--- # Source: gpu-operator/crds/nvidia.com_clusterpolicies.yaml --- apiVersion: apiextensions.k8s.io/v1 kind: CustomResourceDefinition metadata: annotations: controller-gen.kubebuilder.io/version: v0.20.1 name: clusterpolicies.nvidia.com spec: group: nvidia.com names: kind: ClusterPolicy listKind: ClusterPolicyList plural: clusterpolicies singular: clusterpolicy scope: Cluster versions: - additionalPrinterColumns: - jsonPath: .status.state name: Status type: string - jsonPath: .metadata.creationTimestamp name: Age type: string name: v1 schema: openAPIV3Schema: description: ClusterPolicy is the Schema for the clusterpolicies 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: ClusterPolicySpec defines the desired state of ClusterPolicy properties: ccManager: description: CCManager component spec properties: args: description: 'Optional: List of arguments' items: type: string type: array defaultMode: description: Default CC mode setting for compatible GPUs on the node enum: - "on" - "off" - devtools type: string enabled: description: Enabled indicates if deployment of CC Manager is enabled type: boolean env: description: 'Optional: List of environment variables' items: description: EnvVar represents an environment variable present in a Container. properties: name: description: Name of the environment variable. type: string value: description: Value of the environment variable. type: string required: - name type: object type: array hostNetwork: description: HostNetwork indicates whether the CC Manager pod uses the host's network namespace. type: boolean image: description: CC Manager image name pattern: '[a-zA-Z0-9\-]+' type: string imagePullPolicy: description: Image pull policy type: string imagePullSecrets: description: Image pull secrets items: type: string type: array repository: description: CC Manager image repository type: string resources: description: 'Optional: Define resources requests and limits for each pod' properties: limits: 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: |- Limits describes the maximum amount of compute resources allowed. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ type: object requests: 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: |- Requests describes the minimum amount of compute resources required. If Requests is omitted for a container, it defaults to Limits if that is explicitly specified, otherwise to an implementation-defined value. Requests cannot exceed Limits. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ type: object type: object version: description: CC Manager image tag type: string type: object cdi: description: CDI configures how the Container Device Interface is used in the cluster properties: default: default: false description: 'Deprecated: This field is no longer used. Setting cdi.enabled=true will configure CDI as the default mechanism for making GPUs accessible to containers.' type: boolean enabled: default: true description: Enabled indicates whether the Container Device Interface (CDI) should be used as the mechanism for making GPUs accessible to containers. type: boolean nriPluginEnabled: default: false description: NRIPluginEnabled indicates whether an NRI Plugin should be run as a means of injecting CDI devices to gpu management containers. type: boolean type: object daemonsets: description: Daemonset defines common configuration for all Daemonsets properties: annotations: additionalProperties: type: string description: |- Optional: Annotations is an unstructured key value map stored with a resource that may be set by external tools to store and retrieve arbitrary metadata. They are not queryable and should be preserved when modifying objects. type: object labels: additionalProperties: type: string description: |- Optional: Map of string keys and values that can be used to organize and categorize (scope and select) objects. May match selectors of replication controllers and services. type: object podSecurityContext: description: 'Optional: Set pod-level security context for all DaemonSet pods (applies as defaults to all containers)' properties: appArmorProfile: description: |- appArmorProfile is the AppArmor options to use by the containers in this pod. Note that this field cannot be set when spec.os.name is windows. properties: localhostProfile: description: |- localhostProfile indicates a profile loaded on the node that should be used. The profile must be preconfigured on the node to work. Must match the loaded name of the profile. Must be set if and only if type is "Localhost". type: string type: description: |- type indicates which kind of AppArmor profile will be applied. Valid options are: Localhost - a profile pre-loaded on the node. RuntimeDefault - the container runtime's default profile. Unconfined - no AppArmor enforcement. type: string required: - type type: object fsGroup: description: |- A special supplemental group that applies to all containers in a pod. Some volume types allow the Kubelet to change the ownership of that volume to be owned by the pod: 1. The owning GID will be the FSGroup 2. The setgid bit is set (new files created in the volume will be owned by FSGroup) 3. The permission bits are OR'd with rw-rw---- If unset, the Kubelet will not modify the ownership and permissions of any volume. Note that this field cannot be set when spec.os.name is windows. format: int64 type: integer fsGroupChangePolicy: description: |- fsGroupChangePolicy defines behavior of changing ownership and permission of the volume before being exposed inside Pod. This field will only apply to volume types which support