From f2b3e5405ead1f6c995f4d6bfb38123198dce0c3 Mon Sep 17 00:00:00 2001 From: wangjianyu Date: Tue, 18 Feb 2025 20:48:19 +0800 Subject: [PATCH 1/2] Add CHART v1.6.0 Signed-off-by: wangjianyu --- versions/v1.6.0/.helmignore | 23 + versions/v1.6.0/Chart.yaml | 14 + versions/v1.6.0/README.md | 102 + versions/v1.6.0/templates/_helpers.tpl | 97 + ...alysis.koordinator.sh_recommendations.yaml | 247 +++ ...rdinator.sh_clustercolocationprofiles.yaml | 219 ++ ...a.koordinator.sh_elasticquotaprofiles.yaml | 110 ++ .../scheduling.koordinator.sh_devices.yaml | 176 ++ ...uling.koordinator.sh_podmigrationjobs.yaml | 565 ++++++ ...cheduling.koordinator.sh_reservations.yaml | 409 ++++ .../scheduling.sigs.k8s.io_elasticquotas.yaml | 84 + .../crd/scheduling.sigs.k8s.io_podgroups.yaml | 107 + .../crd/slo.koordinator.sh_nodemetrics.yaml | 1014 ++++++++++ .../crd/slo.koordinator.sh_nodeslos.yaml | 1759 +++++++++++++++++ ...gy.node.k8s.io_noderesourcetopologies.yaml | 147 ++ .../templates/koord-descheduler-config.yaml | 61 + .../v1.6.0/templates/koord-descheduler.yaml | 83 + versions/v1.6.0/templates/koord-manager.yaml | 130 ++ .../templates/koord-scheduler-config.yaml | 132 ++ .../v1.6.0/templates/koord-scheduler.yaml | 92 + .../v1.6.0/templates/koordlet-service.yaml | 19 + .../templates/koordlet-servicemonitor.yaml | 27 + versions/v1.6.0/templates/koordlet.yaml | 185 ++ .../templates/priority/koord-batch.yaml | 7 + .../v1.6.0/templates/priority/koord-free.yaml | 7 + .../v1.6.0/templates/priority/koord-mid.yaml | 7 + .../v1.6.0/templates/priority/koord-prod.yaml | 7 + .../templates/rbac/koord-descheduler.yaml | 113 ++ .../v1.6.0/templates/rbac/koord-manager.yaml | 254 +++ .../templates/rbac/koord-scheduler.yaml | 104 + versions/v1.6.0/templates/rbac/koordlet.yaml | 69 + .../templates/slo-controller-config.yaml | 16 + .../templates/webhookconfiguration.yaml | 240 +++ versions/v1.6.0/values.yaml | 173 ++ 34 files changed, 6799 insertions(+) create mode 100644 versions/v1.6.0/.helmignore create mode 100644 versions/v1.6.0/Chart.yaml create mode 100644 versions/v1.6.0/README.md create mode 100644 versions/v1.6.0/templates/_helpers.tpl create mode 100644 versions/v1.6.0/templates/crd/analysis.koordinator.sh_recommendations.yaml create mode 100644 versions/v1.6.0/templates/crd/config.koordinator.sh_clustercolocationprofiles.yaml create mode 100644 versions/v1.6.0/templates/crd/quota.koordinator.sh_elasticquotaprofiles.yaml create mode 100644 versions/v1.6.0/templates/crd/scheduling.koordinator.sh_devices.yaml create mode 100644 versions/v1.6.0/templates/crd/scheduling.koordinator.sh_podmigrationjobs.yaml create mode 100644 versions/v1.6.0/templates/crd/scheduling.koordinator.sh_reservations.yaml create mode 100644 versions/v1.6.0/templates/crd/scheduling.sigs.k8s.io_elasticquotas.yaml create mode 100644 versions/v1.6.0/templates/crd/scheduling.sigs.k8s.io_podgroups.yaml create mode 100644 versions/v1.6.0/templates/crd/slo.koordinator.sh_nodemetrics.yaml create mode 100644 versions/v1.6.0/templates/crd/slo.koordinator.sh_nodeslos.yaml create mode 100644 versions/v1.6.0/templates/crd/topology.node.k8s.io_noderesourcetopologies.yaml create mode 100644 versions/v1.6.0/templates/koord-descheduler-config.yaml create mode 100644 versions/v1.6.0/templates/koord-descheduler.yaml create mode 100644 versions/v1.6.0/templates/koord-manager.yaml create mode 100644 versions/v1.6.0/templates/koord-scheduler-config.yaml create mode 100644 versions/v1.6.0/templates/koord-scheduler.yaml create mode 100644 versions/v1.6.0/templates/koordlet-service.yaml create mode 100644 versions/v1.6.0/templates/koordlet-servicemonitor.yaml create mode 100644 versions/v1.6.0/templates/koordlet.yaml create mode 100644 versions/v1.6.0/templates/priority/koord-batch.yaml create mode 100644 versions/v1.6.0/templates/priority/koord-free.yaml create mode 100644 versions/v1.6.0/templates/priority/koord-mid.yaml create mode 100644 versions/v1.6.0/templates/priority/koord-prod.yaml create mode 100644 versions/v1.6.0/templates/rbac/koord-descheduler.yaml create mode 100644 versions/v1.6.0/templates/rbac/koord-manager.yaml create mode 100644 versions/v1.6.0/templates/rbac/koord-scheduler.yaml create mode 100644 versions/v1.6.0/templates/rbac/koordlet.yaml create mode 100644 versions/v1.6.0/templates/slo-controller-config.yaml create mode 100644 versions/v1.6.0/templates/webhookconfiguration.yaml create mode 100644 versions/v1.6.0/values.yaml diff --git a/versions/v1.6.0/.helmignore b/versions/v1.6.0/.helmignore new file mode 100644 index 0000000..0e8a0eb --- /dev/null +++ b/versions/v1.6.0/.helmignore @@ -0,0 +1,23 @@ +# 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/ diff --git a/versions/v1.6.0/Chart.yaml b/versions/v1.6.0/Chart.yaml new file mode 100644 index 0000000..7381495 --- /dev/null +++ b/versions/v1.6.0/Chart.yaml @@ -0,0 +1,14 @@ +apiVersion: v2 +name: koordinator +description: A Helm chart for Koordinator +type: application +version: 1.6.0 +appVersion: 1.6.0 +icon: https://koordinator.sh/img/logo.svg +keywords: + - koordinator + - co-location + - mixed-workloads +home: https://koordinator.sh +sources: + - https://github.com/koordinator-sh/koordinator diff --git a/versions/v1.6.0/README.md b/versions/v1.6.0/README.md new file mode 100644 index 0000000..69e2726 --- /dev/null +++ b/versions/v1.6.0/README.md @@ -0,0 +1,102 @@ +# Koordinator v1.6.0 + +## Configuration + +Note that installing this chart directly means it will use the default template values for Koordinator. + +You may have to set your specific configurations if it is deployed into a production cluster, or you want to configure feature-gates. + +### Optional: chart parameters + +The following table lists the configurable parameters of the chart and their default values. + +| Parameter | Description | Default | +|----------------------------------------------------|------------------------------------------------------------------|---------------------------------| +| `featureGates` | Feature gates for Koordinator, empty string means all by default | ` ` | +| `installation.namespace` | namespace for Koordinator installation | `koordinator-system` | +| `installation.createNamespace` | Whether to create the installation.namespace | `true` | +| `imageRepositoryHost` | Image repository host | `ghcr.io` | +| `manager.log.level` | Log level that koord-manager printed | `4` | +| `manager.replicas` | Replicas of koord-manager deployment | `2` | +| `manager.image.repository` | Repository for koord-manager image | `koordinatorsh/koord-manager` | +| `manager.image.tag` | Tag for koord-manager image | `v1.6.0` | +| `manager.resources.limits.cpu` | CPU resource limit of koord-manager container | `1000m` | +| `manager.resources.limits.memory` | Memory resource limit of koord-manager container | `1Gi` | +| `manager.resources.requests.cpu` | CPU resource request of koord-manager container | `500m` | +| `manager.resources.requests.memory` | Memory resource request of koord-manager container | `256Mi` | +| `manager.metrics.port` | Port of metrics served | `8080` | +| `manager.webhook.port` | Port of webhook served | `9443` | +| `manager.nodeAffinity` | Node affinity policy for koord-manager pod | `{}` | +| `manager.nodeSelector` | Node labels for koord-manager pod | `{}` | +| `manager.tolerations` | Tolerations for koord-manager pod | `[]` | +| `manager.resyncPeriod` | Resync period of informer koord-manager, defaults no resync | `0` | +| `manager.hostNetwork` | Whether koord-manager pod should run with hostnetwork | `false` | +| `scheduler.log.level` | Log level that koord-scheduler printed | `4` | +| `scheduler.replicas` | Replicas of koord-scheduler deployment | `2` | +| `scheduler.image.repository` | Repository for koord-scheduler image | `koordinatorsh/koord-scheduler` | +| `scheduler.image.tag` | Tag for koord-scheduler image | `v1.6.0` | +| `scheduler.resources.limits.cpu` | CPU resource limit of koord-scheduler container | `1000m` | +| `scheduler.resources.limits.memory` | Memory resource limit of koord-scheduler container | `1Gi` | +| `scheduler.resources.requests.cpu` | CPU resource request of koord-scheduler container | `500m` | +| `scheduler.resources.requests.memory` | Memory resource request of koord-scheduler container | `256Mi` | +| `scheduler.port` | Port of metrics served | `10251` | +| `scheduler.nodeAffinity` | Node affinity policy for koord-scheduler pod | `{}` | +| `scheduler.nodeSelector` | Node labels for koord-scheduler pod | `{}` | +| `scheduler.tolerations` | Tolerations for koord-scheduler pod | `[]` | +| `scheduler.hostNetwork` | Whether koord-scheduler pod should run with hostnetwork | `false` | +| `koordlet.log.level` | Log level that koordlet printed | `4` | +| `koordlet.image.repository` | Repository for koordlet image | `koordinatorsh/koordlet` | +| `koordlet.image.tag` | Tag for koordlet image | `v1.6.0` | +| `koordlet.resources.limits.cpu` | CPU resource limit of koordlet container | `500m` | +| `koordlet.resources.limits.memory` | Memory resource limit of koordlet container | `256Mi` | +| `koordlet.resources.requests.cpu` | CPU resource request of koordlet container | `0` | +| `koordlet.resources.requests.memory` | Memory resource request of koordlet container | `0` | +| `koordlet.affinity` | Affinity policy for koordlet pod | `{}` | +| `koordlet.runtimeClassName` | RuntimeClassName for koordlet pod | ` ` | +| `koordlet.enableServiceMonitor` | Whether to enable ServiceMonitor for koordlet | `false` | +| `webhookConfiguration.failurePolicy.pods` | The failurePolicy for pods in mutating webhook configuration | `Ignore` | +| `webhookConfiguration.failurePolicy.elasticquotas` | The failurePolicy for elasticQuotas in all webhook configuration | `Ignore` | +| `webhookConfiguration.failurePolicy.nodeStatus` | The failurePolicy for node.status in all webhook configuration | `Ignore` | +| `webhookConfiguration.failurePolicy.nodes` | The failurePolicy for nodes in all webhook configuration | `Ignore` | +| `webhookConfiguration.timeoutSeconds` | The timeoutSeconds for all webhook configuration | `30` | +| `crds.managed` | Koordinator will not install CRDs with chart if this is false | `true` | +| `imagePullSecrets` | The list of image pull secrets for koordinator image | `false` | + +Specify each parameter using the `--set key=value[,key=value]` argument to `helm install` or `helm upgrade`. + +### Optional: feature-gate + +Feature-gate controls some influential features in Koordinator: + +| Name | Description | Default | Effect (if closed) | +| ------------------------- | ---------------------------------------------------------------- | ------- | -------------------------------------- | +| `PodMutatingWebhook` | Whether to open a mutating webhook for Pod **create** | `true` | Don't inject koordinator.sh/qosClass, koordinator.sh/priority and don't replace koordinator extend resources ad so on | +| `PodValidatingWebhook` | Whether to open a validating webhook for Pod **create/update** | `true` | It is possible to create some Pods that do not conform to the Koordinator specification, causing some unpredictable problems | + + +If you want to configure the feature-gate, just set the parameter when install or upgrade. Such as: + +```bash +$ helm install koordinator https://... --set featureGates="PodMutatingWebhook=true\,PodValidatingWebhook=true" +``` + +If you want to enable all feature-gates, set the parameter as `featureGates=AllAlpha=true`. + +### Optional: install or upgrade specific CRDs + +If you want to skip specific CRDs during the installation or the upgrade, you can set the parameter `crds.` to `false` and install or upgrade them manually. + +```bash +# skip install the CRD noderesourcetopologies.topology.node.k8s.io +$ helm install koordinator https://... --set featureGates="crds.managed=true,crds.noderesourcetopologies=false" +# only upgrade specific CRDs recommendations, clustercolocationprofiles, elasticquotaprofiles, ..., podgroups +$ helm upgrade koordinator https://... --set featureGates="crds.managed=false,crds.recommendations=true,crds.clustercolocationprofiles=true,crds.elasticquotaprofiles=true,crds.elasticquotas=true,crds.devices=true,crds.podgroups=true" +``` + +### Optional: the local image for China + +If you are in China and have problem to pull image from official DockerHub, you can use the registry hosted on Alibaba Cloud: + +```bash +$ helm install koordinator https://... --set imageRepositoryHost=registry.cn-beijing.aliyuncs.com +``` diff --git a/versions/v1.6.0/templates/_helpers.tpl b/versions/v1.6.0/templates/_helpers.tpl new file mode 100644 index 0000000..56eb792 --- /dev/null +++ b/versions/v1.6.0/templates/_helpers.tpl @@ -0,0 +1,97 @@ +{{/* vim: set filetype=mustache: */}} +{{/* +Expand the name of the chart. +*/}} +{{- define "koordinator.name" -}} +{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" -}} +{{- end -}} + +{{/* +Create a default fully qualified app name. +We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec). +If release name contains chart name it will be used as a full name. +*/}} +{{- define "koordinator.fullname" -}} +{{- if .Values.fullnameOverride }} +{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" }} +{{- else }} +{{- $name := default .Chart.Name .Values.nameOverride }} +{{- if contains $name .Release.Name }} +{{- .Release.Name | trunc 63 | trimSuffix "-" }} +{{- else }} +{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" }} +{{- end }} +{{- end }} +{{- end }} + +{{/* +Create the name of the service account to use +*/}} +{{- define "koordinator.serviceAccountName" -}} +{{- if .Values.serviceAccount.create }} +{{- default (include "koordinator.fullname" .) .Values.serviceAccount.name }} +{{- else }} +{{- default "default" .Values.serviceAccount.name }} +{{- end }} +{{- end }} + +{{/* +Create chart name and version as used by the chart label. +*/}} +{{- define "koordinator.chart" -}} +{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" -}} +{{- end -}} + +{{/* +Lookup existing immutatble resources +*/}} +{{- define "webhookServiceSpec" -}} +{{- $service := lookup "v1" "Service" .Values.installation.namespace "koordinator-webhook-service" -}} +{{- if $service -}} +{{ if $service.spec.clusterIP -}} +clusterIP: {{ $service.spec.clusterIP }} +{{- end }} +{{ if $service.spec.clusterIPs -}} +clusterIPs: + {{ $service.spec.clusterIPs }} +{{- end }} +{{ if $service.spec.ipFamilyPolicy -}} +ipFamilyPolicy: {{ $service.spec.ipFamilyPolicy }} +{{- end }} +{{ if $service.spec.ipFamilies -}} +ipFamilies: + {{ $service.spec.ipFamilies }} +{{- end }} +{{ if $service.spec.type -}} +type: {{ $service.spec.type }} +{{- end }} +{{ if $service.spec.ipFamily -}} +ipFamily: {{ $service.spec.ipFamily }} +{{- end }} +{{- end -}} +ports: +- port: 443 + targetPort: {{ .Values.manager.webhook.port }} +selector: + koord-app: koord-manager +{{- end -}} + +{{- define "webhookSecretData" -}} +{{- $secret := lookup "v1" "Secret" .Values.installation.namespace "koordinator-webhook-certs" -}} +{{- if $secret -}} +data: +{{- range $k, $v := $secret.data }} + {{ $k }}: {{ $v }} +{{- end }} +{{- end }} +{{- end -}} + +{{- define "serviceAccountManager" -}} +{{- $sa := lookup "v1" "ServiceAccount" .Values.installation.namespace "koord-manager" -}} +{{- if $sa -}} +secrets: +{{- range $v := $sa.secrets }} +- name: {{ $v.name }} +{{- end }} +{{- end }} +{{- end -}} diff --git a/versions/v1.6.0/templates/crd/analysis.koordinator.sh_recommendations.yaml b/versions/v1.6.0/templates/crd/analysis.koordinator.sh_recommendations.yaml new file mode 100644 index 0000000..359a2dc --- /dev/null +++ b/versions/v1.6.0/templates/crd/analysis.koordinator.sh_recommendations.yaml @@ -0,0 +1,247 @@ +{{- if and .Values.crds.managed .Values.crds.recommendations }} +--- +apiVersion: apiextensions.k8s.io/v1 +kind: CustomResourceDefinition +metadata: + annotations: + controller-gen.kubebuilder.io/version: v0.14.0 + name: recommendations.analysis.koordinator.sh +spec: + group: analysis.koordinator.sh + names: + kind: Recommendation + listKind: RecommendationList + plural: recommendations + shortNames: + - recom + singular: recommendation + scope: Namespaced + versions: + - additionalPrinterColumns: + - jsonPath: .metadata.creationTimestamp + name: Age + type: date + - jsonPath: .spec.target.type + name: Type + type: string + - jsonPath: .spec.target.workload.kind + name: Kind + type: string + - jsonPath: .spec.target.workload.name + name: Name + type: string + - jsonPath: .status.updateTime + name: LastUpdateTime + type: date + name: v1alpha1 + schema: + openAPIV3Schema: + description: Recommendation is the Schema for the recommendations API + properties: + apiVersion: + description: |- + APIVersion defines the versioned schema of this representation of an object. + Servers should convert recognized schemas to the latest internal value, and + may reject unrecognized values. + More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources + type: string + kind: + description: |- + Kind is a string value representing the REST resource this object represents. + Servers may infer this from the endpoint the client submits requests to. + Cannot be updated. + In CamelCase. + More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds + type: string + metadata: + type: object + spec: + description: RecommendationSpec is the specification of the client object. + properties: + target: + description: Target is the object to be analyzed, which can be a workload + or a series of pods + properties: + podSelector: + description: PodSelector defines the reference of a series of + pods, which is effective when Type is "podSelector" + properties: + matchExpressions: + description: matchExpressions is a list of label selector + requirements. The requirements are ANDed. + items: + description: |- + A label selector requirement is a selector that contains values, a key, and an operator that + relates the key and values. + properties: + key: + description: key is the label key that the selector + applies to. + type: string + operator: + description: |- + operator represents a key's relationship to a set of values. + Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: |- + values is an array of string values. If the operator is In or NotIn, + the values array must be non-empty. If the operator is Exists or DoesNotExist, + the values array must be empty. This array is replaced during a strategic + merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: |- + matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels + map is equivalent to an element of matchExpressions, whose key field is "key", the + operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + x-kubernetes-map-type: atomic + type: + description: Type indicates the type of target + type: string + workload: + description: Workload indicates the target is a k8s workload, + which is effective when Type is "workload" + properties: + apiVersion: + description: API version of the referent + type: string + kind: + description: 'Kind of the referent; More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds"' + type: string + name: + description: 'Name of the referent; More info: http://kubernetes.io/docs/user-guide/identifiers#names' + type: string + required: + - kind + - name + type: object + required: + - type + type: object + required: + - target + type: object + status: + description: RecommendationStatus defines the observed state of Recommendation + properties: + conditions: + description: Conditions is the list of conditions representing the + status of the distribution + items: + description: "Condition contains details for one aspect of the current + state of this API Resource.\n---\nThis struct is intended for + direct use as an array at the field path .status.conditions. For + example,\n\n\n\ttype FooStatus struct{\n\t // Represents the + observations of a foo's current state.\n\t // Known .status.conditions.type + are: \"Available\", \"Progressing\", and \"Degraded\"\n\t // + +patchMergeKey=type\n\t // +patchStrategy=merge\n\t // +listType=map\n\t + \ // +listMapKey=type\n\t Conditions []metav1.Condition `json:\"conditions,omitempty\" + patchStrategy:\"merge\" patchMergeKey:\"type\" protobuf:\"bytes,1,rep,name=conditions\"`\n\n\n\t + \ // other fields\n\t}" + properties: + lastTransitionTime: + description: |- + lastTransitionTime is the last time the condition transitioned from one status to another. + This should be when the underlying condition changed. If that is not known, then using the time when the API field changed is acceptable. + format: date-time + type: string + message: + description: |- + message is a human readable message indicating details about the transition. + This may be an empty string. + maxLength: 32768 + type: string + observedGeneration: + description: |- + observedGeneration represents the .metadata.generation that the condition was set based upon. + For instance, if .metadata.generation is currently 12, but the .status.conditions[x].observedGeneration is 9, the condition is out of date + with respect to the current state of the instance. + format: int64 + minimum: 0 + type: integer + reason: + description: |- + reason contains a programmatic identifier indicating the reason for the condition's last transition. + Producers of specific condition types may define expected values and meanings for this field, + and whether the values are considered a guaranteed API. + The value should be a CamelCase string. + This field may not be empty. + maxLength: 1024 + minLength: 1 + pattern: ^[A-Za-z]([A-Za-z0-9_,:]*[A-Za-z0-9_])?$ + type: string + status: + description: status of the condition, one of True, False, Unknown. + enum: + - "True" + - "False" + - Unknown + type: string + type: + description: |- + type of condition in CamelCase or in foo.example.com/CamelCase. + --- + Many .condition.type values are consistent across resources like Available, but because arbitrary conditions can be + useful (see .node.status.conditions), the ability to deconflict is important. + The regex it matches is (dns1123SubdomainFmt/)?(qualifiedNameFmt) + maxLength: 316 + pattern: ^([a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*/)?(([A-Za-z0-9][-A-Za-z0-9_.]*)?[A-Za-z0-9])$ + type: string + required: + - lastTransitionTime + - message + - reason + - status + - type + type: object + type: array + podStatus: + description: PodStatus records the most recently computed amount of + resources recommended + properties: + containerStatuses: + description: ContainerStatuses records the most recently computed + amount of resources recommended + items: + description: RecommendedContainerStatus defines the observed + state of container + properties: + containerName: + description: Name of the container. + type: string + resources: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: Recommended resources of container + type: object + type: object + type: array + type: object + updateTime: + description: UpdateTime is the update time of the distribution + format: date-time + type: string + type: object + type: object + served: true + storage: true + subresources: + status: {} + +{{- end }} diff --git a/versions/v1.6.0/templates/crd/config.koordinator.sh_clustercolocationprofiles.yaml b/versions/v1.6.0/templates/crd/config.koordinator.sh_clustercolocationprofiles.yaml new file mode 100644 index 0000000..f6a4fdc --- /dev/null +++ b/versions/v1.6.0/templates/crd/config.koordinator.sh_clustercolocationprofiles.yaml @@ -0,0 +1,219 @@ +{{- if and .Values.crds.managed .Values.crds.clustercolocationprofiles }} +--- +apiVersion: apiextensions.k8s.io/v1 +kind: CustomResourceDefinition +metadata: + annotations: + controller-gen.kubebuilder.io/version: v0.14.0 + name: clustercolocationprofiles.config.koordinator.sh +spec: + group: config.koordinator.sh + names: + kind: ClusterColocationProfile + listKind: ClusterColocationProfileList + plural: clustercolocationprofiles + singular: clustercolocationprofile + scope: Cluster + versions: + - name: v1alpha1 + schema: + openAPIV3Schema: + description: ClusterColocationProfile is the Schema for the ClusterColocationProfile + API + properties: + apiVersion: + description: |- + APIVersion defines the versioned schema of this representation of an object. + Servers should convert recognized schemas to the latest internal value, and + may reject unrecognized values. + More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources + type: string + kind: + description: |- + Kind is a string value representing the REST resource this object represents. + Servers may infer this from the endpoint the client submits requests to. + Cannot be updated. + In CamelCase. + More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds + type: string + metadata: + type: object + spec: + description: ClusterColocationProfileSpec is a description of a ClusterColocationProfile. + properties: + annotationKeysMapping: + additionalProperties: + type: string + description: |- + AnnotationKeysMapping describes the annotations that needs to inject into Pod.Annotations with the same values. + It sets the Pod.Annotations[AnnotationsToAnnotations[k]] = Pod.Annotations[k] for each key k. + type: object + annotations: + additionalProperties: + type: string + description: Annotations describes the k/v pair that needs to inject + into Pod.Annotations + type: object + koordinatorPriority: + description: |- + KoordinatorPriority defines the Pod sub-priority in Koordinator. + The priority value will be injected into Pod as label koordinator.sh/priority. + Various Koordinator components determine the priority of the Pod + in the Koordinator through KoordinatorPriority and the priority value in PriorityClassName. + The higher the value, the higher the priority. + format: int32 + type: integer + labelKeysMapping: + additionalProperties: + type: string + description: |- + LabelKeysMapping describes the labels that needs to inject into Pod.Labels with the same values. + It sets the Pod.Labels[LabelsToLabels[k]] = Pod.Labels[k] for each key k. + type: object + labels: + additionalProperties: + type: string + description: Labels describes the k/v pair that needs to inject into + Pod.Labels + type: object + namespaceSelector: + description: |- + NamespaceSelector decides whether to mutate/validate Pods if the + namespace matches the selector. + Default to the empty LabelSelector, which matches everything. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. + The requirements are ANDed. + items: + description: |- + A label selector requirement is a selector that contains values, a key, and an operator that + relates the key and values. + properties: + key: + description: key is the label key that the selector applies + to. + type: string + operator: + description: |- + operator represents a key's relationship to a set of values. + Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: |- + values is an array of string values. If the operator is In or NotIn, + the values array must be non-empty. If the operator is Exists or DoesNotExist, + the values array must be empty. This array is replaced during a strategic + merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: |- + matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels + map is equivalent to an element of matchExpressions, whose key field is "key", the + operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + x-kubernetes-map-type: atomic + patch: + description: Patch indicates patching podTemplate that will be injected + to the Pod. + x-kubernetes-preserve-unknown-fields: true + priorityClassName: + description: |- + If specified, the priorityClassName and the priority value defined in PriorityClass + will be injected into the Pod. + The PriorityClassName, priority value in PriorityClassName and + KoordinatorPriority will affect the scheduling, preemption and + other behaviors of Koordinator system. + type: string + probability: + anyOf: + - type: integer + - type: string + description: Probability indicates profile will make effect with a + probability. + x-kubernetes-int-or-string: true + qosClass: + description: |- + QoSClass describes the type of Koordinator QoS that the Pod is running. + The value will be injected into Pod as label koordinator.sh/qosClass. + Options are LSE/LSR/LS/BE/SYSTEM. + enum: + - LSE + - LSR + - LS + - BE + - SYSTEM + type: string + schedulerName: + description: If specified, the pod will be dispatched by specified + scheduler. + type: string + selector: + description: |- + Selector decides whether to mutate/validate Pods if the + Pod matches the selector. + Default to the empty LabelSelector, which matches everything. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. + The requirements are ANDed. + items: + description: |- + A label selector requirement is a selector that contains values, a key, and an operator that + relates the key and values. + properties: + key: + description: key is the label key that the selector applies + to. + type: string + operator: + description: |- + operator represents a key's relationship to a set of values. + Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: |- + values is an array of string values. If the operator is In or NotIn, + the values array must be non-empty. If the operator is Exists or DoesNotExist, + the values array must be empty. This array is replaced during a strategic + merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: |- + matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels + map is equivalent to an element of matchExpressions, whose key field is "key", the + operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + x-kubernetes-map-type: atomic + type: object + status: + description: ClusterColocationProfileStatus represents information about + the status of a ClusterColocationProfile. + type: object + type: object + served: true + storage: true + subresources: + status: {} + +{{- end }} diff --git a/versions/v1.6.0/templates/crd/quota.koordinator.sh_elasticquotaprofiles.yaml b/versions/v1.6.0/templates/crd/quota.koordinator.sh_elasticquotaprofiles.yaml new file mode 100644 index 0000000..9026175 --- /dev/null +++ b/versions/v1.6.0/templates/crd/quota.koordinator.sh_elasticquotaprofiles.yaml @@ -0,0 +1,110 @@ +{{- if and .Values.crds.managed .Values.crds.elasticquotaprofiles }} +--- +apiVersion: apiextensions.k8s.io/v1 +kind: CustomResourceDefinition +metadata: + annotations: + controller-gen.kubebuilder.io/version: v0.14.0 + name: elasticquotaprofiles.quota.koordinator.sh +spec: + group: quota.koordinator.sh + names: + kind: ElasticQuotaProfile + listKind: ElasticQuotaProfileList + plural: elasticquotaprofiles + shortNames: + - eqp + singular: elasticquotaprofile + scope: Namespaced + versions: + - name: v1alpha1 + schema: + openAPIV3Schema: + properties: + apiVersion: + description: |- + APIVersion defines the versioned schema of this representation of an object. + Servers should convert recognized schemas to the latest internal value, and + may reject unrecognized values. + More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources + type: string + kind: + description: |- + Kind is a string value representing the REST resource this object represents. + Servers may infer this from the endpoint the client submits requests to. + Cannot be updated. + In CamelCase. + More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds + type: string + metadata: + type: object + spec: + properties: + nodeSelector: + description: NodeSelector defines a node selector to select nodes. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. + The requirements are ANDed. + items: + description: |- + A label selector requirement is a selector that contains values, a key, and an operator that + relates the key and values. + properties: + key: + description: key is the label key that the selector applies + to. + type: string + operator: + description: |- + operator represents a key's relationship to a set of values. + Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: |- + values is an array of string values. If the operator is In or NotIn, + the values array must be non-empty. If the operator is Exists or DoesNotExist, + the values array must be empty. This array is replaced during a strategic + merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: |- + matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels + map is equivalent to an element of matchExpressions, whose key field is "key", the + operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + x-kubernetes-map-type: atomic + quotaLabels: + additionalProperties: + type: string + description: QuotaLabels defines the labels of the quota. + type: object + quotaName: + description: QuotaName defines the associated quota name of the profile. + type: string + resourceRatio: + description: |- + ResourceRatio is a ratio, we will use it to fix the resource fragmentation problem. + If the total resource is 100 and the resource ratio is 0.9, the allocable resource is 100*0.9=90 + type: string + required: + - nodeSelector + - quotaName + type: object + status: + type: object + type: object + served: true + storage: true + +{{- end }} \ No newline at end of file diff --git a/versions/v1.6.0/templates/crd/scheduling.koordinator.sh_devices.yaml b/versions/v1.6.0/templates/crd/scheduling.koordinator.sh_devices.yaml new file mode 100644 index 0000000..4ee39c5 --- /dev/null +++ b/versions/v1.6.0/templates/crd/scheduling.koordinator.sh_devices.yaml @@ -0,0 +1,176 @@ +{{- if and .Values.crds.managed .Values.crds.devices }} +--- +apiVersion: apiextensions.k8s.io/v1 +kind: CustomResourceDefinition +metadata: + annotations: + controller-gen.kubebuilder.io/version: v0.14.0 + name: devices.scheduling.koordinator.sh +spec: + group: scheduling.koordinator.sh + names: + kind: Device + listKind: DeviceList + plural: devices + singular: device + scope: Cluster + versions: + - name: v1alpha1 + schema: + openAPIV3Schema: + properties: + apiVersion: + description: |- + APIVersion defines the versioned schema of this representation of an object. + Servers should convert recognized schemas to the latest internal value, and + may reject unrecognized values. + More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources + type: string + kind: + description: |- + Kind is a string value representing the REST resource this object represents. + Servers may infer this from the endpoint the client submits requests to. + Cannot be updated. + In CamelCase. + More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds + type: string + metadata: + type: object + spec: + properties: + devices: + items: + properties: + health: + default: false + description: Health indicates whether the device is normal + type: boolean + id: + description: UUID represents the UUID of device + type: string + labels: + additionalProperties: + type: string + description: Labels represents the device properties that can + be used to organize and categorize (scope and select) objects + type: object + minor: + description: Minor represents the Minor number of Device, starting + from 0 + format: int32 + type: integer + moduleID: + description: ModuleID represents the physical id of Device + format: int32 + type: integer + resources: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: Resources is a set of (resource name, quantity) + pairs + type: object + topology: + description: Topology represents the topology information about + the device + properties: + busID: + description: BusID is the domain:bus:device.function formatted + identifier of PCI/PCIE device + type: string + nodeID: + description: NodeID is the ID of NUMA Node to which the + device belongs, it should be unique across different CPU + Sockets + format: int32 + type: integer + pcieID: + description: PCIEID is the ID of PCIE Switch to which the + device is connected, it should be unique across difference + NUMANodes + type: string + socketID: + description: SocketID is the ID of CPU Socket to which the + device belongs + format: int32 + type: integer + required: + - nodeID + - pcieID + - socketID + type: object + type: + description: Type represents the type of device + type: string + vfGroups: + description: VFGroups represents the virtual function devices + items: + properties: + labels: + additionalProperties: + type: string + description: Labels represents the Virtual Function properties + that can be used to organize and categorize (scope and + select) objects + type: object + vfs: + description: VFs are the virtual function devices which + belong to the group + items: + properties: + busID: + description: BusID is the domain:bus:device.function + formatted identifier of PCI/PCIE virtual function + device + type: string + minor: + description: Minor represents the Minor number of + VirtualFunction, starting from 0, used to identify + virtual function. + format: int32 + type: integer + required: + - minor + type: object + type: array + type: object + type: array + required: + - health + type: object + type: array + type: object + status: + properties: + allocations: + items: + properties: + entries: + items: + properties: + minors: + items: + format: int32 + type: integer + type: array + name: + type: string + namespace: + type: string + uuid: + type: string + type: object + type: array + type: + type: string + type: object + type: array + type: object + type: object + served: true + storage: true + +{{- end }} diff --git a/versions/v1.6.0/templates/crd/scheduling.koordinator.sh_podmigrationjobs.yaml b/versions/v1.6.0/templates/crd/scheduling.koordinator.sh_podmigrationjobs.yaml new file mode 100644 index 0000000..ceba0f4 --- /dev/null +++ b/versions/v1.6.0/templates/crd/scheduling.koordinator.sh_podmigrationjobs.yaml @@ -0,0 +1,565 @@ +{{- if and .Values.crds.managed .Values.crds.podmigrationjobs }} +--- +apiVersion: apiextensions.k8s.io/v1 +kind: CustomResourceDefinition +metadata: + annotations: + controller-gen.kubebuilder.io/version: v0.14.0 + name: podmigrationjobs.scheduling.koordinator.sh +spec: + group: scheduling.koordinator.sh + names: + kind: PodMigrationJob + listKind: PodMigrationJobList + plural: podmigrationjobs + shortNames: + - pmj + singular: podmigrationjob + scope: Cluster + versions: + - additionalPrinterColumns: + - description: The phase of PodMigrationJob + jsonPath: .status.phase + name: Phase + type: string + - description: The status of PodMigrationJob + jsonPath: .status.status + name: Status + type: string + - jsonPath: .metadata.creationTimestamp + name: Age + type: date + - jsonPath: .status.nodeName + name: Node + type: string + - jsonPath: .spec.reservationOptions.reservationRef.name + name: Reservation + type: string + - jsonPath: .spec.podRef.namespace + name: PodNamespace + type: string + - jsonPath: .spec.podRef.name + name: Pod + type: string + - jsonPath: .status.podRef.name + name: NewPod + type: string + - jsonPath: .spec.ttl + name: TTL + type: string + name: v1alpha1 + schema: + openAPIV3Schema: + properties: + apiVersion: + description: |- + APIVersion defines the versioned schema of this representation of an object. + Servers should convert recognized schemas to the latest internal value, and + may reject unrecognized values. + More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources + type: string + kind: + description: |- + Kind is a string value representing the REST resource this object represents. + Servers may infer this from the endpoint the client submits requests to. + Cannot be updated. + In CamelCase. + More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds + type: string + metadata: + type: object + spec: + properties: + deleteOptions: + description: DeleteOptions defines the deleting options for the migrated + Pod and preempted Pods + properties: + apiVersion: + description: |- + APIVersion defines the versioned schema of this representation of an object. + Servers should convert recognized schemas to the latest internal value, and + may reject unrecognized values. + More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources + type: string + dryRun: + description: |- + When present, indicates that modifications should not be + persisted. An invalid or unrecognized dryRun directive will + result in an error response and no further processing of the + request. Valid values are: + - All: all dry run stages will be processed + items: + type: string + type: array + gracePeriodSeconds: + description: |- + The duration in seconds before the object should be deleted. Value must be non-negative integer. + The value zero indicates delete immediately. If this value is nil, the default grace period for the + specified type will be used. + Defaults to a per object value if not specified. zero means delete immediately. + format: int64 + type: integer + kind: + description: |- + Kind is a string value representing the REST resource this object represents. + Servers may infer this from the endpoint the client submits requests to. + Cannot be updated. + In CamelCase. + More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds + type: string + orphanDependents: + description: |- + Deprecated: please use the PropagationPolicy, this field will be deprecated in 1.7. + Should the dependent objects be orphaned. If true/false, the "orphan" + finalizer will be added to/removed from the object's finalizers list. + Either this field or PropagationPolicy may be set, but not both. + type: boolean + preconditions: + description: |- + Must be fulfilled before a deletion is carried out. If not possible, a 409 Conflict status will be + returned. + properties: + resourceVersion: + description: Specifies the target ResourceVersion + type: string + uid: + description: Specifies the target UID. + type: string + type: object + propagationPolicy: + description: |- + Whether and how garbage collection will be performed. + Either this field or OrphanDependents may be set, but not both. + The default policy is decided by the existing finalizer set in the + metadata.finalizers and the resource-specific default policy. + Acceptable values are: 'Orphan' - orphan the dependents; 'Background' - + allow the garbage collector to delete the dependents in the background; + 'Foreground' - a cascading policy that deletes all dependents in the + foreground. + type: string + type: object + mode: + description: |- + Mode represents the operating mode of the Job + Default is PodMigrationJobModeReservationFirst + type: string + paused: + description: |- + Paused indicates whether the PodMigrationJob should to work or not. + Default is false + type: boolean + podRef: + description: PodRef represents the Pod that be migrated + properties: + apiVersion: + description: API version of the referent. + type: string + fieldPath: + description: |- + If referring to a piece of an object instead of an entire object, this string + should contain a valid JSON/Go field access statement, such as desiredState.manifest.containers[2]. + For example, if the object reference is to a container within a pod, this would take on a value like: + "spec.containers{name}" (where "name" refers to the name of the container that triggered + the event) or if no container name is specified "spec.containers[2]" (container with + index 2 in this pod). This syntax is chosen only to have some well-defined way of + referencing a part of an object. + TODO: this design is not final and this field is subject to change in the future. + type: string + kind: + description: |- + Kind of the referent. + More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds + type: string + name: + description: |- + Name of the referent. + More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + type: string + namespace: + description: |- + Namespace of the referent. + More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/namespaces/ + type: string + resourceVersion: + description: |- + Specific resourceVersion to which this reference is made, if any. + More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#concurrency-control-and-consistency + type: string + uid: + description: |- + UID of the referent. + More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#uids + type: string + type: object + x-kubernetes-map-type: atomic + reservationOptions: + description: ReservationOptions defines the Reservation options for + migrated Pod + properties: + preemptionOptions: + description: |- + PreemptionOption decides whether to preempt other Pods. + The preemption is safe and reserves resources for preempted Pods. + type: object + reservationRef: + description: |- + ReservationRef if specified, PodMigrationJob will check if the status of Reservation is available. + ReservationRef if not specified, PodMigrationJob controller will create Reservation by Template, + and update the ReservationRef to reference the Reservation + properties: + apiVersion: + description: API version of the referent. + type: string + fieldPath: + description: |- + If referring to a piece of an object instead of an entire object, this string + should contain a valid JSON/Go field access statement, such as desiredState.manifest.containers[2]. + For example, if the object reference is to a container within a pod, this would take on a value like: + "spec.containers{name}" (where "name" refers to the name of the container that triggered + the event) or if no container name is specified "spec.containers[2]" (container with + index 2 in this pod). This syntax is chosen only to have some well-defined way of + referencing a part of an object. + TODO: this design is not final and this field is subject to change in the future. + type: string + kind: + description: |- + Kind of the referent. + More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds + type: string + name: + description: |- + Name of the referent. + More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + type: string + namespace: + description: |- + Namespace of the referent. + More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/namespaces/ + type: string + resourceVersion: + description: |- + Specific resourceVersion to which this reference is made, if any. + More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#concurrency-control-and-consistency + type: string + uid: + description: |- + UID of the referent. + More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#uids + type: string + type: object + x-kubernetes-map-type: atomic + template: + description: Template is the object that describes the Reservation + that will be created if not specified ReservationRef + x-kubernetes-preserve-unknown-fields: true + type: object + ttl: + description: TTL controls the PodMigrationJob timeout duration. + type: string + required: + - podRef + type: object + status: + properties: + conditions: + description: Conditions records the stats of PodMigrationJob + items: + properties: + lastProbeTime: + description: Last time we probed the condition. + format: date-time + nullable: true + type: string + lastTransitionTime: + description: Last time the condition transitioned from one status + to another. + format: date-time + nullable: true + type: string + message: + description: Human-readable message indicating details about + last transition. + type: string + reason: + description: Unique, one-word, CamelCase reason for the condition's + last transition. + type: string + status: + description: |- + Status is the status of the condition. + Can be True, False, Unknown. + type: string + type: + description: Type is the type of the condition. + type: string + required: + - status + - type + type: object + type: array + message: + description: Message represents a human-readable message indicating + details about why the PodMigrationJob is in this state. + type: string + nodeName: + description: NodeName represents the node's name of migrated Pod + type: string + phase: + description: |- + PodMigrationJobPhase represents the phase of a PodMigrationJob is a simple, high-level summary of where the PodMigrationJob is in its lifecycle. + e.g. Pending/Running/Failed + type: string + podRef: + description: PodRef represents the newly created Pod after being migrated + properties: + apiVersion: + description: API version of the referent. + type: string + fieldPath: + description: |- + If referring to a piece of an object instead of an entire object, this string + should contain a valid JSON/Go field access statement, such as desiredState.manifest.containers[2]. + For example, if the object reference is to a container within a pod, this would take on a value like: + "spec.containers{name}" (where "name" refers to the name of the container that triggered + the event) or if no container name is specified "spec.containers[2]" (container with + index 2 in this pod). This syntax is chosen only to have some well-defined way of + referencing a part of an object. + TODO: this design is not final and this field is subject to change in the future. + type: string + kind: + description: |- + Kind of the referent. + More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds + type: string + name: + description: |- + Name of the referent. + More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + type: string + namespace: + description: |- + Namespace of the referent. + More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/namespaces/ + type: string + resourceVersion: + description: |- + Specific resourceVersion to which this reference is made, if any. + More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#concurrency-control-and-consistency + type: string + uid: + description: |- + UID of the referent. + More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#uids + type: string + type: object + x-kubernetes-map-type: atomic + preemptedPodsRef: + description: PreemptedPodsRef represents the Pods that be preempted + items: + description: |- + ObjectReference contains enough information to let you inspect or modify the referred object. + --- + New uses of this type are discouraged because of difficulty describing its usage when embedded in APIs. + 1. Ignored fields. It includes many fields which are not generally honored. For instance, ResourceVersion and FieldPath are both very rarely valid in actual usage. + 2. Invalid usage help. It is impossible to add specific help for individual usage. In most embedded usages, there are particular + restrictions like, "must refer only to types A and B" or "UID not honored" or "name must be restricted". + Those cannot be well described when embedded. + 3. Inconsistent validation. Because the usages are different, the validation rules are different by usage, which makes it hard for users to predict what will happen. + 4. The fields are both imprecise and overly precise. Kind is not a precise mapping to a URL. This can produce ambiguity + during interpretation and require a REST mapping. In most cases, the dependency is on the group,resource tuple + and the version of