windows_container_private_working_set_usage{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)",
|
||||
"legendFormat": "__auto"
|
||||
}
|
||||
],
|
||||
"title": "Memory Usage (Private Working Set)",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "bytes"
|
||||
},
|
||||
"overrides": [
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byRegexp",
|
||||
"options": "/%/"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "unit",
|
||||
"value": "percentunit"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "Pod"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "links",
|
||||
"value": [
|
||||
{
|
||||
"title": "Drill down to pods",
|
||||
"url": "/d/40597a704a610e936dc6ed374a7ce023/k8s-resources-windows-pod?${datasource:queryparam}&var-cluster=$cluster&var-namespace=$namespace&var-pod=${__data.fields.Pod}"
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 7,
|
||||
"w": 24,
|
||||
"x": 0,
|
||||
"y": 21
|
||||
},
|
||||
"id": 4,
|
||||
"pluginVersion": "v11.4.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "sum(windows_container_private_working_set_usage{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)",
|
||||
"format": "table",
|
||||
"instant": true
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "sum(kube_pod_windows_container_resource_memory_request{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)",
|
||||
"format": "table",
|
||||
"instant": true
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "sum(windows_container_private_working_set_usage{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod) / sum(kube_pod_windows_container_resource_memory_request{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)",
|
||||
"format": "table",
|
||||
"instant": true
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "sum(kube_pod_windows_container_resource_memory_limit{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)",
|
||||
"format": "table",
|
||||
"instant": true
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "sum(windows_container_private_working_set_usage{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod) / sum(kube_pod_windows_container_resource_memory_limit{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)",
|
||||
"format": "table",
|
||||
"instant": true
|
||||
}
|
||||
],
|
||||
"title": "Memory Quota",
|
||||
"transformations": [
|
||||
{
|
||||
"id": "joinByField",
|
||||
"options": {
|
||||
"byField": "pod",
|
||||
"mode": "outer"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "organize",
|
||||
"options": {
|
||||
"excludeByName": {
|
||||
"Time": true,
|
||||
"Time 1": true,
|
||||
"Time 2": true,
|
||||
"Time 3": true,
|
||||
"Time 4": true,
|
||||
"Time 5": true
|
||||
},
|
||||
"indexByName": {
|
||||
"Time 1": 0,
|
||||
"Time 2": 1,
|
||||
"Time 3": 2,
|
||||
"Time 4": 3,
|
||||
"Time 5": 4,
|
||||
"Value #A": 6,
|
||||
"Value #B": 7,
|
||||
"Value #C": 8,
|
||||
"Value #D": 9,
|
||||
"Value #E": 10,
|
||||
"pod": 5
|
||||
},
|
||||
"renameByName": {
|
||||
"Value #A": "Memory Usage",
|
||||
"Value #B": "Memory Requests",
|
||||
"Value #C": "Memory Requests %",
|
||||
"Value #D": "Memory Limits",
|
||||
"Value #E": "Memory Limits %",
|
||||
"pod": "Pod"
|
||||
}
|
||||
}
|
||||
}
|
||||
],
|
||||
"type": "table"
|
||||
}
|
||||
],
|
||||
"refresh": "10s",
|
||||
"schemaVersion": 39,
|
||||
"tags": [
|
||||
"kubernetes"
|
||||
],
|
||||
"templating": {
|
||||
"list": [
|
||||
{
|
||||
"current": {
|
||||
"selected": true,
|
||||
"text": "default",
|
||||
"value": "default"
|
||||
},
|
||||
"hide": 0,
|
||||
"label": "Data source",
|
||||
"name": "datasource",
|
||||
"query": "prometheus",
|
||||
"regex": "",
|
||||
"type": "datasource"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"hide": 2,
|
||||
"label": "cluster",
|
||||
"name": "cluster",
|
||||
"query": "label_values(up{job=\"kubernetes-windows-exporter\"}, cluster)",
|
||||
"refresh": 2,
|
||||
"sort": 1,
|
||||
"type": "query"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"hide": 0,
|
||||
"label": "namespace",
|
||||
"name": "namespace",
|
||||
"query": "label_values(windows_pod_container_available{cluster=\"$cluster\"}, namespace)",
|
||||
"refresh": 2,
|
||||
"sort": 1,
|
||||
"type": "query"
|
||||
}
|
||||
]
|
||||
},
|
||||
"time": {
|
||||
"from": "now-1h",
|
||||
"to": "now"
|
||||
},
|
||||
"timezone": "utc",
|
||||
"title": "Compute Resources / Namespace(Windows)",
|
||||
"uid": "490b402361724ab1d4c45666c1fa9b6f"
|
||||
}
|
||||
@ -1,497 +0,0 @@
|
||||
{
|
||||
"editable": false,
|
||||
"panels": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"custom": {
|
||||
"fillOpacity": 10,
|
||||
"showPoints": "never",
|
||||
"spanNulls": true
|
||||
}
|
||||
}
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 7,
|
||||
"w": 24,
|
||||
"x": 0,
|
||||
"y": 0
|
||||
},
|
||||
"id": 1,
|
||||
"interval": "1m",
|
||||
"options": {
|
||||
"legend": {
|
||||
"asTable": true,
|
||||
"calcs": [
|
||||
"lastNotNull"
|
||||
],
|
||||
"displayMode": "table",
|
||||
"placement": "right",
|
||||
"showLegend": true
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "sum(namespace_pod_container:windows_container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)",
|
||||
"legendFormat": "__auto"
|
||||
}
|
||||
],
|
||||
"title": "CPU Usage",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"overrides": [
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byRegexp",
|
||||
"options": "/%/"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "unit",
|
||||
"value": "percentunit"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "Namespace"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "links",
|
||||
"value": [
|
||||
{
|
||||
"title": "Drill down to pods",
|
||||
"url": "/d/490b402361724ab1d4c45666c1fa9b6f/k8s-resources-windows-namespace?${datasource:queryparam}&var-cluster=$cluster&var-namespace=${__data.fields.Namespace}"
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 7,
|
||||
"w": 24,
|
||||
"x": 0,
|
||||
"y": 7
|
||||
},
|
||||
"id": 2,
|
||||
"pluginVersion": "v11.4.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "sum(namespace_pod_container:windows_container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)",
|
||||
"format": "table",
|
||||
"instant": true
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "sum(kube_pod_windows_container_resource_cpu_cores_request{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)",
|
||||
"format": "table",
|
||||
"instant": true
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "sum(namespace_pod_container:windows_container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container) / sum(kube_pod_windows_container_resource_cpu_cores_request{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)",
|
||||
"format": "table",
|
||||
"instant": true
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "sum(kube_pod_windows_container_resource_cpu_cores_limit{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)",
|
||||
"format": "table",
|
||||
"instant": true
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "sum(namespace_pod_container:windows_container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container) / sum(kube_pod_windows_container_resource_cpu_cores_limit{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)",
|
||||
"format": "table",
|
||||
"instant": true
|
||||
}
|
||||
],
|
||||
"title": "CPU Quota",
|
||||
"transformations": [
|
||||
{
|
||||
"id": "joinByField",
|
||||
"options": {
|
||||
"byField": "container",
|
||||
"mode": "outer"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "organize",
|
||||
"options": {
|
||||
"excludeByName": {
|
||||
"Time": true,
|
||||
"Time 1": true,
|
||||
"Time 2": true,
|
||||
"Time 3": true,
|
||||
"Time 4": true,
|
||||
"Time 5": true
|
||||
},
|
||||
"indexByName": {
|
||||
"Time 1": 0,
|
||||
"Time 2": 1,
|
||||
"Time 3": 2,
|
||||
"Time 4": 3,
|
||||
"Time 5": 4,
|
||||
"Value #A": 6,
|
||||
"Value #B": 7,
|
||||
"Value #C": 8,
|
||||
"Value #D": 9,
|
||||
"Value #E": 10,
|
||||
"container": 5
|
||||
},
|
||||
"renameByName": {
|
||||
"Value #A": "CPU Usage",
|
||||
"Value #B": "CPU Requests",
|
||||
"Value #C": "CPU Requests %",
|
||||
"Value #D": "CPU Limits",
|
||||
"Value #E": "CPU Limits %",
|
||||
"container": "Container"
|
||||
}
|
||||
}
|
||||
}
|
||||
],
|
||||
"type": "table"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"custom": {
|
||||
"fillOpacity": 10,
|
||||
"showPoints": "never",
|
||||
"spanNulls": true
|
||||
},
|
||||
"unit": "decbytes"
|
||||
}
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 7,
|
||||
"w": 24,
|
||||
"x": 0,
|
||||
"y": 14
|
||||
},
|
||||
"id": 3,
|
||||
"interval": "1m",
|
||||
"options": {
|
||||
"legend": {
|
||||
"asTable": true,
|
||||
"calcs": [
|
||||
"lastNotNull"
|
||||
],
|
||||
"displayMode": "table",
|
||||
"placement": "right",
|
||||
"showLegend": true
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "sum(windows_container_private_working_set_usage{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)",
|
||||
"legendFormat": "__auto"
|
||||
}
|
||||
],
|
||||
"title": "Memory Usage",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "bytes"
|
||||
},
|
||||
"overrides": [
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byRegexp",
|
||||
"options": "/%/"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "unit",
|
||||
"value": "percentunit"
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 7,
|
||||
"w": 24,
|
||||
"x": 0,
|
||||
"y": 21
|
||||
},
|
||||
"id": 4,
|
||||
"pluginVersion": "v11.4.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "sum(windows_container_private_working_set_usage{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)",
|
||||
"format": "table",
|
||||
"instant": true
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "sum(kube_pod_windows_container_resource_memory_request{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)",
|
||||
"format": "table",
|
||||
"instant": true
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "sum(windows_container_private_working_set_usage{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container) / sum(kube_pod_windows_container_resource_memory_request{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)",
|
||||
"format": "table",
|
||||
"instant": true
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "sum(kube_pod_windows_container_resource_memory_limit{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)",
|
||||
"format": "table",
|
||||
"instant": true
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "sum(windows_container_private_working_set_usage{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container) / sum(kube_pod_windows_container_resource_memory_limit{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)",
|
||||
"format": "table",
|
||||
"instant": true
|
||||
}
|
||||
],
|
||||
"title": "Memory Quota",
|
||||
"transformations": [
|
||||
{
|
||||
"id": "joinByField",
|
||||
"options": {
|
||||
"byField": "container",
|
||||
"mode": "outer"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "organize",
|
||||
"options": {
|
||||
"excludeByName": {
|
||||
"Time": true,
|
||||
"Time 1": true,
|
||||
"Time 2": true,
|
||||
"Time 3": true,
|
||||
"Time 4": true,
|
||||
"Time 5": true
|
||||
},
|
||||
"indexByName": {
|
||||
"Time 1": 0,
|
||||
"Time 2": 1,
|
||||
"Time 3": 2,
|
||||
"Time 4": 3,
|
||||
"Time 5": 4,
|
||||
"Value #A": 6,
|
||||
"Value #B": 7,
|
||||
"Value #C": 8,
|
||||
"Value #D": 9,
|
||||
"Value #E": 10,
|
||||
"container": 5
|
||||
},
|
||||
"renameByName": {
|
||||
"Value #A": "Memory Usage",
|
||||
"Value #B": "Memory Requests",
|
||||
"Value #C": "Memory Requests %",
|
||||
"Value #D": "Memory Limits",
|
||||
"Value #E": "Memory Limits %",
|
||||
"container": "Container"
|
||||
}
|
||||
}
|
||||
}
|
||||
],
|
||||
"type": "table"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"custom": {
|
||||
"fillOpacity": 10,
|
||||
"showPoints": "never",
|
||||
"spanNulls": true
|
||||
},
|
||||
"unit": "bytes"
|
||||
}
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 7,
|
||||
"w": 24,
|
||||
"x": 0,
|
||||
"y": 28
|
||||
},
|
||||
"id": 5,
|
||||
"interval": "1m",
|
||||
"options": {
|
||||
"legend": {
|
||||
"asTable": true,
|
||||
"calcs": [
|
||||
"lastNotNull"
|
||||
],
|
||||
"displayMode": "table",
|
||||
"placement": "right",
|
||||
"showLegend": true
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "sort_desc(sum by (container) (rate(windows_container_network_received_bytes_total{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval])))",
|
||||
"legendFormat": "Received : {{ container }}"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "sort_desc(sum by (container) (rate(windows_container_network_transmitted_bytes_total{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval])))",
|
||||
"legendFormat": "Transmitted : {{ container }}"
|
||||
}
|
||||
],
|
||||
"title": "Network I/O",
|
||||
"type": "timeseries"
|
||||
}
|
||||
],
|
||||
"refresh": "10s",
|
||||
"schemaVersion": 39,
|
||||
"tags": [
|
||||
"kubernetes"
|
||||
],
|
||||
"templating": {
|
||||
"list": [
|
||||
{
|
||||
"current": {
|
||||
"selected": true,
|
||||
"text": "default",
|
||||
"value": "default"
|
||||
},
|
||||
"hide": 0,
|
||||
"label": "Data source",
|
||||
"name": "datasource",
|
||||
"query": "prometheus",
|
||||
"regex": "",
|
||||
"type": "datasource"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"hide": 2,
|
||||
"label": "cluster",
|
||||
"name": "cluster",
|
||||
"query": "label_values(up{job=\"kubernetes-windows-exporter\"}, cluster)",
|
||||
"refresh": 2,
|
||||
"sort": 1,
|
||||
"type": "query"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"hide": 0,
|
||||
"label": "namespace",
|
||||
"name": "namespace",
|
||||
"query": "label_values(windows_pod_container_available{cluster=\"$cluster\"}, namespace)",
|
||||
"refresh": 2,
|
||||
"sort": 1,
|
||||
"type": "query"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"hide": 0,
|
||||
"label": "pod",
|
||||
"name": "pod",
|
||||
"query": "label_values(windows_pod_container_available{cluster=\"$cluster\",namespace=\"$namespace\"}, pod)",
|
||||
"refresh": 2,
|
||||
"sort": 1,
|
||||
"type": "query"
|
||||
}
|
||||
]
|
||||
},
|
||||
"time": {
|
||||
"from": "now-1h",
|
||||
"to": "now"
|
||||
},
|
||||
"timezone": "utc",
|
||||
"title": "Compute Resources / Pod(Windows)",
|
||||
"uid": "40597a704a610e936dc6ed374a7ce023"
|
||||
}
|
||||
@ -50,7 +50,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -109,7 +109,7 @@
|
||||
"y": 7
|
||||
},
|
||||
"id": 2,
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -240,7 +240,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -302,7 +302,7 @@
|
||||
"y": 21
|
||||
},
|
||||
"id": 4,
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -453,7 +453,7 @@
|
||||
"y": 28
|
||||
},
|
||||
"id": 5,
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -597,7 +597,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -648,7 +648,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -699,7 +699,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -750,7 +750,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -801,7 +801,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -852,7 +852,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -903,7 +903,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -954,7 +954,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
|
||||
@ -102,7 +102,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -189,7 +189,7 @@
|
||||
"y": 7
|
||||
},
|
||||
"id": 2,
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -397,7 +397,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -487,7 +487,7 @@
|
||||
"y": 21
|
||||
},
|
||||
"id": 4,
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -663,7 +663,7 @@
|
||||
"y": 28
|
||||
},
|
||||
"id": 5,
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -807,7 +807,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -858,7 +858,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -909,7 +909,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -960,7 +960,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -1011,7 +1011,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -1062,7 +1062,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -1113,7 +1113,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -1164,7 +1164,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
|
||||
@ -1,404 +0,0 @@
|
||||
{
|
||||
"editable": false,
|
||||
"panels": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"custom": {
|
||||
"fillOpacity": 10,
|
||||
"showPoints": "never",
|
||||
"spanNulls": true
|
||||
},
|
||||
"unit": "percentunit"
|
||||
}
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 7,
|
||||
"w": 24,
|
||||
"x": 0,
|
||||
"y": 0
|
||||
},
|
||||
"id": 1,
|
||||
"interval": "1m",
|
||||
"options": {
|
||||
"legend": {
|
||||
"asTable": true,
|
||||
"calcs": [
|
||||
"lastNotNull"
|
||||
],
|
||||
"displayMode": "table",
|
||||
"placement": "right",
|
||||
"showLegend": true
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "node:windows_node_cpu_utilisation:avg1m{cluster=\"$cluster\"} * node:windows_node_num_cpu:sum{cluster=\"$cluster\"} / scalar(sum(node:windows_node_num_cpu:sum{cluster=\"$cluster\"}))",
|
||||
"legendFormat": "{{instance}}"
|
||||
}
|
||||
],
|
||||
"title": "CPU Utilisation",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"custom": {
|
||||
"fillOpacity": 10,
|
||||
"showPoints": "never",
|
||||
"spanNulls": true
|
||||
},
|
||||
"unit": "percentunit"
|
||||
}
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 7,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 7
|
||||
},
|
||||
"id": 2,
|
||||
"interval": "1m",
|
||||
"options": {
|
||||
"legend": {
|
||||
"asTable": true,
|
||||
"calcs": [
|
||||
"lastNotNull"
|
||||
],
|
||||
"displayMode": "table",
|
||||
"placement": "right",
|
||||
"showLegend": true
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "node:windows_node_memory_utilisation:ratio{cluster=\"$cluster\"}",
|
||||
"legendFormat": "{{instance}}"
|
||||
}
|
||||
],
|
||||
"title": "Memory Utilisation",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"custom": {
|
||||
"fillOpacity": 10,
|
||||
"showPoints": "never",
|
||||
"spanNulls": true
|
||||
},
|
||||
"unit": "short"
|
||||
}
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 7,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 7
|
||||
},
|
||||
"id": 3,
|
||||
"interval": "1m",
|
||||
"options": {
|
||||
"legend": {
|
||||
"asTable": true,
|
||||
"calcs": [
|
||||
"lastNotNull"
|
||||
],
|
||||
"displayMode": "table",
|
||||
"placement": "right",
|
||||
"showLegend": true
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "node:windows_node_memory_swap_io_pages:irate{cluster=\"$cluster\"}",
|
||||
"legendFormat": "{{instance}}"
|
||||
}
|
||||
],
|
||||
"title": "Memory Saturation (Swap I/O Pages)",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"custom": {
|
||||
"fillOpacity": 10,
|
||||
"showPoints": "never",
|
||||
"spanNulls": true
|
||||
},
|
||||
"unit": "percentunit"
|
||||
}
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 7,
|
||||
"w": 24,
|
||||
"x": 0,
|
||||
"y": 14
|
||||
},
|
||||
"id": 4,
|
||||
"interval": "1m",
|
||||
"options": {
|
||||
"legend": {
|
||||
"asTable": true,
|
||||
"calcs": [
|
||||
"lastNotNull"
|
||||
],
|
||||
"displayMode": "table",
|
||||
"placement": "right",
|
||||
"showLegend": true
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "node:windows_node_disk_utilisation:avg_irate{cluster=\"$cluster\"} / scalar(node:windows_node:sum{cluster=\"$cluster\"})",
|
||||
"legendFormat": "{{instance}}"
|
||||
}
|
||||
],
|
||||
"title": "Disk IO Utilisation",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"custom": {
|
||||
"fillOpacity": 10,
|
||||
"showPoints": "never",
|
||||
"spanNulls": true
|
||||
},
|
||||
"unit": "Bps"
|
||||
}
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 7,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 21
|
||||
},
|
||||
"id": 5,
|
||||
"interval": "1m",
|
||||
"options": {
|
||||
"legend": {
|
||||
"asTable": true,
|
||||
"calcs": [
|
||||
"lastNotNull"
|
||||
],
|
||||