fsGroup based ownership(and permissions). It will have no effect on ephemeral volume types such as: secret, configmaps and emptydir. Valid values are "OnRootMismatch" and "Always". If not specified, "Always" is used. Note that this field cannot be set when spec.os.name is windows. type: string runAsGroup: description: |- The GID to run the entrypoint of the container process. Uses runtime default if unset. May also be set in SecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence for that container. Note that this field cannot be set when spec.os.name is windows. format: int64 type: integer runAsNonRoot: description: |- Indicates that the container must run as a non-root user. If true, the Kubelet will validate the image at runtime to ensure that it does not run as UID 0 (root) and fail to start the container if it does. If unset or false, no such validation will be performed. May also be set in SecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. type: boolean runAsUser: description: |- The UID to run the entrypoint of the container process. Defaults to user specified in image metadata if unspecified. May also be set in SecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence for that container. Note that this field cannot be set when spec.os.name is windows. format: int64 type: integer seLinuxChangePolicy: description: |- seLinuxChangePolicy defines how the container's SELinux label is applied to all volumes used by the Pod. It has no effect on nodes that do not support SELinux or to volumes does not support SELinux. Valid values are "MountOption" and "Recursive". "Recursive" means relabeling of all files on all Pod volumes by the container runtime. This may be slow for large volumes, but allows mixing privileged and unprivileged Pods sharing the same volume on the same node. "MountOption" mounts all eligible Pod volumes with `-o context` mount option. This requires all Pods that share the same volume to use the same SELinux label. It is not possible to share the same volume among privileged and unprivileged Pods. Eligible volumes are in-tree FibreChannel and iSCSI volumes, and all CSI volumes whose CSI driver announces SELinux support by setting spec.seLinuxMount: true in their CSIDriver instance. Other volumes are always re-labelled recursively. "MountOption" value is allowed only when SELinuxMount feature gate is enabled. If not specified and SELinuxMount feature gate is enabled, "MountOption" is used. If not specified and SELinuxMount feature gate is disabled, "MountOption" is used for ReadWriteOncePod volumes and "Recursive" for all other volumes. This field affects only Pods that have SELinux label set, either in PodSecurityContext or in SecurityContext of all containers. All Pods that use the same volume should use the same seLinuxChangePolicy, otherwise some pods can get stuck in ContainerCreating state. Note that this field cannot be set when spec.os.name is windows. type: string seLinuxOptions: description: |- The SELinux context to be applied to all containers. If unspecified, the container runtime will allocate a random SELinux context for each container. May also be set in SecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence for that container. Note that this field cannot be set when spec.os.name is windows. properties: level: description: Level is SELinux level label that applies to the container. type: string role: description: Role is a SELinux role label that applies to the container. type: string type: description: Type is a SELinux type label that applies to the container. type: string user: description: User is a SELinux user label that applies to the container. type: string type: object seccompProfile: description: |- The seccomp options to use by the containers in this pod. Note that this field cannot be set when spec.os.name is windows. properties: localhostProfile: description: |- localhostProfile indicates a profile defined in a file on the node should be used. The profile must be preconfigured on the node to work. Must be a descending path, relative to the kubelet's configured seccomp profile location. Must be set if type is "Localhost". Must NOT be set for any other type. type: string type: description: |- type indicates which kind of seccomp profile will be applied. Valid options are: Localhost - a profile defined in a file on the node should be used. RuntimeDefault - the container runtime default profile should be used. Unconfined - no profile should be applied. type: string required: - type type: object supplementalGroups: description: |- A list of groups applied to the first process run in each container, in addition to the container's primary GID and fsGroup (if specified). If the SupplementalGroupsPolicy feature is enabled, the supplementalGroupsPolicy field determines whether these are in addition to or instead of any group memberships defined in the container image. If unspecified, no additional groups are added, though group memberships defined in the container image may still be used, depending on the supplementalGroupsPolicy field. Note that this field cannot be set when spec.os.name is windows. items: format: int64 type: integer type: array x-kubernetes-list-type: atomic supplementalGroupsPolicy: description: |- Defines how supplemental groups of the first container processes are calculated. Valid values are "Merge" and "Strict". If not specified, "Merge" is used. (Alpha) Using the field requires the SupplementalGroupsPolicy feature gate to be enabled and the container runtime must implement support for this feature. Note that this field cannot be set when spec.os.name is windows. type: string sysctls: description: |- Sysctls hold a list of namespaced sysctls used for the pod. Pods with unsupported sysctls (by the container runtime) might fail to launch. Note that this field cannot be set when spec.os.name is windows. items: description: Sysctl defines a kernel parameter to be set properties: name: description: Name of a property to set type: string value: description: Value of a property to set type: string required: - name - value type: object type: array x-kubernetes-list-type: atomic windowsOptions: description: |- The Windows specific settings applied to all containers. If unspecified, the options within a container's SecurityContext will be used. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. Note that this field cannot be set when spec.os.name is linux. properties: gmsaCredentialSpec: description: |- GMSACredentialSpec is where the GMSA admission webhook (https://github.com/kubernetes-sigs/windows-gmsa) inlines the contents of the GMSA credential spec named by the GMSACredentialSpecName field. type: string gmsaCredentialSpecName: description: GMSACredentialSpecName is the name of the GMSA credential spec to use. type: string hostProcess: description: |- HostProcess determines if a container should be run as a 'Host Process' container. All of a Pod's containers must have the same effective HostProcess value (it is not allowed to have a mix of HostProcess containers and non-HostProcess containers). In addition, if HostProcess is true then HostNetwork must also be set to true. type: boolean runAsUserName: description: |- The UserName in Windows to run the entrypoint of the container process. Defaults to the user specified in image metadata if unspecified. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. type: string type: object type: object priorityClassName: type: string rollingUpdate: description: 'Optional: Configuration for rolling update of all DaemonSet pods' properties: maxUnavailable: type: string type: object tolerations: description: 'Optional: Set tolerations' items: description: |- The pod this Toleration is attached to tolerates any taint that matches the triple using the matching operator . properties: effect: description: |- Effect indicates the taint effect to match. Empty means match all taint effects. When specified, allowed values are NoSchedule, PreferNoSchedule and NoExecute. type: string key: description: |- Key is the taint key that the toleration applies to. Empty means match all taint keys. If the key is empty, operator must be Exists; this combination means to match all values and all keys. type: string operator: description: |- Operator represents a key's relationship to the value. Valid operators are Exists, Equal, Lt, and Gt. Defaults to Equal. Exists is equivalent to wildcard for value, so that a pod can tolerate all taints of a particular category. Lt and Gt perform numeric comparisons (requires feature gate TaintTolerationComparisonOperators). type: string tolerationSeconds: description: |- TolerationSeconds represents the period of time the toleration (which must be of effect NoExecute, otherwise this field is ignored) tolerates the taint. By default, it is not set, which means tolerate the taint forever (do not evict). Zero and negative values will be treated as 0 (evict immediately) by the system. format: int64 type: integer value: description: |- Value is the taint value the toleration matches to. If the operator is Exists, the value should be empty, otherwise just a regular string. type: string type: object type: array updateStrategy: default: RollingUpdate enum: - RollingUpdate - OnDelete type: string type: object dcgm: description: DCGM component spec properties: args: description: 'Optional: List of arguments' items: type: string type: array enabled: description: Enabled indicates if deployment of NVIDIA DCGM Hostengine as a separate pod is enabled. type: boolean env: description: 'Optional: List of environment variables' items: description: EnvVar represents an environment variable present in a Container. properties: name: description: Name of the environment variable. type: string value: description: Value of the environment variable. type: string required: - name type: object type: array hostNetwork: description: HostNetwork indicates whether the DCGM pod uses the host's network namespace. type: boolean hostPort: description: 'Deprecated: HostPort represents host port that needs to be bound for DCGM engine (Default: 5555)' format: int32 type: integer image: description: NVIDIA DCGM image name pattern: '[a-zA-Z0-9\-]+' type: string imagePullPolicy: description: Image pull policy type: string imagePullSecrets: description: Image pull secrets items: type: string type: array repository: description: NVIDIA DCGM image repository type: string resources: description: 'Optional: Define resources requests and limits for each pod' properties: limits: 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: |- Limits describes the maximum amount of compute resources allowed. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ type: object requests: 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: |- Requests describes the minimum amount of compute resources required. If Requests is omitted for a container, it defaults to Limits if that is explicitly specified, otherwise to an implementation-defined value. Requests cannot exceed Limits. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ type: object type: object version: description: NVIDIA DCGM image tag type: string type: object dcgmExporter: description: DCGMExporter spec properties: annotations: additionalProperties: type: string description: |- Optional: Annotations is an unstructured key value map stored with a resource that may be set by external tools to store and retrieve arbitrary metadata. They are not queryable and should be preserved when modifying objects. type: object args: description: 'Optional: List of arguments' items: type: string type: array config: description: 'Optional: Custom metrics configuration for NVIDIA DCGM Exporter' properties: name: description: ConfigMap name with file dcgm-metrics.csv for metrics to be collected by NVIDIA DCGM Exporter type: string type: object enablePodLabels: description: |- Enable Kubernetes pod labels as Prometheus label dimensions in DCGM exporter metrics. (Requires cluster-level read access to pods.) type: boolean enablePodUID: description: |- Enable Kubernetes pod UID as a Prometheus label dimension in DCGM exporter metrics. (Requires cluster-level read access to pods.) type: boolean enabled: description: Enabled indicates if deployment of NVIDIA DCGM Exporter through operator is enabled type: boolean env: description: 'Optional: List of environment variables' items: description: EnvVar represents an environment variable present in a Container. properties: name: description: Name of the environment variable. type: string value: description: Value of the environment variable. type: string required: - name type: object type: array hostNetwork: description: HostNetwork allows the DCGM-Exporter daemon set to expose metrics port on the host's network namespace. type: boolean hostPID: description: HostPID allows the DCGM-Exporter daemon set to access the host's PID namespace type: boolean hpcJobMapping: description: 'Optional: HPC job mapping configuration for NVIDIA DCGM Exporter' properties: directory: description: |- Directory path where HPC job mapping files are created by the workload manager Defaults to /var/lib/dcgm-exporter/job-mapping if not specified type: string enabled: description: Enable HPC job mapping for DCGM Exporter type: boolean type: object image: description: NVIDIA DCGM Exporter image name pattern: '[a-zA-Z0-9\-]+' type: string imagePullPolicy: description: Image pull policy type: string imagePullSecrets: description: Image pull secrets items: type: string type: array podLabelAllowlistRegex: description: |- Regex list for filtering which Kubernetes pod labels are included in DCGM exporter metrics. Empty means all pod labels are included. items: type: string type: array repository: description: NVIDIA DCGM Exporter image repository type: string resources: description: 'Optional: Define resources requests and limits for each pod' properties: limits: 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: |- Limits describes the maximum amount of compute resources allowed. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ type: object requests: 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: |- Requests describes the minimum amount of compute resources required. If Requests is omitted for a container, it defaults to Limits if that is explicitly specified, otherwise to an implementation-defined value. Requests cannot exceed Limits. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ type: object type: object service: description: 'Optional: Service configuration for NVIDIA DCGM Exporter' properties: internalTrafficPolicy: description: InternalTrafficPolicy describes how nodes distribute service traffic they receive on the ClusterIP. type: string type: description: Type represents the ServiceType which describes ingress methods for a service type: string type: object serviceMonitor: description: 'Optional: ServiceMonitor configuration for NVIDIA DCGM Exporter' properties: additionalLabels: additionalProperties: type: string description: AdditionalLabels to add to ServiceMonitor instance for NVIDIA DCGM Exporter type: object enabled: description: Enabled indicates if ServiceMonitor is deployed for NVIDIA DCGM Exporter type: boolean honorLabels: description: HonorLabels chooses the metric’s labels on collisions with target labels. type: boolean interval: description: |- Interval which metrics should be scraped from NVIDIA DCGM Exporter. If not specified Prometheus’ global scrape interval is used. Supported units: y, w, d, h, m, s, ms pattern: ^(0|(([0-9]+)y)?(([0-9]+)w)?(([0-9]+)d)?(([0-9]+)h)?(([0-9]+)m)?(([0-9]+)s)?(([0-9]+)ms)?)$ type: string relabelings: description: Relabelings allows to rewrite labels on metric sets for NVIDIA DCGM Exporter items: description: |- RelabelConfig allows dynamic rewriting of the label set for targets, alerts, scraped samples and remote write samples. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#relabel_config properties: action: default: replace description: |- action to perform based on the regex matching. `Uppercase` and `Lowercase` actions require Prometheus >= v2.36.0. `DropEqual` and `KeepEqual` actions require Prometheus >= v2.41.0. Default: "Replace" enum: - replace - Replace - keep - Keep - drop - Drop - hashmod - HashMod - labelmap - LabelMap - labeldrop - LabelDrop - labelkeep - LabelKeep - lowercase - Lowercase - uppercase - Uppercase - keepequal - KeepEqual - dropequal - DropEqual type: string modulus: description: |- modulus to take of the hash of the source label values. Only applicable when the action is `HashMod`. format: int64 type: integer regex: description: regex defines the regular expression against which the extracted value is matched. type: string replacement: description: |- replacement value against which a Replace action