the actual struct is irrelevant. + 5. We cannot easily change it. Because this type is embedded in many locations, updates to this type + will affect numerous schemas. Don't make new APIs embed an underspecified API type they do not control. + + + Instead of using this type, create a locally provided and used type that is well-focused on your reference. + For example, ServiceReferences for admission registration: https://github.com/kubernetes/api/blob/release-1.17/admissionregistration/v1/types.go#L533 . + properties: + apiVersion: + description: API version of the referent. + type: string + fieldPath: + description: |- + If referring to a piece of an object instead of an entire object, this string + should contain a valid JSON/Go field access statement, such as desiredState.manifest.containers[2]. + For example, if the object reference is to a container within a pod, this would take on a value like: + "spec.containers{name}" (where "name" refers to the name of the container that triggered + the event) or if no container name is specified "spec.containers[2]" (container with + index 2 in this pod). This syntax is chosen only to have some well-defined way of + referencing a part of an object. + TODO: this design is not final and this field is subject to change in the future. + type: string + kind: + description: |- + Kind of the referent. + More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds + type: string + name: + description: |- + Name of the referent. + More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + type: string + namespace: + description: |- + Namespace of the referent. + More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/namespaces/ + type: string + resourceVersion: + description: |- + Specific resourceVersion to which this reference is made, if any. + More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#concurrency-control-and-consistency + type: string + uid: + description: |- + UID of the referent. + More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#uids + type: string + type: object + x-kubernetes-map-type: atomic + type: array + preemptedPodsReservation: + description: PreemptedPodsReservations records information about Reservations + created due to preemption + items: + properties: + name: + description: Name represents the name of Reservation + type: string + namespace: + description: Namespace represents the namespace of Reservation + type: string + nodeName: + description: NodeName represents the assigned node for Reservation + by scheduler + type: string + phase: + description: Phase represents the Phase of Reservation + type: string + podsRef: + description: PodsRef represents the newly created Pods after + being preempted + items: + description: |- + ObjectReference contains enough information to let you inspect or modify the referred object. + --- + New uses of this type are discouraged because of difficulty describing its usage when embedded in APIs. + 1. Ignored fields. It includes many fields which are not generally honored. For instance, ResourceVersion and FieldPath are both very rarely valid in actual usage. + 2. Invalid usage help. It is impossible to add specific help for individual usage. In most embedded usages, there are particular + restrictions like, "must refer only to types A and B" or "UID not honored" or "name must be restricted". + Those cannot be well described when embedded. + 3. Inconsistent validation. Because the usages are different, the validation rules are different by usage, which makes it hard for users to predict what will happen. + 4. The fields are both imprecise and overly precise. Kind is not a precise mapping to a URL. This can produce ambiguity + during interpretation and require a REST mapping. In most cases, the dependency is on the group,resource tuple + and the version of the actual struct is irrelevant. + 5. We cannot easily change it. Because this type is embedded in many locations, updates to this type + will affect numerous schemas. Don't make new APIs embed an underspecified API type they do not control. + + + Instead of using this type, create a locally provided and used type that is well-focused on your reference. + For example, ServiceReferences for admission registration: https://github.com/kubernetes/api/blob/release-1.17/admissionregistration/v1/types.go#L533 . + properties: + apiVersion: + description: API version of the referent. + type: string + fieldPath: + description: |- + If referring to a piece of an object instead of an entire object, this string + should contain a valid JSON/Go field access statement, such as desiredState.manifest.containers[2]. + For example, if the object reference is to a container within a pod, this would take on a value like: + "spec.containers{name}" (where "name" refers to the name of the container that triggered + the event) or if no container name is specified "spec.containers[2]" (container with + index 2 in this pod). This syntax is chosen only to have some well-defined way of + referencing a part of an object. + TODO: this design is not final and this field is subject to change in the future. + type: string + kind: + description: |- + Kind of the referent. + More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds + type: string + name: + description: |- + Name of the referent. + More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + type: string + namespace: + description: |- + Namespace of the referent. + More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/namespaces/ + type: string + resourceVersion: + description: |- + Specific resourceVersion to which this reference is made, if any. + More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#concurrency-control-and-consistency + type: string + uid: + description: |- + UID of the referent. + More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#uids + type: string + type: object + x-kubernetes-map-type: atomic + type: array + preemptedPodRef: + description: PreemptedPodRef represents the Pod that be preempted + properties: + apiVersion: + description: API version of the referent. + type: string + fieldPath: + description: |- + If referring to a piece of an object instead of an entire object, this string + should contain a valid JSON/Go field access statement, such as desiredState.manifest.containers[2]. + For example, if the object reference is to a container within a pod, this would take on a value like: + "spec.containers{name}" (where "name" refers to the name of the container that triggered + the event) or if no container name is specified "spec.containers[2]" (container with + index 2 in this pod). This syntax is chosen only to have some well-defined way of + referencing a part of an object. + TODO: this design is not final and this field is subject to change in the future. + type: string + kind: + description: |- + Kind of the referent. + More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds + type: string + name: + description: |- + Name of the referent. + More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + type: string + namespace: + description: |- + Namespace of the referent. + More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/namespaces/ + type: string + resourceVersion: + description: |- + Specific resourceVersion to which this reference is made, if any. + More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#concurrency-control-and-consistency + type: string + uid: + description: |- + UID of the referent. + More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#uids + type: string + type: object + x-kubernetes-map-type: atomic + type: object + type: array + reason: + description: Reason represents a brief CamelCase message indicating + details about why the PodMigrationJob is in this state. + type: string + status: + description: |- + Status represents the current status of PodMigrationJob + e.g. ReservationCreated + type: string + type: object + type: object + served: true + storage: true + subresources: + status: {} + +{{- end }} diff --git a/versions/v1.6.0/templates/crd/scheduling.koordinator.sh_reservations.yaml b/versions/v1.6.0/templates/crd/scheduling.koordinator.sh_reservations.yaml new file mode 100644 index 0000000..82e850b --- /dev/null +++ b/versions/v1.6.0/templates/crd/scheduling.koordinator.sh_reservations.yaml @@ -0,0 +1,409 @@ +{{- if and .Values.crds.managed .Values.crds.reservations }} +--- +apiVersion: apiextensions.k8s.io/v1 +kind: CustomResourceDefinition +metadata: + annotations: + controller-gen.kubebuilder.io/version: v0.14.0 + name: reservations.scheduling.koordinator.sh +spec: + group: scheduling.koordinator.sh + names: + kind: Reservation + listKind: ReservationList + plural: reservations + singular: reservation + scope: Cluster + versions: + - additionalPrinterColumns: + - description: The phase of reservation + jsonPath: .status.phase + name: Phase + type: string + - jsonPath: .metadata.creationTimestamp + name: Age + type: date + - jsonPath: .status.nodeName + name: Node + type: string + - jsonPath: .spec.ttl + name: TTL + type: string + - jsonPath: .spec.expires + name: Expires + type: string + name: v1alpha1 + schema: + openAPIV3Schema: + description: |- + Reservation is the Schema for the reservation API. + A Reservation object is non-namespaced. + Any namespaced affinity/anti-affinity of reservation scheduling can be specified in the spec.template. + properties: + apiVersion: + description: |- + APIVersion defines the versioned schema of this representation of an object. + Servers should convert recognized schemas to the latest internal value, and + may reject unrecognized values. + More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources + type: string + kind: + description: |- + Kind is a string value representing the REST resource this object represents. + Servers may infer this from the endpoint the client submits requests to. + Cannot be updated. + In CamelCase. + More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds + type: string + metadata: + type: object + spec: + properties: + allocateOnce: + default: true + description: |- + When `AllocateOnce` is set, the reserved resources are only available for the first owner who allocates successfully + and are not allocatable to other owners anymore. Defaults to true. + type: boolean + allocatePolicy: + description: AllocatePolicy represents the allocation policy of reserved + resources that Reservation expects. + enum: + - Aligned + - Restricted + type: string + expires: + description: |- + Expired timestamp when the reservation is expected to expire. + If both `expires` and `ttl` are set, `expires` is checked first. + `expires` and `ttl` are mutually exclusive. Defaults to being set dynamically at runtime based on the `ttl`. + format: date-time + type: string + owners: + description: |- + Specify the owners who can allocate the reserved resources. + Multiple owner selectors and ORed. + items: + description: ReservationOwner indicates the owner specification + which can allocate reserved resources. + minProperties: 1 + properties: + controller: + properties: + apiVersion: + description: API version of the referent. + type: string + blockOwnerDeletion: + description: |- + If true, AND if the owner has the "foregroundDeletion" finalizer, then + the owner cannot be deleted from the key-value store until this + reference is removed. + See https://kubernetes.io/docs/concepts/architecture/garbage-collection/#foreground-deletion + for how the garbage collector interacts with this field and enforces the foreground deletion. + Defaults to false. + To set this field, a user needs "delete" permission of the owner, + otherwise 422 (Unprocessable Entity) will be returned. + type: boolean + controller: + description: If true, this reference points to the managing + controller. + type: boolean + kind: + description: |- + Kind of the referent. + More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds + type: string + name: + description: |- + Name of the referent. + More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names#names + type: string + namespace: + type: string + uid: + description: |- + UID of the referent. + More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names#uids + type: string + required: + - apiVersion + - kind + - name + - uid + type: object + x-kubernetes-map-type: atomic + labelSelector: + description: |- + A label selector is a label query over a set of resources. The result of matchLabels and + matchExpressions are ANDed. An empty label selector matches all objects. A null + label selector matches no objects. + properties: + matchExpressions: + description: matchExpressions is a list of label selector + requirements. The requirements are ANDed. + items: + description: |- + A label selector requirement is a selector that contains values, a key, and an operator that + relates the key and values. + properties: + key: + description: key is the label key that the selector + applies to. + type: string + operator: + description: |- + operator represents a key's relationship to a set of values. + Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: |- + values is an array of string values. If the operator is In or NotIn, + the values array must be non-empty. If the operator is Exists or DoesNotExist, + the values array must be empty. This array is replaced during a strategic + merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: |- + matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels + map is equivalent to an element of matchExpressions, whose key field is "key", the + operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + x-kubernetes-map-type: atomic + object: + description: Multiple field selectors are ANDed. + properties: + apiVersion: + description: API version of the referent. + type: string + fieldPath: + description: |- + If referring to a piece of an object instead of an entire object, this string + should contain a valid JSON/Go field access statement, such as desiredState.manifest.containers[2]. + For example, if the object reference is to a container within a pod, this would take on a value like: + "spec.containers{name}" (where "name" refers to the name of the container that triggered + the event) or if no container name is specified "spec.containers[2]" (container with + index 2 in this pod). This syntax is chosen only to have some well-defined way of + referencing a part of an object. + TODO: this design is not final and this field is subject to change in the future. + type: string + kind: + description: |- + Kind of the referent. + More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds + type: string + name: + description: |- + Name of the referent. + More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + type: string + namespace: + description: |- + Namespace of the referent. + More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/namespaces/ + type: string + resourceVersion: + description: |- + Specific resourceVersion to which this reference is made, if any. + More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#concurrency-control-and-consistency + type: string + uid: + description: |- + UID of the referent. + More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#uids + type: string + type: object + x-kubernetes-map-type: atomic + type: object + minItems: 1 + type: array + preAllocation: + description: |- + By default, the resources requirements of reservation (specified in `template.spec`) is filtered by whether the + node has sufficient free resources (i.e. Reservation Request < Node Free). + When `preAllocation` is set, the scheduler will skip this validation and allow overcommitment. The scheduled + reservation would be waiting to be available until free resources are sufficient. + type: boolean + taints: + description: |- + Specifies the reservation's taints. This can be toleranted by the reservation tolerance. + Eviction is not supported for NoExecute taints + items: + description: |- + The node this Taint is attached to has the "effect" on + any pod that does not tolerate the Taint. + properties: + effect: + description: |- + Required. The effect of the taint on pods + that do not tolerate the taint. + Valid effects are NoSchedule, PreferNoSchedule and NoExecute. + type: string + key: + description: Required. The taint key to be applied to a node. + type: string + timeAdded: + description: |- + TimeAdded represents the time at which the taint was added. + It is only written for NoExecute taints. + format: date-time + type: string + value: + description: The taint value corresponding to the taint key. + type: string + required: + - effect + - key + type: object + type: array + template: + description: |- + Template defines the scheduling requirements (resources, affinities, images, ...) processed by the scheduler just + like a normal pod. + If the `template.spec.nodeName` is specified, the scheduler will not choose another node but reserve resources on + the specified node. + x-kubernetes-preserve-unknown-fields: true + ttl: + default: 24h + description: |- + Time-to-Live period for the reservation. + `expires` and `ttl` are mutually exclusive. Defaults to 24h. Set 0 to disable expiration. + type: string + unschedulable: + description: Unschedulable controls reservation schedulability of + new pods. By default, reservation is schedulable. + type: boolean + required: + - owners + - template + type: object + status: + properties: + allocatable: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: Resource reserved and allocatable for owners. + type: object + allocated: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: Resource allocated by current owners. + type: object + conditions: + description: The `conditions` indicate the messages of reason why + the reservation is still pending. + items: + properties: + lastProbeTime: + format: date-time + type: string + lastTransitionTime: + format: date-time + type: string + message: + type: string + reason: + type: string + status: + type: string + type: + type: string + type: object + type: array + currentOwners: + description: Current resource owners which allocated the reservation + resources. + items: + description: |- + ObjectReference contains enough information to let you inspect or modify the referred object. + --- + New uses of this type are discouraged because of difficulty describing its usage when embedded in APIs. + 1. Ignored fields. It includes many fields which are not generally honored. For instance, ResourceVersion and FieldPath are both very rarely valid in actual usage. + 2. Invalid usage help. It is impossible to add specific help for individual usage. In most embedded usages, there are particular + restrictions like, "must refer only to types A and B" or "UID not honored" or "name must be restricted". + Those cannot be well described when embedded. + 3. Inconsistent validation. Because the usages are different, the validation rules are different by usage, which makes it hard for users to predict what will happen. + 4. The fields are both imprecise and overly precise. Kind is not a precise mapping to a URL. This can produce ambiguity + during interpretation and require a REST mapping. In most cases, the dependency is on the group,resource tuple + and the version of the actual struct is irrelevant. + 5. We cannot easily change it. Because this type is embedded in many locations, updates to this type + will affect numerous schemas. Don't make new APIs embed an underspecified API type they do not control. + + + Instead of using this type, create a locally provided and used type that is well-focused on your reference. + For example, ServiceReferences for admission registration: https://github.com/kubernetes/api/blob/release-1.17/admissionregistration/v1/types.go#L533 . + properties: + apiVersion: + description: API version of the referent. + type: string + fieldPath: + description: |- + If referring to a piece of an object instead of an entire object, this string + should contain a valid JSON/Go field access statement, such as desiredState.manifest.containers[2]. + For example, if the object reference is to a container within a pod, this would take on a value like: + "spec.containers{name}" (where "name" refers to the name of the container that triggered + the event) or if no container name is specified "spec.containers[2]" (container with + index 2 in this pod). This syntax is chosen only to have some well-defined way of + referencing a part of an object. + TODO: this design is not final and this field is subject to change in the future. + type: string + kind: + description: |- + Kind of the referent. + More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds + type: string + name: + description: |- + Name of the referent. + More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + type: string + namespace: + description: |- + Namespace of the referent. + More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/namespaces/ + type: string + resourceVersion: + description: |- + Specific resourceVersion to which this reference is made, if any. + More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#concurrency-control-and-consistency + type: string + uid: + description: |- + UID of the referent. + More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#uids + type: string + type: object + x-kubernetes-map-type: atomic + type: array + nodeName: + description: Name of node the reservation is scheduled on. + type: string + phase: + description: |- + The `phase` indicates whether is reservation is waiting for process, available to allocate or failed/expired to + get cleanup. + type: string + type: object + type: object + served: true + storage: true + subresources: + status: {} +{{- end}} \ No newline at end of file diff --git a/versions/v1.6.0/templates/crd/scheduling.sigs.k8s.io_elasticquotas.yaml b/versions/v1.6.0/templates/crd/scheduling.sigs.k8s.io_elasticquotas.yaml new file mode 100644 index 0000000..0f6eae0 --- /dev/null +++ b/versions/v1.6.0/templates/crd/scheduling.sigs.k8s.io_elasticquotas.yaml @@ -0,0 +1,84 @@ +{{- if and .Values.crds.managed .Values.crds.elasticquotas }} +--- +apiVersion: apiextensions.k8s.io/v1 +kind: CustomResourceDefinition +metadata: + annotations: + api-approved.kubernetes.io: https://github.com/kubernetes-sigs/scheduler-plugins/pull/52 + controller-gen.kubebuilder.io/version: v0.14.0 + name: elasticquotas.scheduling.sigs.k8s.io +spec: + group: scheduling.sigs.k8s.io + names: + kind: ElasticQuota + listKind: ElasticQuotaList + plural: elasticquotas + singular: elasticquota + scope: Namespaced + versions: + - name: v1alpha1 + schema: + openAPIV3Schema: + description: ElasticQuota sets elastic quota restrictions per namespace + properties: + apiVersion: + description: |- + APIVersion defines the versioned schema of this representation of an object. + Servers should convert recognized schemas to the latest internal value, and + may reject unrecognized values. + More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources + type: string + kind: + description: |- + Kind is a string value representing the REST resource this object represents. + Servers may infer this from the endpoint the client submits requests to. + Cannot be updated. + In CamelCase. + More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds + type: string + metadata: + type: object + spec: + description: ElasticQuotaSpec defines the Min and Max for Quota. + properties: + max: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: |- + Max is the set of desired max limits for each named resource. The usage of max is based on the resource configurations of + successfully scheduled pods. + type: object + min: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: Min is the set of desired guaranteed limits for each + named resource. + type: object + type: object + status: + description: ElasticQuotaStatus defines the observed use. + properties: + used: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: Used is the current observed total usage of the resource + in the namespace. + type: object + type: object + type: object + served: true + storage: true + +{{- end }} diff --git a/versions/v1.6.0/templates/crd/scheduling.sigs.k8s.io_podgroups.yaml b/versions/v1.6.0/templates/crd/scheduling.sigs.k8s.io_podgroups.yaml new file mode 100644 index 0000000..57f7664 --- /dev/null +++ b/versions/v1.6.0/templates/crd/scheduling.sigs.k8s.io_podgroups.yaml @@ -0,0 +1,107 @@ +{{- if and .Values.crds.managed .Values.crds.podgroups }} +--- +apiVersion: apiextensions.k8s.io/v1 +kind: CustomResourceDefinition +metadata: + annotations: + api-approved.kubernetes.io: https://github.com/kubernetes-sigs/scheduler-plugins/pull/52 + controller-gen.kubebuilder.io/version: v0.14.0 + name: podgroups.scheduling.sigs.k8s.io +spec: + group: scheduling.sigs.k8s.io + names: + kind: PodGroup + listKind: PodGroupList + plural: podgroups + singular: podgroup + scope: Namespaced + versions: + - name: v1alpha1 + schema: + openAPIV3Schema: + description: PodGroup is a collection of Pod; used for batch workload. + properties: + apiVersion: + description: |- + APIVersion defines the versioned schema of this representation of an object. + Servers should convert recognized schemas to the latest internal value, and + may reject unrecognized values. + More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources + type: string + kind: + description: |- + Kind is a string value