"displayMode": "table",
|
||||
"placement": "right",
|
||||
"showLegend": true
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "node:windows_node_net_utilisation:sum_irate{cluster=\"$cluster\"}",
|
||||
"legendFormat": "{{instance}}"
|
||||
}
|
||||
],
|
||||
"title": "Net Utilisation (Transmitted)",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"custom": {
|
||||
"fillOpacity": 10,
|
||||
"showPoints": "never",
|
||||
"spanNulls": true
|
||||
},
|
||||
"unit": "Bps"
|
||||
}
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 7,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 21
|
||||
},
|
||||
"id": 6,
|
||||
"interval": "1m",
|
||||
"options": {
|
||||
"legend": {
|
||||
"asTable": true,
|
||||
"calcs": [
|
||||
"lastNotNull"
|
||||
],
|
||||
"displayMode": "table",
|
||||
"placement": "right",
|
||||
"showLegend": true
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "node:windows_node_net_saturation:sum_irate{cluster=\"$cluster\"}",
|
||||
"legendFormat": "{{instance}}"
|
||||
}
|
||||
],
|
||||
"title": "Net Utilisation (Dropped)",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"custom": {
|
||||
"fillOpacity": 10,
|
||||
"showPoints": "never",
|
||||
"spanNulls": true
|
||||
},
|
||||
"unit": "percentunit"
|
||||
}
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 7,
|
||||
"w": 24,
|
||||
"x": 0,
|
||||
"y": 28
|
||||
},
|
||||
"id": 7,
|
||||
"interval": "1m",
|
||||
"options": {
|
||||
"legend": {
|
||||
"asTable": true,
|
||||
"calcs": [
|
||||
"lastNotNull"
|
||||
],
|
||||
"displayMode": "table",
|
||||
"placement": "right",
|
||||
"showLegend": true
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "sum by (instance)(node:windows_node_filesystem_usage:{cluster=\"$cluster\"})",
|
||||
"legendFormat": "{{instance}}"
|
||||
}
|
||||
],
|
||||
"title": "Disk Capacity",
|
||||
"type": "timeseries"
|
||||
}
|
||||
],
|
||||
"refresh": "10s",
|
||||
"schemaVersion": 39,
|
||||
"tags": [
|
||||
"kubernetes"
|
||||
],
|
||||
"templating": {
|
||||
"list": [
|
||||
{
|
||||
"current": {
|
||||
"selected": true,
|
||||
"text": "default",
|
||||
"value": "default"
|
||||
},
|
||||
"hide": 0,
|
||||
"label": "Data source",
|
||||
"name": "datasource",
|
||||
"query": "prometheus",
|
||||
"regex": "",
|
||||
"type": "datasource"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"hide": 2,
|
||||
"label": "cluster",
|
||||
"name": "cluster",
|
||||
"query": "label_values(up{job=\"kubernetes-windows-exporter\"}, cluster)",
|
||||
"refresh": 2,
|
||||
"sort": 1,
|
||||
"type": "query"
|
||||
}
|
||||
]
|
||||
},
|
||||
"time": {
|
||||
"from": "now-1h",
|
||||
"to": "now"
|
||||
},
|
||||
"timezone": "utc",
|
||||
"title": "USE Method / Cluster(Windows)",
|
||||
"uid": "53a43377ec9aaf2ff64dfc7a1f539334"
|
||||
}
|
||||
@ -1,615 +0,0 @@
|
||||
{
|
||||
"editable": false,
|
||||
"panels": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"custom": {
|
||||
"fillOpacity": 10,
|
||||
"showPoints": "never",
|
||||
"spanNulls": true
|
||||
},
|
||||
"unit": "percentunit"
|
||||
}
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 7,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 0
|
||||
},
|
||||
"id": 1,
|
||||
"interval": "1m",
|
||||
"options": {
|
||||
"legend": {
|
||||
"asTable": true,
|
||||
"calcs": [
|
||||
"lastNotNull"
|
||||
],
|
||||
"displayMode": "table",
|
||||
"placement": "right",
|
||||
"showLegend": true
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "node:windows_node_cpu_utilisation:avg1m{cluster=\"$cluster\", instance=\"$instance\"}",
|
||||
"legendFormat": "Utilisation"
|
||||
}
|
||||
],
|
||||
"title": "CPU Utilisation",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"custom": {
|
||||
"fillOpacity": 10,
|
||||
"showPoints": "never",
|
||||
"spanNulls": true
|
||||
},
|
||||
"unit": "percentunit"
|
||||
}
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 7,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 0
|
||||
},
|
||||
"id": 2,
|
||||
"interval": "1m",
|
||||
"options": {
|
||||
"legend": {
|
||||
"asTable": true,
|
||||
"calcs": [
|
||||
"lastNotNull"
|
||||
],
|
||||
"displayMode": "table",
|
||||
"placement": "right",
|
||||
"showLegend": true
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "sum by (core) (irate(windows_cpu_time_total{cluster=\"$cluster\", job=\"kubernetes-windows-exporter\", mode!=\"idle\", instance=\"$instance\"}[$__rate_interval]))",
|
||||
"legendFormat": "{{core}}"
|
||||
}
|
||||
],
|
||||
"title": "CPU Usage Per Core",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"custom": {
|
||||
"fillOpacity": 10,
|
||||
"showPoints": "never",
|
||||
"spanNulls": true
|
||||
},
|
||||
"unit": "percentunit"
|
||||
}
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 7,
|
||||
"w": 8,
|
||||
"x": 0,
|
||||
"y": 7
|
||||
},
|
||||
"id": 3,
|
||||
"interval": "1m",
|
||||
"options": {
|
||||
"legend": {
|
||||
"asTable": true,
|
||||
"calcs": [
|
||||
"lastNotNull"
|
||||
],
|
||||
"displayMode": "table",
|
||||
"placement": "right",
|
||||
"showLegend": true
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "node:windows_node_memory_utilisation:{cluster=\"$cluster\", instance=\"$instance\"}",
|
||||
"legendFormat": "Memory"
|
||||
}
|
||||
],
|
||||
"title": "Memory Utilisation %",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"custom": {
|
||||
"fillOpacity": 10,
|
||||
"showPoints": "never",
|
||||
"spanNulls": true
|
||||
},
|
||||
"unit": "bytes"
|
||||
}
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 7,
|
||||
"w": 8,
|
||||
"x": 8,
|
||||
"y": 7
|
||||
},
|
||||
"id": 4,
|
||||
"interval": "1m",
|
||||
"options": {
|
||||
"legend": {
|
||||
"asTable": true,
|
||||
"calcs": [
|
||||
"lastNotNull"
|
||||
],
|
||||
"displayMode": "table",
|
||||
"placement": "right",
|
||||
"showLegend": true
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "max(\n windows_os_visible_memory_bytes{cluster=\"$cluster\", job=\"kubernetes-windows-exporter\", instance=\"$instance\"}\n - windows_memory_available_bytes{cluster=\"$cluster\", job=\"kubernetes-windows-exporter\", instance=\"$instance\"}\n)\n",
|
||||
"legendFormat": "memory used"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "max(node:windows_node_memory_totalCached_bytes:sum{cluster=\"$cluster\", instance=\"$instance\"})",
|
||||
"legendFormat": "memory cached"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "max(windows_memory_available_bytes{cluster=\"$cluster\", job=\"kubernetes-windows-exporter\", instance=\"$instance\"})",
|
||||
"legendFormat": "memory free"
|
||||
}
|
||||
],
|
||||
"title": "Memory Usage",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"custom": {
|
||||
"fillOpacity": 10,
|
||||
"showPoints": "never",
|
||||
"spanNulls": true
|
||||
},
|
||||
"unit": "short"
|
||||
}
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 7,
|
||||
"w": 8,
|
||||
"x": 16,
|
||||
"y": 7
|
||||
},
|
||||
"id": 5,
|
||||
"interval": "1m",
|
||||
"options": {
|
||||
"legend": {
|
||||
"asTable": true,
|
||||
"calcs": [
|
||||
"lastNotNull"
|
||||
],
|
||||
"displayMode": "table",
|
||||
"placement": "right",
|
||||
"showLegend": true
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "node:windows_node_memory_swap_io_pages:irate{cluster=\"$cluster\", instance=\"$instance\"}",
|
||||
"legendFormat": "Swap IO"
|
||||
}
|
||||
],
|
||||
"title": "Memory Saturation (Swap I/O) Pages",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"custom": {
|
||||
"fillOpacity": 10,
|
||||
"showPoints": "never",
|
||||
"spanNulls": true
|
||||
},
|
||||
"unit": "percentunit"
|
||||
}
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 7,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 14
|
||||
},
|
||||
"id": 6,
|
||||
"interval": "1m",
|
||||
"options": {
|
||||
"legend": {
|
||||
"asTable": true,
|
||||
"calcs": [
|
||||
"lastNotNull"
|
||||
],
|
||||
"displayMode": "table",
|
||||
"placement": "right",
|
||||
"showLegend": true
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "node:windows_node_disk_utilisation:avg_irate{cluster=\"$cluster\", instance=\"$instance\"}",
|
||||
"legendFormat": "Utilisation"
|
||||
}
|
||||
],
|
||||
"title": "Disk IO Utilisation",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"custom": {
|
||||
"fillOpacity": 10,
|
||||
"showPoints": "never",
|
||||
"spanNulls": true
|
||||
},
|
||||
"unit": "bytes"
|
||||
},
|
||||
"overrides": [
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byRegexp",
|
||||
"options": "/io time/"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "unit",
|
||||
"value": "ms"
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 7,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 14
|
||||
},
|
||||
"id": 7,
|
||||
"interval": "1m",
|
||||
"options": {
|
||||
"legend": {
|
||||
"asTable": true,
|
||||
"calcs": [
|
||||
"lastNotNull"
|
||||
],
|
||||
"displayMode": "table",
|
||||
"placement": "right",
|
||||
"showLegend": true
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "max(rate(windows_logical_disk_read_bytes_total{cluster=\"$cluster\", job=\"kubernetes-windows-exporter\", instance=\"$instance\"}[$__rate_interval]))",
|
||||
"legendFormat": "read"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "max(rate(windows_logical_disk_write_bytes_total{cluster=\"$cluster\", job=\"kubernetes-windows-exporter\", instance=\"$instance\"}[$__rate_interval]))",
|
||||
"legendFormat": "written"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "max(rate(windows_logical_disk_read_seconds_total{cluster=\"$cluster\", job=\"kubernetes-windows-exporter\", instance=\"$instance\"}[$__rate_interval]) + rate(windows_logical_disk_write_seconds_total{cluster=\"$cluster\", job=\"kubernetes-windows-exporter\", instance=\"$instance\"}[$__rate_interval]))",
|
||||
"legendFormat": "io time"
|
||||
}
|
||||
],
|
||||
"title": "Disk IO",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"custom": {
|
||||
"fillOpacity": 10,
|
||||
"showPoints": "never",
|
||||
"spanNulls": true
|
||||
},
|
||||
"unit": "percentunit"
|
||||
}
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 7,
|
||||
"w": 24,
|
||||
"x": 0,
|
||||
"y": 21
|
||||
},
|
||||
"id": 8,
|
||||
"interval": "1m",
|
||||
"options": {
|
||||
"legend": {
|
||||
"asTable": true,
|
||||
"calcs": [
|
||||
"lastNotNull"
|
||||
],
|
||||
"displayMode": "table",
|
||||
"placement": "right",
|
||||
"showLegend": true
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "node:windows_node_filesystem_usage:{cluster=\"$cluster\", instance=\"$instance\"}",
|
||||
"legendFormat": "{{volume}}"
|
||||
}
|
||||
],
|
||||
"title": "Disk Utilisation",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"custom": {
|
||||
"fillOpacity": 10,
|
||||
"showPoints": "never",
|
||||
"spanNulls": true
|
||||
},
|
||||
"unit": "Bps"
|
||||
}
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 7,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 28
|
||||
},
|
||||
"id": 9,
|
||||
"interval": "1m",
|
||||
"options": {
|
||||
"legend": {
|
||||
"asTable": true,
|
||||
"calcs": [
|
||||
"lastNotNull"
|
||||
],
|
||||
"displayMode": "table",
|
||||
"placement": "right",
|
||||
"showLegend": true
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "node:windows_node_net_utilisation:sum_irate{cluster=\"$cluster\", instance=\"$instance\"}",
|
||||
"legendFormat": "Utilisation"
|
||||
}
|
||||
],
|
||||
"title": "Net Utilisation (Transmitted)",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"custom": {
|
||||
"fillOpacity": 10,
|
||||
"showPoints": "never",
|
||||
"spanNulls": true
|
||||
},
|
||||
"unit": "Bps"
|
||||
}
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 7,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 28
|
||||
},
|
||||
"id": 10,
|
||||
"interval": "1m",
|
||||
"options": {
|
||||
"legend": {
|
||||
"asTable": true,
|
||||
"calcs": [
|
||||
"lastNotNull"
|
||||
],
|
||||
"displayMode": "table",
|
||||
"placement": "right",
|
||||
"showLegend": true
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "node:windows_node_net_saturation:sum_irate{cluster=\"$cluster\", instance=\"$instance\"}",
|
||||
"legendFormat": "Saturation"
|
||||
}
|
||||
],
|
||||
"title": "Net Saturation (Dropped)",
|
||||
"type": "timeseries"
|
||||
}
|
||||
],
|
||||
"refresh": "10s",
|
||||
"schemaVersion": 39,
|
||||
"tags": [
|
||||
"kubernetes"
|
||||
],
|
||||
"templating": {
|
||||
"list": [
|
||||
{
|
||||
"current": {
|
||||
"selected": true,
|
||||
"text": "default",
|
||||
"value": "default"
|
||||
},
|
||||
"hide": 0,
|
||||
"label": "Data source",
|
||||
"name": "datasource",
|
||||
"query": "prometheus",
|
||||
"regex": "",
|
||||
"type": "datasource"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"hide": 2,
|
||||
"label": "cluster",
|
||||
"name": "cluster",
|
||||
"query": "label_values(up{job=\"kubernetes-windows-exporter\"}, cluster)",
|
||||
"refresh": 2,
|
||||
"sort": 1,
|
||||
"type": "query"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"hide": 0,
|
||||
"label": "instance",
|
||||
"name": "instance",
|
||||
"query": "label_values(windows_system_system_up_time{cluster=\"$cluster\"}, instance)",
|
||||
"refresh": 2,
|
||||
"type": "query"
|
||||
}
|
||||
]
|
||||
},
|
||||
"time": {
|
||||
"from": "now-1h",
|
||||
"to": "now"
|
||||
},
|
||||
"timezone": "utc",
|
||||
"title": "USE Method / Node(Windows)",
|
||||
"uid": "96e7484b0bb53b74fbc2bcb7723cd40b"
|
||||
}
|
||||
@ -35,7 +35,7 @@
|
||||
"options": {
|
||||
"colorMode": "none"
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -70,7 +70,7 @@
|
||||
"options": {
|
||||
"colorMode": "none"
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -105,7 +105,7 @@
|
||||
"options": {
|
||||
"colorMode": "none"
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -140,7 +140,7 @@
|
||||
"options": {
|
||||
"colorMode": "none"
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -175,7 +175,7 @@
|
||||
"options": {
|
||||
"colorMode": "none"
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -210,7 +210,7 @@
|
||||
"options": {
|
||||
"colorMode": "none"
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -261,7 +261,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -312,7 +312,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -363,7 +363,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -414,7 +414,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -473,7 +473,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -532,7 +532,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -583,7 +583,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -634,7 +634,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -685,7 +685,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -736,7 +736,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -787,7 +787,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -838,7 +838,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -889,7 +889,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -940,7 +940,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -1015,15 +1015,15 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\", instance=~\"$instance\"}[$__rate_interval])) by (instance, verb, le))",
|
||||
"legendFormat": "{{instance}} {{verb}}"
|
||||
"expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\", instance=~\"$instance\"}[$__rate_interval])) by (instance, verb, url, le))",
|
||||
"legendFormat": "{{instance}} {{verb}} {{url}}"
|
||||
}
|
||||
],
|
||||
"title": "Request duration 99th quantile",
|
||||
@ -1066,7 +1066,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -1117,7 +1117,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -1168,7 +1168,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
|
||||
@ -53,7 +53,7 @@
|
||||
"y": 0
|
||||
},
|
||||
"id": 1,
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -106,7 +106,7 @@
|
||||
"y": 0
|
||||
},
|
||||
"id": 2,
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -177,7 +177,7 @@
|
||||
"y": 9
|
||||
},
|
||||
"id": 3,
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -316,7 +316,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -362,7 +362,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -408,7 +408,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -454,7 +454,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -500,7 +500,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -546,7 +546,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
|
||||
@ -39,7 +39,7 @@
|
||||
"displayMode": "basic",
|
||||
"showUnfilled": false
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -78,7 +78,7 @@
|
||||
"displayMode": "basic",
|
||||
"showUnfilled": false
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -149,7 +149,7 @@
|
||||
"y": 9
|
||||
},
|
||||
"id": 3,
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -335,7 +335,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -386,7 +386,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -437,7 +437,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -488,7 +488,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -539,7 +539,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -590,7 +590,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -641,7 +641,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -692,7 +692,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
|
||||
@ -50,7 +50,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -112,7 +112,7 @@
|
||||
},
|
||||
"id": 2,
|
||||
"interval": "1m",
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -162,7 +162,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -224,7 +224,7 @@
|
||||
},
|
||||
"id": 4,
|
||||
"interval": "1m",
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
|
||||
@ -53,7 +53,7 @@
|
||||
"y": 0
|
||||
},
|
||||
"id": 1,
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -106,7 +106,7 @@
|
||||
"y": 0
|
||||
},
|
||||
"id": 2,
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -152,7 +152,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -198,7 +198,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -244,7 +244,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -290,7 +290,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -336,7 +336,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -382,7 +382,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
|
||||
@ -35,7 +35,7 @@
|
||||
"options": {
|
||||
"colorMode": "none"
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -86,7 +86,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -137,7 +137,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -188,7 +188,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -239,7 +239,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -290,7 +290,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -365,15 +365,15 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-proxy\",instance=~\"$instance\",verb=\"POST\"}[$__rate_interval])) by (verb, le))",
|
||||
"legendFormat": "{{verb}}"
|
||||
"expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-proxy\",instance=~\"$instance\",verb=\"POST\"}[$__rate_interval])) by (verb, url, le))",
|
||||
"legendFormat": "{{verb}} {{url}}"
|
||||
}
|
||||
],
|
||||
"title": "Post Request Latency 99th Quantile",
|
||||
@ -416,15 +416,15 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\", verb=\"GET\"}[$__rate_interval])) by (verb, le))",
|
||||
"legendFormat": "{{verb}}"
|
||||
"expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\", verb=\"GET\"}[$__rate_interval])) by (verb, url, le))",
|
||||
"legendFormat": "{{verb}} {{url}}"
|
||||
}
|
||||
],
|
||||
"title": "Get Request Latency 99th Quantile",
|
||||
@ -467,7 +467,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -518,7 +518,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -569,7 +569,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
|
||||
@ -35,7 +35,7 @@
|
||||
"options": {
|
||||
"colorMode": "none"
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -86,7 +86,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -161,7 +161,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -236,7 +236,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -311,15 +311,15 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\", verb=\"POST\"}[$__rate_interval])) by (verb, le))",