representing the REST resource this object represents. + Servers may infer this from the endpoint the client submits requests to. + Cannot be updated. + In CamelCase. + More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds + type: string + metadata: + type: object + spec: + description: Specification of the desired behavior of the pod group. + properties: + minMember: + description: |- + MinMember defines the minimal number of members/tasks to run the pod group; + if there's not enough resources to start all tasks, the scheduler + will not start anyone. + format: int32 + type: integer + minResources: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: |- + MinResources defines the minimal resource of members/tasks to run the pod group; + if there's not enough resources to start all tasks, the scheduler + will not start anyone. + type: object + scheduleTimeoutSeconds: + description: ScheduleTimeoutSeconds defines the maximal time of members/tasks + to wait before run the pod group; + format: int32 + type: integer + type: object + status: + description: |- + Status represents the current information about a pod group. + This data may not be up to date. + properties: + failed: + description: The number of pods which reached phase Failed. + format: int32 + type: integer + occupiedBy: + description: |- + OccupiedBy marks the workload (e.g., deployment, statefulset) UID that occupy the podgroup. + It is empty if not initialized. + type: string + phase: + description: Current phase of PodGroup. + type: string + running: + description: The number of actively running pods. + format: int32 + type: integer + scheduleStartTime: + description: ScheduleStartTime of the group + format: date-time + type: string + scheduled: + description: The number of actively running pods. + format: int32 + type: integer + succeeded: + description: The number of pods which reached phase Succeeded. + format: int32 + type: integer + type: object + type: object + served: true + storage: true + +{{- end }} diff --git a/versions/v1.6.0/templates/crd/slo.koordinator.sh_nodemetrics.yaml b/versions/v1.6.0/templates/crd/slo.koordinator.sh_nodemetrics.yaml new file mode 100644 index 0000000..da44542 --- /dev/null +++ b/versions/v1.6.0/templates/crd/slo.koordinator.sh_nodemetrics.yaml @@ -0,0 +1,1014 @@ +{{- if and .Values.crds.managed .Values.crds.nodemetrics }} +--- +apiVersion: apiextensions.k8s.io/v1 +kind: CustomResourceDefinition +metadata: + annotations: + controller-gen.kubebuilder.io/version: v0.14.0 + name: nodemetrics.slo.koordinator.sh +spec: + group: slo.koordinator.sh + names: + kind: NodeMetric + listKind: NodeMetricList + plural: nodemetrics + singular: nodemetric + scope: Cluster + versions: + - name: v1alpha1 + schema: + openAPIV3Schema: + description: NodeMetric is the Schema for the nodemetrics API + properties: + apiVersion: + description: |- + APIVersion defines the versioned schema of this representation of an object. + Servers should convert recognized schemas to the latest internal value, and + may reject unrecognized values. + More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources + type: string + kind: + description: |- + Kind is a string value representing the REST resource this object represents. + Servers may infer this from the endpoint the client submits requests to. + Cannot be updated. + In CamelCase. + More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds + type: string + metadata: + type: object + spec: + description: NodeMetricSpec defines the desired state of NodeMetric + properties: + metricCollectPolicy: + description: CollectPolicy defines the Metric collection policy + properties: + aggregateDurationSeconds: + description: AggregateDurationSeconds represents the aggregation + period in seconds + format: int64 + type: integer + nodeAggregatePolicy: + description: NodeAggregatePolicy represents the target grain of + node aggregated usage + properties: + durations: + items: + type: string + type: array + type: object + nodeMemoryCollectPolicy: + description: NodeMemoryPolicy represents apply which method collect + memory info + enum: + - usageWithHotPageCache + - usageWithoutPageCache + - usageWithPageCache + type: string + reportIntervalSeconds: + description: ReportIntervalSeconds represents the report period + in seconds + format: int64 + type: integer + type: object + type: object + status: + description: NodeMetricStatus defines the observed state of NodeMetric + properties: + hostApplicationMetric: + description: HostApplicationMetric contains the metrics of out-out-band + applications on node. + items: + properties: + name: + description: Name of the host application + type: string + priority: + description: Priority class of the application + type: string + qos: + description: QoS class of the application + type: string + usage: + description: Resource usage of the host application + properties: + devices: + items: + properties: + health: + default: false + description: Health indicates whether the device is + normal + type: boolean + id: + description: UUID represents the UUID of device + type: string + labels: + additionalProperties: + type: string + description: Labels represents the device properties + that can be used to organize and categorize (scope + and select) objects + type: object + minor: + description: Minor represents the Minor number of + Device, starting from 0 + format: int32 + type: integer + moduleID: + description: ModuleID represents the physical id of + Device + format: int32 + type: integer + resources: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: Resources is a set of (resource name, + quantity) pairs + type: object + topology: + description: Topology represents the topology information + about the device + properties: + busID: + description: BusID is the domain:bus:device.function + formatted identifier of PCI/PCIE device + type: string + nodeID: + description: NodeID is the ID of NUMA Node to + which the device belongs, it should be unique + across different CPU Sockets + format: int32 + type: integer + pcieID: + description: PCIEID is the ID of PCIE Switch to + which the device is connected, it should be + unique across difference NUMANodes + type: string + socketID: + description: SocketID is the ID of CPU Socket + to which the device belongs + format: int32 + type: integer + required: + - nodeID + - pcieID + - socketID + type: object + type: + description: Type represents the type of device + type: string + vfGroups: + description: VFGroups represents the virtual function + devices + items: + properties: + labels: + additionalProperties: + type: string + description: Labels represents the Virtual Function + properties that can be used to organize and + categorize (scope and select) objects + type: object + vfs: + description: VFs are the virtual function devices + which belong to the group + items: + properties: + busID: + description: BusID is the domain:bus:device.function + formatted identifier of PCI/PCIE virtual + function device + type: string + minor: + description: Minor represents the Minor + number of VirtualFunction, starting + from 0, used to identify virtual function. + format: int32 + type: integer + required: + - minor + type: object + type: array + type: object + type: array + required: + - health + type: object + type: array + resources: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: ResourceList is a set of (resource name, quantity) + pairs. + type: object + type: object + type: object + type: array + nodeMetric: + description: NodeMetric contains the metrics for this node. + properties: + aggregatedNodeUsages: + description: AggregatedNodeUsages will report only if there are + enough samples + items: + properties: + duration: + type: string + usage: + additionalProperties: + properties: + devices: + items: + properties: + health: + default: false + description: Health indicates whether the device + is normal + type: boolean + id: + description: UUID represents the UUID of device + type: string + labels: + additionalProperties: + type: string + description: Labels represents the device properties + that can be used to organize and categorize + (scope and select) objects + type: object + minor: + description: Minor represents the Minor number + of Device, starting from 0 + format: int32 + type: integer + moduleID: + description: ModuleID represents the physical + id of Device + format: int32 + type: integer + resources: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: Resources is a set of (resource + name, quantity) pairs + type: object + topology: + description: Topology represents the topology + information about the device + properties: + busID: + description: BusID is the domain:bus:device.function + formatted identifier of PCI/PCIE device + type: string + nodeID: + description: NodeID is the ID of NUMA Node + to which the device belongs, it should + be unique across different CPU Sockets + format: int32 + type: integer + pcieID: + description: PCIEID is the ID of PCIE Switch + to which the device is connected, it should + be unique across difference NUMANodes + type: string + socketID: + description: SocketID is the ID of CPU Socket + to which the device belongs + format: int32 + type: integer + required: + - nodeID + - pcieID + - socketID + type: object + type: + description: Type represents the type of device + type: string + vfGroups: + description: VFGroups represents the virtual + function devices + items: + properties: + labels: + additionalProperties: + type: string + description: Labels represents the Virtual + Function properties that can be used + to organize and categorize (scope and + select) objects + type: object + vfs: + description: VFs are the virtual function + devices which belong to the group + items: + properties: + busID: + description: BusID is the domain:bus:device.function + formatted identifier of PCI/PCIE + virtual function device + type: string + minor: + description: Minor represents the + Minor number of VirtualFunction, + starting from 0, used to identify + virtual function. + format: int32 + type: integer + required: + - minor + type: object + type: array + type: object + type: array + required: + - health + type: object + type: array + resources: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: ResourceList is a set of (resource name, + quantity) pairs. + type: object + type: object + type: object + type: object + type: array + aggregatedSystemUsages: + description: |- + AggregatedSystemUsages will report only if there are enough samples + Deleted pods will be excluded during aggregation + items: + properties: + duration: + type: string + usage: + additionalProperties: + properties: + devices: + items: + properties: + health: + default: false + description: Health indicates whether the device + is normal + type: boolean + id: + description: UUID represents the UUID of device + type: string + labels: + additionalProperties: + type: string + description: Labels represents the device properties + that can be used to organize and categorize + (scope and select) objects + type: object + minor: + description: Minor represents the Minor number + of Device, starting from 0 + format: int32 + type: integer + moduleID: + description: ModuleID represents the physical + id of Device + format: int32 + type: integer + resources: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: Resources is a set of (resource + name, quantity) pairs + type: object + topology: + description: Topology represents the topology + information about the device + properties: + busID: + description: BusID is the domain:bus:device.function + formatted identifier of PCI/PCIE device + type: string + nodeID: + description: NodeID is the ID of NUMA Node + to which the device belongs, it should + be unique across different CPU Sockets + format: int32 + type: integer + pcieID: + description: PCIEID is the ID of PCIE Switch + to which the device is connected, it should + be unique across difference NUMANodes + type: string + socketID: + description: SocketID is the ID of CPU Socket + to which the device belongs + format: int32 + type: integer + required: + - nodeID + - pcieID + - socketID + type: object + type: + description: Type represents the type of device + type: string + vfGroups: + description: VFGroups represents the virtual + function devices + items: + properties: + labels: + additionalProperties: + type: string + description: Labels represents the Virtual + Function properties that can be used + to organize and categorize (scope and + select) objects + type: object + vfs: + description: VFs are the virtual function + devices which belong to the group + items: + properties: + busID: + description: BusID is the domain:bus:device.function + formatted identifier of PCI/PCIE + virtual function device + type: string + minor: + description: Minor represents the + Minor number of VirtualFunction, + starting from 0, used to identify + virtual function. + format: int32 + type: integer + required: + - minor + type: object + type: array + type: object + type: array + required: + - health + type: object + type: array + resources: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: ResourceList is a set of (resource name, + quantity) pairs. + type: object + type: object + type: object + type: object + type: array + nodeUsage: + description: NodeUsage is the total resource usage of node + properties: + devices: + items: + properties: + health: + default: false + description: Health indicates whether the device is + normal + type: boolean + id: + description: UUID represents the UUID of device + type: string + labels: + additionalProperties: + type: string + description: Labels represents the device properties + that can be used to organize and categorize (scope + and select) objects + type: object + minor: + description: Minor represents the Minor number of Device, + starting from 0 + format: int32 + type: integer + moduleID: + description: ModuleID represents the physical id of + Device + format: int32 + type: integer + resources: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: Resources is a set of (resource name, quantity) + pairs + type: object + topology: + description: Topology represents the topology information + about the device + properties: + busID: + description: BusID is the domain:bus:device.function + formatted identifier of PCI/PCIE device + type: string + nodeID: + description: NodeID is the ID of NUMA Node to which + the device belongs, it should be unique across + different CPU Sockets + format: int32 + type: integer + pcieID: + description: PCIEID is the ID of PCIE Switch to + which the device is connected, it should be unique + across difference NUMANodes + type: string + socketID: + description: SocketID is the ID of CPU Socket to + which the device belongs + format: int32 + type: integer + required: + - nodeID + - pcieID + - socketID + type: object + type: + description: Type represents the type of device + type: string + vfGroups: + description: VFGroups represents the virtual function + devices + items: + properties: + labels: + additionalProperties: + type: string + description: Labels represents the Virtual Function + properties that can be used to organize and + categorize (scope and select) objects + type: object + vfs: + description: VFs are the virtual function devices + which belong to the group + items: + properties: + busID: + description: BusID is the domain:bus:device.function + formatted identifier of PCI/PCIE virtual + function device + type: string + minor: + description: Minor represents the Minor + number of VirtualFunction, starting from + 0, used to identify virtual function. + format: int32 + type: integer + required: + - minor + type: object + type: array + type: object + type: array + required: + - health + type: object + type: array + resources: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: ResourceList is a set of (resource name, quantity) + pairs. + type: object + type: object + systemUsage: + description: SystemUsage is the resource usage of daemon processes + and OS kernel, calculated by `NodeUsage - sum(podUsage)` + properties: + devices: + items: + properties: + health: + default: false + description: Health indicates whether the device is + normal + type: boolean + id: + description: UUID represents the UUID of device + type: string + labels: + additionalProperties: + type: string + description: Labels represents the device properties + that can be used to organize and categorize (scope + and select) objects + type: object + minor: + description: Minor represents the Minor number of Device, + starting from 0 + format: int32 + type: integer + moduleID: + description: ModuleID represents the physical id of + Device + format: int32 + type: integer + resources: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: Resources is a set of (resource name, quantity) + pairs + type: object + topology: + description: Topology represents the topology information + about the device + properties: + busID: + description: BusID is the domain:bus:device.function + formatted identifier of PCI/PCIE device + type: string + nodeID: + description: NodeID is the ID of NUMA Node to which + the device belongs, it should be unique across + different CPU Sockets + format: int32 + type: integer + pcieID: + description: PCIEID is the ID of PCIE Switch to + which the device is connected, it should be unique + across difference NUMANodes + type: string + socketID: + description: SocketID is the ID of CPU Socket to + which the device belongs + format: int32 + type: integer + required: + - nodeID + - pcieID + - socketID + type: object + type: + description: Type represents the type of device + type: string + vfGroups: + description: VFGroups represents the virtual function + devices + items: + properties: + labels: + additionalProperties: + type: string + description: Labels represents the Virtual Function + properties that can be used to organize and + categorize (scope and select) objects + type: object + vfs: + description: VFs are the virtual function devices + which belong to the group + items: + properties: + busID: + description: BusID is the domain:bus:device.function + formatted identifier of PCI/PCIE virtual + function device + type: string + minor: + description: Minor represents the Minor + number of VirtualFunction, starting from + 0, used to identify virtual function. + format: int32 + type: integer + required: + - minor + type: object + type: array + type: object + type: array + required: + - health + type: object + type: array + resources: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: ResourceList is a set of (resource name, quantity) + pairs. + type: object + type: object + type: object + podsMetric: + description: PodsMetric contains the metrics for pods belong to this + node. + items: + properties: + extensions: + description: Third party extensions for PodMetric + type: object + x-kubernetes-preserve-unknown-fields: true + name: + type: string + namespace: + type: string + podUsage: + properties: + devices: + items: + properties: + health: + default: false + description: Health indicates whether the device is + normal + type: boolean + id: + description: UUID represents the UUID of device + type: string + labels: + additionalProperties: + type: string + description: Labels represents the device properties + that can be used to organize and categorize (scope + and select) objects + type: object + minor: + description: Minor represents the Minor number of + Device, starting from 0 + format: int32 + type: integer + moduleID: + description: ModuleID represents the physical id of + Device + format: int32 + type: integer + resources: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: Resources is a set of (resource name, + quantity) pairs + type: object + topology: + description: Topology represents the topology information + about the device + properties: + busID: + description: BusID is the domain:bus:device.function + formatted identifier of PCI/PCIE device + type: string + nodeID: + description: NodeID is the ID of NUMA Node to + which the device belongs, it should be unique + across different CPU Sockets + format: int32 + type: integer + pcieID: + description: PCIEID is the ID of PCIE Switch to + which the device is connected, it should be + unique across difference NUMANodes + type: string + socketID: + description: SocketID is the ID of CPU Socket + to which the device belongs + format: int32 + type: integer + required: + - nodeID + - pcieID + - socketID + type: object + type: + description: Type represents the type of device + type: string + vfGroups: + description: VFGroups represents the virtual function + devices + items: + properties: + labels: + additionalProperties: + type: string + description: Labels represents the Virtual Function + properties that can be used to organize and + categorize (scope and select) objects + type: object + vfs: + description: VFs are the virtual function devices + which belong to the group + items: + properties: + busID: + description: BusID is the domain:bus:device.function + formatted identifier of PCI/PCIE virtual + function device + type: string + minor: + description: Minor represents the Minor + number of VirtualFunction, starting + from 0, used to identify virtual function. + format: int32 + type: integer + required: + - minor + type: object + type: array + type: object + type: array + required: + - health + type: object + type: array + resources: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: ResourceList is a set of (resource name, quantity) + pairs. + type: object + type: object + priority: + description: Priority class of the application + type: string + qos: + description: QoS class of the application + type: string + type: object + type: array + prodReclaimableMetric: + description: ProdReclaimableMetric is the indicator statistics of + Prod type resources reclaimable + properties: + resource: + description: Resource is the resource usage of the prediction + properties: + devices: + items: + properties: + health: + default: false + description: Health indicates whether the device is + normal + type: boolean + id: + description: UUID represents the UUID of device + type: string + labels: + additionalProperties: + type: string + description: Labels represents the device properties + that can be used to organize and categorize (scope + and select) objects + type: object + minor: + description: Minor represents the Minor number of Device, + starting from 0 + format: int32 + type: integer + moduleID: + description: ModuleID represents the physical id of + Device + format: int32 + type: integer + resources: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: Resources is a set of (resource name, quantity) + pairs + type: object + topology: + description: Topology represents the topology information + about the device + properties: + busID: + description: BusID is the domain:bus:device.function + formatted identifier of PCI/PCIE device + type: string + nodeID: + description: NodeID is the ID of NUMA Node to which + the device belongs, it should be unique across + different CPU Sockets + format: int32 + type: integer + pcieID: + description: PCIEID is the ID of PCIE Switch to + which the device is connected, it should be unique + across difference NUMANodes + type: string + socketID: + description: SocketID is the ID of CPU Socket to + which the device belongs + format: int32 + type: integer + required: + - nodeID + - pcieID + - socketID + type: object + type: + description: Type represents the type of device + type: string + vfGroups: + description: VFGroups represents the virtual function + devices + items: + properties: + labels: + additionalProperties: + type: string + description: Labels represents the Virtual Function + properties that can be used to organize and + categorize (scope and select) objects + type: object + vfs: + description: VFs are the virtual function devices + which belong to the group + items: + properties: + busID: + description: BusID is the domain:bus:device.function + formatted identifier of PCI/PCIE virtual + function device + type: string + minor: + description: Minor represents the Minor + number of VirtualFunction, starting from + 0, used to identify virtual function. + format: int32 + type: integer + required: + - minor + type: object + type: array + type: object + type: array + required: + - health + type: object + type: array + resources: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: ResourceList is a set of (resource name, quantity) + pairs. + type: object + type: object + type: object + updateTime: + description: UpdateTime is the last time this NodeMetric was updated. + format: date-time + type: string + type: object + type: object + served: true + storage: true + subresources: + status: {} + +{{- end }} diff --git a/versions/v1.6.0/templates/crd/slo.koordinator.sh_nodeslos.yaml b/versions/v1.6.0/templates/crd/slo.koordinator.sh_nodeslos.yaml new file mode 100644 index 0000000..1b6562b --- /dev/null +++ b/versions/v1.6.0/templates/crd/slo.koordinator.sh_nodeslos.yaml @@ -0,0 +1,1759 @@ +{{- if and .Values.crds.managed .Values.crds.nodeslos }} +--- +apiVersion: apiextensions.k8s.io/v1 +kind: CustomResourceDefinition +metadata: + annotations: + controller-gen.kubebuilder.io/version: v0.14.0 + name: nodeslos.slo.koordinator.sh +spec: + group: slo.koordinator.sh + names: + kind: NodeSLO + listKind: NodeSLOList + plural: nodeslos + singular: nodeslo + scope: Cluster + versions: + - name: v1alpha1 + schema: + openAPIV3Schema: + description: NodeSLO is the Schema for the nodeslos API + properties: + apiVersion: + description: |- + APIVersion defines the versioned schema of this representation of an object. + Servers should convert recognized schemas to the latest internal value, and + may reject unrecognized values. + More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources + type: string + kind: + description: |- + Kind is a string value representing the REST resource this object represents. + Servers may infer this from the endpoint the client submits requests to. + Cannot be updated. + In CamelCase. + More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds + type: string + metadata: + type: object + spec: + description: NodeSLOSpec defines the desired state of NodeSLO + properties: + cpuBurstStrategy: + description: CPU Burst Strategy + properties: + cfsQuotaBurstPercent: + description: pod cfs quota scale up ceil percentage, default = + 300 (300%) + format: int64 + type: integer + cfsQuotaBurstPeriodSeconds: + description: specifies a period of time for pod can use at burst, + default = -1 (unlimited) + format: int64 + type: integer + cpuBurstPercent: + description: 'cpu burst percentage for setting cpu.cfs_burst_us, + legal range: [0, 10000], default as 1000 (1000%)' + format: int64 + maximum: 10000 + minimum: 0 + type: integer + policy: + type: string + sharePoolThresholdPercent: + description: scale down cfs quota if node cpu overload, default + = 50 + format: int64 + type: integer + type: object + extensions: + description: Third party extensions for NodeSLO + type: object + x-kubernetes-preserve-unknown-fields: true + hostApplications: + description: QoS management for out-of-band applications + items: + description: HostApplicationSpec describes the QoS management for + out-out-band applications on node + properties: + cgroupPath: + description: Optional, defines the host cgroup configuration, + use default if not specified according to priority and qos + properties: + base: + description: cgroup base dir, the format is various across + cgroup drivers + type: string + parentDir: + description: cgroup parent path under base dir + type: string + relativePath: + description: cgroup relative path under parent dir + type: string + type: object + name: + type: string + priority: + description: Priority class of the application + type: string + qos: + description: QoS class of the application + type: string + strategy: + description: QoS Strategy of host application + type: object + type: object + type: array + resourceQOSStrategy: + description: QoS config strategy for pods of different qos-class + properties: + beClass: + description: ResourceQOS for BE pods. + properties: + blkioQOS: + properties: + blocks: + items: + properties: + ioCfg: + properties: + enableUserModel: + description: |- + configure the cost model of blkio-cost manually + whether the user model is enabled. Default value: false + type: boolean + ioWeightPercent: + description: 'This field is used to set the + weight of a sub-group. Default value: 100. + Valid values: 1 to 100.' + format: int64 + maximum: 100 + minimum: 1 + type: integer + modelReadBPS: + description: the read BPS of user model + format: int64 + minimum: 1 + type: integer + modelReadRandIOPS: + description: the random read iops of user model + format: int64 + minimum: 1 + type: integer + modelReadSeqIOPS: + description: the sequential read iops of user + model + format: int64 + minimum: 1 + type: integer + modelWriteBPS: + description: the write BPS of user model + format: int64 + minimum: 1 + type: integer + modelWriteRandIOPS: + description: the random write iops of user model + format: int64 + minimum: 1 + type: integer + modelWriteSeqIOPS: + description: the sequential write iops of user + model + format: int64 + minimum: 1 + type: integer + readBPS: + description: |- + Throttling of throughput + The value is set to 0, which indicates that the feature is disabled. + format: int64 + minimum: 0 + type: integer + readIOPS: + description: |- + Throttling of IOPS + The value is set to 0, which indicates that the feature is disabled. + format: int64 + minimum: 0 + type: integer + readLatency: + description: |- + Configure the weight-based throttling feature of blk-iocost + Only used for RootClass + After blk-iocost is enabled, the kernel calculates the proportion of requests that exceed the read or write latency threshold out of all requests. When the proportion is greater than the read or write latency percentile (95%), the kernel considers the disk to be saturated and reduces the rate at which requests are sent to the disk. + the read latency threshold. Unit: microseconds. + format: int64 + type: integer + readLatencyPercent: + description: the read latency percentile + format: int64 + maximum: 100 + minimum: 0 + type: integer + writeBPS: + format: int64 + minimum: 0 + type: integer + writeIOPS: + format: int64 + minimum: 0 + type: integer + writeLatency: + description: 'the write latency threshold. Unit: + microseconds.' + format: int64 + type: integer + writeLatencyPercent: + description: the write latency percentile + format: int64 + maximum: 100 + minimum: 0 + type: integer + type: object + name: + type: string + type: + type: string + type: object + type: array + enable: + type: boolean + type: object + cpuQOS: + description: CPUQOSCfg stores node-level config of cpu qos + properties: + coreExpeller: + description: |- + whether pods of the QoS class can expel the cgroup idle pods at the SMT-level. default = false + If set to true, pods of this QoS will use a dedicated core sched group for noise clean with the SchedIdle pods. + NOTE: It takes effect if cpuPolicy = "coreSched". + type: boolean + enable: + description: Enable indicates whether the cpu qos is enabled. + type: boolean + groupIdentity: + description: |- + group identity value for pods, default = 0 + NOTE: It takes effect if cpuPolicy = "groupIdentity". + format: int64 + type: integer + schedIdle: + description: |- + cpu.idle value for pods, default = 0. + `1` means using SCHED_IDLE. + CGroup Idle (introduced since mainline Linux 5.15): https://lore.kernel.org/lkml/162971078674.25758.15464079371945307825.tip-bot2@tip-bot2/#r + NOTE: It takes effect if cpuPolicy = "coreSched". + format: int64 + type: integer + type: object + memoryQOS: + description: MemoryQOSCfg stores node-level config of memory + qos + properties: + enable: + description: |- + Enable indicates whether the memory qos is enabled (default: false). + This field is used for node-level control, while pod-level configuration is done with MemoryQOS and `Policy` + instead of an `Enable` option. Please view the differences between MemoryQOSCfg and PodMemoryQOSConfig structs. + type: boolean + lowLimitPercent: + description: |- + LowLimitPercent specifies the lowLimitFactor percentage to calculate `memory.low`, which TRIES BEST + protecting memory from global reclamation when memory usage does not exceed the low limit unless no unprotected + memcg can be reclaimed. + NOTE: `memory.low` should be larger than `memory.min`. If spec.requests.memory == spec.limits.memory, + pod `memory.low` and `memory.high` become invalid, while `memory.wmark_ratio` is still in effect. + Close: 0. + format: int64 + minimum: 0 + type: integer + minLimitPercent: + description: |- + memcg qos + If enabled, memcg qos will be set by the agent, where some fields are implicitly calculated from pod spec. + 1. `memory.min` := spec.requests.memory * minLimitFactor / 100 (use 0 if requests.memory is not set) + 2. `memory.low` := spec.requests.memory * lowLimitFactor / 100 (use 0 if requests.memory is not set) + 3. `memory.limit_in_bytes` := spec.limits.memory (set $node.allocatable.memory if limits.memory is not set) + 4. `memory.high` := floor[(spec.requests.memory + throttlingFactor / 100 * (memory.limit_in_bytes or node allocatable memory - spec.requests.memory))/pageSize] * pageSize + MinLimitPercent specifies the minLimitFactor percentage to calculate `memory.min`, which protects memory + from global reclamation when memory usage does not exceed the min limit. + Close: 0. + format: int64 + minimum: 0 + type: integer + oomKillGroup: + format: int64 + type: integer + priority: + format: int64 + type: integer + priorityEnable: + description: 'TODO: enhance the usages of oom priority + and oom kill group' + format: int64 + type: integer + throttlingPercent: + description: |- + ThrottlingPercent specifies the throttlingFactor percentage to calculate `memory.high` with pod + memory.limits or node allocatable memory, which triggers memcg direct reclamation when memory usage exceeds. + Lower the factor brings more heavier reclaim pressure. + Close: 0. + format: int64 + minimum: 0 + type: integer + wmarkMinAdj: + description: |- + wmark_min_adj (Anolis OS required) + WmarkMinAdj specifies `memory.wmark_min_adj` which adjusts per-memcg threshold for global memory + reclamation. Lower the factor brings later reclamation. + The adjustment uses different formula for different value range. + [-25, 0)：global_wmark_min' = global_wmark_min + (global_wmark_min - 0) * wmarkMinAdj + (0, 50]：global_wmark_min' = global_wmark_min + (global_wmark_low - global_wmark_min) * wmarkMinAdj + Close: [LSR:0, LS:0, BE:0]. Recommended: [LSR:-25, LS:-25, BE:50]. + format: int64 + maximum: 50 + minimum: -25 + type: integer + wmarkRatio: + description: |- + wmark_ratio (Anolis OS required) + Async memory reclamation is triggered when cgroup memory usage exceeds `memory.wmark_high` and the reclamation + stops when usage is below `memory.wmark_low`. Basically, + `memory.wmark_high` := min(memory.high, memory.limit_in_bytes) * memory.memory.wmark_ratio + `memory.wmark_low` := min(memory.high, memory.limit_in_bytes) * (memory.wmark_ratio - memory.wmark_scale_factor) + WmarkRatio specifies `memory.wmark_ratio` that help calculate `memory.wmark_high`, which triggers async + memory reclamation when memory usage exceeds. + Close: 0. Recommended: 95. + format: int64 + maximum: 100 + minimum: 0 + type: integer + wmarkScalePermill: + description: |- + WmarkScalePermill specifies `memory.wmark_scale_factor` that helps calculate `memory.wmark_low`, which + stops async memory reclamation when memory usage belows. + Close: 50. Recommended: 20. + format: int64 + maximum: 1000 + minimum: 1 + type: integer + type: object + networkQOS: + properties: + egressLimit: + anyOf: + - type: integer + - type: string + default: 100 + description: |- + EgressLimit describes the maximum network bandwidth can be used in the egress direction, + unit: bps(bytes per second), two expressions are supported，int and string, + int: percentage based on total bandwidth，valid in 0-100 + string: a specific network bandwidth value, eg: 50M. + x-kubernetes-int-or-string: true + egressRequest: + anyOf: + - type: integer + - type: string + default: 0 + description: |- + EgressRequest describes the minimum network bandwidth guaranteed in the egress direction. + unit: bps(bytes per second), two expressions are supported，int and string, + int: percentage based on total bandwidth，valid in 0-100 + string: a specific network bandwidth value, eg: 50M. + x-kubernetes-int-or-string: true + enable: + type: boolean + ingressLimit: + anyOf: + - type: integer + - type: string + default: 100 + description: |- + IngressLimit describes the maximum network bandwidth can be used in the ingress direction, + unit: bps(bytes per second), two expressions are supported，int and string, + int: percentage based on total bandwidth，valid in 0-100 + string: a specific network bandwidth value, eg: 50M. + x-kubernetes-int-or-string: true + ingressRequest: + anyOf: + - type: integer + - type: string + default: 0 + description: |- + IngressRequest describes the minimum network bandwidth guaranteed in the ingress direction. + unit: bps(bytes per second), two expressions are supported，int and string, + int: percentage based on total bandwidth，valid in 0-100 + string: a specific network bandwidth value, eg: 50M. + x-kubernetes-int-or-string: true + type: object + resctrlQOS: + description: ResctrlQOSCfg stores node-level config of resctrl + qos + properties: + catRangeEndPercent: + description: LLC available range end for pods by percentage + format: int64 + maximum: 100 + minimum: 0 + type: integer + catRangeStartPercent: + description: LLC available range start for pods by percentage + format: int64 + maximum: 100 + minimum: 0 + type: integer + enable: + description: Enable indicates whether the resctrl qos + is enabled. + type: boolean + mbaPercent: + description: MBA percent + format: int64 + maximum: 100 + minimum: 0 + type: integer + type: object + type: object + cgroupRoot: + description: ResourceQOS for root cgroup. + properties: + blkioQOS: + properties: + blocks: + items: + properties: + ioCfg: + properties: + enableUserModel: + description: |- + configure the cost model of blkio-cost manually + whether the user model is enabled. Default value: false + type: boolean + ioWeightPercent: + description: 'This field is used to set the + weight of a sub-group. Default value: 100. + Valid values: 1 to 100.' + format: int64 + maximum: 100 + minimum: 1 + type: integer + modelReadBPS: + description: the read BPS of user model + format: int64 + minimum: 1 + type: integer + modelReadRandIOPS: + description: the random read iops of user model + format: int64 + minimum: 1 + type: integer + modelReadSeqIOPS: + description: the sequential read iops of user + model + format: int64 + minimum: 1 + type: integer + modelWriteBPS: + description: the write BPS of user model + format: int64 + minimum: 1 + type: integer + modelWriteRandIOPS: + description: the random write iops of user model + format: int64 + minimum: 1 + type: integer + modelWriteSeqIOPS: + description: the sequential write iops of user + model + format: int64 + minimum: 1 + type: integer + readBPS: + description: |- + Throttling of throughput + The value is set to 0, which indicates that the feature is disabled. + format: int64 + minimum: 0 + type: integer + readIOPS: + description: |- + Throttling of IOPS + The value is set to 0, which indicates that the feature is disabled. + format: int64 + minimum: 0 + type: integer + readLatency: + description: |- + Configure the weight-based throttling feature of blk-iocost + Only used for RootClass + After blk-iocost is enabled, the kernel calculates the proportion of requests that exceed the read or write latency threshold out of all requests. When the proportion is greater than the read or write latency percentile (95%), the kernel considers the disk to be saturated and reduces the rate at which requests are sent to the disk. + the read latency threshold. Unit: microseconds. + format: int64 + type: integer + readLatencyPercent: + description: the read latency percentile + format: int64 + maximum: 100 + minimum: 0 + type: integer + writeBPS: + format: int64 + minimum: 0 + type: integer + writeIOPS: + format: int64 + minimum: 0 + type: integer + writeLatency: + description: 'the write latency threshold. Unit: + microseconds.' + format: int64 + type: integer + writeLatencyPercent: + description: the write latency percentile + format: int64 + maximum: 100 + minimum: 0 + type: integer + type: object + name: + type: string + type: + type: string + type: object + type: array + enable: + type: boolean + type: object + cpuQOS: + description: CPUQOSCfg stores node-level config of cpu qos + properties: + coreExpeller: + description: |- + whether pods of the QoS class can expel the cgroup idle pods at the SMT-level. default = false + If set to true, pods of this QoS will use a dedicated core sched group for noise clean with the SchedIdle pods. + NOTE: It takes effect if cpuPolicy = "coreSched". + type: boolean + enable: + description: Enable indicates whether the cpu qos is enabled. + type: boolean + groupIdentity: + description: |- + group identity value for pods, default = 0 + NOTE: It takes effect if cpuPolicy = "groupIdentity". + format: int64 + type: integer + schedIdle: + description: |- + cpu.idle value for pods, default = 0. + `1` means using SCHED_IDLE. + CGroup Idle (introduced since mainline Linux 5.15): https://lore.kernel.org/lkml/162971078674.25758.15464079371945307825.tip-bot2@tip-bot2/#r + NOTE: It takes effect if cpuPolicy = "coreSched". + format: int64 + type: integer + type: object + memoryQOS: + description: MemoryQOSCfg stores node-level config of memory + qos + properties: + enable: + description: |- + Enable indicates whether the memory qos is enabled (default: false). + This field is used for node-level control, while pod-level configuration is done with MemoryQOS and `Policy` + instead of an `Enable` option. Please view the differences between MemoryQOSCfg and PodMemoryQOSConfig structs. + type: boolean + lowLimitPercent: + description: |- + LowLimitPercent specifies the lowLimitFactor percentage to calculate `memory.low`, which TRIES BEST + protecting memory from global reclamation when memory usage does not exceed the low limit unless no unprotected + memcg can be reclaimed. + NOTE: `memory.low` should be larger than `memory.min`. If spec.requests.memory == spec.limits.memory, + pod `memory.low` and `memory.high` become invalid, while `memory.wmark_ratio` is still in effect. + Close: 0. + format: int64 + minimum: 0 + type: integer + minLimitPercent: + description: |- + memcg qos + If enabled, memcg qos will be set by the agent, where some fields are implicitly calculated from pod spec. + 1. `memory.min` := spec.requests.memory * minLimitFactor / 100 (use 0 if requests.memory is not set) + 2. `memory.low` := spec.requests.memory * lowLimitFactor / 100 (use 0 if requests.memory is not set) + 3. `memory.limit_in_bytes` := spec.limits.memory (set $node.allocatable.memory if limits.memory is not set) + 4. `memory.high` := floor[(spec.requests.memory + throttlingFactor / 100 * (memory.limit_in_bytes or node allocatable memory - spec.requests.memory))/pageSize] * pageSize + MinLimitPercent specifies the minLimitFactor percentage to calculate `memory.min`, which protects memory + from global reclamation when memory usage does not exceed the min limit. + Close: 0. + format: int64 + minimum: 0 + type: integer + oomKillGroup: + format: int64 + type: integer + priority: + format: int64 + type: integer + priorityEnable: + description: 'TODO: enhance the usages of oom priority + and oom kill group' + format: int64 + type: integer + throttlingPercent: + description: |- + ThrottlingPercent specifies the throttlingFactor percentage to calculate `memory.high` with pod + memory.limits or node allocatable memory, which triggers memcg direct reclamation when memory usage exceeds. + Lower the factor brings more heavier reclaim pressure. + Close: 0. + format: int64 + minimum: 0 + type: integer + wmarkMinAdj: + description: |- + wmark_min_adj (Anolis OS required) + WmarkMinAdj specifies `memory.wmark_min_adj` which adjusts per-memcg threshold for global memory + reclamation. Lower the factor brings later reclamation. + The adjustment uses different formula for different value range. + [-25, 0)：global_wmark_min' = global_wmark_min + (global_wmark_min - 0) * wmarkMinAdj + (0, 50]：global_wmark_min' = global_wmark_min + (global_wmark_low - global_wmark_min) * wmarkMinAdj + Close: [LSR:0, LS:0, BE:0]. Recommended: [LSR:-25, LS:-25, BE:50]. + format: int64 + maximum: 50 + minimum: -25 + type: integer + wmarkRatio: + description: |- + wmark_ratio (Anolis OS required) + Async memory reclamation is triggered when cgroup memory usage exceeds `memory.wmark_high` and the reclamation + stops when usage is below `memory.wmark_low`. Basically, + `memory.wmark_high` := min(memory.high, memory.limit_in_bytes) * memory.memory.wmark_ratio + `memory.wmark_low` := min(memory.high, memory.limit_in_bytes) * (memory.wmark_ratio - memory.wmark_scale_factor) + WmarkRatio specifies `memory.wmark_ratio` that help calculate `memory.wmark_high`, which triggers async + memory reclamation when memory usage exceeds. + Close: 0. Recommended: 95. + format: int64 + maximum: 100 + minimum: 0 + type: integer + wmarkScalePermill: + description: |- + WmarkScalePermill specifies `memory.wmark_scale_factor` that helps calculate `memory.wmark_low`, which + stops async memory reclamation when memory usage belows. + Close: 50. Recommended: 20. + format: int64 + maximum: 1000 + minimum: 1 + type: integer + type: object + networkQOS: + properties: + egressLimit: + anyOf: + - type: integer + - type: string + default: 100 + description: |- + EgressLimit describes the maximum network bandwidth can be used in the egress direction, + unit: bps(bytes per second), two expressions are supported，int and string, + int: percentage based on total bandwidth，valid in 0-100 + string: a specific network bandwidth value, eg: 50M. + x-kubernetes-int-or-string: true + egressRequest: + anyOf: + - type: integer + - type: string + default: 0 + description: |- + EgressRequest describes the minimum network bandwidth guaranteed in the egress direction. + unit: bps(bytes per second), two expressions are supported，int and string, + int: percentage based on total bandwidth，valid in 0-100 + string: a specific network bandwidth value, eg: 50M. + x-kubernetes-int-or-string: true + enable: + type: boolean + ingressLimit: + anyOf: + - type: integer + - type: string + default: 100 + description: |- + IngressLimit describes the maximum network bandwidth can be used in the ingress direction, + unit: bps(bytes per second), two expressions are supported，int and string, + int: percentage based on total bandwidth，valid in 0-100 + string: a specific network bandwidth value, eg: 50M. + x-kubernetes-int-or-string: true + ingressRequest: + anyOf: + - type: integer + - type: string + default: 0 + description: |- + IngressRequest describes the minimum network bandwidth guaranteed in the ingress direction. + unit: bps(bytes per second), two expressions are supported，int and string, + int: percentage based on total bandwidth，valid in 0-100 + string: a specific network bandwidth value, eg: 50M. + x-kubernetes-int-or-string: true + type: object + resctrlQOS: + description: ResctrlQOSCfg stores node-level config of resctrl + qos + properties: + catRangeEndPercent: + description: LLC available range end for pods by percentage + format: int64 + maximum: 100 + minimum: 0 + type: integer + catRangeStartPercent: + description: LLC available range start for pods by percentage + format: int64 + maximum: 100 + minimum: 0 + type: integer + enable: + description: Enable indicates whether the resctrl qos + is enabled. + type: boolean + mbaPercent: + description: MBA percent + format: int64 + maximum: 100 + minimum: 0 + type: integer + type: object + type: object + lsClass: + description: ResourceQOS for LS pods. + properties: + blkioQOS: + properties: + blocks: + items: + properties: + ioCfg: + properties: + enableUserModel: + description: |- + configure the cost model of blkio-cost manually + whether the user model is enabled. Default value: false + type: boolean + ioWeightPercent: + description: 'This field is used to set the + weight of a sub-group. Default value: 100. + Valid values: 1 to 100.' + format: int64 + maximum: 100 + minimum: 1 + type: integer + modelReadBPS: + description: the read BPS of user model + format: int64 + minimum: 1 + type: integer + modelReadRandIOPS: + description: the random read iops of user model + format: int64 + minimum: 1 + type: integer + modelReadSeqIOPS: + description: the sequential read iops of user + model + format: int64 + minimum: 1 + type: integer + modelWriteBPS: + description: the write BPS of user model + format: int64 + minimum: 1 + type: integer + modelWriteRandIOPS: + description: the random write iops of user model + format: int64 + minimum: 1 + type: integer + modelWriteSeqIOPS: + description: the sequential write iops of user + model + format: int64 + minimum: 1 + type: integer + readBPS: + description: |- + Throttling of throughput + The value is set to 0, which indicates that the feature is disabled. + format: int64 + minimum: 0 + type: integer + readIOPS: + description: |- + Throttling of IOPS + The value is set to 0, which indicates that the feature is disabled. + format: int64 + minimum: 0 + type: integer + readLatency: + description: |- + Configure the weight-based throttling feature of blk-iocost + Only used for RootClass + After blk-iocost is enabled, the kernel calculates the proportion of requests that exceed the read or write latency threshold out of all requests. When the proportion is greater than the read or write latency percentile (95%), the kernel considers the disk to be saturated and reduces the rate at which requests are sent to the disk. + the read latency threshold. Unit: microseconds. + format: int64 + type: integer + readLatencyPercent: + description: the read latency percentile + format: int64 + maximum: 100 + minimum: 0 + type: integer + writeBPS: + format: int64 + minimum: 0 + type: integer + writeIOPS: + format: int64 + minimum: 0 + type: integer + writeLatency: + description: 'the write latency threshold. Unit: + microseconds.' + format: int64 + type: integer + writeLatencyPercent: + description: the write latency percentile + format: int64 + maximum: 100 + minimum: 0 + type: integer + type: object + name: + type: string + type: + type: string + type: object + type: array + enable: + type: boolean + type: object + cpuQOS: + description: CPUQOSCfg stores node-level config of cpu qos + properties: + coreExpeller: + description: |- + whether pods of the QoS class can expel the cgroup idle pods at the SMT-level. default = false + If set to true, pods of this QoS will use a dedicated core sched group for noise clean with the SchedIdle pods. + NOTE: It takes effect if cpuPolicy = "coreSched". + type: boolean + enable: + description: Enable indicates whether the cpu qos is enabled. + type: boolean + groupIdentity: + description: |- + group identity value for pods, default = 0 + NOTE: It takes effect if cpuPolicy = "groupIdentity". + format: int64 + type: integer + schedIdle: + description: |- + cpu.idle value for pods, default = 0. + `1` means using SCHED_IDLE. + CGroup Idle (introduced since mainline Linux 5.15): https://lore.kernel.org/lkml/162971078674.25758.15464079371945307825.tip-bot2@tip-bot2/#r + NOTE: It takes effect if cpuPolicy = "coreSched". + format: int64 + type: integer + type: object + memoryQOS: + description: MemoryQOSCfg stores node-level config of memory + qos + properties: + enable: + description: |- + Enable indicates whether the memory qos is enabled (default: false). + This field is used for node-level control, while pod-level configuration is done with MemoryQOS and `Policy` + instead of an `Enable` option. Please view the differences between MemoryQOSCfg and PodMemoryQOSConfig structs. + type: boolean + lowLimitPercent: + description: |- + LowLimitPercent specifies the lowLimitFactor percentage to calculate `memory.low`, which TRIES BEST + protecting memory from global reclamation when memory usage does not exceed the low limit unless no unprotected + memcg can be reclaimed. + NOTE: `memory.low` should be larger than `memory.min`. If spec.requests.memory == spec.limits.memory, + pod `memory.low` and `memory.high` become invalid, while `memory.wmark_ratio` is still in effect. + Close: 0. + format: int64 + minimum: 0 + type: integer + minLimitPercent: + description: |- + memcg qos + If enabled, memcg qos will be set by the agent, where some fields are implicitly calculated from pod spec. + 1. `memory.min` := spec.requests.memory * minLimitFactor / 100 (use 0 if requests.memory is not set) + 2. `memory.low` := spec.requests.memory * lowLimitFactor / 100 (use 0 if requests.memory is not set) + 3. `memory.limit_in_bytes` := spec.limits.memory (set $node.allocatable.memory if limits.memory is not set) + 4. `memory.high` := floor[(spec.requests.memory + throttlingFactor / 100 * (memory.limit_in_bytes or node allocatable memory - spec.requests.memory))/pageSize] * pageSize + MinLimitPercent specifies the minLimitFactor percentage to calculate `memory.min`, which protects memory + from global reclamation when memory usage does not exceed the min limit. + Close: 0. + format: int64 + minimum: 0 + type: integer + oomKillGroup: + format: int64 + type: integer + priority: + format: int64 + type: integer + priorityEnable: + description: 'TODO: enhance the usages of oom priority + and oom kill group' + format: int64 + type: integer + throttlingPercent: + description: |- + ThrottlingPercent specifies the throttlingFactor percentage to calculate `memory.high` with pod + memory.limits or node allocatable memory, which triggers memcg direct reclamation when memory usage exceeds. + Lower the factor brings more heavier reclaim pressure. + Close: 0. + format: int64 + minimum: 0 + type: integer + wmarkMinAdj: + description: |- + wmark_min_adj (Anolis OS required) + WmarkMinAdj specifies `memory.wmark_min_adj` which adjusts per-memcg threshold for global memory + reclamation. Lower the factor brings later reclamation. + The adjustment uses different formula for different value range. + [-25, 0)：global_wmark_min' = global_wmark_min + (global_wmark_min - 0) * wmarkMinAdj + (0, 50]：global_wmark_min' = global_wmark_min + (global_wmark_low - global_wmark_min) * wmarkMinAdj + Close: [LSR:0, LS:0, BE:0]. Recommended: [LSR:-25, LS:-25, BE:50]. + format: int64 + maximum: 50 + minimum: -25 + type: integer + wmarkRatio: + description: |- + wmark_ratio (Anolis OS required) + Async memory reclamation is triggered when cgroup memory usage exceeds `memory.wmark_high` and the reclamation + stops when usage is below `memory.wmark_low`. Basically, + `memory.wmark_high` := min(memory.high, memory.limit_in_bytes) * memory.memory.wmark_ratio + `memory.wmark_low` := min(memory.high, memory.limit_in_bytes) * (memory.wmark_ratio - memory.wmark_scale_factor) + WmarkRatio specifies `memory.wmark_ratio` that help calculate `memory.wmark_high`, which triggers async + memory reclamation when memory usage exceeds. + Close: 0. Recommended: 95. + format: int64 + maximum: 100 + minimum: 0 + type: integer + wmarkScalePermill: + description: |- + WmarkScalePermill specifies `memory.wmark_scale_factor` that helps calculate `memory.wmark_low`, which + stops async memory reclamation when memory usage belows. + Close: 50. Recommended: 20. + format: int64 + maximum: 1000 + minimum: 1 + type: integer + type: object + networkQOS: + properties: + egressLimit: + anyOf: + - type: integer + - type: string + default: 100 + description: |- + EgressLimit describes the maximum network bandwidth can be used in the egress direction, + unit: bps(bytes per second), two expressions are supported，int and string, + int: percentage based on total bandwidth，valid in 0-100 + string: a specific network bandwidth value, eg: 50M. + x-kubernetes-int-or-string: true + egressRequest: + anyOf: + - type: integer + - type: string + default: 0 + description: |- + EgressRequest describes the minimum network bandwidth guaranteed in the egress direction. + unit: bps(bytes per second), two expressions are supported，int and string, + int: percentage based on total bandwidth，valid in 0-100 + string: a specific network bandwidth value, eg: 50M. + x-kubernetes-int-or-string: true + enable: + type: boolean + ingressLimit: + anyOf: + - type: integer + - type: string + default: 100 + description: |- + IngressLimit describes the maximum network bandwidth can be used in the ingress direction, + unit: bps(bytes per second), two expressions are supported，int and string, + int: percentage based on total bandwidth，valid in 0-100 + string: a specific network bandwidth value, eg: 50M. + x-kubernetes-int-or-string: true + ingressRequest: + anyOf: + - type: integer + - type: string + default: 0 + description: |- + IngressRequest describes the minimum network bandwidth guaranteed in the ingress direction. + unit: bps(bytes per second), two expressions are supported，int and string, + int: percentage based on total bandwidth，valid in 0-100 + string: a specific network bandwidth value, eg: 50M. + x-kubernetes-int-or-string: true + type: object + resctrlQOS: + description: ResctrlQOSCfg stores node-level config of resctrl + qos + properties: + catRangeEndPercent: + description: LLC available range end for pods by percentage + format: int64 + maximum: 100 + minimum: 0 + type: integer + catRangeStartPercent: + description: LLC available range start for pods by percentage + format: int64 + maximum: 100 + minimum: 0 + type: integer + enable: + description: Enable indicates whether the resctrl qos + is enabled. + type: boolean + mbaPercent: + description: MBA percent + format: int64 + maximum: 100 + minimum: 0 + type: integer + type: object + type: object + lsrClass: + description: ResourceQOS for LSR pods. + properties: + blkioQOS: + properties: + blocks: + items: + properties: + ioCfg: + properties: + enableUserModel: + description: |- + configure the cost model of blkio-cost manually + whether the user model is enabled. Default value: false + type: boolean + ioWeightPercent: + description: 'This field is used to set the + weight of a sub-group. Default value: 100. + Valid values: 1 to 100.' + format: int64 + maximum: 100 + minimum: 1 + type: integer + modelReadBPS: + description: the read BPS of user model + format: int64 + minimum: 1 + type: integer + modelReadRandIOPS: + description: the random read iops of user model + format: int64 + minimum: 1 + type: integer + modelReadSeqIOPS: + description: the sequential read iops of user + model + format: int64 + minimum: 1 + type: integer + modelWriteBPS: + description: the write BPS of user model + format: int64 + minimum: 1 + type: integer + modelWriteRandIOPS: + description: the random write iops of user model + format: int64 + minimum: 1 + type: integer + modelWriteSeqIOPS: + description: the sequential write iops of user + model + format: int64 + minimum: 1 + type: integer + readBPS: + description: |- + Throttling of throughput + The value is set to 0, which indicates that the feature is disabled. + format: int64 + minimum: 0 + type: integer + readIOPS: + description: |- + Throttling of IOPS + The value is set to 0, which indicates that the feature is disabled. + format: int64 + minimum: 0 + type: integer + readLatency: + description: |- + Configure the weight-based throttling feature of blk-iocost + Only used for RootClass + After blk-iocost is enabled, the kernel calculates the proportion of requests that exceed the read or write latency threshold out of all requests. When the proportion is greater than the read or write latency percentile (95%), the kernel considers the disk to be saturated and reduces the rate at which requests are sent to the disk. + the read latency threshold. Unit: microseconds. + format: int64 + type: integer + readLatencyPercent: + description: the read latency percentile + format: int64 + maximum: 100 + minimum: 0 + type: integer + writeBPS: + format: int64 + minimum: 0 + type: integer + writeIOPS: + format: int64 + minimum: 0 + type: integer + writeLatency: + description: 'the write latency threshold. Unit: + microseconds.' + format: int64 + type: integer + writeLatencyPercent: + description: the write latency percentile + format: int64 + maximum: 100 + minimum: 0 + type: integer + type: object + name: + type: string + type: + type: string + type: object + type: array + enable: + type: boolean + type: object + cpuQOS: + description: CPUQOSCfg stores node-level config of cpu qos + properties: + coreExpeller: + description: |- + whether pods of the QoS class can expel the cgroup idle pods at the SMT-level. default = false + If set to true, pods of this QoS will use a dedicated core sched group for noise clean with the SchedIdle pods. + NOTE: It takes effect if cpuPolicy = "coreSched". + type: boolean + enable: + description: Enable indicates whether the cpu qos is enabled. + type: boolean + groupIdentity: + description: |- + group identity value for pods, default = 0 + NOTE: It takes effect if cpuPolicy = "groupIdentity". + format: int64 + type: integer + schedIdle: + description: |- + cpu.idle value for pods, default = 0. + `1` means using SCHED_IDLE. + CGroup Idle (introduced since mainline Linux 5.15): https://lore.kernel.org/lkml/162971078674.25758.15464079371945307825.tip-bot2@tip-bot2/#r + NOTE: It takes effect if cpuPolicy = "coreSched". + format: int64 + type: integer + type: object + memoryQOS: + description: MemoryQOSCfg stores node-level config of memory + qos + properties: + enable: + description: |- + Enable indicates whether the memory qos is enabled (default: false). + This field is used for node-level control, while pod-level configuration is done with MemoryQOS and `Policy` + instead of an `Enable` option. Please view the differences between MemoryQOSCfg and PodMemoryQOSConfig structs. + type: boolean + lowLimitPercent: + description: |- + LowLimitPercent specifies the lowLimitFactor percentage to calculate `memory.low`, which TRIES BEST + protecting memory from global reclamation when memory usage does not exceed the low limit unless no unprotected + memcg can be reclaimed. + NOTE: `memory.low` should be larger than `memory.min`. If spec.requests.memory == spec.limits.memory, + pod `memory.low` and `memory.high` become invalid, while `memory.wmark_ratio` is still in effect. + Close: 0. + format: int64 + minimum: 0 + type: integer + minLimitPercent: + description: |- + memcg qos + If enabled, memcg qos will be set by the agent, where some fields are implicitly calculated from pod spec. + 1. `memory.min` := spec.requests.memory * minLimitFactor / 100 (use 0 if requests.memory is not set) + 2. `memory.low` := spec.requests.memory * lowLimitFactor / 100 (use 0 if requests.memory is not set) + 3. `memory.limit_in_bytes` := spec.limits.memory (set $node.allocatable.memory if limits.memory is not set) + 4. `memory.high` := floor[(spec.requests.memory + throttlingFactor / 100 * (memory.limit_in_bytes or node allocatable memory - spec.requests.memory))/pageSize] * pageSize + MinLimitPercent specifies the minLimitFactor percentage to calculate `memory.min`, which protects memory + from global reclamation when memory usage does not exceed the min limit. + Close: 0. + format: int64 + minimum: 0 + type: integer + oomKillGroup: + format: int64 + type: integer + priority: + format: int64 + type: integer + priorityEnable: + description: 'TODO: enhance the usages of oom priority + and oom kill group' + format: int64 + type: integer + throttlingPercent: + description: |- + ThrottlingPercent specifies the throttlingFactor percentage to calculate `memory.high` with pod + memory.limits or node allocatable memory, which triggers memcg direct reclamation when memory usage exceeds. + Lower the factor brings more heavier reclaim pressure. + Close: 0. + format: int64 + minimum: 0 + type: integer + wmarkMinAdj: + description: |- + wmark_min_adj (Anolis OS required) + WmarkMinAdj specifies `memory.wmark_min_adj` which adjusts per-memcg threshold for global memory + reclamation. Lower the factor brings later reclamation. + The adjustment uses different formula for different value range. + [-25, 0)：global_wmark_min' = global_wmark_min + (global_wmark_min - 0) * wmarkMinAdj + (0, 50]：global_wmark_min' = global_wmark_min + (global_wmark_low - global_wmark_min) * wmarkMinAdj + Close: [LSR:0, LS:0, BE:0]. Recommended: [LSR:-25, LS:-25, BE:50]. + format: int64 + maximum: 50 + minimum: -25 + type: integer + wmarkRatio: + description: |- + wmark_ratio (Anolis OS required) + Async memory reclamation is triggered when cgroup memory usage exceeds `memory.wmark_high` and the reclamation + stops when usage is below `memory.wmark_low`. Basically, + `memory.wmark_high` := min(memory.high, memory.limit_in_bytes) * memory.memory.wmark_ratio + `memory.wmark_low` := min(memory.high, memory.limit_in_bytes) * (memory.wmark_ratio - memory.wmark_scale_factor) + WmarkRatio specifies `memory.wmark_ratio` that help calculate `memory.wmark_high`, which triggers async + memory reclamation when memory usage exceeds. + Close: 0. Recommended: 95. + format: int64 + maximum: 100 + minimum: 0 + type: integer + wmarkScalePermill: + description: |- + WmarkScalePermill specifies `memory.wmark_scale_factor` that helps calculate `memory.wmark_low`, which + stops async memory reclamation when memory usage belows. + Close: 50. Recommended: 20. + format: int64 + maximum: 1000 + minimum: 1 + type: integer + type: object + networkQOS: + properties: + egressLimit: + anyOf: + - type: integer + - type: string + default: 100 + description: |- + EgressLimit describes the maximum network bandwidth can be used in the egress direction, + unit: bps(bytes per second), two expressions are supported，int and string, + int: percentage based on total bandwidth，valid in 0-100 + string: a specific network bandwidth value, eg: 50M. + x-kubernetes-int-or-string: true + egressRequest: + anyOf: + - type: integer + - type: string + default: 0 + description: |- + EgressRequest describes the minimum network bandwidth guaranteed in the egress direction. + unit: bps(bytes per second), two expressions are supported，int and string, + int: percentage based on total bandwidth，valid in 0-100 + string: a specific network bandwidth value, eg: 50M. + x-kubernetes-int-or-string: true + enable: + type: boolean + ingressLimit: + anyOf: + - type: integer + - type: string + default: 100 + description: |- + IngressLimit describes the maximum network bandwidth can be used in the ingress direction, + unit: bps(bytes per second), two expressions are supported，int and string, + int: percentage based on total bandwidth，valid in 0-100 + string: a specific network bandwidth value, eg: 50M. + x-kubernetes-int-or-string: true + ingressRequest: + anyOf: + - type: integer + - type: string + default: 0 + description: |- + IngressRequest describes the minimum network bandwidth guaranteed in the ingress direction. + unit: bps(bytes per second), two expressions are supported，int and string, + int: percentage based on total bandwidth，valid in 0-100 + string: a specific network bandwidth value, eg: 50M. + x-kubernetes-int-or-string: true + type: object + resctrlQOS: + description: ResctrlQOSCfg stores node-level config of resctrl + qos + properties: + catRangeEndPercent: + description: LLC available range end for pods by percentage + format: int64 + maximum: 100 + minimum: 0 + type: integer + catRangeStartPercent: + description: LLC available range start for pods by percentage + format: int64 + maximum: 100 + minimum: 0 + type: integer + enable: + description: Enable indicates whether the resctrl qos + is enabled. + type: boolean + mbaPercent: + description: MBA percent + format: int64 + maximum: 100 + minimum: 0 + type: integer + type: object + type: object + policies: + description: Policies of pod QoS. + properties: + cpuPolicy: + description: applied policy for the CPU QoS, default = "groupIdentity" + type: string + netQOSPolicy: + description: applied policy for the Net QoS, default = "tc" + type: string + type: object + systemClass: + description: ResourceQOS for system pods + properties: + blkioQOS: + properties: + blocks: + items: + properties: + ioCfg: + properties: + enableUserModel: + description: |- + configure the cost model of blkio-cost manually + whether the user model is enabled. Default value: false + type: boolean + ioWeightPercent: + description: 'This field is used to set the + weight of a sub-group. Default value: 100. + Valid values: 1 to 100.' + format: int64 + maximum: 100 + minimum: 1 + type: integer + modelReadBPS: + description: the read BPS of user model + format: int64 + minimum: 1 + type: integer + modelReadRandIOPS: + description: the random read iops of user model + format: int64 + minimum: 1 + type: integer + modelReadSeqIOPS: + description: the sequential read iops of user + model + format: int64 + minimum: 1 + type: integer + modelWriteBPS: + description: the write BPS of user model + format: int64 + minimum: 1 + type: integer + modelWriteRandIOPS: + description: the random write iops of user model + format: int64 + minimum: 1 + type: integer + modelWriteSeqIOPS: + description: the sequential write iops of user + model + format: int64 + minimum: 1 + type: integer + readBPS: + description: |- + Throttling of throughput + The value is set to 0, which indicates that the feature is disabled. + format: int64 + minimum: 0 + type: integer + readIOPS: + description: |- + Throttling of IOPS + The value is set to 0, which indicates that the feature is disabled. + format: int64 + minimum: 0 + type: integer + readLatency: + description: |- + Configure the weight-based throttling feature of blk-iocost + Only used for RootClass + After blk-iocost is enabled, the kernel calculates the proportion of requests that exceed the read or write latency threshold out of all requests. When the proportion is greater than the read or write latency percentile (95%), the kernel considers the disk to be saturated and reduces the rate at which requests are sent to the disk. + the read latency threshold. Unit: microseconds. + format: int64 + type: integer + readLatencyPercent: + description: the read latency percentile + format: int64 + maximum: 100 + minimum: 0 + type: integer + writeBPS: + format: int64 + minimum: 0 + type: integer + writeIOPS: + format: int64 + minimum: 0 + type: integer + writeLatency: + description: 'the write latency threshold. Unit: + microseconds.' + format: int64 + type: integer + writeLatencyPercent: + description: the write latency percentile + format: int64 + maximum: 100 + minimum: 0 + type: integer + type: object + name: + type: string + type: + type: string + type: object + type: array + enable: + type: boolean + type: object + cpuQOS: + description: CPUQOSCfg stores node-level config of cpu qos + properties: + coreExpeller: + description: |- + whether pods of the QoS class can expel the cgroup idle pods at the SMT-level. default = false + If set to true, pods of this QoS will use a dedicated core sched group for noise clean with the SchedIdle pods. + NOTE: It takes effect if cpuPolicy = "coreSched". + type: boolean + enable: + description: Enable indicates whether the cpu qos is enabled. + type: boolean + groupIdentity: + description: |- + group identity value for pods, default = 0 + NOTE: It takes effect if cpuPolicy = "groupIdentity". + format: int64 + type: integer + schedIdle: + description: |- + cpu.idle value for pods, default = 0. + `1` means using SCHED_IDLE. + CGroup Idle (introduced since mainline Linux 5.15): https://lore.kernel.org/lkml/162971078674.25758.15464079371945307825.tip-bot2@tip-bot2/#r + NOTE: It takes effect if cpuPolicy = "coreSched". + format: int64 + type: integer + type: object + memoryQOS: + description: MemoryQOSCfg stores node-level config of memory + qos + properties: + enable: + description: |- + Enable indicates whether the memory qos is enabled (default: false). + This field is used for node-level control, while pod-level configuration is done with MemoryQOS and `Policy` + instead of an `Enable` option. Please view the differences between MemoryQOSCfg and PodMemoryQOSConfig structs. + type: boolean + lowLimitPercent: + description: |- + LowLimitPercent specifies the lowLimitFactor percentage to calculate `memory.low`, which TRIES BEST + protecting memory from global reclamation when memory usage does not exceed the low limit unless no unprotected + memcg can be reclaimed. + NOTE: `memory.low` should be larger than `memory.min`. If spec.requests.memory == spec.limits.memory, + pod `memory.low` and `memory.high` become invalid, while `memory.wmark_ratio` is still in effect. + Close: 0. + format: int64 + minimum: 0 + type: integer + minLimitPercent: + description: |- + memcg qos + If enabled, memcg qos will be set by the agent, where some fields are implicitly calculated from pod spec. + 1. `memory.min` := spec.requests.memory * minLimitFactor / 100 (use 0 if requests.memory is not set) + 2. `memory.low` := spec.requests.memory * lowLimitFactor / 100 (use 0 if requests.memory is not set) + 3. `memory.limit_in_bytes` := spec.limits.memory (set $node.allocatable.memory if limits.memory is not set) + 4. `memory.high` := floor[(spec.requests.memory + throttlingFactor / 100 * (memory.limit_in_bytes or node allocatable memory - spec.requests.memory))/pageSize] * pageSize + MinLimitPercent specifies the minLimitFactor percentage to calculate `memory.min`, which protects memory + from global reclamation when memory usage does not exceed the min limit. + Close: 0. + format: int64 + minimum: 0 + type: integer + oomKillGroup: + format: int64 + type: integer + priority: + format: int64 + type: integer + priorityEnable: + description: 'TODO: enhance the usages of oom priority + and oom kill group' + format: int64 + type: integer + throttlingPercent: + description: |- + ThrottlingPercent specifies the throttlingFactor percentage to calculate `memory.high` with pod + memory.limits or node allocatable memory, which triggers memcg direct reclamation when memory usage exceeds. + Lower the factor brings more heavier reclaim pressure. + Close: 0. + format: int64 + minimum: 0 + type: integer + wmarkMinAdj: + description: |- + wmark_min_adj (Anolis OS required) + WmarkMinAdj specifies `memory.wmark_min_adj` which adjusts per-memcg threshold for global memory + reclamation. Lower the factor brings later reclamation. + The adjustment uses different formula for different value range. + [-25, 0)：global_wmark_min' = global_wmark_min + (global_wmark_min - 0) * wmarkMinAdj + (0, 50]：global_wmark_min' = global_wmark_min + (global_wmark_low - global_wmark_min) * wmarkMinAdj + Close: [LSR:0, LS:0, BE:0]. Recommended: [LSR:-25, LS:-25, BE:50]. + format: int64 + maximum: 50 + minimum: -25 + type: integer + wmarkRatio: + description: |- + wmark_ratio (Anolis OS required) + Async memory reclamation is triggered when cgroup memory usage exceeds `memory.wmark_high` and the reclamation + stops when usage is below `memory.wmark_low`. Basically, + `memory.wmark_high` := min(memory.high, memory.limit_in_bytes) * memory.memory.wmark_ratio + `memory.wmark_low` := min(memory.high, memory.limit_in_bytes) * (memory.wmark_ratio - memory.wmark_scale_factor) + WmarkRatio specifies `memory.wmark_ratio` that help calculate `memory.wmark_high`, which triggers async + memory reclamation when memory usage exceeds. + Close: 0. Recommended: 95. + format: int64 + maximum: 100 + minimum: 0 + type: integer + wmarkScalePermill: + description: |- + WmarkScalePermill specifies `memory.wmark_scale_factor` that helps calculate `memory.wmark_low`, which + stops async memory reclamation when memory usage belows. + Close: 50. Recommended: 20. + format: int64 + maximum: 1000 + minimum: 1 + type: integer + type: object + networkQOS: + properties: + egressLimit: + anyOf: + - type: integer + - type: string + default: 100 + description: |- + EgressLimit describes the maximum network bandwidth can be used in the egress direction, + unit: bps(bytes per second), two expressions are supported，int and string, + int: percentage based on total bandwidth，valid in 0-100 + string: a specific network bandwidth value, eg: 50M. + x-kubernetes-int-or-string: true + egressRequest: + anyOf: + - type: integer + - type: string + default: 0 + description: |- + EgressRequest describes the minimum network bandwidth guaranteed in the egress direction. + unit: bps(bytes per second), two expressions are supported，int and string, + int: percentage based on total bandwidth，valid in 0-100 + string: a specific network bandwidth value, eg: 50M. + x-kubernetes-int-or-string: true + enable: + type: boolean + ingressLimit: + anyOf: + - type: integer + - type: string + default: 100 + description: |- + IngressLimit describes the maximum network bandwidth can be used in the ingress direction, + unit: bps(bytes per second), two expressions are supported，int and string, + int: percentage based on total bandwidth，valid in 0-100 + string: a specific network bandwidth value, eg: 50M. + x-kubernetes-int-or-string: true + ingressRequest: + anyOf: + - type: integer + - type: string + default: 0 + description: |- + IngressRequest describes the minimum network bandwidth guaranteed in the ingress direction. + unit: bps(bytes per second), two expressions are supported，int and string, + int: percentage based on total bandwidth，valid in 0-100 + string: a specific network bandwidth value, eg: 50M. + x-kubernetes-int-or-string: true + type: object + resctrlQOS: + description: ResctrlQOSCfg stores node-level config of resctrl + qos + properties: + catRangeEndPercent: + description: LLC available range end for pods by percentage + format: int64 + maximum: 100 + minimum: 0 + type: integer + catRangeStartPercent: + description: LLC available range start for pods by percentage + format: int64 + maximum: 100 + minimum: 0 + type: integer + enable: + description: Enable indicates whether the resctrl qos + is enabled. + type: boolean + mbaPercent: + description: MBA percent + format: int64 + maximum: 100 + minimum: 0 + type: integer + type: object + type: object + type: object + resourceUsedThresholdWithBE: + description: BE pods will be limited if node resource usage overload + properties: + cpuEvictBESatisfactionLowerPercent: + description: |- + be.satisfactionRate = be.CPURealLimit/be.CPURequest; be.cpuUsage = be.CPUUsed/be.CPURealLimit + if be.satisfactionRate < CPUEvictBESatisfactionLowerPercent/100 && be.usage >= CPUEvictBEUsageThresholdPercent/100, + then start to evict pod, and will evict to ${CPUEvictBESatisfactionUpperPercent} + format: int64 + type: integer + cpuEvictBESatisfactionUpperPercent: + description: |- + be.satisfactionRate = be.CPURealLimit/be.CPURequest + if be.satisfactionRate > CPUEvictBESatisfactionUpperPercent/100, then stop to evict. + format: int64 + type: integer + cpuEvictBEUsageThresholdPercent: + description: if be.cpuUsage >= CPUEvictBEUsageThresholdPercent/100, + then start to calculate the resources need to be released. + format: int64 + type: integer + cpuEvictPolicy: + description: |- + CPUEvictPolicy defines the policy for the BECPUEvict feature. + Default: `evictByRealLimit`. + type: string + cpuEvictTimeWindowSeconds: + description: |- + when avg(cpuusage) > CPUEvictThresholdPercent, will start to evict pod by cpu, + and avg(cpuusage) is calculated based on the most recent CPUEvictTimeWindowSeconds data + format: int64 + type: integer + cpuSuppressPolicy: + description: CPUSuppressPolicy + type: string + cpuSuppressThresholdPercent: + description: cpu suppress threshold percentage (0,100), default + = 65 + format: int64 + maximum: 100 + minimum: 0 + type: integer + enable: + description: whether the strategy is enabled, default = false + type: boolean + memoryEvictLowerPercent: + description: 'lower: memory release util usage under MemoryEvictLowerPercent, + default = MemoryEvictThresholdPercent - 2' + format: int64 + maximum: 100 + minimum: 0 + type: integer + memoryEvictThresholdPercent: + description: 'upper: memory evict threshold percentage (0,100), + default = 70' + format: int64 + maximum: 100 + minimum: 0 + type: integer + type: object + systemStrategy: + description: node global system config + properties: + memcgReapBackGround: + description: /sys/kernel/mm/memcg_reaper/reap_background + format: int64 + type: integer + minFreeKbytesFactor: + description: for /proc/sys/vm/min_free_kbytes, min_free_kbytes + = minFreeKbytesFactor * nodeTotalMemory /10000 + format: int64 + type: integer + totalNetworkBandwidth: + anyOf: + - type: integer + - type: string + description: 'TotalNetworkBandwidth indicates the overall network + bandwidth, cluster manager can set this field, and default value + taken from /sys/class/net/${NIC_NAME}/speed, unit: Mbps' + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + watermarkScaleFactor: + description: /proc/sys/vm/watermark_scale_factor + format: int64 + type: integer + type: object + type: object + status: + description: NodeSLOStatus defines the observed state of NodeSLO + type: object + type: object + served: true + storage: true + subresources: + status: {} + +{{- end }} diff --git a/versions/v1.6.0/templates/crd/topology.node.k8s.io_noderesourcetopologies.yaml b/versions/v1.6.0/templates/crd/topology.node.k8s.io_noderesourcetopologies.yaml new file mode 100644 index 0000000..5a466f4 --- /dev/null +++ b/versions/v1.6.0/templates/crd/topology.node.k8s.io_noderesourcetopologies.yaml @@ -0,0 +1,147 @@ +{{- if and .Values.crds.managed .Values.crds.noderesourcetopologies }} +--- +apiVersion: apiextensions.k8s.io/v1 +kind: CustomResourceDefinition +metadata: + annotations: + api-approved.kubernetes.io: https://github.com/kubernetes/enhancements/pull/1870 + controller-gen.kubebuilder.io/version: v0.7.0 + creationTimestamp: null + name: noderesourcetopologies.topology.node.k8s.io +spec: + group: topology.node.k8s.io + names: + kind: NodeResourceTopology + listKind: NodeResourceTopologyList + plural: noderesourcetopologies + shortNames: + - node-res-topo + singular: noderesourcetopology + scope: Cluster + versions: + - name: v1alpha1 + schema: + openAPIV3Schema: + description: NodeResourceTopology describes node resources and their topology. + properties: + apiVersion: + description: 'APIVersion defines the versioned schema of this representation + of an object. Servers should convert recognized schemas to the latest + internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources' + type: string + kind: + description: 'Kind is a string value representing the REST resource this + object represents. Servers may infer this from the endpoint the client + submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds' + type: string + metadata: + type: object + topologyPolicies: + items: + type: string + type: array + zones: + description: ZoneList contains an array of Zone objects. + items: + description: Zone represents a resource topology zone, e.g. socket, + node, die or core. + properties: + attributes: + description: AttributeList contains an array of AttributeInfo objects. + items: + description: AttributeInfo contains one attribute of a Zone. + properties: + name: + type: string + value: + type: string + required: + - name + - value + type: object + type: array + costs: + description: CostList contains an array of CostInfo objects. + items: + description: CostInfo describes the cost (or distance) between + two Zones. + properties: + name: + type: string + value: + format: int64 + type: integer + required: + - name + - value + type: object + type: array + name: + type: string + parent: + type: string + resources: + description: ResourceInfoList contains an array of ResourceInfo + objects. + items: + description: ResourceInfo contains information about one resource + type. + properties: + allocatable: + anyOf: + - type: integer + - type: string + description: Allocatable quantity of the resource, corresponding + to allocatable in node status, i.e. total amount of this + resource available to be used by pods. + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + available: + anyOf: + - type: integer + - type: string + description: Available is the amount of this resource currently + available for new (to be scheduled) pods, i.e. Allocatable + minus the resources reserved by currently running pods. + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + capacity: + anyOf: + - type: integer + - type: string + description: Capacity of the resource, corresponding to capacity + in node status, i.e. total amount of this resource that + the node has. + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + name: + description: Name of the resource. + type: string + required: + - allocatable + - available + - capacity + - name + type: object + type: array + type: + type: string + required: + - name + - type + type: object + type: array + required: + - topologyPolicies + - zones + type: object + served: true + storage: true +status: + acceptedNames: + kind: "" + plural: "" + conditions: [] + storedVersions: [] + +{{- end }} diff --git a/versions/v1.6.0/templates/koord-descheduler-config.yaml b/versions/v1.6.0/templates/koord-descheduler-config.yaml new file mode 100644 index 0000000..a05016e --- /dev/null +++ b/versions/v1.6.0/templates/koord-descheduler-config.yaml @@ -0,0 +1,61 @@ +apiVersion: v1 +kind: ConfigMap +metadata: + name: koord-descheduler-config + namespace: {{ .Values.installation.namespace }} +data: + koord-descheduler-config: | + apiVersion: descheduler/v1alpha2 + kind: DeschedulerConfiguration + enableContentionProfiling: true + enableProfiling: true + healthzBindAddress: 0.0.0.0:10251 + metricsBindAddress: 0.0.0.0:10251 + leaderElection: + resourceLock: leases + resourceName: koord-descheduler + resourceNamespace: {{ .Values.installation.namespace }} + deschedulingInterval: 10s + dryRun: false + profiles: + - name: koord-descheduler + plugins: + deschedule: + disabled: + - name: "*" + # disable LowNodeLoad by default + # balance: + # enabled: + # - name: LowNodeLoad + evict: + disabled: + - name: "*" + enabled: + - name: MigrationController + pluginConfig: + - name: MigrationController + args: + apiVersion: descheduler/v1alpha2 + kind: MigrationControllerArgs + evictionPolicy: Eviction + namespaces: + exclude: + - kube-system + - {{ .Values.installation.namespace }} + evictQPS: "10" + evictBurst: 1 + - name: LowNodeLoad + args: + apiVersion: descheduler/v1alpha2 + kind: LowNodeLoadArgs + evictableNamespaces: + exclude: + - kube-system + - {{ .Values.installation.namespace }} + useDeviationThresholds: false + lowThresholds: + cpu: 45 + memory: 55 + highThresholds: + cpu: 75 + memory: 80 \ No newline at end of file diff --git a/versions/v1.6.0/templates/koord-descheduler.yaml b/versions/v1.6.0/templates/koord-descheduler.yaml new file mode 100644 index 0000000..33083cf --- /dev/null +++ b/versions/v1.6.0/templates/koord-descheduler.yaml @@ -0,0 +1,83 @@ +apiVersion: apps/v1 +kind: Deployment +metadata: + labels: + koord-app: koord-descheduler + name: koord-descheduler + namespace: {{ .Values.installation.namespace }} +spec: + replicas: {{ .Values.descheduler.replicas }} + selector: + matchLabels: + koord-app: koord-descheduler + minReadySeconds: 3 + strategy: + type: RollingUpdate + rollingUpdate: + maxUnavailable: 0 + maxSurge: 100% + template: + metadata: + labels: + koord-app: koord-descheduler + spec: +{{- with .Values.imagePullSecrets }} + imagePullSecrets: +{{- toYaml . | nindent 8 }} +{{- end }} + containers: + - args: + - --v={{ .Values.descheduler.log.level }} + - --config=/config/koord-descheduler.config + command: + - /koord-descheduler + image: "{{ .Values.imageRepositoryHost }}/{{ .Values.descheduler.image.repository }}:{{ .Values.descheduler.image.tag }}" + imagePullPolicy: Always + name: descheduler + volumeMounts: + - mountPath: /config + name: koord-descheduler-config-volume + readinessProbe: + httpGet: + path: healthz + port: {{ .Values.descheduler.port }} + resources: + {{- toYaml .Values.descheduler.resources | nindent 12 }} + hostNetwork: {{ .Values.descheduler.hostNetwork }} + terminationGracePeriodSeconds: 10 + serviceAccountName: koord-descheduler + volumes: + - configMap: + defaultMode: 420 + items: + - key: koord-descheduler-config + path: koord-descheduler.config + name: koord-descheduler-config + name: koord-descheduler-config-volume + affinity: + podAntiAffinity: + preferredDuringSchedulingIgnoredDuringExecution: + - podAffinityTerm: + labelSelector: + matchExpressions: + - key: koord-app + operator: In + values: + - koord-descheduler + topologyKey: kubernetes.io/hostname + weight: 100 +{{- with .Values.descheduler.nodeAffinity }} + nodeAffinity: +{{ toYaml . | indent 10 }} +{{- end }} + +{{- if .Values.descheduler.nodeSelector }} + nodeSelector: +{{ toYaml .Values.descheduler.nodeSelector | indent 8 }} +{{- end }} + +{{- if .Values.descheduler.tolerations }} + tolerations: +{{ toYaml .Values.descheduler.tolerations | indent 8 }} +{{- end }} + diff --git a/versions/v1.6.0/templates/koord-manager.yaml b/versions/v1.6.0/templates/koord-manager.yaml new file mode 100644 index 0000000..d80bf25 --- /dev/null +++ b/versions/v1.6.0/templates/koord-manager.yaml @@ -0,0 +1,130 @@ +apiVersion: v1 +kind: Namespace +metadata: + labels: + controle-plane: koordinator + name: {{ .Values.installation.namespace }} +--- +apiVersion: v1 +kind: Service +metadata: + name: koordinator-webhook-service + namespace: {{ .Values.installation.namespace }} +spec: +{{ ( include "webhookServiceSpec" . ) | indent 2 }} +--- +apiVersion: v1 +kind: Secret +metadata: + name: koordinator-webhook-certs + namespace: {{ .Values.installation.namespace }} +{{ ( include "webhookSecretData" . ) }} +--- +apiVersion: apps/v1 +kind: Deployment +metadata: + labels: + koord-app: koord-manager + name: koord-manager + namespace: {{ .Values.installation.namespace }} +spec: + replicas: {{ .Values.manager.replicas }} + selector: + matchLabels: + koord-app: koord-manager + minReadySeconds: 3 + strategy: + type: RollingUpdate + rollingUpdate: + maxUnavailable: 0 + maxSurge: 100% + template: + metadata: + labels: + koord-app: koord-manager + spec: +{{- with .Values.imagePullSecrets }} + imagePullSecrets: +{{- toYaml . | nindent 8 }} +{{- end }} + containers: + - args: + - --enable-leader-election + - --metrics-addr={{ .Values.manager.metrics.addr }}:{{ .Values.manager.metrics.port }} + - --health-probe-addr=:{{ .Values.manager.healthProbe.port }} + - --logtostderr=true + - --leader-election-namespace={{ .Values.installation.namespace }} + - --v={{ .Values.manager.log.level }} + - --feature-gates={{ .Values.featureGates }} + - --sync-period={{ .Values.manager.resyncPeriod }} + - --config-namespace={{ .Values.installation.namespace }} + command: + - /koord-manager + image: "{{ .Values.imageRepositoryHost }}/{{ .Values.manager.image.repository }}:{{ .Values.manager.image.tag }}" + imagePullPolicy: Always + name: manager + env: + - name: POD_NAMESPACE + valueFrom: + fieldRef: + fieldPath: metadata.namespace + - name: WEBHOOK_PORT + value: "{{ .Values.manager.webhook.port }}" + - name: WEBHOOK_CONFIGURATION_FAILURE_POLICY_PODS + value: {{ .Values.webhookConfiguration.failurePolicy.pods }} + ports: + - containerPort: {{ .Values.manager.webhook.port }} + name: webhook-server + protocol: TCP + - containerPort: {{ .Values.manager.metrics.port }} + name: metrics + protocol: TCP + - containerPort: {{ .Values.manager.healthProbe.port }} + name: health + protocol: TCP + readinessProbe: + httpGet: + path: readyz + port: {{ .Values.manager.healthProbe.port }} + resources: + {{- toYaml .Values.manager.resources | nindent 12 }} + hostNetwork: {{ .Values.manager.hostNetwork }} + terminationGracePeriodSeconds: 10 + serviceAccountName: koord-manager + affinity: + podAntiAffinity: + preferredDuringSchedulingIgnoredDuringExecution: + - podAffinityTerm: + labelSelector: + matchExpressions: + - key: koord-app + operator: In + values: + - koord-manager + topologyKey: kubernetes.io/hostname + weight: 100 +{{- with .Values.manager.nodeAffinity }} + nodeAffinity: +{{ toYaml . | indent 10 }} +{{- end }} + +{{- if .Values.manager.nodeSelector }} + nodeSelector: +{{ toYaml .Values.manager.nodeSelector | indent 8 }} +{{- end }} + +{{- if .Values.manager.tolerations }} + tolerations: +{{ toYaml .Values.manager.tolerations | indent 8 }} +{{- end }} +--- +apiVersion: v1 +kind: ServiceAccount +metadata: + name: koord-manager +{{- if .Values.serviceAccount.annotations }} + annotations: +{{ toYaml .Values.serviceAccount.annotations | indent 4 }} +{{- end }} + namespace: {{ .Values.installation.namespace }} +{{ ( include "serviceAccountManager" . ) }} diff --git a/versions/v1.6.0/templates/koord-scheduler-config.yaml b/versions/v1.6.0/templates/koord-scheduler-config.yaml new file mode 100644 index 0000000..3f7befa --- /dev/null +++ b/versions/v1.6.0/templates/koord-scheduler-config.yaml @@ -0,0 +1,132 @@ +apiVersion: v1 +kind: ConfigMap +metadata: + name: koord-scheduler-config + namespace: {{ .Values.installation.namespace }} +data: + koord-scheduler-config: | + apiVersion: kubescheduler.config.k8s.io/v1 + kind: KubeSchedulerConfiguration + leaderElection: + leaderElect: true + resourceLock: leases + resourceName: koord-scheduler + resourceNamespace: {{ .Values.installation.namespace }} + profiles: + - pluginConfig: + - name: NodeResourcesFit + args: + apiVersion: kubescheduler.config.k8s.io/v1 + kind: NodeResourcesFitArgs + scoringStrategy: + type: LeastAllocated + resources: + - name: cpu + weight: 1 + - name: memory + weight: 1 + - name: "kubernetes.io/batch-cpu" + weight: 1 + - name: "kubernetes.io/batch-memory" + weight: 1 + - name: LoadAwareScheduling + args: + apiVersion: kubescheduler.config.k8s.io/v1 + kind: LoadAwareSchedulingArgs + filterExpiredNodeMetrics: false + nodeMetricExpirationSeconds: 300 + resourceWeights: + cpu: 1 + memory: 1 + usageThresholds: + cpu: 65 + memory: 95 + # disable by default + # prodUsageThresholds indicates the resource utilization threshold of Prod Pods compared to the whole machine. + # prodUsageThresholds: + # cpu: 55 + # memory: 75 + # scoreAccordingProdUsage controls whether to score according to the utilization of Prod Pod + # scoreAccordingProdUsage: true + # aggregated supports resource utilization filtering and scoring based on percentile statistics + # aggregated: + # usageThresholds: + # cpu: 65 + # memory: 95 + # usageAggregationType: "p95" + # scoreAggregationType: "p95" + estimatedScalingFactors: + cpu: 85 + memory: 70 + - name: ElasticQuota + args: + apiVersion: kubescheduler.config.k8s.io/v1 + kind: ElasticQuotaArgs + quotaGroupNamespace: {{ .Values.installation.namespace }} + plugins: + queueSort: + disabled: + - name: "*" + enabled: + - name: Coscheduling + preFilter: + enabled: + - name: Coscheduling + - name: Reservation + - name: NodeNUMAResource + - name: DeviceShare + - name: ElasticQuota + filter: + enabled: + - name: Reservation + - name: LoadAwareScheduling + - name: NodeNUMAResource + - name: DeviceShare + postFilter: + disabled: + - name: "*" + enabled: + - name: Reservation + - name: Coscheduling + - name: ElasticQuota + - name: DefaultPreemption + preScore: + enabled: + - name: Reservation # The Reservation plugin must come first + score: + enabled: + - name: LoadAwareScheduling + weight: 1 + - name: NodeNUMAResource + weight: 1 + - name: DeviceShare + weight: 1 + - name: Reservation + weight: 5000 + reserve: + enabled: + - name: Reservation # The Reservation plugin must come first + - name: LoadAwareScheduling + - name: NodeNUMAResource + - name: DeviceShare + - name: Coscheduling + - name: ElasticQuota + permit: + enabled: + - name: Coscheduling + preBind: + enabled: + - name: NodeNUMAResource + - name: DeviceShare + - name: Reservation + - name: DefaultPreBind + bind: + disabled: + - name: "*" + enabled: + - name: Reservation + - name: DefaultBinder + postBind: + enabled: + - name: Coscheduling + schedulerName: koord-scheduler \ No newline at end of file diff --git a/versions/v1.6.0/templates/koord-scheduler.yaml b/versions/v1.6.0/templates/koord-scheduler.yaml new file mode 100644 index 0000000..b38afbc --- /dev/null +++ b/versions/v1.6.0/templates/koord-scheduler.yaml @@ -0,0 +1,92 @@ +apiVersion: apps/v1 +kind: Deployment +metadata: + labels: + koord-app: koord-scheduler + name: koord-scheduler + namespace: {{ .Values.installation.namespace }} +spec: + replicas: {{ .Values.scheduler.replicas }} + selector: + matchLabels: + koord-app: koord-scheduler + minReadySeconds: 3 + strategy: + type: RollingUpdate + rollingUpdate: + maxUnavailable: 0 + maxSurge: 100% + template: + metadata: + labels: + koord-app: koord-scheduler + spec: +{{- with .Values.imagePullSecrets }} + imagePullSecrets: +{{- toYaml . | nindent 8 }} +{{- end }} + containers: + - args: + - --port={{ .Values.scheduler.port }} + - --authentication-skip-lookup=true + - --v={{ .Values.scheduler.log.level }} +{{- if semverCompare "= 1.22-0" .Capabilities.KubeVersion.Version }} + - --feature-gates={{ .Values.scheduler.compatible122FeatureGates }} +{{- else if semverCompare "< 1.22-0" .Capabilities.KubeVersion.Version }} + - --feature-gates={{ .Values.scheduler.compatibleBelow122FeatureGates }} +{{- else }} + - --feature-gates={{ .Values.scheduler.featureGates }} +{{- end }} + - --config=/config/koord-scheduler.config + command: + - /koord-scheduler + image: "{{ .Values.imageRepositoryHost }}/{{ .Values.scheduler.image.repository }}:{{ .Values.scheduler.image.tag }}" + imagePullPolicy: Always + name: scheduler + volumeMounts: + - mountPath: /config + name: koord-scheduler-config-volume + readinessProbe: + httpGet: + path: healthz + port: {{ .Values.scheduler.port }} + resources: + {{- toYaml .Values.scheduler.resources | nindent 12 }} + hostNetwork: {{ .Values.scheduler.hostNetwork }} + terminationGracePeriodSeconds: 10 + serviceAccountName: koord-scheduler + volumes: + - configMap: + defaultMode: 420 + items: + - key: koord-scheduler-config + path: koord-scheduler.config + name: koord-scheduler-config + name: koord-scheduler-config-volume + affinity: + podAntiAffinity: + preferredDuringSchedulingIgnoredDuringExecution: + - podAffinityTerm: + labelSelector: + matchExpressions: + - key: koord-app + operator: In + values: + - koord-scheduler + topologyKey: kubernetes.io/hostname + weight: 100 +{{- with .Values.scheduler.nodeAffinity }} + nodeAffinity: +{{ toYaml . | indent 10 }} +{{- end }} + +{{- if .Values.scheduler.nodeSelector }} + nodeSelector: +{{ toYaml .Values.scheduler.nodeSelector | indent 8 }} +{{- end }} + +{{- if .Values.scheduler.tolerations }} + tolerations: +{{ toYaml .Values.scheduler.tolerations | indent 8 }} +{{- end }} + diff --git a/versions/v1.6.0/templates/koordlet-service.yaml b/versions/v1.6.0/templates/koordlet-service.yaml new file mode 100644 index 0000000..3857b16 --- /dev/null +++ b/versions/v1.6.0/templates/koordlet-service.yaml @@ -0,0 +1,19 @@ +{{- if .Values.koordlet.enableServiceMonitor }} +--- +apiVersion: v1 +kind: Service +metadata: + labels: + koord-app: koordlet + name: koordlet-service + namespace: {{ .Values.installation.namespace }} +spec: + clusterIP: None + ports: + - name: http + port: {{ .Values.koordlet.metrics.port }} + targetPort: {{ .Values.koordlet.metrics.port }} + selector: + koord-app: koordlet + +{{- end }} diff --git a/versions/v1.6.0/templates/koordlet-servicemonitor.yaml b/versions/v1.6.0/templates/koordlet-servicemonitor.yaml new file mode 100644 index 0000000..02e2174 --- /dev/null +++ b/versions/v1.6.0/templates/koordlet-servicemonitor.yaml @@ -0,0 +1,27 @@ +{{- if .Values.koordlet.enableServiceMonitor }} +--- +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + labels: + koord-app: koordlet + name: koordlet-service-monitor + namespace: {{ .Values.installation.namespace }} +spec: + endpoints: + - interval: 30s + port: http + relabelings: + - action: replace + regex: (.