|
||||
"legendFormat": "{{verb}}"
|
||||
"expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\", verb=\"POST\"}[$__rate_interval])) by (verb, url, le))",
|
||||
"legendFormat": "{{verb}} {{url}}"
|
||||
}
|
||||
],
|
||||
"title": "Post Request Latency 99th Quantile",
|
||||
@ -362,15 +362,15 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\", verb=\"GET\"}[$__rate_interval])) by (verb, le))",
|
||||
"legendFormat": "{{verb}}"
|
||||
"expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\", verb=\"GET\"}[$__rate_interval])) by (verb, url, le))",
|
||||
"legendFormat": "{{verb}} {{url}}"
|
||||
}
|
||||
],
|
||||
"title": "Get Request Latency 99th Quantile",
|
||||
@ -413,7 +413,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -464,7 +464,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -515,7 +515,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
|
||||
@ -39,7 +39,7 @@
|
||||
"displayMode": "basic",
|
||||
"showUnfilled": false
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -78,7 +78,7 @@
|
||||
"displayMode": "basic",
|
||||
"showUnfilled": false
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -117,7 +117,7 @@
|
||||
"displayMode": "basic",
|
||||
"showUnfilled": false
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -156,7 +156,7 @@
|
||||
"displayMode": "basic",
|
||||
"showUnfilled": false
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -207,7 +207,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -258,7 +258,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -309,7 +309,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -360,7 +360,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -411,7 +411,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
@ -462,7 +462,7 @@
|
||||
"mode": "single"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.4.0",
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
|
||||
@ -18,8 +18,8 @@
|
||||
"subdir": "contrib/mixin"
|
||||
}
|
||||
},
|
||||
"version": "f30cbaac111aa01a310fe75360c759cdd4d9cd14",
|
||||
"sum": "XmXkOCriQIZmXwlIIFhqlJMa0e6qGWdxZD+ZDYaN0Po="
|
||||
"version": "2b323071a8bd4f02ddaf63e0dfa1fd98c221dccb",
|
||||
"sum": "IXI3LQIT9NmTPJAk8WLUJd5+qZfcGpeNCyWIK7oEpws="
|
||||
},
|
||||
{
|
||||
"source": {
|
||||
@ -41,6 +41,16 @@
|
||||
"version": "a1d61cce1da59c71409b99b5c7568511fec661ea",
|
||||
"sum": "342u++/7rViR/zj2jeJOjshzglkZ1SY+hFNuyCBFMdc="
|
||||
},
|
||||
{
|
||||
"source": {
|
||||
"git": {
|
||||
"remote": "https://github.com/grafana/grafonnet-lib.git",
|
||||
"subdir": "grafonnet-7.0"
|
||||
}
|
||||
},
|
||||
"version": "a1d61cce1da59c71409b99b5c7568511fec661ea",
|
||||
"sum": "gCtR9s/4D5fxU9aKXg0Bru+/njZhA0YjLjPiASc61FM="
|
||||
},
|
||||
{
|
||||
"source": {
|
||||
"git": {
|
||||
@ -48,8 +58,8 @@
|
||||
"subdir": "gen/grafonnet-latest"
|
||||
}
|
||||
},
|
||||
"version": "d20e609202733790caf5b554c9945d049f243ae3",
|
||||
"sum": "V9vAj21qJOc2DlMPDgB1eEjSQU4A+sAA4AXuJ6bd4xc="
|
||||
"version": "82a19822e54a0a12a51e24dbd48fcde717dc0864",
|
||||
"sum": "64fMUPI3frXGj4X1FqFd1t7r04w3CUSmXaDcJ23EYbQ="
|
||||
},
|
||||
{
|
||||
"source": {
|
||||
@ -58,18 +68,18 @@
|
||||
"subdir": "gen/grafonnet-v10.0.0"
|
||||
}
|
||||
},
|
||||
"version": "d20e609202733790caf5b554c9945d049f243ae3",
|
||||
"version": "82a19822e54a0a12a51e24dbd48fcde717dc0864",
|
||||
"sum": "xdcrJPJlpkq4+5LpGwN4tPAuheNNLXZjE6tDcyvFjr0="
|
||||
},
|
||||
{
|
||||
"source": {
|
||||
"git": {
|
||||
"remote": "https://github.com/grafana/grafonnet.git",
|
||||
"subdir": "gen/grafonnet-v11.4.0"
|
||||
"subdir": "gen/grafonnet-v11.1.0"
|
||||
}
|
||||
},
|
||||
"version": "d20e609202733790caf5b554c9945d049f243ae3",
|
||||
"sum": "aVAX09paQYNOoCSKVpuk1exVIyBoMt/C50QJI+Q/3nA="
|
||||
"version": "82a19822e54a0a12a51e24dbd48fcde717dc0864",
|
||||
"sum": "41w7p/rwrNsITqNHMXtGSJAfAyKmnflg6rFhKBduUxM="
|
||||
},
|
||||
{
|
||||
"source": {
|
||||
@ -78,7 +88,7 @@
|
||||
"subdir": "grafana-builder"
|
||||
}
|
||||
},
|
||||
"version": "d6c38bb26f576b128cadca4137d73a037afdd872",
|
||||
"version": "767befa8fb46a07be516dec2777d7d89909a529d",
|
||||
"sum": "yxqWcq/N3E/a/XreeU6EuE6X7kYPnG0AspAQFKOjASo="
|
||||
},
|
||||
{
|
||||
@ -98,8 +108,8 @@
|
||||
"subdir": ""
|
||||
}
|
||||
},
|
||||
"version": "1199b50e9d2ff53d4bb5fb2304ad1fb69d38e609",
|
||||
"sum": "LfbgcJbilu4uBdKYZSvmkoOTPwEAzg10L3/VqKAIWtA="
|
||||
"version": "63d430b69a95741061c2f7fc9d84b1a778511d9c",
|
||||
"sum": "qiZi3axUSXCVzKUF83zSAxklwrnitMmrDK4XAfjPMdE="
|
||||
},
|
||||
{
|
||||
"source": {
|
||||
@ -108,8 +118,8 @@
|
||||
"subdir": ""
|
||||
}
|
||||
},
|
||||
"version": "e27267571be06c2bdc3d2fd8dbd70161cd709cb4",
|
||||
"sum": "je1RPCp2aFNefYs5Q57Q5wDm93p8pL4pdBtA5rC7jLA="
|
||||
"version": "a3fbf21977deb89b7d843eb8371170c011ea6835",
|
||||
"sum": "57zW2IGJ9zbYd8BI0qe6JkoWTRSMNiBUWC6+YcnEsWo="
|
||||
},
|
||||
{
|
||||
"source": {
|
||||
@ -118,8 +128,8 @@
|
||||
"subdir": "jsonnet/kube-state-metrics"
|
||||
}
|
||||
},
|
||||
"version": "2a95d4649b2fea55799032fb9c0b571c4ba7f776",
|
||||
"sum": "3bioG7CfTfY9zeu5xU4yon6Zt3kYvNkyl492nOhQxnM="
|
||||
"version": "32e7727ff4613b0f55dfc18aff15afb8c04d03c5",
|
||||
"sum": "lO7jUSzAIy8Yk9pOWJIWgPRhubkWzVh56W6wtYfbVH4="
|
||||
},
|
||||
{
|
||||
"source": {
|
||||
@ -128,7 +138,7 @@
|
||||
"subdir": "jsonnet/kube-state-metrics-mixin"
|
||||
}
|
||||
},
|
||||
"version": "2a95d4649b2fea55799032fb9c0b571c4ba7f776",
|
||||
"version": "32e7727ff4613b0f55dfc18aff15afb8c04d03c5",
|
||||
"sum": "qclI7LwucTjBef3PkGBkKxF0mfZPbHnn4rlNWKGtR4c="
|
||||
},
|
||||
{
|
||||
@ -138,8 +148,8 @@
|
||||
"subdir": "jsonnet/kube-prometheus"
|
||||
}
|
||||
},
|
||||
"version": "1eea946a1532f1e8cccfceea98d907bf3a10b1d9",
|
||||
"sum": "17LhiwefVfoNDsF3DcFZw/UL4PMU7YpNNUaOdaYd1gE="
|
||||
"version": "7e5a571a3fb735c78e17c76a637eb7e8bb5dd086",
|
||||
"sum": "uTw/Mj+X91S+oqUpAX81xcfWPDlox0tdSZY/YBw7nGE="
|
||||
},
|
||||
{
|
||||
"source": {
|
||||
@ -148,7 +158,7 @@
|
||||
"subdir": "jsonnet/mixin"
|
||||
}
|
||||
},
|
||||
"version": "465bcbaf2a727c942e7f923aacfb9dff9af8d4a1",
|
||||
"version": "a366602bacb2c8d773a9cee058b6971b8d2e3732",
|
||||
"sum": "gi+knjdxs2T715iIQIntrimbHRgHnpM8IFBJDD1gYfs=",
|
||||
"name": "prometheus-operator-mixin"
|
||||
},
|
||||
@ -159,8 +169,8 @@
|
||||
"subdir": "jsonnet/prometheus-operator"
|
||||
}
|
||||
},
|
||||
"version": "465bcbaf2a727c942e7f923aacfb9dff9af8d4a1",
|
||||
"sum": "LctDdofQostvviE5y8vpRKWGGO1ZKO3dgJe7P9xifW0="
|
||||
"version": "a366602bacb2c8d773a9cee058b6971b8d2e3732",
|
||||
"sum": "z0/lCiMusMHTqntsosMVGYkVcSZjCpyZBmUMVUsK5nA="
|
||||
},
|
||||
{
|
||||
"source": {
|
||||
@ -169,7 +179,7 @@
|
||||
"subdir": "doc/alertmanager-mixin"
|
||||
}
|
||||
},
|
||||
"version": "b5d1a64ad5bb0ff879705714d1e40cea82efbd5c",
|
||||
"version": "0f65e8fa5fc72d2678655105c0213b416ca6f34c",
|
||||
"sum": "Mf4h1BYLle2nrgjf/HXrBbl0Zk8N+xaoEM017o0BC+k=",
|
||||
"name": "alertmanager"
|
||||
},
|
||||
@ -180,8 +190,8 @@
|
||||
"subdir": "docs/node-mixin"
|
||||
}
|
||||
},
|
||||
"version": "11365f97bef6cb0e6259d536a7e21c49e3f5c065",
|
||||
"sum": "xYj6VYFT/eafsbleNlC+Z2VfLy1CndyYrJs9BcTmnX8="
|
||||
"version": "cf8c6891cc610e54f70383addd4bb6079f0add35",
|
||||
"sum": "cQCW+1N0Xae5yXecCWDK2oAlN0luBS/5GrwBYSlaFms="
|
||||
},
|
||||
{
|
||||
"source": {
|
||||
@ -190,8 +200,8 @@
|
||||
"subdir": "documentation/prometheus-mixin"
|
||||
}
|
||||
},
|
||||
"version": "509b978f0d675b4c9b3ccf8c0fc06961b0f03e8f",
|
||||
"sum": "2c+wttfee9TwuQJZIkNV7Tekem74Qgc7iZ842P28rNw=",
|
||||
"version": "b407c2930da4f50c0d17fc39404c6302a9eb740b",
|
||||
"sum": "OYT5u3S8DbamuJV/v3gbWSteOvFzMeNwMj+u4Apk7jM=",
|
||||
"name": "prometheus"
|
||||
},
|
||||
{
|
||||
@ -212,7 +222,7 @@
|
||||
"subdir": "mixin"
|
||||
}
|
||||
},
|
||||
"version": "346d18bb0f8011c63d7106de494cf3b9253161a1",
|
||||
"version": "7037331e6ea7dbe85a1b7af37bf8ea277a80663d",
|
||||
"sum": "ieCD4eMgGbOlrI8GmckGPHBGQDcLasE1rULYq56W/bs=",
|
||||
"name": "thanos-mixin"
|
||||
}
|
||||
|
||||
@ -6,5 +6,5 @@ dashboards:
|
||||
url: https://grafana.com/api/dashboards/9578/revisions/4/download
|
||||
tags: []
|
||||
- name: Prometheus
|
||||
url: https://grafana.com/api/dashboards/19105/revisions/7/download
|
||||
url: https://grafana.com/api/dashboards/3662/revisions/2/download
|
||||
tags: []
|
||||
|
||||
@ -7,7 +7,7 @@
|
||||
"app.kubernetes.io/instance": "main",
|
||||
"app.kubernetes.io/name": "alertmanager",
|
||||
"app.kubernetes.io/part-of": "kube-prometheus",
|
||||
"app.kubernetes.io/version": "0.28.0",
|
||||
"app.kubernetes.io/version": "0.27.0",
|
||||
"prometheus": "k8s",
|
||||
"role": "alert-rules"
|
||||
},
|
||||
|
||||
@ -20,9 +20,9 @@
|
||||
"summary": "etcd cluster members are down."
|
||||
},
|
||||
"expr": "max without (endpoint) (\n sum without (instance, pod) (up{job=~\".*etcd.*\"} == bool 0)\nor\n count without (To) (\n sum without (instance, pod) (rate(etcd_network_peer_sent_failures_total{job=~\".*etcd.*\"}[120s])) > 0.01\n )\n)\n> 0\n",
|
||||
"for": "20m",
|
||||
"for": "10m",
|
||||
"labels": {
|
||||
"severity": "warning"
|
||||
"severity": "critical"
|
||||
}
|
||||
},
|
||||
{
|
||||
|
||||
@ -6,7 +6,7 @@
|
||||
"app.kubernetes.io/component": "exporter",
|
||||
"app.kubernetes.io/name": "kube-state-metrics",
|
||||
"app.kubernetes.io/part-of": "kube-prometheus",
|
||||
"app.kubernetes.io/version": "2.15.0",
|
||||
"app.kubernetes.io/version": "2.14.0",
|
||||
"prometheus": "k8s",
|
||||
"role": "alert-rules"
|
||||
},
|
||||
|
||||
@ -19,7 +19,7 @@
|
||||
{
|
||||
"alert": "KubePodCrashLooping",
|
||||
"annotations": {
|
||||
"description": "Pod {{ $labels.namespace }}/{{ $labels.pod }} ({{ $labels.container }}) is in waiting state (reason: \"CrashLoopBackOff\") on cluster {{ $labels.cluster }}.",
|
||||
"description": "Pod {{ $labels.namespace }}/{{ $labels.pod }} ({{ $labels.container }}) is in waiting state (reason: \"CrashLoopBackOff\").",
|
||||
"runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubepodcrashlooping",
|
||||
"summary": "Pod is crash looping."
|
||||
},
|
||||
@ -32,7 +32,7 @@
|
||||
{
|
||||
"alert": "KubePodNotReady",
|
||||
"annotations": {
|
||||
"description": "Pod {{ $labels.namespace }}/{{ $labels.pod }} has been in a non-ready state for longer than 15 minutes on cluster {{ $labels.cluster }}.",
|
||||
"description": "Pod {{ $labels.namespace }}/{{ $labels.pod }} has been in a non-ready state for longer than 15 minutes.",
|
||||
"runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubepodnotready",
|
||||
"summary": "Pod has been in a non-ready state for more than 15 minutes."
|
||||
},
|
||||
@ -45,7 +45,7 @@
|
||||
{
|
||||
"alert": "KubeDeploymentGenerationMismatch",
|
||||
"annotations": {
|
||||
"description": "Deployment generation for {{ $labels.namespace }}/{{ $labels.deployment }} does not match, this indicates that the Deployment has failed but has not been rolled back on cluster {{ $labels.cluster }}.",
|
||||
"description": "Deployment generation for {{ $labels.namespace }}/{{ $labels.deployment }} does not match, this indicates that the Deployment has failed but has not been rolled back.",
|
||||
"runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubedeploymentgenerationmismatch",
|
||||
"summary": "Deployment generation mismatch due to possible roll-back"
|
||||
},
|
||||
@ -58,7 +58,7 @@
|
||||
{
|
||||
"alert": "KubeDeploymentReplicasMismatch",
|
||||
"annotations": {
|
||||
"description": "Deployment {{ $labels.namespace }}/{{ $labels.deployment }} has not matched the expected number of replicas for longer than 15 minutes on cluster {{ $labels.cluster }}.",
|
||||
"description": "Deployment {{ $labels.namespace }}/{{ $labels.deployment }} has not matched the expected number of replicas for longer than 15 minutes.",
|
||||
"runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubedeploymentreplicasmismatch",
|
||||
"summary": "Deployment has not matched the expected number of replicas."
|
||||
},
|
||||
@ -71,7 +71,7 @@
|
||||
{
|
||||
"alert": "KubeDeploymentRolloutStuck",
|
||||
"annotations": {
|
||||
"description": "Rollout of deployment {{ $labels.namespace }}/{{ $labels.deployment }} is not progressing for longer than 15 minutes on cluster {{ $labels.cluster }}.",
|
||||
"description": "Rollout of deployment {{ $labels.namespace }}/{{ $labels.deployment }} is not progressing for longer than 15 minutes.",
|
||||
"runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubedeploymentrolloutstuck",
|
||||
"summary": "Deployment rollout is not progressing."
|
||||
},
|
||||
@ -84,7 +84,7 @@
|
||||
{
|
||||
"alert": "KubeStatefulSetReplicasMismatch",
|
||||
"annotations": {
|
||||
"description": "StatefulSet {{ $labels.namespace }}/{{ $labels.statefulset }} has not matched the expected number of replicas for longer than 15 minutes on cluster {{ $labels.cluster }}.",
|
||||
"description": "StatefulSet {{ $labels.namespace }}/{{ $labels.statefulset }} has not matched the expected number of replicas for longer than 15 minutes.",
|
||||
"runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubestatefulsetreplicasmismatch",
|
||||
"summary": "StatefulSet has not matched the expected number of replicas."
|
||||
},
|
||||
@ -97,7 +97,7 @@
|
||||
{
|
||||
"alert": "KubeStatefulSetGenerationMismatch",
|
||||
"annotations": {
|
||||
"description": "StatefulSet generation for {{ $labels.namespace }}/{{ $labels.statefulset }} does not match, this indicates that the StatefulSet has failed but has not been rolled back on cluster {{ $labels.cluster }}.",
|
||||
"description": "StatefulSet generation for {{ $labels.namespace }}/{{ $labels.statefulset }} does not match, this indicates that the StatefulSet has failed but has not been rolled back.",
|
||||
"runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubestatefulsetgenerationmismatch",
|
||||
"summary": "StatefulSet generation mismatch due to possible roll-back"
|
||||
},
|
||||
@ -110,7 +110,7 @@
|
||||
{
|
||||
"alert": "KubeStatefulSetUpdateNotRolledOut",
|
||||
"annotations": {
|
||||
"description": "StatefulSet {{ $labels.namespace }}/{{ $labels.statefulset }} update has not been rolled out on cluster {{ $labels.cluster }}.",
|
||||
"description": "StatefulSet {{ $labels.namespace }}/{{ $labels.statefulset }} update has not been rolled out.",
|
||||
"runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubestatefulsetupdatenotrolledout",
|
||||
"summary": "StatefulSet update has not been rolled out."
|
||||
},
|
||||
@ -123,7 +123,7 @@
|
||||
{
|
||||
"alert": "KubeDaemonSetRolloutStuck",
|
||||
"annotations": {
|
||||
"description": "DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} has not finished or progressed for at least 15m on cluster {{ $labels.cluster }}.",
|
||||
"description": "DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} has not finished or progressed for at least 15m.",
|
||||
"runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubedaemonsetrolloutstuck",
|
||||
"summary": "DaemonSet rollout is stuck."
|
||||
},
|
||||
@ -136,7 +136,7 @@
|
||||
{
|
||||
"alert": "KubeContainerWaiting",
|
||||
"annotations": {
|
||||
"description": "pod/{{ $labels.pod }} in namespace {{ $labels.namespace }} on container {{ $labels.container}} has been in waiting state for longer than 1 hour. (reason: \"{{ $labels.reason }}\") on cluster {{ $labels.cluster }}.",
|
||||
"description": "pod/{{ $labels.pod }} in namespace {{ $labels.namespace }} on container {{ $labels.container}} has been in waiting state for longer than 1 hour. (reason: \"{{ $labels.reason }}\").",
|
||||
"runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubecontainerwaiting",
|
||||
"summary": "Pod container waiting longer than 1 hour"
|
||||
},
|
||||
@ -149,7 +149,7 @@
|
||||
{
|
||||
"alert": "KubeDaemonSetNotScheduled",
|
||||
"annotations": {
|
||||
"description": "{{ $value }} Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} are not scheduled on cluster {{ $labels.cluster }}.",
|
||||
"description": "{{ $value }} Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} are not scheduled.",
|
||||
"runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubedaemonsetnotscheduled",
|
||||
"summary": "DaemonSet pods are not scheduled."
|
||||
},
|
||||
@ -162,7 +162,7 @@
|
||||
{
|
||||
"alert": "KubeDaemonSetMisScheduled",
|
||||
"annotations": {
|
||||
"description": "{{ $value }} Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} are running where they are not supposed to run on cluster {{ $labels.cluster }}.",
|
||||
"description": "{{ $value }} Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} are running where they are not supposed to run.",
|
||||
"runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubedaemonsetmisscheduled",
|
||||
"summary": "DaemonSet pods are misscheduled."
|
||||
},
|
||||
@ -175,7 +175,7 @@
|
||||
{
|
||||
"alert": "KubeJobNotCompleted",
|
||||
"annotations": {
|
||||
"description": "Job {{ $labels.namespace }}/{{ $labels.job_name }} is taking more than {{ \"43200\" | humanizeDuration }} to complete on cluster {{ $labels.cluster }}.",
|
||||
"description": "Job {{ $labels.namespace }}/{{ $labels.job_name }} is taking more than {{ \"43200\" | humanizeDuration }} to complete.",
|
||||
"runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubejobnotcompleted",
|
||||
"summary": "Job did not complete in time"
|
||||
},
|
||||
@ -187,7 +187,7 @@
|
||||
{
|
||||
"alert": "KubeJobFailed",
|
||||
"annotations": {
|
||||
"description": "Job {{ $labels.namespace }}/{{ $labels.job_name }} failed to complete. Removing failed job after investigation should clear this alert on cluster {{ $labels.cluster }}.",
|
||||
"description": "Job {{ $labels.namespace }}/{{ $labels.job_name }} failed to complete. Removing failed job after investigation should clear this alert.",
|
||||
"runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubejobfailed",
|
||||
"summary": "Job failed to complete."
|
||||
},
|
||||
@ -200,7 +200,7 @@
|
||||
{
|
||||
"alert": "KubeHpaReplicasMismatch",
|
||||
"annotations": {
|
||||
"description": "HPA {{ $labels.namespace }}/{{ $labels.horizontalpodautoscaler }} has not matched the desired number of replicas for longer than 15 minutes on cluster {{ $labels.cluster }}.",
|
||||
"description": "HPA {{ $labels.namespace }}/{{ $labels.horizontalpodautoscaler }} has not matched the desired number of replicas for longer than 15 minutes.",
|
||||
"runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubehpareplicasmismatch",
|
||||
"summary": "HPA has not matched desired number of replicas."
|
||||
},
|
||||
@ -213,7 +213,7 @@
|
||||
{
|
||||
"alert": "KubeHpaMaxedOut",
|
||||
"annotations": {
|
||||
"description": "HPA {{ $labels.namespace }}/{{ $labels.horizontalpodautoscaler }} has been running at max replicas for longer than 15 minutes on cluster {{ $labels.cluster }}.",
|
||||
"description": "HPA {{ $labels.namespace }}/{{ $labels.horizontalpodautoscaler }} has been running at max replicas for longer than 15 minutes.",
|
||||
"runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubehpamaxedout",
|
||||
"summary": "HPA is running at max replicas"
|
||||
},
|
||||
@ -257,7 +257,7 @@
|
||||
{
|
||||
"alert": "KubeQuotaAlmostFull",
|
||||
"annotations": {
|
||||
"description": "Namespace {{ $labels.namespace }} is using {{ $value | humanizePercentage }} of its {{ $labels.resource }} quota on cluster {{ $labels.cluster }}.",
|
||||
"description": "Namespace {{ $labels.namespace }} is using {{ $value | humanizePercentage }} of its {{ $labels.resource }} quota.",
|
||||
"runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubequotaalmostfull",
|
||||
"summary": "Namespace quota is going to be full."
|
||||
},
|
||||
@ -270,7 +270,7 @@
|
||||
{
|
||||
"alert": "KubeQuotaFullyUsed",
|
||||
"annotations": {
|
||||
"description": "Namespace {{ $labels.namespace }} is using {{ $value | humanizePercentage }} of its {{ $labels.resource }} quota on cluster {{ $labels.cluster }}.",
|
||||
"description": "Namespace {{ $labels.namespace }} is using {{ $value | humanizePercentage }} of its {{ $labels.resource }} quota.",
|
||||
"runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubequotafullyused",
|
||||
"summary": "Namespace quota is fully used."
|
||||
},
|
||||
@ -283,7 +283,7 @@
|
||||
{
|
||||
"alert": "KubeQuotaExceeded",
|
||||
"annotations": {
|
||||
"description": "Namespace {{ $labels.namespace }} is using {{ $value | humanizePercentage }} of its {{ $labels.resource }} quota on cluster {{ $labels.cluster }}.",
|
||||
"description": "Namespace {{ $labels.namespace }} is using {{ $value | humanizePercentage }} of its {{ $labels.resource }} quota.",
|
||||
"runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubequotaexceeded",
|
||||
"summary": "Namespace quota has exceeded the limits."
|
||||
},
|
||||
@ -296,7 +296,7 @@
|
||||
{
|
||||
"alert": "CPUThrottlingHigh",
|
||||
"annotations": {
|
||||
"description": "{{ $value | humanizePercentage }} throttling of CPU in namespace {{ $labels.namespace }} for container {{ $labels.container }} in pod {{ $labels.pod }} on cluster {{ $labels.cluster }}.",
|
||||
"description": "{{ $value | humanizePercentage }} throttling of CPU in namespace {{ $labels.namespace }} for container {{ $labels.container }} in pod {{ $labels.pod }}.",
|
||||
"runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/kubernetes/cputhrottlinghigh",
|
||||
"summary": "Processes experience elevated CPU throttling."
|
||||
},
|
||||
@ -396,7 +396,7 @@
|
||||
{
|
||||
"alert": "KubeVersionMismatch",
|
||||
"annotations": {
|
||||
"description": "There are {{ $value }} different semantic versions of Kubernetes components running on cluster {{ $labels.cluster }}.",
|
||||
"description": "There are {{ $value }} different semantic versions of Kubernetes components running.",
|
||||
"runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeversionmismatch",
|
||||
"summary": "Different semantic versions of Kubernetes components running."
|
||||
},
|
||||
@ -409,7 +409,7 @@
|
||||
{
|
||||
"alert": "KubeClientErrors",
|
||||
"annotations": {
|
||||
"description": "Kubernetes API server client '{{ $labels.job }}/{{ $labels.instance }}' is experiencing {{ $value | humanizePercentage }} errors on cluster {{ $labels.cluster }}.",
|
||||
"description": "Kubernetes API server client '{{ $labels.job }}/{{ $labels.instance }}' is experiencing {{ $value | humanizePercentage }} errors.'",
|
||||
"runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeclienterrors",
|
||||
"summary": "Kubernetes API server client is experiencing errors."
|
||||
},
|
||||
@ -427,7 +427,7 @@
|
||||
{
|
||||
"alert": "KubeAPIErrorBudgetBurn",
|
||||
"annotations": {
|
||||
"description": "The API server is burning too much error budget on cluster {{ $labels.cluster }}.",
|
||||
"description": "The API server is burning too much error budget.",
|
||||
"runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeapierrorbudgetburn",
|
||||
"summary": "The API server is burning too much error budget."
|
||||
},
|
||||
@ -442,7 +442,7 @@
|
||||
{
|
||||
"alert": "KubeAPIErrorBudgetBurn",
|
||||
"annotations": {
|
||||
"description": "The API server is burning too much error budget on cluster {{ $labels.cluster }}.",
|
||||
"description": "The API server is burning too much error budget.",
|
||||
"runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeapierrorbudgetburn",
|
||||
"summary": "The API server is burning too much error budget."
|
||||
},
|
||||
@ -457,7 +457,7 @@
|
||||
{
|
||||
"alert": "KubeAPIErrorBudgetBurn",
|
||||
"annotations": {
|
||||
"description": "The API server is burning too much error budget on cluster {{ $labels.cluster }}.",
|
||||
"description": "The API server is burning too much error budget.",
|
||||
"runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeapierrorbudgetburn",
|
||||
"summary": "The API server is burning too much error budget."
|
||||
},
|
||||
@ -472,7 +472,7 @@
|
||||
{
|
||||
"alert": "KubeAPIErrorBudgetBurn",
|
||||
"annotations": {
|
||||
"description": "The API server is burning too much error budget on cluster {{ $labels.cluster }}.",
|
||||
"description": "The API server is burning too much error budget.",
|
||||
"runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeapierrorbudgetburn",
|
||||
"summary": "The API server is burning too much error budget."
|
||||
},
|
||||
@ -518,12 +518,11 @@
|
||||
{
|
||||
"alert": "KubeAggregatedAPIErrors",
|
||||
"annotations": {
|
||||
"description": "Kubernetes aggregated API {{ $labels.instance }}/{{ $labels.name }} has reported {{ $labels.reason }} errors on cluster {{ $labels.cluster }}.",
|
||||
"description": "Kubernetes aggregated API {{ $labels.name }}/{{ $labels.namespace }} has reported errors. It has appeared unavailable {{ $value | humanize }} times averaged over the past 10m.",
|
||||
"runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeaggregatedapierrors",
|
||||
"summary": "Kubernetes aggregated API has reported errors."
|
||||
},
|
||||
"expr": "sum by(cluster, instance, name, reason)(increase(aggregator_unavailable_apiservice_total{job=\"apiserver\"}[1m])) > 0\n",
|
||||
"for": "10m",
|
||||
"expr": "sum by(name, namespace, cluster)(increase(aggregator_unavailable_apiservice_total{job=\"apiserver\"}[10m])) > 4\n",
|
||||
"labels": {
|
||||
"severity": "warning"
|
||||
}
|
||||
@ -531,7 +530,7 @@
|
||||
{
|
||||
"alert": "KubeAggregatedAPIDown",
|
||||
"annotations": {
|
||||
"description": "Kubernetes aggregated API {{ $labels.name }}/{{ $labels.namespace }} has been only {{ $value | humanize }}% available over the last 10m on cluster {{ $labels.cluster }}.",
|
||||
"description": "Kubernetes aggregated API {{ $labels.name }}/{{ $labels.namespace }} has been only {{ $value | humanize }}% available over the last 10m.",
|
||||
"runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeaggregatedapidown",
|
||||
"summary": "Kubernetes aggregated API is down."
|
||||
},
|
||||
@ -557,7 +556,7 @@
|
||||
{
|
||||
"alert": "KubeAPITerminatedRequests",
|
||||
"annotations": {
|
||||
"description": "The kubernetes apiserver has terminated {{ $value | humanizePercentage }} of its incoming requests on cluster {{ $labels.cluster }}.",
|
||||
"description": "The kubernetes apiserver has terminated {{ $value | humanizePercentage }} of its incoming requests.",
|
||||
"runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeapiterminatedrequests",
|
||||
"summary": "The kubernetes apiserver has terminated {{ $value | humanizePercentage }} of its incoming requests."
|
||||
},
|
||||
@ -575,11 +574,11 @@
|
||||
{
|
||||
"alert": "KubeNodeNotReady",
|
||||
"annotations": {
|
||||
"description": "{{ $labels.node }} has been unready for more than 15 minutes on cluster {{ $labels.cluster }}.",
|
||||
"description": "{{ $labels.node }} has been unready for more than 15 minutes.",
|
||||
"runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubenodenotready",
|
||||
"summary": "Node is not ready."
|
||||
},
|
||||
"expr": "kube_node_status_condition{job=\"kube-state-metrics\",condition=\"Ready\",status=\"true\"} == 0\nand on (cluster, node)\nkube_node_spec_unschedulable{job=\"kube-state-metrics\"} == 0\n",
|
||||
"expr": "kube_node_status_condition{job=\"kube-state-metrics\",condition=\"Ready\",status=\"true\"} == 0\n",
|
||||
"for": "15m",
|
||||
"labels": {
|
||||
"severity": "warning"
|
||||
@ -588,7 +587,7 @@
|
||||
{
|
||||
"alert": "KubeNodeUnreachable",
|
||||
"annotations": {
|
||||
"description": "{{ $labels.node }} is unreachable and some workloads may be rescheduled on cluster {{ $labels.cluster }}.",
|
||||
"description": "{{ $labels.node }} is unreachable and some workloads may be rescheduled.",
|
||||
"runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubenodeunreachable",
|
||||
"summary": "Node is unreachable."
|
||||
},
|
||||
@ -601,11 +600,11 @@
|
||||
{
|
||||
"alert": "KubeletTooManyPods",
|
||||
"annotations": {
|
||||
"description": "Kubelet '{{ $labels.node }}' is running at {{ $value | humanizePercentage }} of its Pod capacity on cluster {{ $labels.cluster }}.",
|
||||
"description": "Kubelet '{{ $labels.node }}' is running at {{ $value | humanizePercentage }} of its Pod capacity.",
|
||||
"runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubelettoomanypods",
|
||||
"summary": "Kubelet is running at capacity."
|
||||
},
|
||||
"expr": "(\n max by (cluster, instance) (\n kubelet_running_pods{job=\"kubelet\", metrics_path=\"/metrics\"} > 1\n )\n * on (cluster, instance) group_left(node)\n max by (cluster, instance, node) (\n kubelet_node_name{job=\"kubelet\", metrics_path=\"/metrics\"}\n )\n)\n/ on (cluster, node) group_left()\nmax by (cluster, node) (\n kube_node_status_capacity{job=\"kube-state-metrics\", resource=\"pods\"} != 1\n) > 0.95\n",
|
||||
"expr": "count by(cluster, node) (\n (kube_pod_status_phase{job=\"kube-state-metrics\",phase=\"Running\"} == 1) * on(instance,pod,namespace,cluster) group_left(node) topk by(instance,pod,namespace,cluster) (1, kube_pod_info{job=\"kube-state-metrics\"})\n)\n/\nmax by(cluster, node) (\n kube_node_status_capacity{job=\"kube-state-metrics\",resource=\"pods\"} != 1\n) > 0.95\n",
|
||||
"for": "15m",
|
||||
"labels": {
|
||||
"severity": "info"
|
||||
@ -614,11 +613,11 @@
|
||||
{
|
||||
"alert": "KubeNodeReadinessFlapping",
|
||||
"annotations": {
|
||||
"description": "The readiness status of node {{ $labels.node }} has changed {{ $value }} times in the last 15 minutes on cluster {{ $labels.cluster }}.",
|
||||
"description": "The readiness status of node {{ $labels.node }} has changed {{ $value }} times in the last 15 minutes.",
|
||||
"runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubenodereadinessflapping",
|
||||
"summary": "Node readiness status is flapping."
|
||||
},
|
||||
"expr": "sum(changes(kube_node_status_condition{job=\"kube-state-metrics\",status=\"true\",condition=\"Ready\"}[15m])) by (cluster, node) > 2\nand on (cluster, node)\nkube_node_spec_unschedulable{job=\"kube-state-metrics\"} == 0\n",
|
||||
"expr": "sum(changes(kube_node_status_condition{job=\"kube-state-metrics\",status=\"true\",condition=\"Ready\"}[15m])) by (cluster, node) > 2\n",
|
||||
"for": "15m",
|
||||
"labels": {
|
||||
"severity": "warning"
|
||||
@ -627,7 +626,7 @@
|
||||
{
|
||||
"alert": "KubeletPlegDurationHigh",
|
||||
"annotations": {
|
||||
"description": "The Kubelet Pod Lifecycle Event Generator has a 99th percentile duration of {{ $value }} seconds on node {{ $labels.node }} on cluster {{ $labels.cluster }}.",
|
||||
"description": "The Kubelet Pod Lifecycle Event Generator has a 99th percentile duration of {{ $value }} seconds on node {{ $labels.node }}.",
|
||||
"runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletplegdurationhigh",
|
||||
"summary": "Kubelet Pod Lifecycle Event Generator is taking too long to relist."
|
||||
},
|
||||
@ -640,7 +639,7 @@
|
||||
{
|
||||
"alert": "KubeletPodStartUpLatencyHigh",
|
||||
"annotations": {
|
||||
"description": "Kubelet Pod startup 99th percentile latency is {{ $value }} seconds on node {{ $labels.node }} on cluster {{ $labels.cluster }}.",
|
||||
"description": "Kubelet Pod startup 99th percentile latency is {{ $value }} seconds on node {{ $labels.node }}.",
|
||||
"runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletpodstartuplatencyhigh",
|
||||
"summary": "Kubelet Pod startup latency is too high."
|
||||
},
|
||||
@ -653,7 +652,7 @@
|
||||
{
|
||||
"alert": "KubeletClientCertificateExpiration",
|
||||
"annotations": {
|
||||
"description": "Client certificate for Kubelet on node {{ $labels.node }} expires in {{ $value | humanizeDuration }} on cluster {{ $labels.cluster }}.",
|
||||
"description": "Client certificate for Kubelet on node {{ $labels.node }} expires in {{ $value | humanizeDuration }}.",
|
||||
"runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletclientcertificateexpiration",
|
||||
"summary": "Kubelet client certificate is about to expire."
|
||||
},
|
||||
@ -665,7 +664,7 @@
|
||||
{
|
||||
"alert": "KubeletClientCertificateExpiration",
|
||||
"annotations": {
|
||||
"description": "Client certificate for Kubelet on node {{ $labels.node }} expires in {{ $value | humanizeDuration }} on cluster {{ $labels.cluster }}.",
|
||||
"description": "Client certificate for Kubelet on node {{ $labels.node }} expires in {{ $value | humanizeDuration }}.",
|
||||
"runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletclientcertificateexpiration",
|
||||
"summary": "Kubelet client certificate is about to expire."
|
||||
},
|
||||
@ -677,7 +676,7 @@
|
||||
{
|
||||
"alert": "KubeletServerCertificateExpiration",
|
||||
"annotations": {
|
||||
"description": "Server certificate for Kubelet on node {{ $labels.node }} expires in {{ $value | humanizeDuration }} on cluster {{ $labels.cluster }}.",
|
||||
"description": "Server certificate for Kubelet on node {{ $labels.node }} expires in {{ $value | humanizeDuration }}.",
|
||||
"runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletservercertificateexpiration",
|
||||
"summary": "Kubelet server certificate is about to expire."
|
||||
},
|
||||
@ -689,7 +688,7 @@
|
||||
{
|
||||
"alert": "KubeletServerCertificateExpiration",
|
||||
"annotations": {
|
||||
"description": "Server certificate for Kubelet on node {{ $labels.node }} expires in {{ $value | humanizeDuration }} on cluster {{ $labels.cluster }}.",
|
||||
"description": "Server certificate for Kubelet on node {{ $labels.node }} expires in {{ $value | humanizeDuration }}.",
|
||||
"runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletservercertificateexpiration",
|
||||
"summary": "Kubelet server certificate is about to expire."
|
||||
},
|
||||
@ -701,7 +700,7 @@
|
||||
{
|
||||
"alert": "KubeletClientCertificateRenewalErrors",
|
||||
"annotations": {
|
||||
"description": "Kubelet on node {{ $labels.node }} has failed to renew its client certificate ({{ $value | humanize }} errors in the last 5 minutes) on cluster {{ $labels.cluster }}.",
|
||||
"description": "Kubelet on node {{ $labels.node }} has failed to renew its client certificate ({{ $value | humanize }} errors in the last 5 minutes).",
|
||||
"runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletclientcertificaterenewalerrors",
|
||||
"summary": "Kubelet has failed to renew its client certificate."
|
||||
},
|
||||
@ -714,7 +713,7 @@
|
||||
{
|
||||
"alert": "KubeletServerCertificateRenewalErrors",
|
||||
"annotations": {
|
||||
"description": "Kubelet on node {{ $labels.node }} has failed to renew its server certificate ({{ $value | humanize }} errors in the last 5 minutes) on cluster {{ $labels.cluster }}.",
|
||||
"description": "Kubelet on node {{ $labels.node }} has failed to renew its server certificate ({{ $value | humanize }} errors in the last 5 minutes).",
|
||||
"runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletservercertificaterenewalerrors",
|
||||
"summary": "Kubelet has failed to renew its server certificate."