*) + replacement: $1 + sourceLabels: + - __meta_kubernetes_pod_node_name + targetLabel: node + scheme: http + jobLabel: koord-app + selector: + matchLabels: + koord-app: koordlet + +{{- end }} diff --git a/versions/v1.6.0/templates/koordlet.yaml b/versions/v1.6.0/templates/koordlet.yaml new file mode 100644 index 0000000..7a6a04d --- /dev/null +++ b/versions/v1.6.0/templates/koordlet.yaml @@ -0,0 +1,185 @@ +apiVersion: apps/v1 +kind: DaemonSet +metadata: + name: koordlet + namespace: {{ .Values.installation.namespace }} + labels: + koord-app: koordlet +spec: + selector: + matchLabels: + koord-app: koordlet + minReadySeconds: 10 + updateStrategy: + type: RollingUpdate + rollingUpdate: + maxUnavailable: 20% + template: + metadata: + labels: + koord-app: koordlet + runtimeproxy.koordinator.sh/skip-hookserver: "true" + spec: + {{- with .Values.imagePullSecrets }} + imagePullSecrets: + {{- toYaml . | nindent 8 }} + {{- end }} + containers: + - command: + - /koordlet + args: + - -addr=:{{ .Values.koordlet.metrics.port }} + - -cgroup-root-dir=/host-cgroup/ +{{- if .Values.koordlet.features }} + - -feature-gates={{ .Values.koordlet.features }} +{{- else }} + # other feature-gates enabled by default include BECPUSuppress, CPUBurst, RdtResctrl and NodeTopologyReport + - -feature-gates=BECPUEvict=true,BEMemoryEvict=true,CgroupReconcile=true,Accelerators=true +{{- end }} + - -runtime-hooks-host-endpoint={{ .Values.koordlet.hostDirs.koordletSockDir }}/koordlet.sock + - --logtostderr=true + - --v={{ .Values.koordlet.log.level }} + image: "{{ .Values.imageRepositoryHost }}/{{ .Values.koordlet.image.repository }}:{{ .Values.koordlet.image.tag }}" + imagePullPolicy: Always + name: koordlet + env: + - name: NODE_NAME + valueFrom: + fieldRef: + apiVersion: v1 + fieldPath: spec.nodeName + resources: + {{- toYaml .Values.koordlet.resources | nindent 12 }} + securityContext: + allowPrivilegeEscalation: true + capabilities: + add: + - SYS_ADMIN + privileged: true + volumeMounts: + - mountPath: /etc/localtime + name: host-time + readOnly: true + - mountPath: /host-cgroup/ + name: host-cgroup-root + - mountPath: /host-sys-fs/ + name: host-sys-fs + mountPropagation: Bidirectional + - mountPath: /host-var-run/ + name: host-var-run + readOnly: true + - mountPath: /host-run/ + name: host-run + readOnly: true + - mountPath: /host-var-run-koordlet/ + name: host-var-run-koordlet + mountPropagation: Bidirectional + - mountPath: /prediction-checkpoints + name: host-koordlet-checkpoint-dir + mountPropagation: Bidirectional + - mountPath: /host-sys/ + name: host-sys + readOnly: true + - mountPath: /etc/kubernetes/ + name: host-kubernetes + readOnly: true + - mountPath: /host-etc-hookserver/ + name: host-etc-hookserver + mountPropagation: Bidirectional + - mountPath: /var/lib/kubelet + name: host-kubelet-rootdir + readOnly: true + - mountPath: /var/run/koordlet/pod-resources/ + mountPropagation: Bidirectional + name: pod-resources-proxy +{{- if contains "TerwayQoS=true" .Values.koordlet.features }} + - mountPath: /host-var-lib/terway/qos + name: host-terway-qos +{{- end }} + - mountPath: /dev + name: host-dev + mountPropagation: HostToContainer + - mountPath: /metric-data/ + name: metric-db-path +{{- if .Values.koordlet.runtimeClassName }} + runtimeClassName: {{ .Values.koordlet.runtimeClassName }} +{{- end }} +{{- if .Values.koordlet.nodeAffinity }} + affinity: + {{- toYaml .Values.koordlet.nodeAffinity | nindent 8 }} +{{- end }} + tolerations: + - operator: Exists + hostNetwork: true + hostPID: true + terminationGracePeriodSeconds: 10 + serviceAccountName: koordlet + volumes: + - hostPath: + path: /etc/localtime + type: "" + name: host-time + - hostPath: + path: /sys/fs/cgroup/ + type: "" + name: host-cgroup-root + - hostPath: + path: /sys/fs/ + type: "" + name: host-sys-fs + - hostPath: + path: /var/run/ + type: "" + name: host-var-run + - hostPath: + path: /run/ + type: "" + name: host-run + - hostPath: + path: {{ .Values.koordlet.hostDirs.koordletSockDir }} + type: "DirectoryOrCreate" + name: host-var-run-koordlet + - hostPath: + path: {{ .Values.koordlet.hostDirs.predictionCheckpointDir }} + type: "DirectoryOrCreate" + name: host-koordlet-checkpoint-dir + - hostPath: + path: /sys/ + type: "" + name: host-sys + - hostPath: + path: {{ .Values.koordlet.hostDirs.kubeletConfigDir }} + type: "" + name: host-kubernetes + - hostPath: + path: {{ .Values.koordlet.hostDirs.koordProxyRegisterDir }} + type: "" + name: host-etc-hookserver + - hostPath: + path: {{ .Values.koordlet.hostDirs.kubeletLibDir }} + type: "" + name: host-kubelet-rootdir + - hostPath: + path: /dev + type: "" + name: host-dev + - hostPath: + path: {{ .Values.koordlet.hostDirs.podResourcesProxyPath }} + type: DirectoryOrCreate + name: pod-resources-proxy +{{- if contains "TerwayQoS=true" .Values.koordlet.features }} + - hostPath: + path: /var/lib/terway/qos + type: "DirectoryOrCreate" + name: host-terway-qos +{{- end }} +{{- if .Values.koordlet.hostDirs.koordletTSDBDir }} + - hostPath: + path: {{ .Values.koordlet.hostDirs.koordletTSDBDir }} + type: "" +{{- else }} + - emptyDir: + medium: Memory + sizeLimit: 150Mi +{{- end }} + name: metric-db-path diff --git a/versions/v1.6.0/templates/priority/koord-batch.yaml b/versions/v1.6.0/templates/priority/koord-batch.yaml new file mode 100644 index 0000000..24408f4 --- /dev/null +++ b/versions/v1.6.0/templates/priority/koord-batch.yaml @@ -0,0 +1,7 @@ +apiVersion: scheduling.k8s.io/v1 +description: Offline tasks, computing tasks, etc. +kind: PriorityClass +metadata: + name: koord-batch +preemptionPolicy: PreemptLowerPriority +value: 5000 \ No newline at end of file diff --git a/versions/v1.6.0/templates/priority/koord-free.yaml b/versions/v1.6.0/templates/priority/koord-free.yaml new file mode 100644 index 0000000..acb18fa --- /dev/null +++ b/versions/v1.6.0/templates/priority/koord-free.yaml @@ -0,0 +1,7 @@ +apiVersion: scheduling.k8s.io/v1 +description: Run lowest-priority offline batch jobs, generally refers to not making resource budgets. +kind: PriorityClass +metadata: + name: koord-free +preemptionPolicy: PreemptLowerPriority +value: 3000 \ No newline at end of file diff --git a/versions/v1.6.0/templates/priority/koord-mid.yaml b/versions/v1.6.0/templates/priority/koord-mid.yaml new file mode 100644 index 0000000..aabf190 --- /dev/null +++ b/versions/v1.6.0/templates/priority/koord-mid.yaml @@ -0,0 +1,7 @@ +apiVersion: scheduling.k8s.io/v1 +description: Nearline computation jobs whose SLO weaker than koord-prod. +kind: PriorityClass +metadata: + name: koord-mid +preemptionPolicy: PreemptLowerPriority +value: 7000 \ No newline at end of file diff --git a/versions/v1.6.0/templates/priority/koord-prod.yaml b/versions/v1.6.0/templates/priority/koord-prod.yaml new file mode 100644 index 0000000..b0664c3 --- /dev/null +++ b/versions/v1.6.0/templates/priority/koord-prod.yaml @@ -0,0 +1,7 @@ +apiVersion: scheduling.k8s.io/v1 +description: Online production system for applications and businesses. +kind: PriorityClass +metadata: + name: koord-prod +preemptionPolicy: PreemptLowerPriority +value: 9000 \ No newline at end of file diff --git a/versions/v1.6.0/templates/rbac/koord-descheduler.yaml b/versions/v1.6.0/templates/rbac/koord-descheduler.yaml new file mode 100644 index 0000000..3363b3a --- /dev/null +++ b/versions/v1.6.0/templates/rbac/koord-descheduler.yaml @@ -0,0 +1,113 @@ + +apiVersion: v1 +kind: ServiceAccount +metadata: + namespace: {{ .Values.installation.namespace }} + name: koord-descheduler +--- +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRole +metadata: + name: koord-descheduler-role +rules: +- apiGroups: + - "" + - events.k8s.io + resources: + - events + verbs: + - '*' +- apiGroups: + - coordination.k8s.io + resources: + - leases + verbs: + - create + - get + - update +- apiGroups: + - "" + resources: + - namespaces + verbs: + - list + - get + - watch +- apiGroups: + - "" + resources: + - nodes + verbs: + - list + - get + - patch + - update + - watch +- apiGroups: + - "" + resources: + - pods + verbs: + - '*' +- apiGroups: + - "" + resources: + - pods/eviction + verbs: + - create +- apiGroups: + - scheduling.k8s.io + resources: + - priorityclasses + verbs: + - get + - watch + - list +- apiGroups: + - apiextensions.k8s.io + resources: + - customresourcedefinitions + verbs: + - get + - list + - patch + - update + - watch +- apiGroups: + - apps + resources: + - '*' + verbs: + - get + - list + - watch +- apiGroups: + - apps.kruise.io + resources: + - '*' + verbs: + - get + - list + - watch +- apiGroups: + - config.koordinator.sh + - slo.koordinator.sh + - scheduling.koordinator.sh + - topology.node.k8s.io + resources: + - '*' + verbs: + - '*' +--- +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + name: koord-descheduler-rolebinding +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: koord-descheduler-role +subjects: + - kind: ServiceAccount + name: koord-descheduler + namespace: {{ .Values.installation.namespace }} \ No newline at end of file diff --git a/versions/v1.6.0/templates/rbac/koord-manager.yaml b/versions/v1.6.0/templates/rbac/koord-manager.yaml new file mode 100644 index 0000000..e6b66d4 --- /dev/null +++ b/versions/v1.6.0/templates/rbac/koord-manager.yaml @@ -0,0 +1,254 @@ +apiVersion: rbac.authorization.k8s.io/v1 +kind: Role +metadata: + name: koord-leader-election-role + namespace: {{ .Values.installation.namespace }} +rules: +- apiGroups: + - "" + resources: + - configmaps + verbs: + - get + - list + - watch + - create + - update + - patch + - delete +- apiGroups: + - coordination.k8s.io + resources: + - leases + verbs: + - get + - list + - watch + - create + - update + - patch + - delete +- apiGroups: + - "" + resources: + - events + verbs: + - create + - patch +--- +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRole +metadata: + creationTimestamp: null + name: koord-manager-role +rules: +- apiGroups: + - admissionregistration.k8s.io + resources: + - mutatingwebhookconfigurations + verbs: + - get + - list + - patch + - update + - watch +- apiGroups: + - admissionregistration.k8s.io + resources: + - validatingwebhookconfigurations + verbs: + - get + - list + - patch + - update + - watch +- apiGroups: + - config.koordinator.sh + resources: + - clustercolocationprofiles + verbs: + - get + - list + - watch +- apiGroups: + - "" + resources: + - configmaps + verbs: + - get + - list + - watch +- apiGroups: + - "" + resources: + - namespaces + verbs: + - get + - list + - watch +- apiGroups: + - "" + resources: + - nodes + verbs: + - get + - list + - watch + - patch +- apiGroups: + - "" + resources: + - nodes/status + verbs: + - get + - list + - watch + - patch + - update +- apiGroups: + - "" + resources: + - pods + verbs: + - get + - list + - watch +- apiGroups: + - "" + resources: + - secrets + verbs: + - create + - delete + - get + - list + - patch + - update + - watch +- apiGroups: + - quota.koordinator.sh + resources: + - elasticquotaprofiles + verbs: + - create + - delete + - get + - list + - patch + - update + - watch +- apiGroups: + - quota.koordinator.sh + resources: + - elasticquotaprofiles/status + verbs: + - get + - patch + - update +- apiGroups: + - scheduling.k8s.io + resources: + - priorityclasses + verbs: + - get + - list + - watch +- apiGroups: + - scheduling.koordinator.sh + resources: + - devices + verbs: + - get + - list + - watch +- apiGroups: + - scheduling.sigs.k8s.io + resources: + - elasticquotas + verbs: + - create + - delete + - get + - list + - patch + - update + - watch +- apiGroups: + - slo.koordinator.sh + resources: + - nodemetrics + verbs: + - create + - delete + - get + - list + - patch + - update + - watch +- apiGroups: + - slo.koordinator.sh + resources: + - nodemetrics/status + verbs: + - get + - patch + - update +- apiGroups: + - slo.koordinator.sh + resources: + - nodeslos + verbs: + - create + - delete + - get + - list + - patch + - update + - watch +- apiGroups: + - slo.koordinator.sh + resources: + - nodeslos/status + verbs: + - get + - patch + - update +- apiGroups: + - topology.node.k8s.io + resources: + - noderesourcetopologies + verbs: + - create + - delete + - get + - list + - patch + - update + - watch +--- +apiVersion: rbac.authorization.k8s.io/v1 +kind: RoleBinding +metadata: + name: koord-leader-election-rolebinding + namespace: {{ .Values.installation.namespace }} +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: Role + name: koord-leader-election-role +subjects: + - kind: ServiceAccount + name: koord-manager + namespace: {{ .Values.installation.namespace }} +--- +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + name: koord-manager-rolebinding +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: koord-manager-role +subjects: + - kind: ServiceAccount + name: koord-manager + namespace: {{ .Values.installation.namespace }} \ No newline at end of file diff --git a/versions/v1.6.0/templates/rbac/koord-scheduler.yaml b/versions/v1.6.0/templates/rbac/koord-scheduler.yaml new file mode 100644 index 0000000..f50daec --- /dev/null +++ b/versions/v1.6.0/templates/rbac/koord-scheduler.yaml @@ -0,0 +1,104 @@ + +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRole +metadata: + name: koord-scheduler-role +rules: +{{- if semverCompare "<= 1.20-0" .Capabilities.KubeVersion.Version }} +- apiGroups: + - "" + resources: + - namespaces + verbs: + - get + - list + - watch +{{- end }} +- apiGroups: + - coordination.k8s.io + resources: + - leases + verbs: + - create + - get + - update +- apiGroups: + - "" + resources: + - pods + verbs: + - patch + - update +- apiGroups: + - apiextensions.k8s.io + resources: + - customresourcedefinitions + verbs: + - get + - list + - patch + - update + - watch +- apiGroups: + - storage.k8s.io + resources: + - csidrivers + verbs: + - get + - list + - watch +- apiGroups: + - config.koordinator.sh + - slo.koordinator.sh + - scheduling.koordinator.sh + - topology.node.k8s.io + - scheduling.sigs.k8s.io + resources: + - '*' + verbs: + - '*' +--- +apiVersion: v1 +kind: ServiceAccount +metadata: + name: koord-scheduler + namespace: {{ .Values.installation.namespace }} +--- +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + name: koord-scheduler-rolebinding-custom +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: koord-scheduler-role +subjects: + - kind: ServiceAccount + name: koord-scheduler + namespace: {{ .Values.installation.namespace }} +--- +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + name: koord-scheduler-rolebinding +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: system:kube-scheduler +subjects: + - kind: ServiceAccount + name: koord-scheduler + namespace: {{ .Values.installation.namespace }} +--- +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + name: koord-scheduler-rolebinding-volume +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: system:volume-scheduler +subjects: + - kind: ServiceAccount + name: koord-scheduler + namespace: {{ .Values.installation.namespace }} \ No newline at end of file diff --git a/versions/v1.6.0/templates/rbac/koordlet.yaml b/versions/v1.6.0/templates/rbac/koordlet.yaml new file mode 100644 index 0000000..8cf1f36 --- /dev/null +++ b/versions/v1.6.0/templates/rbac/koordlet.yaml @@ -0,0 +1,69 @@ + +apiVersion: v1 +kind: ServiceAccount +metadata: + namespace: {{ .Values.installation.namespace }} + name: koordlet +--- +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRole +metadata: + name: koordlet-role +rules: +- apiGroups: + - config.koordinator.sh + - slo.koordinator.sh + - scheduling.koordinator.sh + - topology.node.k8s.io + resources: + - '*' + verbs: + - '*' +- apiGroups: + - "" + resources: + - configmaps + - configmaps/status + verbs: + - '*' +- apiGroups: + - "" + resources: + - nodes + - nodes/status + - nodes/proxy + - pods + - pods/status + - persistentvolumeclaims + - persistentvolumeclaims/status + verbs: + - patch + - update + - get + - list + - watch +- apiGroups: + - "" + resources: + - pods/eviction + verbs: + - '*' +- apiGroups: + - "" + resources: + - events + verbs: + - '*' +--- +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + name: koordlet-rolebinding +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: koordlet-role +subjects: + - kind: ServiceAccount + name: koordlet + namespace: {{ .Values.installation.namespace }} \ No newline at end of file diff --git a/versions/v1.6.0/templates/slo-controller-config.yaml b/versions/v1.6.0/templates/slo-controller-config.yaml new file mode 100644 index 0000000..f7e95fe --- /dev/null +++ b/versions/v1.6.0/templates/slo-controller-config.yaml @@ -0,0 +1,16 @@ +apiVersion: v1 +kind: ConfigMap +metadata: + name: slo-controller-config + namespace: {{ .Values.installation.namespace }} +data: + colocation-config: | + { + "enable": true + } + resource-threshold-config: | + { + "clusterStrategy": { + "enable": true + } + } diff --git a/versions/v1.6.0/templates/webhookconfiguration.yaml b/versions/v1.6.0/templates/webhookconfiguration.yaml new file mode 100644 index 0000000..68026fc --- /dev/null +++ b/versions/v1.6.0/templates/webhookconfiguration.yaml @@ -0,0 +1,240 @@ +apiVersion: admissionregistration.k8s.io/v1 +kind: MutatingWebhookConfiguration +metadata: + name: koordinator-mutating-webhook-configuration + annotations: + template: "" +webhooks: +{{ if contains "PodMutatingWebhook=false" .Values.featureGates }}{{ else }} +- clientConfig: + caBundle: Cg== + service: + name: koordinator-webhook-service + namespace: {{ .Values.installation.namespace }} + path: /mutate-pod + failurePolicy: {{ .Values.webhookConfiguration.failurePolicy.pods }} + admissionReviewVersions: + - v1 + - v1beta1 + sideEffects: None + timeoutSeconds: {{ .Values.webhookConfiguration.timeoutSeconds }} + name: mpod-create.koordinator.sh + namespaceSelector: + matchExpressions: + - key: control-plane + operator: DoesNotExist + rules: + - apiGroups: + - "" + apiVersions: + - v1 + operations: + - CREATE + resources: + - pods +- admissionReviewVersions: + - v1 + - v1beta1 + clientConfig: + caBundle: Cg== + service: + name: koordinator-webhook-service + namespace: {{ .Values.installation.namespace }} + path: /mutate-pod + failurePolicy: {{ .Values.webhookConfiguration.failurePolicy.pods }} + name: mpod-update.koordinator.sh + namespaceSelector: + matchExpressions: + - key: control-plane + operator: DoesNotExist + objectSelector: + matchExpressions: + - key: pod.koordinator.sh/mutating-update + operator: In + values: + - "true" + rules: + - apiGroups: + - "" + apiVersions: + - v1 + operations: + - UPDATE + resources: + - pods + sideEffects: None + timeoutSeconds: {{ .Values.webhookConfiguration.timeoutSeconds }} +{{- end }} +{{ if contains "ElasticMutatingWebhook=false" .Values.featureGates }}{{ else }} +- clientConfig: + caBundle: Cg== + service: + name: koordinator-webhook-service + namespace: {{ .Values.installation.namespace }} + path: /mutate-scheduling-sigs-k8s-io-v1alpha1-elasticquota + failurePolicy: {{ .Values.webhookConfiguration.failurePolicy.elasticquotas }} + admissionReviewVersions: + - v1 + - v1beta1 + sideEffects: None + timeoutSeconds: {{ .Values.webhookConfiguration.timeoutSeconds }} + name: melasticquota.koordinator.sh + namespaceSelector: + matchExpressions: + - key: control-plane + operator: DoesNotExist + rules: + - apiGroups: + - scheduling.sigs.k8s.io + apiVersions: + - v1alpha1 + operations: + - CREATE + resources: + - elasticquotas +{{- end }} +{{ if contains "NodeMutatingWebhook=true" .Values.featureGates }} +- admissionReviewVersions: + - v1 + - v1beta1 + clientConfig: + caBundle: Cg== + service: + name: koordinator-webhook-service + namespace: {{ .Values.installation.namespace }} + path: /mutate-node-status + failurePolicy: {{ .Values.webhookConfiguration.failurePolicy.nodeStatus }} + name: mnode-status.koordinator.sh + rules: + - apiGroups: + - "" + apiVersions: + - v1 + operations: + - CREATE + - UPDATE + resources: + - nodes/status + timeoutSeconds: {{ .Values.webhookConfiguration.timeoutSeconds }} + sideEffects: None +{{- end }} +--- +apiVersion: admissionregistration.k8s.io/v1 +kind: ValidatingWebhookConfiguration +metadata: + name: koordinator-validating-webhook-configuration + annotations: + template: "" +webhooks: +{{- if contains "ConfigMapValidatingWebhook=true" .Values.featureGates }} +- admissionReviewVersions: + - v1beta1 + clientConfig: + service: + name: koordinator-webhook-service + namespace: {{ .Values.installation.namespace }} + path: /validate-configmap + failurePolicy: Fail + name: vconfigmap.koordinator.sh + objectSelector: + matchExpressions: + - key: koordinator.sh/configmap-type + operator: In + values: + - slo-controller-config + rules: + - apiGroups: + - "" + apiVersions: + - v1 + operations: + - CREATE + - UPDATE + - DELETE + resources: + - configmaps + sideEffects: None +{{- end }} +{{- if contains "NodeValidatingWebhook=true" .Values.featureGates }} +- admissionReviewVersions: + - v1 + - v1beta1 + clientConfig: + service: + name: koordinator-webhook-service + namespace: {{ .Values.installation.namespace }} + path: /validate-node + failurePolicy: {{ .Values.webhookConfiguration.failurePolicy.nodes }} + timeoutSeconds: {{ .Values.webhookConfiguration.timeoutSeconds }} + name: vnode.koordinator.sh + rules: + - apiGroups: + - "" + apiVersions: + - v1 + operations: + - CREATE + - UPDATE + resources: + - nodes + sideEffects: None +{{- end }} +{{- if contains "PodValidatingWebhook=false" .Values.featureGates }}{{ else }} +- clientConfig: + caBundle: Cg== + service: + name: koordinator-webhook-service + namespace: {{ .Values.installation.namespace }} + path: /validate-pod + failurePolicy: {{ .Values.webhookConfiguration.failurePolicy.pods }} + admissionReviewVersions: + - v1 + - v1beta1 + sideEffects: None + timeoutSeconds: {{ .Values.webhookConfiguration.timeoutSeconds }} + name: vpod.koordinator.sh + namespaceSelector: + matchExpressions: + - key: control-plane + operator: DoesNotExist + rules: + - apiGroups: + - "" + apiVersions: + - v1 + operations: + - CREATE + - UPDATE + resources: + - pods +{{- end }} +{{- if contains "ElasticValidatingWebhook=false" .Values.featureGates }}{{ else }} +- clientConfig: + caBundle: Cg== + service: + name: koordinator-webhook-service + namespace: {{ .Values.installation.namespace }} + path: /validate-scheduling-sigs-k8s-io-v1alpha1-elasticquota + failurePolicy: {{ .Values.webhookConfiguration.failurePolicy.elasticquotas }} + admissionReviewVersions: + - v1 + - v1beta1 + sideEffects: None + timeoutSeconds: {{ .Values.webhookConfiguration.timeoutSeconds }} + name: velasticquota.koordinator.sh + namespaceSelector: + matchExpressions: + - key: control-plane + operator: DoesNotExist + rules: + - apiGroups: + - scheduling.sigs.k8s.io + apiVersions: + - v1alpha1 + operations: + - CREATE + - UPDATE + - DELETE + resources: + - elasticquotas +{{- end }} diff --git a/versions/v1.6.0/values.yaml b/versions/v1.6.0/values.yaml new file mode 100644 index 0000000..add2d2b --- /dev/null +++ b/versions/v1.6.0/values.yaml @@ -0,0 +1,173 @@ +# Default values for koordinator. +# This is a YAML-formatted file. +# Declare variables to be passed into your templates. + +crds: + # whether enable crds + managed: true + # enable or disable specific crds + clustercolocationprofiles: true + devices: true + elasticquotaprofiles: true + elasticquotas: true + nodemetrics: true + nodeslos: true + noderesourcetopologies: true + recommendations: true + reservations: true + podgroups: true + podmigrationjobs: true + +# values for koordinator installation +installation: + namespace: koordinator-system + roleListGroups: + - '*' + +featureGates: "" + +imageRepositoryHost: registry.cn-beijing.aliyuncs.com + +imagePullSecrets: {} + +koordlet: + image: + repository: koordinator-sh/koordlet + tag: "v1.6.0" + resources: + limits: + cpu: 200m + # recommended for less than 200 pods per node + memory: 256Mi + requests: + cpu: "0" + memory: "0" + features: "" + log: + # log level for koordlet + level: "4" + hostDirs: + kubeletConfigDir: /etc/kubernetes/ + kubeletLibDir: /var/lib/kubelet/ + koordProxyRegisterDir: /etc/runtime/hookserver.d/ + koordletSockDir: /var/run/koordlet + predictionCheckpointDir: /var/run/koordlet/prediction-checkpoints + # if not specified, use tmpfs by default + koordletTSDBDir: "" + podResourcesProxyPath: /var/run/koordlet/pod-resources/ + runtimeClassName: "" + nodeAffinity: {} + metrics: + port: 9316 + enableServiceMonitor: false + + +manager: + # settings for log print + log: + # log level for koord-manager + level: "4" + + replicas: 2 + image: + repository: koordinator-sh/koord-manager + tag: "v1.6.0" + webhook: + port: 9876 + metrics: + addr: "" + port: 8080 + healthProbe: + port: 8000 + + resyncPeriod: "0" + + # resources of koord-manager container + resources: + limits: + cpu: 1000m + memory: 1Gi + requests: + cpu: 500m + memory: 256Mi + + hostNetwork: false + + nodeAffinity: {} + nodeSelector: {} + tolerations: [] + +webhookConfiguration: + failurePolicy: + pods: Ignore + elasticquotas: Ignore + nodeStatus: Ignore + nodes: Ignore + timeoutSeconds: 30 + +serviceAccount: + annotations: {} + + +scheduler: + # settings for log print + log: + # log level for koord-scheduler + level: "4" + + replicas: 2 + image: + repository: koordinator-sh/koord-scheduler + tag: "v1.6.0" + port: 10251 + + # feature-gates for k8s > 1.22 + featureGates: "" + # feature-gates for k8s 1.22 + compatible122FeatureGates: "CompatibleCSIStorageCapacity=true" + # feature-gates for k8s < 1.22 + compatibleBelow122FeatureGates: "DisableCSIStorageCapacityInformer=true,CompatiblePodDisruptionBudget=true" + + # resources of koord-scheduler container + resources: + limits: + cpu: 1000m + memory: 1Gi + requests: + cpu: 500m + memory: 256Mi + + hostNetwork: false + + nodeAffinity: {} + nodeSelector: {} + tolerations: [] + +descheduler: + # settings for log print + log: + # log level for koord-descheduler + level: "4" + + replicas: 2 + image: + repository: koordinator-sh/koord-descheduler + tag: "v1.6.0" + port: 10251 + + featureGates: "" + + # resources of koord-descheduler container + resources: + limits: + cpu: 1000m + memory: 1Gi + requests: + cpu: 500m + memory: 256Mi + + hostNetwork: false + + nodeAffinity: {} + nodeSelector: {} + tolerations: [] From 47c39abb97da5d99f72577ffb3269d4749e825ef Mon Sep 17 00:00:00 2001 From: wangjianyu Date: Thu, 20 Feb 2025 21:00:58 +0800 Subject: [PATCH 2/2] Update lint-and-test.yml Signed-off-by: wangjianyu --- .github/workflows/lint-and-test.yml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.github/workflows/lint-and-test.yml b/.github/workflows/lint-and-test.yml index b76f328..6215fe0 100644 --- a/.github/workflows/lint-and-test.yml +++ b/.github/workflows/lint-and-test.yml @@ -17,7 +17,7 @@ jobs: - name: Set up python uses: actions/setup-python@v2 with: - python-version: 3.7 + python-version: 3.13.2 - name: Setup Chart Linting id: lint