|
||||
},
|
||||
@ -810,25 +809,25 @@
|
||||
"record": "cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase1h"
|
||||
},
|
||||
{
|
||||
"expr": "sum by (cluster, verb, scope) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{le=\"+Inf\"})\n",
|
||||
"expr": "sum by (cluster, verb, scope) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{le=\"+Inf\"} * 24 * 30)\n",
|
||||
"record": "cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase30d"
|
||||
},
|
||||
{
|
||||
"expr": "1 - (\n (\n # write too slow\n sum by (cluster) (cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase30d{verb=~\"POST|PUT|PATCH|DELETE\"})\n -\n sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~\"POST|PUT|PATCH|DELETE\",le=~\"1(\\\\.0)?\"})\n ) +\n (\n # read too slow\n sum by (cluster) (cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase30d{verb=~\"LIST|GET\"})\n -\n (\n (\n sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=~\"resource|\",le=~\"1(\\\\.0)?\"})\n or\n vector(0)\n )\n +\n sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=\"namespace\",le=~\"5(\\\\.0)?\"})\n +\n sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=\"cluster\",le=~\"30(\\\\.0)?\"})\n )\n ) +\n # errors\n sum by (cluster) (code:apiserver_request_total:increase30d{code=~\"5..\"} or vector(0))\n)\n/\nsum by (cluster) (code:apiserver_request_total:increase30d)\n",
|
||||
"expr": "1 - (\n (\n # write too slow\n sum by (cluster) (cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase30d{verb=~\"POST|PUT|PATCH|DELETE\"})\n -\n sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~\"POST|PUT|PATCH|DELETE\",le=\"1\"})\n ) +\n (\n # read too slow\n sum by (cluster) (cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase30d{verb=~\"LIST|GET\"})\n -\n (\n (\n sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=~\"resource|\",le=\"1\"})\n or\n vector(0)\n )\n +\n sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=\"namespace\",le=\"5\"})\n +\n sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=\"cluster\",le=\"30\"})\n )\n ) +\n # errors\n sum by (cluster) (code:apiserver_request_total:increase30d{code=~\"5..\"} or vector(0))\n)\n/\nsum by (cluster) (code:apiserver_request_total:increase30d)\n",
|
||||
"labels": {
|
||||
"verb": "all"
|
||||
},
|
||||
"record": "apiserver_request:availability30d"
|
||||
},
|
||||
{
|
||||
"expr": "1 - (\n sum by (cluster) (cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase30d{verb=~\"LIST|GET\"})\n -\n (\n # too slow\n (\n sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=~\"resource|\",le=~\"1(\\\\.0)?\"})\n or\n vector(0)\n )\n +\n sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=\"namespace\",le=~\"5(\\\\.0)?\"})\n +\n sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=\"cluster\",le=~\"30(\\\\.0)?\"})\n )\n +\n # errors\n sum by (cluster) (code:apiserver_request_total:increase30d{verb=\"read\",code=~\"5..\"} or vector(0))\n)\n/\nsum by (cluster) (code:apiserver_request_total:increase30d{verb=\"read\"})\n",
|
||||
"expr": "1 - (\n sum by (cluster) (cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase30d{verb=~\"LIST|GET\"})\n -\n (\n # too slow\n (\n sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=~\"resource|\",le=\"1\"})\n or\n vector(0)\n )\n +\n sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=\"namespace\",le=\"5\"})\n +\n sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=\"cluster\",le=\"30\"})\n )\n +\n # errors\n sum by (cluster) (code:apiserver_request_total:increase30d{verb=\"read\",code=~\"5..\"} or vector(0))\n)\n/\nsum by (cluster) (code:apiserver_request_total:increase30d{verb=\"read\"})\n",
|
||||
"labels": {
|
||||
"verb": "read"
|
||||
},
|
||||
"record": "apiserver_request:availability30d"
|
||||
},
|
||||
{
|
||||
"expr": "1 - (\n (\n # too slow\n sum by (cluster) (cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase30d{verb=~\"POST|PUT|PATCH|DELETE\"})\n -\n sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~\"POST|PUT|PATCH|DELETE\",le=~\"1(\\\\.0)?\"})\n )\n +\n # errors\n sum by (cluster) (code:apiserver_request_total:increase30d{verb=\"write\",code=~\"5..\"} or vector(0))\n)\n/\nsum by (cluster) (code:apiserver_request_total:increase30d{verb=\"write\"})\n",
|
||||
"expr": "1 - (\n (\n # too slow\n sum by (cluster) (cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase30d{verb=~\"POST|PUT|PATCH|DELETE\"})\n -\n sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~\"POST|PUT|PATCH|DELETE\",le=\"1\"})\n )\n +\n # errors\n sum by (cluster) (code:apiserver_request_total:increase30d{verb=\"write\",code=~\"5..\"} or vector(0))\n)\n/\nsum by (cluster) (code:apiserver_request_total:increase30d{verb=\"write\"})\n",
|
||||
"labels": {
|
||||
"verb": "write"
|
||||
},
|
||||
@ -870,98 +869,98 @@
|
||||
"name": "kube-apiserver-burnrate.rules",
|
||||
"rules": [
|
||||
{
|
||||
"expr": "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\"}[1d]))\n -\n (\n (\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=~\"resource|\",le=~\"1(\\\\.0)?\"}[1d]))\n or\n vector(0)\n )\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"namespace\",le=~\"5(\\\\.0)?\"}[1d]))\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"cluster\",le=~\"30(\\\\.0)?\"}[1d]))\n )\n )\n +\n # errors\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[1d]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[1d]))\n",
|
||||
"expr": "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\"}[1d]))\n -\n (\n (\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=~\"resource|\",le=\"1\"}[1d]))\n or\n vector(0)\n )\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"namespace\",le=\"5\"}[1d]))\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"cluster\",le=\"30\"}[1d]))\n )\n )\n +\n # errors\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[1d]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[1d]))\n",
|
||||
"labels": {
|
||||
"verb": "read"
|
||||
},
|
||||
"record": "apiserver_request:burnrate1d"
|
||||
},
|
||||
{
|
||||
"expr": "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\"}[1h]))\n -\n (\n (\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=~\"resource|\",le=~\"1(\\\\.0)?\"}[1h]))\n or\n vector(0)\n )\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"namespace\",le=~\"5(\\\\.0)?\"}[1h]))\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"cluster\",le=~\"30(\\\\.0)?\"}[1h]))\n )\n )\n +\n # errors\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[1h]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[1h]))\n",
|
||||
"expr": "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\"}[1h]))\n -\n (\n (\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=~\"resource|\",le=\"1\"}[1h]))\n or\n vector(0)\n )\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"namespace\",le=\"5\"}[1h]))\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"cluster\",le=\"30\"}[1h]))\n )\n )\n +\n # errors\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[1h]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[1h]))\n",
|
||||
"labels": {
|
||||
"verb": "read"
|
||||
},
|
||||
"record": "apiserver_request:burnrate1h"
|
||||
},
|
||||
{
|
||||
"expr": "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\"}[2h]))\n -\n (\n (\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=~\"resource|\",le=~\"1(\\\\.0)?\"}[2h]))\n or\n vector(0)\n )\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"namespace\",le=~\"5(\\\\.0)?\"}[2h]))\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"cluster\",le=~\"30(\\\\.0)?\"}[2h]))\n )\n )\n +\n # errors\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[2h]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[2h]))\n",
|
||||
"expr": "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\"}[2h]))\n -\n (\n (\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=~\"resource|\",le=\"1\"}[2h]))\n or\n vector(0)\n )\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"namespace\",le=\"5\"}[2h]))\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"cluster\",le=\"30\"}[2h]))\n )\n )\n +\n # errors\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[2h]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[2h]))\n",
|
||||
"labels": {
|
||||
"verb": "read"
|
||||
},
|
||||
"record": "apiserver_request:burnrate2h"
|
||||
},
|
||||
{
|
||||
"expr": "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\"}[30m]))\n -\n (\n (\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=~\"resource|\",le=~\"1(\\\\.0)?\"}[30m]))\n or\n vector(0)\n )\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"namespace\",le=~\"5(\\\\.0)?\"}[30m]))\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"cluster\",le=~\"30(\\\\.0)?\"}[30m]))\n )\n )\n +\n # errors\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[30m]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[30m]))\n",
|
||||
"expr": "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\"}[30m]))\n -\n (\n (\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=~\"resource|\",le=\"1\"}[30m]))\n or\n vector(0)\n )\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"namespace\",le=\"5\"}[30m]))\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"cluster\",le=\"30\"}[30m]))\n )\n )\n +\n # errors\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[30m]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[30m]))\n",
|
||||
"labels": {
|
||||
"verb": "read"
|
||||
},
|
||||
"record": "apiserver_request:burnrate30m"
|
||||
},
|
||||
{
|
||||
"expr": "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\"}[3d]))\n -\n (\n (\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=~\"resource|\",le=~\"1(\\\\.0)?\"}[3d]))\n or\n vector(0)\n )\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"namespace\",le=~\"5(\\\\.0)?\"}[3d]))\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"cluster\",le=~\"30(\\\\.0)?\"}[3d]))\n )\n )\n +\n # errors\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[3d]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[3d]))\n",
|
||||
"expr": "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\"}[3d]))\n -\n (\n (\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=~\"resource|\",le=\"1\"}[3d]))\n or\n vector(0)\n )\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"namespace\",le=\"5\"}[3d]))\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"cluster\",le=\"30\"}[3d]))\n )\n )\n +\n # errors\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[3d]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[3d]))\n",
|
||||
"labels": {
|
||||
"verb": "read"
|
||||
},
|
||||
"record": "apiserver_request:burnrate3d"
|
||||
},
|
||||
{
|
||||
"expr": "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\"}[5m]))\n -\n (\n (\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=~\"resource|\",le=~\"1(\\\\.0)?\"}[5m]))\n or\n vector(0)\n )\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"namespace\",le=~\"5(\\\\.0)?\"}[5m]))\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"cluster\",le=~\"30(\\\\.0)?\"}[5m]))\n )\n )\n +\n # errors\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[5m]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[5m]))\n",
|
||||
"expr": "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\"}[5m]))\n -\n (\n (\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=~\"resource|\",le=\"1\"}[5m]))\n or\n vector(0)\n )\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"namespace\",le=\"5\"}[5m]))\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"cluster\",le=\"30\"}[5m]))\n )\n )\n +\n # errors\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[5m]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[5m]))\n",
|
||||
"labels": {
|
||||
"verb": "read"
|
||||
},
|
||||
"record": "apiserver_request:burnrate5m"
|
||||
},
|
||||
{
|
||||
"expr": "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\"}[6h]))\n -\n (\n (\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=~\"resource|\",le=~\"1(\\\\.0)?\"}[6h]))\n or\n vector(0)\n )\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"namespace\",le=~\"5(\\\\.0)?\"}[6h]))\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"cluster\",le=~\"30(\\\\.0)?\"}[6h]))\n )\n )\n +\n # errors\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[6h]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[6h]))\n",
|
||||
"expr": "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\"}[6h]))\n -\n (\n (\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=~\"resource|\",le=\"1\"}[6h]))\n or\n vector(0)\n )\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"namespace\",le=\"5\"}[6h]))\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"cluster\",le=\"30\"}[6h]))\n )\n )\n +\n # errors\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[6h]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[6h]))\n",
|
||||
"labels": {
|
||||
"verb": "read"
|
||||
},
|
||||
"record": "apiserver_request:burnrate6h"
|
||||
},
|
||||
{
|
||||
"expr": "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\"}[1d]))\n -\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\",le=~\"1(\\\\.0)?\"}[1d]))\n )\n +\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[1d]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[1d]))\n",
|
||||
"expr": "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\"}[1d]))\n -\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\",le=\"1\"}[1d]))\n )\n +\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[1d]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[1d]))\n",
|
||||
"labels": {
|
||||
"verb": "write"
|
||||
},
|
||||
"record": "apiserver_request:burnrate1d"
|
||||
},
|
||||
{
|
||||
"expr": "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\"}[1h]))\n -\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\",le=~\"1(\\\\.0)?\"}[1h]))\n )\n +\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[1h]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[1h]))\n",
|
||||
"expr": "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\"}[1h]))\n -\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\",le=\"1\"}[1h]))\n )\n +\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[1h]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[1h]))\n",
|
||||
"labels": {
|
||||
"verb": "write"
|
||||
},
|
||||
"record": "apiserver_request:burnrate1h"
|
||||
},
|
||||
{
|
||||
"expr": "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\"}[2h]))\n -\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\",le=~\"1(\\\\.0)?\"}[2h]))\n )\n +\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[2h]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[2h]))\n",
|
||||
"expr": "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\"}[2h]))\n -\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\",le=\"1\"}[2h]))\n )\n +\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[2h]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[2h]))\n",
|
||||
"labels": {
|
||||
"verb": "write"
|
||||
},
|
||||
"record": "apiserver_request:burnrate2h"
|
||||
},
|
||||
{
|
||||
"expr": "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\"}[30m]))\n -\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\",le=~\"1(\\\\.0)?\"}[30m]))\n )\n +\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[30m]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[30m]))\n",
|
||||
"expr": "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\"}[30m]))\n -\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\",le=\"1\"}[30m]))\n )\n +\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[30m]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[30m]))\n",
|
||||
"labels": {
|
||||
"verb": "write"
|
||||
},
|
||||
"record": "apiserver_request:burnrate30m"
|
||||
},
|
||||
{
|
||||
"expr": "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\"}[3d]))\n -\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\",le=~\"1(\\\\.0)?\"}[3d]))\n )\n +\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[3d]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[3d]))\n",
|
||||
"expr": "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\"}[3d]))\n -\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\",le=\"1\"}[3d]))\n )\n +\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[3d]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[3d]))\n",
|
||||
"labels": {
|
||||
"verb": "write"
|
||||
},
|
||||
"record": "apiserver_request:burnrate3d"
|
||||
},
|
||||
{
|
||||
"expr": "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\"}[5m]))\n -\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\",le=~\"1(\\\\.0)?\"}[5m]))\n )\n +\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[5m]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[5m]))\n",
|
||||
"expr": "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\"}[5m]))\n -\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\",le=\"1\"}[5m]))\n )\n +\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[5m]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[5m]))\n",
|
||||
"labels": {
|
||||
"verb": "write"
|
||||
},
|
||||
"record": "apiserver_request:burnrate5m"
|
||||
},
|
||||
{
|
||||
"expr": "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\"}[6h]))\n -\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\",le=~\"1(\\\\.0)?\"}[6h]))\n )\n +\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[6h]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[6h]))\n",
|
||||
"expr": "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\"}[6h]))\n -\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\",le=\"1\"}[6h]))\n )\n +\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[6h]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[6h]))\n",
|
||||
"labels": {
|
||||
"verb": "write"
|
||||
},
|
||||
@ -1238,144 +1237,6 @@
|
||||
"record": "node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "windows.node.rules",
|
||||
"rules": [
|
||||
{
|
||||
"expr": "count by (cluster) (\n windows_system_system_up_time{job=\"kubernetes-windows-exporter\"}\n)\n",
|
||||
"record": "node:windows_node:sum"
|
||||
},
|
||||
{
|
||||
"expr": "count by (cluster, instance) (sum by (cluster, instance, core) (\n windows_cpu_time_total{job=\"kubernetes-windows-exporter\"}\n))\n",
|
||||
"record": "node:windows_node_num_cpu:sum"
|
||||
},
|
||||
{
|
||||
"expr": "1 - avg by (cluster) (rate(windows_cpu_time_total{job=\"kubernetes-windows-exporter\",mode=\"idle\"}[1m]))\n",
|
||||
"record": ":windows_node_cpu_utilisation:avg1m"
|
||||
},
|
||||
{
|
||||
"expr": "1 - avg by (cluster, instance) (\n rate(windows_cpu_time_total{job=\"kubernetes-windows-exporter\",mode=\"idle\"}[1m])\n)\n",
|
||||
"record": "node:windows_node_cpu_utilisation:avg1m"
|
||||
},
|
||||
{
|
||||
"expr": "1 -\nsum by (cluster) (windows_memory_available_bytes{job=\"kubernetes-windows-exporter\"})\n/\nsum by (cluster) (windows_os_visible_memory_bytes{job=\"kubernetes-windows-exporter\"})\n",
|
||||
"record": ":windows_node_memory_utilisation:"
|
||||
},
|
||||
{
|
||||
"expr": "sum by (cluster) (windows_memory_available_bytes{job=\"kubernetes-windows-exporter\"} + windows_memory_cache_bytes{job=\"kubernetes-windows-exporter\"})\n",
|
||||
"record": ":windows_node_memory_MemFreeCached_bytes:sum"
|
||||
},
|
||||
{
|
||||
"expr": "(windows_memory_cache_bytes{job=\"kubernetes-windows-exporter\"} + windows_memory_modified_page_list_bytes{job=\"kubernetes-windows-exporter\"} + windows_memory_standby_cache_core_bytes{job=\"kubernetes-windows-exporter\"} + windows_memory_standby_cache_normal_priority_bytes{job=\"kubernetes-windows-exporter\"} + windows_memory_standby_cache_reserve_bytes{job=\"kubernetes-windows-exporter\"})\n",
|
||||
"record": "node:windows_node_memory_totalCached_bytes:sum"
|
||||
},
|
||||
{
|
||||
"expr": "sum by (cluster) (windows_os_visible_memory_bytes{job=\"kubernetes-windows-exporter\"})\n",
|
||||
"record": ":windows_node_memory_MemTotal_bytes:sum"
|
||||
},
|
||||
{
|
||||
"expr": "sum by (cluster, instance) (\n (windows_memory_available_bytes{job=\"kubernetes-windows-exporter\"})\n)\n",
|
||||
"record": "node:windows_node_memory_bytes_available:sum"
|
||||
},
|
||||
{
|
||||
"expr": "sum by (cluster, instance) (\n windows_os_visible_memory_bytes{job=\"kubernetes-windows-exporter\"}\n)\n",
|
||||
"record": "node:windows_node_memory_bytes_total:sum"
|
||||
},
|
||||
{
|
||||
"expr": "(node:windows_node_memory_bytes_total:sum - node:windows_node_memory_bytes_available:sum)\n/\nscalar(sum(node:windows_node_memory_bytes_total:sum))\n",
|
||||
"record": "node:windows_node_memory_utilisation:ratio"
|
||||
},
|
||||
{
|
||||
"expr": "1 - (node:windows_node_memory_bytes_available:sum / node:windows_node_memory_bytes_total:sum)\n",
|
||||
"record": "node:windows_node_memory_utilisation:"
|
||||
},
|
||||
{
|
||||
"expr": "irate(windows_memory_swap_page_operations_total{job=\"kubernetes-windows-exporter\"}[5m])\n",
|
||||
"record": "node:windows_node_memory_swap_io_pages:irate"
|
||||
},
|
||||
{
|
||||
"expr": "avg by (cluster) (irate(windows_logical_disk_read_seconds_total{job=\"kubernetes-windows-exporter\"}[1m]) +\n irate(windows_logical_disk_write_seconds_total{job=\"kubernetes-windows-exporter\"}[1m])\n )\n",
|
||||
"record": ":windows_node_disk_utilisation:avg_irate"
|
||||
},
|
||||
{
|
||||
"expr": "avg by (cluster, instance) (\n (irate(windows_logical_disk_read_seconds_total{job=\"kubernetes-windows-exporter\"}[1m]) +\n irate(windows_logical_disk_write_seconds_total{job=\"kubernetes-windows-exporter\"}[1m]))\n)\n",
|
||||
"record": "node:windows_node_disk_utilisation:avg_irate"
|
||||
},
|
||||
{
|
||||
"expr": "max by (cluster,instance,volume)(\n (windows_logical_disk_size_bytes{job=\"kubernetes-windows-exporter\"}\n- windows_logical_disk_free_bytes{job=\"kubernetes-windows-exporter\"})\n/ windows_logical_disk_size_bytes{job=\"kubernetes-windows-exporter\"}\n)\n",
|
||||
"record": "node:windows_node_filesystem_usage:"
|
||||
},
|
||||
{
|
||||
"expr": "max by (cluster, instance, volume) (windows_logical_disk_free_bytes{job=\"kubernetes-windows-exporter\"} / windows_logical_disk_size_bytes{job=\"kubernetes-windows-exporter\"})\n",
|
||||
"record": "node:windows_node_filesystem_avail:"
|
||||
},
|
||||
{
|
||||
"expr": "sum by (cluster) (irate(windows_net_bytes_total{job=\"kubernetes-windows-exporter\"}[1m]))\n",
|
||||
"record": ":windows_node_net_utilisation:sum_irate"
|
||||
},
|
||||
{
|
||||
"expr": "sum by (cluster, instance) (\n (irate(windows_net_bytes_total{job=\"kubernetes-windows-exporter\"}[1m]))\n)\n",
|
||||
"record": "node:windows_node_net_utilisation:sum_irate"
|
||||
},
|
||||
{
|
||||
"expr": "sum by (cluster) (irate(windows_net_packets_received_discarded_total{job=\"kubernetes-windows-exporter\"}[1m])) +\nsum by (cluster) (irate(windows_net_packets_outbound_discarded_total{job=\"kubernetes-windows-exporter\"}[1m]))\n",
|
||||
"record": ":windows_node_net_saturation:sum_irate"
|
||||
},
|
||||
{
|
||||
"expr": "sum by (cluster, instance) (\n (irate(windows_net_packets_received_discarded_total{job=\"kubernetes-windows-exporter\"}[1m]) +\n irate(windows_net_packets_outbound_discarded_total{job=\"kubernetes-windows-exporter\"}[1m]))\n)\n",
|
||||
"record": "node:windows_node_net_saturation:sum_irate"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "windows.pod.rules",
|
||||
"rules": [
|
||||
{
|
||||
"expr": "windows_container_available{job=\"kubernetes-windows-exporter\", container_id != \"\"} * on(container_id, cluster) group_left(container, pod, namespace) max(kube_pod_container_info{job=\"kube-state-metrics\", container_id != \"\"}) by(container, container_id, pod, namespace, cluster)\n",
|
||||
"record": "windows_pod_container_available"
|
||||
},
|
||||
{
|
||||
"expr": "windows_container_cpu_usage_seconds_total{job=\"kubernetes-windows-exporter\", container_id != \"\"} * on(container_id, cluster) group_left(container, pod, namespace) max(kube_pod_container_info{job=\"kube-state-metrics\", container_id != \"\"}) by(container, container_id, pod, namespace, cluster)\n",
|
||||
"record": "windows_container_total_runtime"
|
||||
},
|
||||
{
|
||||
"expr": "windows_container_memory_usage_commit_bytes{job=\"kubernetes-windows-exporter\", container_id != \"\"} * on(container_id, cluster) group_left(container, pod, namespace) max(kube_pod_container_info{job=\"kube-state-metrics\", container_id != \"\"}) by(container, container_id, pod, namespace, cluster)\n",
|
||||
"record": "windows_container_memory_usage"
|
||||
},
|
||||
{
|
||||
"expr": "windows_container_memory_usage_private_working_set_bytes{job=\"kubernetes-windows-exporter\", container_id != \"\"} * on(container_id, cluster) group_left(container, pod, namespace) max(kube_pod_container_info{job=\"kube-state-metrics\", container_id != \"\"}) by(container, container_id, pod, namespace, cluster)\n",
|
||||
"record": "windows_container_private_working_set_usage"
|
||||
},
|
||||
{
|
||||
"expr": "windows_container_network_receive_bytes_total{job=\"kubernetes-windows-exporter\", container_id != \"\"} * on(container_id, cluster) group_left(container, pod, namespace) max(kube_pod_container_info{job=\"kube-state-metrics\", container_id != \"\"}) by(container, container_id, pod, namespace, cluster)\n",
|
||||
"record": "windows_container_network_received_bytes_total"
|
||||
},
|
||||
{
|
||||
"expr": "windows_container_network_transmit_bytes_total{job=\"kubernetes-windows-exporter\", container_id != \"\"} * on(container_id, cluster) group_left(container, pod, namespace) max(kube_pod_container_info{job=\"kube-state-metrics\", container_id != \"\"}) by(container, container_id, pod, namespace, cluster)\n",
|
||||
"record": "windows_container_network_transmitted_bytes_total"
|
||||
},
|
||||
{
|
||||
"expr": "max by (cluster, namespace, pod, container) (\n kube_pod_container_resource_requests{resource=\"memory\",job=\"kube-state-metrics\"}\n) * on(container,pod,namespace,cluster) (windows_pod_container_available)\n",
|
||||
"record": "kube_pod_windows_container_resource_memory_request"
|
||||
},
|
||||
{
|
||||
"expr": "kube_pod_container_resource_limits{resource=\"memory\",job=\"kube-state-metrics\"} * on(container,pod,namespace,cluster) (windows_pod_container_available)\n",
|
||||
"record": "kube_pod_windows_container_resource_memory_limit"
|
||||
},
|
||||
{
|
||||
"expr": "max by (cluster, namespace, pod, container) (\n kube_pod_container_resource_requests{resource=\"cpu\",job=\"kube-state-metrics\"}\n) * on(container,pod,namespace,cluster) (windows_pod_container_available)\n",
|
||||
"record": "kube_pod_windows_container_resource_cpu_cores_request"
|
||||
},
|
||||
{
|
||||
"expr": "kube_pod_container_resource_limits{resource=\"cpu\",job=\"kube-state-metrics\"} * on(container,pod,namespace,cluster) (windows_pod_container_available)\n",
|
||||
"record": "kube_pod_windows_container_resource_cpu_cores_limit"
|
||||
},
|
||||
{
|
||||
"expr": "sum by (cluster, namespace, pod, container) (\n rate(windows_container_total_runtime{}[5m])\n)\n",
|
||||
"record": "namespace_pod_container:windows_container_cpu_usage_seconds_total:sum_rate"
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
|
||||
@ -151,7 +151,7 @@
|
||||
{
|
||||
"alert": "NodeHighNumberConntrackEntriesUsed",
|
||||
"annotations": {
|
||||
"description": "{{ $labels.instance }} {{ $value | humanizePercentage }} of conntrack entries are used.",
|
||||
"description": "{{ $value | humanizePercentage }} of conntrack entries are used.",
|
||||
"runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/node/nodehighnumberconntrackentriesused",
|
||||
"summary": "Number of conntrack are getting close to the limit."
|
||||
},
|
||||
@ -256,7 +256,7 @@
|
||||
"runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/node/nodecpuhighusage",
|
||||
"summary": "High CPU usage."
|
||||
},
|
||||
"expr": "sum without(mode) (avg without (cpu) (rate(node_cpu_seconds_total{job=\"node-exporter\", mode!~\"idle|iowait\"}[2m]))) * 100 > 90\n",
|
||||
"expr": "sum without(mode) (avg without (cpu) (rate(node_cpu_seconds_total{job=\"node-exporter\", mode!=\"idle\"}[2m]))) * 100 > 90\n",
|
||||
"for": "15m",
|
||||
"labels": {
|
||||
"severity": "info"
|
||||
|
||||
@ -6,7 +6,7 @@
|
||||
"app.kubernetes.io/component": "controller",
|
||||
"app.kubernetes.io/name": "prometheus-operator",
|
||||
"app.kubernetes.io/part-of": "kube-prometheus",
|
||||
"app.kubernetes.io/version": "0.80.0",
|
||||
"app.kubernetes.io/version": "0.78.2",
|
||||
"prometheus": "k8s",
|
||||
"role": "alert-rules"
|
||||
},
|
||||
|
||||
@ -7,7 +7,7 @@
|
||||
"app.kubernetes.io/instance": "k8s",
|
||||
"app.kubernetes.io/name": "prometheus",
|
||||
"app.kubernetes.io/part-of": "kube-prometheus",
|
||||
"app.kubernetes.io/version": "3.1.0",
|
||||
"app.kubernetes.io/version": "3.0.1",
|
||||
"prometheus": "k8s",
|
||||
"role": "alert-rules"
|
||||
},
|
||||
|
||||
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
@ -14,9 +14,9 @@ spec:
|
||||
description: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": members are down ({{`{{`}} $value {{`}}`}}).'
|
||||
summary: etcd cluster members are down.
|
||||
expr: "max without (endpoint) (\n sum without (instance, pod) (up{job=~\".*etcd.*\"} == bool 0)\nor\n count without (To) (\n sum without (instance, pod) (rate(etcd_network_peer_sent_failures_total{job=~\".*etcd.*\"}[120s])) > 0.01\n )\n)\n> 0\n"
|
||||
for: 20m
|
||||
for: 10m
|
||||
labels:
|
||||
severity: warning
|
||||
severity: critical
|
||||
- alert: etcdInsufficientMembers
|
||||
annotations:
|
||||
description: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": insufficient members ({{`{{`}} $value {{`}}`}}).'
|
||||
|
||||
@ -11,7 +11,7 @@ spec:
|
||||
rules:
|
||||
- alert: KubePodCrashLooping
|
||||
annotations:
|
||||
description: 'Pod {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.pod {{`}}`}} ({{`{{`}} $labels.container {{`}}`}}) is in waiting state (reason: "CrashLoopBackOff") on cluster {{`{{`}} $labels.cluster {{`}}`}}.'
|
||||
description: 'Pod {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.pod {{`}}`}} ({{`{{`}} $labels.container {{`}}`}}) is in waiting state (reason: "CrashLoopBackOff").'
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubepodcrashlooping
|
||||
summary: Pod is crash looping.
|
||||
expr: 'max_over_time(kube_pod_container_status_waiting_reason{reason="CrashLoopBackOff", job="kube-state-metrics"}[5m]) >= 1
|
||||
@ -22,7 +22,7 @@ spec:
|
||||
severity: warning
|
||||
- alert: KubePodNotReady
|
||||
annotations:
|
||||
description: Pod {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.pod {{`}}`}} has been in a non-ready state for longer than 15 minutes on cluster {{`{{`}} $labels.cluster {{`}}`}}.
|
||||
description: Pod {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.pod {{`}}`}} has been in a non-ready state for longer than 15 minutes.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubepodnotready
|
||||
summary: Pod has been in a non-ready state for more than 15 minutes.
|
||||
expr: "sum by (namespace, pod, cluster) (\n max by(namespace, pod, cluster) (\n kube_pod_status_phase{job=\"kube-state-metrics\", phase=~\"Pending|Unknown|Failed\"}\n ) * on(namespace, pod, cluster) group_left(owner_kind) topk by(namespace, pod, cluster) (\n 1, max by(namespace, pod, owner_kind, cluster) (kube_pod_owner{owner_kind!=\"Job\"})\n )\n) > 0\n"
|
||||
@ -31,7 +31,7 @@ spec:
|
||||
severity: warning
|
||||
- alert: KubeDeploymentGenerationMismatch
|
||||
annotations:
|
||||
description: Deployment generation for {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.deployment {{`}}`}} does not match, this indicates that the Deployment has failed but has not been rolled back on cluster {{`{{`}} $labels.cluster {{`}}`}}.
|
||||
description: Deployment generation for {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.deployment {{`}}`}} does not match, this indicates that the Deployment has failed but has not been rolled back.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubedeploymentgenerationmismatch
|
||||
summary: Deployment generation mismatch due to possible roll-back
|
||||
expr: "kube_deployment_status_observed_generation{job=\"kube-state-metrics\"}\n !=\nkube_deployment_metadata_generation{job=\"kube-state-metrics\"}\n"
|
||||
@ -40,7 +40,7 @@ spec:
|
||||
severity: warning
|
||||
- alert: KubeDeploymentReplicasMismatch
|
||||
annotations:
|
||||
description: Deployment {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.deployment {{`}}`}} has not matched the expected number of replicas for longer than 15 minutes on cluster {{`{{`}} $labels.cluster {{`}}`}}.
|
||||
description: Deployment {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.deployment {{`}}`}} has not matched the expected number of replicas for longer than 15 minutes.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubedeploymentreplicasmismatch
|
||||
summary: Deployment has not matched the expected number of replicas.
|
||||
expr: "(\n kube_deployment_spec_replicas{job=\"kube-state-metrics\"}\n >\n kube_deployment_status_replicas_available{job=\"kube-state-metrics\"}\n) and (\n changes(kube_deployment_status_replicas_updated{job=\"kube-state-metrics\"}[10m])\n ==\n 0\n)\n"
|
||||
@ -49,7 +49,7 @@ spec:
|
||||
severity: warning
|
||||
- alert: KubeDeploymentRolloutStuck
|
||||
annotations:
|
||||
description: Rollout of deployment {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.deployment {{`}}`}} is not progressing for longer than 15 minutes on cluster {{`{{`}} $labels.cluster {{`}}`}}.
|
||||
description: Rollout of deployment {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.deployment {{`}}`}} is not progressing for longer than 15 minutes.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubedeploymentrolloutstuck
|
||||
summary: Deployment rollout is not progressing.
|
||||
expr: 'kube_deployment_status_condition{condition="Progressing", status="false",job="kube-state-metrics"}
|
||||
@ -62,7 +62,7 @@ spec:
|
||||
severity: warning
|
||||
- alert: KubeStatefulSetReplicasMismatch
|
||||
annotations:
|
||||
description: StatefulSet {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.statefulset {{`}}`}} has not matched the expected number of replicas for longer than 15 minutes on cluster {{`{{`}} $labels.cluster {{`}}`}}.
|
||||
description: StatefulSet {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.statefulset {{`}}`}} has not matched the expected number of replicas for longer than 15 minutes.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubestatefulsetreplicasmismatch
|
||||
summary: StatefulSet has not matched the expected number of replicas.
|
||||
expr: "(\n kube_statefulset_status_replicas_ready{job=\"kube-state-metrics\"}\n !=\n kube_statefulset_status_replicas{job=\"kube-state-metrics\"}\n) and (\n changes(kube_statefulset_status_replicas_updated{job=\"kube-state-metrics\"}[10m])\n ==\n 0\n)\n"
|
||||
@ -71,7 +71,7 @@ spec:
|
||||
severity: warning
|
||||
- alert: KubeStatefulSetGenerationMismatch
|
||||
annotations:
|
||||
description: StatefulSet generation for {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.statefulset {{`}}`}} does not match, this indicates that the StatefulSet has failed but has not been rolled back on cluster {{`{{`}} $labels.cluster {{`}}`}}.
|
||||
description: StatefulSet generation for {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.statefulset {{`}}`}} does not match, this indicates that the StatefulSet has failed but has not been rolled back.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubestatefulsetgenerationmismatch
|
||||
summary: StatefulSet generation mismatch due to possible roll-back
|
||||
expr: "kube_statefulset_status_observed_generation{job=\"kube-state-metrics\"}\n !=\nkube_statefulset_metadata_generation{job=\"kube-state-metrics\"}\n"
|
||||
@ -80,7 +80,7 @@ spec:
|
||||
severity: warning
|
||||
- alert: KubeStatefulSetUpdateNotRolledOut
|
||||
annotations:
|
||||
description: StatefulSet {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.statefulset {{`}}`}} update has not been rolled out on cluster {{`{{`}} $labels.cluster {{`}}`}}.
|
||||
description: StatefulSet {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.statefulset {{`}}`}} update has not been rolled out.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubestatefulsetupdatenotrolledout
|
||||
summary: StatefulSet update has not been rolled out.
|
||||
expr: "(\n max by(namespace, statefulset, job, cluster) (\n kube_statefulset_status_current_revision{job=\"kube-state-metrics\"}\n unless\n kube_statefulset_status_update_revision{job=\"kube-state-metrics\"}\n )\n *\n (\n kube_statefulset_replicas{job=\"kube-state-metrics\"}\n !=\n kube_statefulset_status_replicas_updated{job=\"kube-state-metrics\"}\n )\n) and (\n changes(kube_statefulset_status_replicas_updated{job=\"kube-state-metrics\"}[5m])\n ==\n 0\n)\n"
|
||||
@ -89,7 +89,7 @@ spec:
|
||||
severity: warning
|
||||
- alert: KubeDaemonSetRolloutStuck
|
||||
annotations:
|
||||
description: DaemonSet {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.daemonset {{`}}`}} has not finished or progressed for at least 15m on cluster {{`{{`}} $labels.cluster {{`}}`}}.
|
||||
description: DaemonSet {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.daemonset {{`}}`}} has not finished or progressed for at least 15m.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubedaemonsetrolloutstuck
|
||||
summary: DaemonSet rollout is stuck.
|
||||
expr: "(\n (\n kube_daemonset_status_current_number_scheduled{job=\"kube-state-metrics\"}\n !=\n kube_daemonset_status_desired_number_scheduled{job=\"kube-state-metrics\"}\n ) or (\n kube_daemonset_status_number_misscheduled{job=\"kube-state-metrics\"}\n !=\n 0\n ) or (\n kube_daemonset_status_updated_number_scheduled{job=\"kube-state-metrics\"}\n !=\n kube_daemonset_status_desired_number_scheduled{job=\"kube-state-metrics\"}\n ) or (\n kube_daemonset_status_number_available{job=\"kube-state-metrics\"}\n !=\n kube_daemonset_status_desired_number_scheduled{job=\"kube-state-metrics\"}\n )\n) and (\n changes(kube_daemonset_status_updated_number_scheduled{job=\"kube-state-metrics\"}[5m])\n ==\n 0\n)\n"
|
||||
@ -98,7 +98,7 @@ spec:
|
||||
severity: warning
|
||||
- alert: KubeContainerWaiting
|
||||
annotations:
|
||||
description: 'pod/{{`{{`}} $labels.pod {{`}}`}} in namespace {{`{{`}} $labels.namespace {{`}}`}} on container {{`{{`}} $labels.container{{`}}`}} has been in waiting state for longer than 1 hour. (reason: "{{`{{`}} $labels.reason {{`}}`}}") on cluster {{`{{`}} $labels.cluster {{`}}`}}.'
|
||||
description: 'pod/{{`{{`}} $labels.pod {{`}}`}} in namespace {{`{{`}} $labels.namespace {{`}}`}} on container {{`{{`}} $labels.container{{`}}`}} has been in waiting state for longer than 1 hour. (reason: "{{`{{`}} $labels.reason {{`}}`}}").'
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubecontainerwaiting
|
||||
summary: Pod container waiting longer than 1 hour
|
||||
expr: 'kube_pod_container_status_waiting_reason{reason!="CrashLoopBackOff", job="kube-state-metrics"} > 0
|
||||
@ -109,7 +109,7 @@ spec:
|
||||
severity: warning
|
||||
- alert: KubeDaemonSetNotScheduled
|
||||
annotations:
|
||||
description: '{{`{{`}} $value {{`}}`}} Pods of DaemonSet {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.daemonset {{`}}`}} are not scheduled on cluster {{`{{`}} $labels.cluster {{`}}`}}.'
|
||||
description: '{{`{{`}} $value {{`}}`}} Pods of DaemonSet {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.daemonset {{`}}`}} are not scheduled.'
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubedaemonsetnotscheduled
|
||||
summary: DaemonSet pods are not scheduled.
|
||||
expr: "kube_daemonset_status_desired_number_scheduled{job=\"kube-state-metrics\"}\n -\nkube_daemonset_status_current_number_scheduled{job=\"kube-state-metrics\"} > 0\n"
|
||||
@ -118,7 +118,7 @@ spec:
|
||||
severity: warning
|
||||
- alert: KubeDaemonSetMisScheduled
|
||||
annotations:
|
||||
description: '{{`{{`}} $value {{`}}`}} Pods of DaemonSet {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.daemonset {{`}}`}} are running where they are not supposed to run on cluster {{`{{`}} $labels.cluster {{`}}`}}.'
|
||||
description: '{{`{{`}} $value {{`}}`}} Pods of DaemonSet {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.daemonset {{`}}`}} are running where they are not supposed to run.'
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubedaemonsetmisscheduled
|
||||
summary: DaemonSet pods are misscheduled.
|
||||
expr: 'kube_daemonset_status_number_misscheduled{job="kube-state-metrics"} > 0
|
||||
@ -129,7 +129,7 @@ spec:
|
||||
severity: warning
|
||||
- alert: KubeJobNotCompleted
|
||||
annotations:
|
||||
description: Job {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.job_name {{`}}`}} is taking more than {{`{{`}} "43200" | humanizeDuration {{`}}`}} to complete on cluster {{`{{`}} $labels.cluster {{`}}`}}.
|
||||
description: Job {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.job_name {{`}}`}} is taking more than {{`{{`}} "43200" | humanizeDuration {{`}}`}} to complete.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubejobnotcompleted
|
||||
summary: Job did not complete in time
|
||||
expr: "time() - max by(namespace, job_name, cluster) (kube_job_status_start_time{job=\"kube-state-metrics\"}\n and\nkube_job_status_active{job=\"kube-state-metrics\"} > 0) > 43200\n"
|
||||
@ -137,7 +137,7 @@ spec:
|
||||
severity: warning
|
||||
- alert: KubeJobFailed
|
||||
annotations:
|
||||
description: Job {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.job_name {{`}}`}} failed to complete. Removing failed job after investigation should clear this alert on cluster {{`{{`}} $labels.cluster {{`}}`}}.
|
||||
description: Job {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.job_name {{`}}`}} failed to complete. Removing failed job after investigation should clear this alert.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubejobfailed
|
||||
summary: Job failed to complete.
|
||||
expr: 'kube_job_failed{job="kube-state-metrics"} > 0
|
||||
@ -148,7 +148,7 @@ spec:
|
||||
severity: warning
|
||||
- alert: KubeHpaReplicasMismatch
|
||||
annotations:
|
||||
description: HPA {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.horizontalpodautoscaler {{`}}`}} has not matched the desired number of replicas for longer than 15 minutes on cluster {{`{{`}} $labels.cluster {{`}}`}}.
|
||||
description: HPA {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.horizontalpodautoscaler {{`}}`}} has not matched the desired number of replicas for longer than 15 minutes.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubehpareplicasmismatch
|
||||
summary: HPA has not matched desired number of replicas.
|
||||
expr: "(kube_horizontalpodautoscaler_status_desired_replicas{job=\"kube-state-metrics\"}\n !=\nkube_horizontalpodautoscaler_status_current_replicas{job=\"kube-state-metrics\"})\n and\n(kube_horizontalpodautoscaler_status_current_replicas{job=\"kube-state-metrics\"}\n >\nkube_horizontalpodautoscaler_spec_min_replicas{job=\"kube-state-metrics\"})\n and\n(kube_horizontalpodautoscaler_status_current_replicas{job=\"kube-state-metrics\"}\n <\nkube_horizontalpodautoscaler_spec_max_replicas{job=\"kube-state-metrics\"})\n and\nchanges(kube_horizontalpodautoscaler_status_current_replicas{job=\"kube-state-metrics\"}[15m]) == 0\n"
|
||||
@ -157,7 +157,7 @@ spec:
|
||||
severity: warning
|
||||
- alert: KubeHpaMaxedOut
|
||||
annotations:
|
||||
description: HPA {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.horizontalpodautoscaler {{`}}`}} has been running at max replicas for longer than 15 minutes on cluster {{`{{`}} $labels.cluster {{`}}`}}.
|
||||
description: HPA {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.horizontalpodautoscaler {{`}}`}} has been running at max replicas for longer than 15 minutes.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubehpamaxedout
|
||||
summary: HPA is running at max replicas
|
||||
expr: "kube_horizontalpodautoscaler_status_current_replicas{job=\"kube-state-metrics\"}\n ==\nkube_horizontalpodautoscaler_spec_max_replicas{job=\"kube-state-metrics\"}\n"
|
||||
@ -186,7 +186,7 @@ spec:
|
||||
severity: warning
|
||||
- alert: KubeQuotaAlmostFull
|
||||
annotations:
|
||||
description: Namespace {{`{{`}} $labels.namespace {{`}}`}} is using {{`{{`}} $value | humanizePercentage {{`}}`}} of its {{`{{`}} $labels.resource {{`}}`}} quota on cluster {{`{{`}} $labels.cluster {{`}}`}}.
|
||||
description: Namespace {{`{{`}} $labels.namespace {{`}}`}} is using {{`{{`}} $value | humanizePercentage {{`}}`}} of its {{`{{`}} $labels.resource {{`}}`}} quota.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubequotaalmostfull
|
||||
summary: Namespace quota is going to be full.
|
||||
expr: "kube_resourcequota{job=\"kube-state-metrics\", type=\"used\"}\n / ignoring(instance, job, type)\n(kube_resourcequota{job=\"kube-state-metrics\", type=\"hard\"} > 0)\n > 0.9 < 1\n"
|
||||
@ -195,7 +195,7 @@ spec:
|
||||
severity: info
|
||||
- alert: KubeQuotaFullyUsed
|
||||
annotations:
|
||||
description: Namespace {{`{{`}} $labels.namespace {{`}}`}} is using {{`{{`}} $value | humanizePercentage {{`}}`}} of its {{`{{`}} $labels.resource {{`}}`}} quota on cluster {{`{{`}} $labels.cluster {{`}}`}}.
|
||||
description: Namespace {{`{{`}} $labels.namespace {{`}}`}} is using {{`{{`}} $value | humanizePercentage {{`}}`}} of its {{`{{`}} $labels.resource {{`}}`}} quota.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubequotafullyused
|
||||
summary: Namespace quota is fully used.
|
||||
expr: "kube_resourcequota{job=\"kube-state-metrics\", type=\"used\"}\n / ignoring(instance, job, type)\n(kube_resourcequota{job=\"kube-state-metrics\", type=\"hard\"} > 0)\n == 1\n"
|
||||
@ -204,7 +204,7 @@ spec:
|
||||
severity: info
|
||||
- alert: KubeQuotaExceeded
|
||||
annotations:
|
||||
description: Namespace {{`{{`}} $labels.namespace {{`}}`}} is using {{`{{`}} $value | humanizePercentage {{`}}`}} of its {{`{{`}} $labels.resource {{`}}`}} quota on cluster {{`{{`}} $labels.cluster {{`}}`}}.
|
||||
description: Namespace {{`{{`}} $labels.namespace {{`}}`}} is using {{`{{`}} $value | humanizePercentage {{`}}`}} of its {{`{{`}} $labels.resource {{`}}`}} quota.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubequotaexceeded
|
||||
summary: Namespace quota has exceeded the limits.
|
||||
expr: "kube_resourcequota{job=\"kube-state-metrics\", type=\"used\"}\n / ignoring(instance, job, type)\n(kube_resourcequota{job=\"kube-state-metrics\", type=\"hard\"} > 0)\n > 1\n"
|
||||
@ -213,7 +213,7 @@ spec:
|
||||
severity: warning
|
||||
- alert: CPUThrottlingHigh
|
||||
annotations:
|
||||
description: '{{`{{`}} $value | humanizePercentage {{`}}`}} throttling of CPU in namespace {{`{{`}} $labels.namespace {{`}}`}} for container {{`{{`}} $labels.container {{`}}`}} in pod {{`{{`}} $labels.pod {{`}}`}} on cluster {{`{{`}} $labels.cluster {{`}}`}}.'
|
||||
description: '{{`{{`}} $value | humanizePercentage {{`}}`}} throttling of CPU in namespace {{`{{`}} $labels.namespace {{`}}`}} for container {{`{{`}} $labels.container {{`}}`}} in pod {{`{{`}} $labels.pod {{`}}`}}.'
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/cputhrottlinghigh
|
||||
summary: Processes experience elevated CPU throttling.
|
||||
expr: "sum(increase(container_cpu_cfs_throttled_periods_total{container!=\"\", job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", }[5m])) without (id, metrics_path, name, image, endpoint, job, node)\n /\nsum(increase(container_cpu_cfs_periods_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", }[5m])) without (id, metrics_path, name, image, endpoint, job, node)\n > ( 25 / 100 )\n"
|
||||
@ -281,7 +281,7 @@ spec:
|
||||
rules:
|
||||
- alert: KubeVersionMismatch
|
||||
annotations:
|
||||
description: There are {{`{{`}} $value {{`}}`}} different semantic versions of Kubernetes components running on cluster {{`{{`}} $labels.cluster {{`}}`}}.
|
||||
description: There are {{`{{`}} $value {{`}}`}} different semantic versions of Kubernetes components running.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeversionmismatch
|
||||
summary: Different semantic versions of Kubernetes components running.
|
||||
expr: 'count by (cluster) (count by (git_version, cluster) (label_replace(kubernetes_build_info{job!~"kube-dns|coredns"},"git_version","$1","git_version","(v[0-9]*.[0-9]*).*"))) > 1
|
||||
@ -292,7 +292,7 @@ spec:
|
||||
severity: warning
|
||||
- alert: KubeClientErrors
|
||||
annotations:
|
||||
description: Kubernetes API server client '{{`{{`}} $labels.job {{`}}`}}/{{`{{`}} $labels.instance {{`}}`}}' is experiencing {{`{{`}} $value | humanizePercentage {{`}}`}} errors on cluster {{`{{`}} $labels.cluster {{`}}`}}.
|
||||
description: Kubernetes API server client '{{`{{`}} $labels.job {{`}}`}}/{{`{{`}} $labels.instance {{`}}`}}' is experiencing {{`{{`}} $value | humanizePercentage {{`}}`}} errors.'
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeclienterrors
|
||||
summary: Kubernetes API server client is experiencing errors.
|
||||
expr: "(sum(rate(rest_client_requests_total{job=\"apiserver\",code=~\"5..\"}[5m])) by (cluster, instance, job, namespace)\n /\nsum(rate(rest_client_requests_total{job=\"apiserver\"}[5m])) by (cluster, instance, job, namespace))\n> 0.01\n"
|
||||
@ -303,7 +303,7 @@ spec:
|
||||
rules:
|
||||
- alert: KubeAPIErrorBudgetBurn
|
||||
annotations:
|
||||
description: The API server is burning too much error budget on cluster {{`{{`}} $labels.cluster {{`}}`}}.
|
||||
description: The API server is burning too much error budget.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeapierrorbudgetburn
|
||||
summary: The API server is burning too much error budget.
|
||||
expr: 'sum by(cluster) (apiserver_request:burnrate1h) > (14.40 * 0.01000)
|
||||
@ -320,7 +320,7 @@ spec:
|
||||
short: 5m
|
||||
- alert: KubeAPIErrorBudgetBurn
|
||||
annotations:
|
||||
description: The API server is burning too much error budget on cluster {{`{{`}} $labels.cluster {{`}}`}}.
|
||||
description: The API server is burning too much error budget.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeapierrorbudgetburn
|
||||
summary: The API server is burning too much error budget.
|
||||
expr: 'sum by(cluster) (apiserver_request:burnrate6h) > (6.00 * 0.01000)
|
||||
@ -337,7 +337,7 @@ spec:
|
||||
short: 30m
|
||||
- alert: KubeAPIErrorBudgetBurn
|
||||
annotations:
|
||||
description: The API server is burning too much error budget on cluster {{`{{`}} $labels.cluster {{`}}`}}.
|
||||
description: The API server is burning too much error budget.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeapierrorbudgetburn
|
||||
summary: The API server is burning too much error budget.
|
||||
expr: 'sum by(cluster) (apiserver_request:burnrate1d) > (3.00 * 0.01000)
|
||||
@ -354,7 +354,7 @@ spec:
|
||||
short: 2h
|
||||
- alert: KubeAPIErrorBudgetBurn
|
||||
annotations:
|
||||
description: The API server is burning too much error budget on cluster {{`{{`}} $labels.cluster {{`}}`}}.
|
||||
description: The API server is burning too much error budget.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeapierrorbudgetburn
|
||||
summary: The API server is burning too much error budget.
|
||||
expr: 'sum by(cluster) (apiserver_request:burnrate3d) > (1.00 * 0.01000)
|
||||
@ -403,18 +403,17 @@ spec:
|
||||
severity: critical
|
||||
- alert: KubeAggregatedAPIErrors
|
||||
annotations:
|
||||
description: Kubernetes aggregated API {{`{{`}} $labels.instance {{`}}`}}/{{`{{`}} $labels.name {{`}}`}} has reported {{`{{`}} $labels.reason {{`}}`}} errors on cluster {{`{{`}} $labels.cluster {{`}}`}}.
|
||||
description: Kubernetes aggregated API {{`{{`}} $labels.name {{`}}`}}/{{`{{`}} $labels.namespace {{`}}`}} has reported errors. It has appeared unavailable {{`{{`}} $value | humanize {{`}}`}} times averaged over the past 10m.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeaggregatedapierrors
|
||||
summary: Kubernetes aggregated API has reported errors.
|
||||
expr: 'sum by(cluster, instance, name, reason)(increase(aggregator_unavailable_apiservice_total{job="apiserver"}[1m])) > 0
|
||||
expr: 'sum by(name, namespace, cluster)(increase(aggregator_unavailable_apiservice_total{job="apiserver"}[10m])) > 4
|
||||
|
||||
'
|
||||
for: 10m
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: KubeAggregatedAPIDown
|
||||
annotations:
|
||||
description: Kubernetes aggregated API {{`{{`}} $labels.name {{`}}`}}/{{`{{`}} $labels.namespace {{`}}`}} has been only {{`{{`}} $value | humanize {{`}}`}}% available over the last 10m on cluster {{`{{`}} $labels.cluster {{`}}`}}.
|
||||
description: Kubernetes aggregated API {{`{{`}} $labels.name {{`}}`}}/{{`{{`}} $labels.namespace {{`}}`}} has been only {{`{{`}} $value | humanize {{`}}`}}% available over the last 10m.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeaggregatedapidown
|
||||
summary: Kubernetes aggregated API is down.
|
||||
expr: '(1 - max by(name, namespace, cluster)(avg_over_time(aggregator_unavailable_apiservice{job="apiserver"}[10m]))) * 100 < 85
|
||||
@ -436,7 +435,7 @@ spec:
|
||||
severity: critical
|
||||
- alert: KubeAPITerminatedRequests
|
||||
annotations:
|
||||
description: The kubernetes apiserver has terminated {{`{{`}} $value | humanizePercentage {{`}}`}} of its incoming requests on cluster {{`{{`}} $labels.cluster {{`}}`}}.
|
||||
description: The kubernetes apiserver has terminated {{`{{`}} $value | humanizePercentage {{`}}`}} of its incoming requests.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeapiterminatedrequests
|
||||
summary: The kubernetes apiserver has terminated {{`{{`}} $value | humanizePercentage {{`}}`}} of its incoming requests.
|
||||
expr: 'sum by(cluster) (rate(apiserver_request_terminations_total{job="apiserver"}[10m])) / ( sum by(cluster) (rate(apiserver_request_total{job="apiserver"}[10m])) + sum by(cluster) (rate(apiserver_request_terminations_total{job="apiserver"}[10m])) ) > 0.20
|
||||
@ -449,22 +448,18 @@ spec:
|
||||
rules:
|
||||
- alert: KubeNodeNotReady
|
||||
annotations:
|
||||
description: '{{`{{`}} $labels.node {{`}}`}} has been unready for more than 15 minutes on cluster {{`{{`}} $labels.cluster {{`}}`}}.'
|
||||
description: '{{`{{`}} $labels.node {{`}}`}} has been unready for more than 15 minutes.'
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubenodenotready
|
||||
summary: Node is not ready.
|
||||
expr: 'kube_node_status_condition{job="kube-state-metrics",condition="Ready",status="true"} == 0
|
||||
|
||||
and on (cluster, node)
|
||||
|
||||
kube_node_spec_unschedulable{job="kube-state-metrics"} == 0
|
||||
|
||||
'
|
||||
for: 15m
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: KubeNodeUnreachable
|
||||
annotations:
|
||||
description: '{{`{{`}} $labels.node {{`}}`}} is unreachable and some workloads may be rescheduled on cluster {{`{{`}} $labels.cluster {{`}}`}}.'
|
||||
description: '{{`{{`}} $labels.node {{`}}`}} is unreachable and some workloads may be rescheduled.'
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubenodeunreachable
|
||||
summary: Node is unreachable.
|
||||
expr: '(kube_node_spec_taint{job="kube-state-metrics",key="node.kubernetes.io/unreachable",effect="NoSchedule"} unless ignoring(key,value) kube_node_spec_taint{job="kube-state-metrics",key=~"ToBeDeletedByClusterAutoscaler|cloud.google.com/impending-node-termination|aws-node-termination-handler/spot-itn"}) == 1
|
||||
@ -475,31 +470,27 @@ spec:
|
||||
severity: warning
|
||||
- alert: KubeletTooManyPods
|
||||
annotations:
|
||||
description: Kubelet '{{`{{`}} $labels.node {{`}}`}}' is running at {{`{{`}} $value | humanizePercentage {{`}}`}} of its Pod capacity on cluster {{`{{`}} $labels.cluster {{`}}`}}.
|
||||
description: Kubelet '{{`{{`}} $labels.node {{`}}`}}' is running at {{`{{`}} $value | humanizePercentage {{`}}`}} of its Pod capacity.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubelettoomanypods
|
||||
summary: Kubelet is running at capacity.
|
||||
expr: "(\n max by (cluster, instance) (\n kubelet_running_pods{job=\"kubelet\", metrics_path=\"/metrics\"} > 1\n )\n * on (cluster, instance) group_left(node)\n max by (cluster, instance, node) (\n kubelet_node_name{job=\"kubelet\", metrics_path=\"/metrics\"}\n )\n)\n/ on (cluster, node) group_left()\nmax by (cluster, node) (\n kube_node_status_capacity{job=\"kube-state-metrics\", resource=\"pods\"} != 1\n) > 0.95\n"
|
||||
expr: "count by(cluster, node) (\n (kube_pod_status_phase{job=\"kube-state-metrics\",phase=\"Running\"} == 1) * on(instance,pod,namespace,cluster) group_left(node) topk by(instance,pod,namespace,cluster) (1, kube_pod_info{job=\"kube-state-metrics\"})\n)\n/\nmax by(cluster, node) (\n kube_node_status_capacity{job=\"kube-state-metrics\",resource=\"pods\"} != 1\n) > 0.95\n"
|
||||
for: 15m
|
||||
labels:
|
||||
severity: info
|
||||
- alert: KubeNodeReadinessFlapping
|
||||
annotations:
|
||||
description: The readiness status of node {{`{{`}} $labels.node {{`}}`}} has changed {{`{{`}} $value {{`}}`}} times in the last 15 minutes on cluster {{`{{`}} $labels.cluster {{`}}`}}.
|
||||
description: The readiness status of node {{`{{`}} $labels.node {{`}}`}} has changed {{`{{`}} $value {{`}}`}} times in the last 15 minutes.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubenodereadinessflapping
|
||||
summary: Node readiness status is flapping.
|
||||
expr: 'sum(changes(kube_node_status_condition{job="kube-state-metrics",status="true",condition="Ready"}[15m])) by (cluster, node) > 2
|
||||
|
||||
and on (cluster, node)
|
||||
|
||||
kube_node_spec_unschedulable{job="kube-state-metrics"} == 0
|
||||
|
||||
'
|
||||
for: 15m
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: KubeletPlegDurationHigh
|
||||
annotations:
|
||||
description: The Kubelet Pod Lifecycle Event Generator has a 99th percentile duration of {{`{{`}} $value {{`}}`}} seconds on node {{`{{`}} $labels.node {{`}}`}} on cluster {{`{{`}} $labels.cluster {{`}}`}}.
|
||||
description: The Kubelet Pod Lifecycle Event Generator has a 99th percentile duration of {{`{{`}} $value {{`}}`}} seconds on node {{`{{`}} $labels.node {{`}}`}}.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletplegdurationhigh
|
||||
summary: Kubelet Pod Lifecycle Event Generator is taking too long to relist.
|
||||
expr: 'node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile{quantile="0.99"} >= 10
|
||||
@ -510,7 +501,7 @@ spec:
|
||||
severity: warning
|
||||
- alert: KubeletPodStartUpLatencyHigh
|
||||
annotations:
|
||||
description: Kubelet Pod startup 99th percentile latency is {{`{{`}} $value {{`}}`}} seconds on node {{`{{`}} $labels.node {{`}}`}} on cluster {{`{{`}} $labels.cluster {{`}}`}}.
|
||||
description: Kubelet Pod startup 99th percentile latency is {{`{{`}} $value {{`}}`}} seconds on node {{`{{`}} $labels.node {{`}}`}}.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletpodstartuplatencyhigh
|
||||
summary: Kubelet Pod startup latency is too high.
|
||||
expr: 'histogram_quantile(0.99, sum(rate(kubelet_pod_worker_duration_seconds_bucket{job="kubelet", metrics_path="/metrics"}[5m])) by (cluster, instance, le)) * on(cluster, instance) group_left(node) kubelet_node_name{job="kubelet", metrics_path="/metrics"} > 60
|
||||
@ -521,7 +512,7 @@ spec:
|
||||
severity: warning
|
||||
- alert: KubeletClientCertificateExpiration
|
||||
annotations:
|
||||
description: Client certificate for Kubelet on node {{`{{`}} $labels.node {{`}}`}} expires in {{`{{`}} $value | humanizeDuration {{`}}`}} on cluster {{`{{`}} $labels.cluster {{`}}`}}.
|
||||
description: Client certificate for Kubelet on node {{`{{`}} $labels.node {{`}}`}} expires in {{`{{`}} $value | humanizeDuration {{`}}`}}.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletclientcertificateexpiration
|
||||
summary: Kubelet client certificate is about to expire.
|
||||
expr: 'kubelet_certificate_manager_client_ttl_seconds < 604800
|
||||
@ -531,7 +522,7 @@ spec:
|
||||
severity: warning
|
||||
- alert: KubeletClientCertificateExpiration
|
||||
annotations:
|
||||
description: Client certificate for Kubelet on node {{`{{`}} $labels.node {{`}}`}} expires in {{`{{`}} $value | humanizeDuration {{`}}`}} on cluster {{`{{`}} $labels.cluster {{`}}`}}.
|
||||
description: Client certificate for Kubelet on node {{`{{`}} $labels.node {{`}}`}} expires in {{`{{`}} $value | humanizeDuration {{`}}`}}.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletclientcertificateexpiration
|
||||
summary: Kubelet client certificate is about to expire.
|
||||
expr: 'kubelet_certificate_manager_client_ttl_seconds < 86400
|
||||
@ -541,7 +532,7 @@ spec:
|
||||
severity: critical
|
||||
- alert: KubeletServerCertificateExpiration
|
||||
annotations:
|
||||
description: Server certificate for Kubelet on node {{`{{`}} $labels.node {{`}}`}} expires in {{`{{`}} $value | humanizeDuration {{`}}`}} on cluster {{`{{`}} $labels.cluster {{`}}`}}.
|
||||
description: Server certificate for Kubelet on node {{`{{`}} $labels.node {{`}}`}} expires in {{`{{`}} $value | humanizeDuration {{`}}`}}.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletservercertificateexpiration
|
||||
summary: Kubelet server certificate is about to expire.
|
||||
expr: 'kubelet_certificate_manager_server_ttl_seconds < 604800
|
||||
@ -551,7 +542,7 @@ spec:
|
||||
severity: warning
|
||||
- alert: KubeletServerCertificateExpiration
|
||||
annotations:
|
||||
description: Server certificate for Kubelet on node {{`{{`}} $labels.node {{`}}`}} expires in {{`{{`}} $value | humanizeDuration {{`}}`}} on cluster {{`{{`}} $labels.cluster {{`}}`}}.
|
||||
description: Server certificate for Kubelet on node {{`{{`}} $labels.node {{`}}`}} expires in {{`{{`}} $value | humanizeDuration {{`}}`}}.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletservercertificateexpiration
|
||||
summary: Kubelet server certificate is about to expire.
|
||||
expr: 'kubelet_certificate_manager_server_ttl_seconds < 86400
|
||||
@ -561,7 +552,7 @@ spec:
|
||||
severity: critical
|
||||
- alert: KubeletClientCertificateRenewalErrors
|
||||
annotations:
|
||||
description: Kubelet on node {{`{{`}} $labels.node {{`}}`}} has failed to renew its client certificate ({{`{{`}} $value | humanize {{`}}`}} errors in the last 5 minutes) on cluster {{`{{`}} $labels.cluster {{`}}`}}.
|
||||
description: Kubelet on node {{`{{`}} $labels.node {{`}}`}} has failed to renew its client certificate ({{`{{`}} $value | humanize {{`}}`}} errors in the last 5 minutes).
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletclientcertificaterenewalerrors
|
||||
summary: Kubelet has failed to renew its client certificate.
|
||||
expr: 'increase(kubelet_certificate_manager_client_expiration_renew_errors[5m]) > 0
|
||||
@ -572,7 +563,7 @@ spec:
|
||||
severity: warning
|
||||
- alert: KubeletServerCertificateRenewalErrors
|
||||
annotations:
|
||||
description: Kubelet on node {{`{{`}} $labels.node {{`}}`}} has failed to renew its server certificate ({{`{{`}} $value | humanize {{`}}`}} errors in the last 5 minutes) on cluster {{`{{`}} $labels.cluster {{`}}`}}.
|
||||
description: Kubelet on node {{`{{`}} $labels.node {{`}}`}} has failed to renew its server certificate ({{`{{`}} $value | humanize {{`}}`}} errors in the last 5 minutes).
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletservercertificaterenewalerrors
|
||||
summary: Kubelet has failed to renew its server certificate.
|
||||
expr: 'increase(kubelet_server_expiration_renew_errors[5m]) > 0
|
||||
@ -649,20 +640,20 @@ spec:
|
||||
|
||||
'
|
||||
record: cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase1h
|
||||
- expr: 'sum by (cluster, verb, scope) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{le="+Inf"})
|
||||
- expr: 'sum by (cluster, verb, scope) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{le="+Inf"} * 24 * 30)
|
||||
|
||||
'
|
||||
record: cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase30d
|
||||
- expr: "1 - (\n (\n # write too slow\n sum by (cluster) (cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase30d{verb=~\"POST|PUT|PATCH|DELETE\"})\n -\n sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~\"POST|PUT|PATCH|DELETE\",le=~\"1(\\\\.0)?\"})\n ) +\n (\n # read too slow\n sum by (cluster) (cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase30d{verb=~\"LIST|GET\"})\n -\n (\n (\n sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=~\"resource|\",le=~\"1(\\\\.0)?\"})\n or\n vector(0)\n )\n +\n sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=\"namespace\",le=~\"5(\\\\.0)?\"})\n +\n sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~\"\
|
||||
LIST|GET\",scope=\"cluster\",le=~\"30(\\\\.0)?\"})\n )\n ) +\n # errors\n sum by (cluster) (code:apiserver_request_total:increase30d{code=~\"5..\"} or vector(0))\n)\n/\nsum by (cluster) (code:apiserver_request_total:increase30d)\n"
|
||||
- expr: "1 - (\n (\n # write too slow\n sum by (cluster) (cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase30d{verb=~\"POST|PUT|PATCH|DELETE\"})\n -\n sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~\"POST|PUT|PATCH|DELETE\",le=\"1\"})\n ) +\n (\n # read too slow\n sum by (cluster) (cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase30d{verb=~\"LIST|GET\"})\n -\n (\n (\n sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=~\"resource|\",le=\"1\"})\n or\n vector(0)\n )\n +\n sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=\"namespace\",le=\"5\"})\n +\n sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=\"\
|
||||
cluster\",le=\"30\"})\n )\n ) +\n # errors\n sum by (cluster) (code:apiserver_request_total:increase30d{code=~\"5..\"} or vector(0))\n)\n/\nsum by (cluster) (code:apiserver_request_total:increase30d)\n"
|
||||
labels:
|
||||
verb: all
|
||||
record: apiserver_request:availability30d
|
||||
- expr: "1 - (\n sum by (cluster) (cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase30d{verb=~\"LIST|GET\"})\n -\n (\n # too slow\n (\n sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=~\"resource|\",le=~\"1(\\\\.0)?\"})\n or\n vector(0)\n )\n +\n sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=\"namespace\",le=~\"5(\\\\.0)?\"})\n +\n sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=\"cluster\",le=~\"30(\\\\.0)?\"})\n )\n +\n # errors\n sum by (cluster) (code:apiserver_request_total:increase30d{verb=\"read\",code=~\"5..\"} or vector(0))\n)\n/\nsum by (cluster) (code:apiserver_request_total:increase30d{verb=\"read\"})\n"
|
||||
- expr: "1 - (\n sum by (cluster) (cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase30d{verb=~\"LIST|GET\"})\n -\n (\n # too slow\n (\n sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=~\"resource|\",le=\"1\"})\n or\n vector(0)\n )\n +\n sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=\"namespace\",le=\"5\"})\n +\n sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=\"cluster\",le=\"30\"})\n )\n +\n # errors\n sum by (cluster) (code:apiserver_request_total:increase30d{verb=\"read\",code=~\"5..\"} or vector(0))\n)\n/\nsum by (cluster) (code:apiserver_request_total:increase30d{verb=\"read\"})\n"
|
||||
labels:
|
||||
verb: read
|
||||
record: apiserver_request:availability30d
|
||||
- expr: "1 - (\n (\n # too slow\n sum by (cluster) (cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase30d{verb=~\"POST|PUT|PATCH|DELETE\"})\n -\n sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~\"POST|PUT|PATCH|DELETE\",le=~\"1(\\\\.0)?\"})\n )\n +\n # errors\n sum by (cluster) (code:apiserver_request_total:increase30d{verb=\"write\",code=~\"5..\"} or vector(0))\n)\n/\nsum by (cluster) (code:apiserver_request_total:increase30d{verb=\"write\"})\n"
|
||||
- expr: "1 - (\n (\n # too slow\n sum by (cluster) (cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase30d{verb=~\"POST|PUT|PATCH|DELETE\"})\n -\n sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~\"POST|PUT|PATCH|DELETE\",le=\"1\"})\n )\n +\n # errors\n sum by (cluster) (code:apiserver_request_total:increase30d{verb=\"write\",code=~\"5..\"} or vector(0))\n)\n/\nsum by (cluster) (code:apiserver_request_total:increase30d{verb=\"write\"})\n"
|
||||
labels:
|
||||
verb: write
|
||||
record: apiserver_request:availability30d
|
||||
@ -696,66 +687,66 @@ spec:
|
||||
record: code_verb:apiserver_request_total:increase1h
|
||||
- name: kube-apiserver-burnrate.rules
|
||||
rules:
|
||||
- expr: "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\"}[1d]))\n -\n (\n (\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=~\"resource|\",le=~\"1(\\\\.0)?\"}[1d]))\n or\n vector(0)\n )\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"namespace\",le=~\"5(\\\\.0)?\"}[1d]))\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"cluster\",le=~\"30(\\\\.0)?\"}[1d]))\n )\n )\n +\n # errors\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\"\
|
||||
,verb=~\"LIST|GET\",code=~\"5..\"}[1d]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[1d]))\n"
|
||||
- expr: "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\"}[1d]))\n -\n (\n (\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=~\"resource|\",le=\"1\"}[1d]))\n or\n vector(0)\n )\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"namespace\",le=\"5\"}[1d]))\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"cluster\",le=\"30\"}[1d]))\n )\n )\n +\n # errors\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"\
|
||||
5..\"}[1d]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[1d]))\n"
|
||||
labels:
|
||||
verb: read
|
||||
record: apiserver_request:burnrate1d
|
||||
- expr: "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\"}[1h]))\n -\n (\n (\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=~\"resource|\",le=~\"1(\\\\.0)?\"}[1h]))\n or\n vector(0)\n )\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"namespace\",le=~\"5(\\\\.0)?\"}[1h]))\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"cluster\",le=~\"30(\\\\.0)?\"}[1h]))\n )\n )\n +\n # errors\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\"\
|
||||
,verb=~\"LIST|GET\",code=~\"5..\"}[1h]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[1h]))\n"
|
||||
- expr: "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\"}[1h]))\n -\n (\n (\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=~\"resource|\",le=\"1\"}[1h]))\n or\n vector(0)\n )\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"namespace\",le=\"5\"}[1h]))\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"cluster\",le=\"30\"}[1h]))\n )\n )\n +\n # errors\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"\
|
||||
5..\"}[1h]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[1h]))\n"
|
||||
labels:
|
||||
verb: read
|
||||
record: apiserver_request:burnrate1h
|
||||
- expr: "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\"}[2h]))\n -\n (\n (\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=~\"resource|\",le=~\"1(\\\\.0)?\"}[2h]))\n or\n vector(0)\n )\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"namespace\",le=~\"5(\\\\.0)?\"}[2h]))\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"cluster\",le=~\"30(\\\\.0)?\"}[2h]))\n )\n )\n +\n # errors\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\"\
|
||||
,verb=~\"LIST|GET\",code=~\"5..\"}[2h]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[2h]))\n"
|
||||
- expr: "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\"}[2h]))\n -\n (\n (\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=~\"resource|\",le=\"1\"}[2h]))\n or\n vector(0)\n )\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"namespace\",le=\"5\"}[2h]))\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"cluster\",le=\"30\"}[2h]))\n )\n )\n +\n # errors\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"\
|
||||
5..\"}[2h]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[2h]))\n"
|
||||
labels:
|
||||
verb: read
|
||||
record: apiserver_request:burnrate2h
|
||||
- expr: "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\"}[30m]))\n -\n (\n (\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=~\"resource|\",le=~\"1(\\\\.0)?\"}[30m]))\n or\n vector(0)\n )\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"namespace\",le=~\"5(\\\\.0)?\"}[30m]))\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"cluster\",le=~\"30(\\\\.0)?\"}[30m]))\n )\n )\n +\n # errors\n sum by (cluster) (rate(apiserver_request_total{job=\"\
|
||||
apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[30m]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[30m]))\n"
|
||||
- expr: "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\"}[30m]))\n -\n (\n (\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=~\"resource|\",le=\"1\"}[30m]))\n or\n vector(0)\n )\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"namespace\",le=\"5\"}[30m]))\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"cluster\",le=\"30\"}[30m]))\n )\n )\n +\n # errors\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"\
|
||||
,code=~\"5..\"}[30m]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[30m]))\n"
|
||||
labels:
|
||||
verb: read
|
||||
record: apiserver_request:burnrate30m
|
||||
- expr: "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\"}[3d]))\n -\n (\n (\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=~\"resource|\",le=~\"1(\\\\.0)?\"}[3d]))\n or\n vector(0)\n )\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"namespace\",le=~\"5(\\\\.0)?\"}[3d]))\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"cluster\",le=~\"30(\\\\.0)?\"}[3d]))\n )\n )\n +\n # errors\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\"\
|
||||
,verb=~\"LIST|GET\",code=~\"5..\"}[3d]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[3d]))\n"
|
||||
- expr: "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\"}[3d]))\n -\n (\n (\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=~\"resource|\",le=\"1\"}[3d]))\n or\n vector(0)\n )\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"namespace\",le=\"5\"}[3d]))\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"cluster\",le=\"30\"}[3d]))\n )\n )\n +\n # errors\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"\
|
||||
5..\"}[3d]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[3d]))\n"
|
||||
labels:
|
||||
verb: read
|
||||
record: apiserver_request:burnrate3d
|
||||
- expr: "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\"}[5m]))\n -\n (\n (\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=~\"resource|\",le=~\"1(\\\\.0)?\"}[5m]))\n or\n vector(0)\n )\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"namespace\",le=~\"5(\\\\.0)?\"}[5m]))\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"cluster\",le=~\"30(\\\\.0)?\"}[5m]))\n )\n )\n +\n # errors\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\"\
|
||||
,verb=~\"LIST|GET\",code=~\"5..\"}[5m]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[5m]))\n"
|
||||
- expr: "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\"}[5m]))\n -\n (\n (\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=~\"resource|\",le=\"1\"}[5m]))\n or\n vector(0)\n )\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"namespace\",le=\"5\"}[5m]))\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"cluster\",le=\"30\"}[5m]))\n )\n )\n +\n # errors\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"\
|
||||
5..\"}[5m]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[5m]))\n"
|
||||
labels:
|
||||
verb: read
|
||||
record: apiserver_request:burnrate5m
|
||||
- expr: "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\"}[6h]))\n -\n (\n (\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=~\"resource|\",le=~\"1(\\\\.0)?\"}[6h]))\n or\n vector(0)\n )\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"namespace\",le=~\"5(\\\\.0)?\"}[6h]))\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"cluster\",le=~\"30(\\\\.0)?\"}[6h]))\n )\n )\n +\n # errors\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\"\
|
||||
,verb=~\"LIST|GET\",code=~\"5..\"}[6h]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[6h]))\n"
|
||||
- expr: "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\"}[6h]))\n -\n (\n (\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=~\"resource|\",le=\"1\"}[6h]))\n or\n vector(0)\n )\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"namespace\",le=\"5\"}[6h]))\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"cluster\",le=\"30\"}[6h]))\n )\n )\n +\n # errors\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"\
|
||||
5..\"}[6h]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[6h]))\n"
|
||||
labels:
|
||||
verb: read
|
||||
record: apiserver_request:burnrate6h
|
||||
- expr: "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\"}[1d]))\n -\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\",le=~\"1(\\\\.0)?\"}[1d]))\n )\n +\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[1d]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[1d]))\n"
|
||||
- expr: "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\"}[1d]))\n -\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\",le=\"1\"}[1d]))\n )\n +\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[1d]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[1d]))\n"
|
||||
labels:
|
||||
verb: write
|
||||
record: apiserver_request:burnrate1d
|
||||
- expr: "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\"}[1h]))\n -\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\",le=~\"1(\\\\.0)?\"}[1h]))\n )\n +\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[1h]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[1h]))\n"
|
||||
- expr: "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\"}[1h]))\n -\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\",le=\"1\"}[1h]))\n )\n +\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[1h]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[1h]))\n"
|
||||
labels:
|
||||
verb: write
|
||||
record: apiserver_request:burnrate1h
|
||||
- expr: "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\"}[2h]))\n -\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\",le=~\"1(\\\\.0)?\"}[2h]))\n )\n +\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[2h]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[2h]))\n"
|
||||
- expr: "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\"}[2h]))\n -\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\",le=\"1\"}[2h]))\n )\n +\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[2h]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[2h]))\n"
|
||||
labels:
|
||||
verb: write
|
||||
record: apiserver_request:burnrate2h
|
||||
- expr: "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\"}[30m]))\n -\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\",le=~\"1(\\\\.0)?\"}[30m]))\n )\n +\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[30m]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[30m]))\n"
|
||||
- expr: "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\"}[30m]))\n -\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\",le=\"1\"}[30m]))\n )\n +\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[30m]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[30m]))\n"
|
||||
labels:
|
||||
verb: write
|
||||
record: apiserver_request:burnrate30m
|
||||
- expr: "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\"}[3d]))\n -\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\",le=~\"1(\\\\.0)?\"}[3d]))\n )\n +\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[3d]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[3d]))\n"
|
||||
- expr: "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\"}[3d]))\n -\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\",le=\"1\"}[3d]))\n )\n +\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[3d]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[3d]))\n"
|
||||
labels:
|
||||
verb: write
|
||||
record: apiserver_request:burnrate3d
|
||||
- expr: "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\"}[5m]))\n -\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\",le=~\"1(\\\\.0)?\"}[5m]))\n )\n +\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[5m]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[5m]))\n"
|
||||
- expr: "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\"}[5m]))\n -\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\",le=\"1\"}[5m]))\n )\n +\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[5m]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[5m]))\n"
|
||||
labels:
|
||||
verb: write
|
||||
record: apiserver_request:burnrate5m
|
||||
- expr: "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\"}[6h]))\n -\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\",le=~\"1(\\\\.0)?\"}[6h]))\n )\n +\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[6h]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[6h]))\n"
|
||||
- expr: "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\"}[6h]))\n -\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\",le=\"1\"}[6h]))\n )\n +\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[6h]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[6h]))\n"
|
||||
labels:
|
||||
verb: write
|
||||
record: apiserver_request:burnrate6h
|
||||
@ -925,122 +916,4 @@ spec:
|
||||
labels:
|
||||
quantile: '0.5'
|
||||
record: node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile
|
||||
- name: windows.node.rules
|
||||
rules:
|
||||
- expr: "count by (cluster) (\n windows_system_system_up_time{job=\"kubernetes-windows-exporter\"}\n)\n"
|
||||
record: node:windows_node:sum
|
||||
- expr: "count by (cluster, instance) (sum by (cluster, instance, core) (\n windows_cpu_time_total{job=\"kubernetes-windows-exporter\"}\n))\n"
|
||||
record: node:windows_node_num_cpu:sum
|
||||
- expr: '1 - avg by (cluster) (rate(windows_cpu_time_total{job="kubernetes-windows-exporter",mode="idle"}[1m]))
|
||||
|
||||
'
|
||||
record: :windows_node_cpu_utilisation:avg1m
|
||||
- expr: "1 - avg by (cluster, instance) (\n rate(windows_cpu_time_total{job=\"kubernetes-windows-exporter\",mode=\"idle\"}[1m])\n)\n"
|
||||
record: node:windows_node_cpu_utilisation:avg1m
|
||||
- expr: '1 -
|
||||
|
||||
sum by (cluster) (windows_memory_available_bytes{job="kubernetes-windows-exporter"})
|
||||
|
||||
/
|
||||
|
||||
sum by (cluster) (windows_os_visible_memory_bytes{job="kubernetes-windows-exporter"})
|
||||
|
||||
'
|
||||
record: ':windows_node_memory_utilisation:'
|
||||
- expr: 'sum by (cluster) (windows_memory_available_bytes{job="kubernetes-windows-exporter"} + windows_memory_cache_bytes{job="kubernetes-windows-exporter"})
|
||||
|
||||
'
|
||||
record: :windows_node_memory_MemFreeCached_bytes:sum
|
||||
- expr: '(windows_memory_cache_bytes{job="kubernetes-windows-exporter"} + windows_memory_modified_page_list_bytes{job="kubernetes-windows-exporter"} + windows_memory_standby_cache_core_bytes{job="kubernetes-windows-exporter"} + windows_memory_standby_cache_normal_priority_bytes{job="kubernetes-windows-exporter"} + windows_memory_standby_cache_reserve_bytes{job="kubernetes-windows-exporter"})
|
||||
|
||||
'
|
||||
record: node:windows_node_memory_totalCached_bytes:sum
|
||||
- expr: 'sum by (cluster) (windows_os_visible_memory_bytes{job="kubernetes-windows-exporter"})
|
||||
|
||||
'
|
||||
record: :windows_node_memory_MemTotal_bytes:sum
|
||||
- expr: "sum by (cluster, instance) (\n (windows_memory_available_bytes{job=\"kubernetes-windows-exporter\"})\n)\n"
|
||||
record: node:windows_node_memory_bytes_available:sum
|
||||
- expr: "sum by (cluster, instance) (\n windows_os_visible_memory_bytes{job=\"kubernetes-windows-exporter\"}\n)\n"
|
||||
record: node:windows_node_memory_bytes_total:sum
|
||||
- expr: '(node:windows_node_memory_bytes_total:sum - node:windows_node_memory_bytes_available:sum)
|
||||
|
||||
/
|
||||
|
||||
scalar(sum(node:windows_node_memory_bytes_total:sum))
|
||||
|
||||
'
|
||||
record: node:windows_node_memory_utilisation:ratio
|
||||
- expr: '1 - (node:windows_node_memory_bytes_available:sum / node:windows_node_memory_bytes_total:sum)
|
||||
|
||||
'
|
||||
record: 'node:windows_node_memory_utilisation:'
|
||||
- expr: 'irate(windows_memory_swap_page_operations_total{job="kubernetes-windows-exporter"}[5m])
|
||||
|
||||
'
|
||||
record: node:windows_node_memory_swap_io_pages:irate
|
||||
- expr: "avg by (cluster) (irate(windows_logical_disk_read_seconds_total{job=\"kubernetes-windows-exporter\"}[1m]) +\n irate(windows_logical_disk_write_seconds_total{job=\"kubernetes-windows-exporter\"}[1m])\n )\n"
|
||||
record: :windows_node_disk_utilisation:avg_irate
|
||||
- expr: "avg by (cluster, instance) (\n (irate(windows_logical_disk_read_seconds_total{job=\"kubernetes-windows-exporter\"}[1m]) +\n irate(windows_logical_disk_write_seconds_total{job=\"kubernetes-windows-exporter\"}[1m]))\n)\n"
|
||||
record: node:windows_node_disk_utilisation:avg_irate
|
||||
- expr: "max by (cluster,instance,volume)(\n (windows_logical_disk_size_bytes{job=\"kubernetes-windows-exporter\"}\n- windows_logical_disk_free_bytes{job=\"kubernetes-windows-exporter\"})\n/ windows_logical_disk_size_bytes{job=\"kubernetes-windows-exporter\"}\n)\n"
|
||||
record: 'node:windows_node_filesystem_usage:'
|
||||
- expr: 'max by (cluster, instance, volume) (windows_logical_disk_free_bytes{job="kubernetes-windows-exporter"} / windows_logical_disk_size_bytes{job="kubernetes-windows-exporter"})
|
||||
|
||||
'
|
||||
record: 'node:windows_node_filesystem_avail:'
|
||||
- expr: 'sum by (cluster) (irate(windows_net_bytes_total{job="kubernetes-windows-exporter"}[1m]))
|
||||
|
||||
'
|
||||
record: :windows_node_net_utilisation:sum_irate
|
||||
- expr: "sum by (cluster, instance) (\n (irate(windows_net_bytes_total{job=\"kubernetes-windows-exporter\"}[1m]))\n)\n"
|
||||
record: node:windows_node_net_utilisation:sum_irate
|
||||
- expr: 'sum by (cluster) (irate(windows_net_packets_received_discarded_total{job="kubernetes-windows-exporter"}[1m])) +
|
||||
|
||||
sum by (cluster) (irate(windows_net_packets_outbound_discarded_total{job="kubernetes-windows-exporter"}[1m]))
|
||||
|
||||
'
|
||||
record: :windows_node_net_saturation:sum_irate
|
||||
- expr: "sum by (cluster, instance) (\n (irate(windows_net_packets_received_discarded_total{job=\"kubernetes-windows-exporter\"}[1m]) +\n irate(windows_net_packets_outbound_discarded_total{job=\"kubernetes-windows-exporter\"}[1m]))\n)\n"
|
||||
record: node:windows_node_net_saturation:sum_irate
|
||||
- name: windows.pod.rules
|
||||
rules:
|
||||
- expr: 'windows_container_available{job="kubernetes-windows-exporter", container_id != ""} * on(container_id, cluster) group_left(container, pod, namespace) max(kube_pod_container_info{job="kube-state-metrics", container_id != ""}) by(container, container_id, pod, namespace, cluster)
|
||||
|
||||
'
|
||||
record: windows_pod_container_available
|
||||
- expr: 'windows_container_cpu_usage_seconds_total{job="kubernetes-windows-exporter", container_id != ""} * on(container_id, cluster) group_left(container, pod, namespace) max(kube_pod_container_info{job="kube-state-metrics", container_id != ""}) by(container, container_id, pod, namespace, cluster)
|
||||
|
||||
'
|
||||
record: windows_container_total_runtime
|
||||
- expr: 'windows_container_memory_usage_commit_bytes{job="kubernetes-windows-exporter", container_id != ""} * on(container_id, cluster) group_left(container, pod, namespace) max(kube_pod_container_info{job="kube-state-metrics", container_id != ""}) by(container, container_id, pod, namespace, cluster)
|
||||
|
||||
'
|
||||
record: windows_container_memory_usage
|
||||
- expr: 'windows_container_memory_usage_private_working_set_bytes{job="kubernetes-windows-exporter", container_id != ""} * on(container_id, cluster) group_left(container, pod, namespace) max(kube_pod_container_info{job="kube-state-metrics", container_id != ""}) by(container, container_id, pod, namespace, cluster)
|
||||
|
||||
'
|
||||
record: windows_container_private_working_set_usage
|
||||
- expr: 'windows_container_network_receive_bytes_total{job="kubernetes-windows-exporter", container_id != ""} * on(container_id, cluster) group_left(container, pod, namespace) max(kube_pod_container_info{job="kube-state-metrics", container_id != ""}) by(container, container_id, pod, namespace, cluster)
|
||||
|
||||
'
|
||||
record: windows_container_network_received_bytes_total
|
||||
- expr: 'windows_container_network_transmit_bytes_total{job="kubernetes-windows-exporter", container_id != ""} * on(container_id, cluster) group_left(container, pod, namespace) max(kube_pod_container_info{job="kube-state-metrics", container_id != ""}) by(container, container_id, pod, namespace, cluster)
|
||||
|
||||
'
|
||||
record: windows_container_network_transmitted_bytes_total
|
||||
- expr: "max by (cluster, namespace, pod, container) (\n kube_pod_container_resource_requests{resource=\"memory\",job=\"kube-state-metrics\"}\n) * on(container,pod,namespace,cluster) (windows_pod_container_available)\n"
|
||||
record: kube_pod_windows_container_resource_memory_request
|
||||
- expr: 'kube_pod_container_resource_limits{resource="memory",job="kube-state-metrics"} * on(container,pod,namespace,cluster) (windows_pod_container_available)
|
||||
|
||||
'
|
||||
record: kube_pod_windows_container_resource_memory_limit
|
||||
- expr: "max by (cluster, namespace, pod, container) (\n kube_pod_container_resource_requests{resource=\"cpu\",job=\"kube-state-metrics\"}\n) * on(container,pod,namespace,cluster) (windows_pod_container_available)\n"
|
||||
record: kube_pod_windows_container_resource_cpu_cores_request
|
||||
- expr: 'kube_pod_container_resource_limits{resource="cpu",job="kube-state-metrics"} * on(container,pod,namespace,cluster) (windows_pod_container_available)
|
||||
|
||||
'
|
||||
record: kube_pod_windows_container_resource_cpu_cores_limit
|
||||
- expr: "sum by (cluster, namespace, pod, container) (\n rate(windows_container_total_runtime{}[5m])\n)\n"
|
||||
record: namespace_pod_container:windows_container_cpu_usage_seconds_total:sum_rate
|
||||
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Loading…
x
Reference in New Issue
Block a user