is performed if the regular expression matches. Regex capture groups are available. type: string separator: description: separator defines the string between concatenated SourceLabels. type: string sourceLabels: description: |- sourceLabels defines the source labels select values from existing labels. Their content is concatenated using the configured Separator and matched against the configured regular expression. items: description: |- LabelName is a valid Prometheus label name. For Prometheus 3.x, a label name is valid if it contains UTF-8 characters. For Prometheus 2.x, a label name is only valid if it contains ASCII characters, letters, numbers, as well as underscores. type: string type: array targetLabel: description: |- targetLabel defines the label to which the resulting string is written in a replacement. It is mandatory for `Replace`, `HashMod`, `Lowercase`, `Uppercase`, `KeepEqual` and `DropEqual` actions. Regex capture groups are available. type: string type: object type: array type: object version: description: NVIDIA DCGM Exporter image tag type: string type: object devicePlugin: description: DevicePlugin component spec properties: args: description: 'Optional: List of arguments' items: type: string type: array config: description: 'Optional: Configuration for the NVIDIA Device Plugin via the ConfigMap' properties: default: description: Default config name within the ConfigMap for the NVIDIA Device Plugin config type: string name: description: ConfigMap name for NVIDIA Device Plugin config including shared config between plugin and GFD type: string type: object enabled: description: Enabled indicates if deployment of NVIDIA Device Plugin through operator is enabled type: boolean env: description: 'Optional: List of environment variables' items: description: EnvVar represents an environment variable present in a Container. properties: name: description: Name of the environment variable. type: string value: description: Value of the environment variable. type: string required: - name type: object type: array hostNetwork: description: HostNetwork indicates whether the Device Plugin pod uses the host's network namespace. type: boolean image: description: NVIDIA Device Plugin image name pattern: '[a-zA-Z0-9\-]+' type: string imagePullPolicy: description: Image pull policy type: string imagePullSecrets: description: Image pull secrets items: type: string type: array mps: description: 'Optional: MPS related configuration for the NVIDIA Device Plugin' properties: root: default: /run/nvidia/mps description: Root defines the MPS root path on the host type: string type: object repository: description: NVIDIA Device Plugin image repository type: string resources: description: 'Optional: Define resources requests and limits for each pod' properties: limits: 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: |- Limits describes the maximum amount of compute resources allowed. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ type: object requests: 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: |- Requests describes the minimum amount of compute resources required. If Requests is omitted for a container, it defaults to Limits if that is explicitly specified, otherwise to an implementation-defined value. Requests cannot exceed Limits. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ type: object type: object version: description: NVIDIA Device Plugin image tag type: string type: object driver: description: Driver component spec properties: args: description: 'Optional: List of arguments' items: type: string type: array certConfig: description: 'Optional: Custom certificates configuration for NVIDIA Driver container' properties: name: type: string type: object enabled: description: Enabled indicates if deployment of NVIDIA Driver through operator is enabled type: boolean env: description: 'Optional: List of environment variables' items: description: EnvVar represents an environment variable present in a Container. properties: name: description: Name of the environment variable. type: string value: description: Value of the environment variable. type: string required: - name type: object type: array hostNetwork: description: HostNetwork indicates whether the Driver pod uses the host's network namespace. type: boolean image: description: NVIDIA Driver image name pattern: '[a-zA-Z0-9\-]+' type: string imagePullPolicy: description: Image pull policy type: string imagePullSecrets: description: Image pull secrets items: type: string type: array kernelModuleConfig: description: 'Optional: Kernel module configuration parameters for the NVIDIA Driver' properties: name: type: string type: object kernelModuleType: default: auto description: |- KernelModuleType represents the type of driver kernel modules to be used when installing the GPU driver. Accepted values are auto, proprietary and open. NOTE: If auto is chosen, it means that the recommended kernel module type is chosen based on the GPU devices on the host and the driver branch used enum: - auto - open - proprietary type: string licensingConfig: description: 'Optional: Licensing configuration for NVIDIA vGPU licensing' properties: configMapName: description: 'Deprecated: ConfigMapName has been deprecated in favour of SecretName. Please use secrets to handle the licensing server configuration more securely' type: string nlsEnabled: description: NLSEnabled indicates if NVIDIA Licensing System is used for licensing. type: boolean secretName: description: SecretName indicates the name of the secret containing the licensing token type: string type: object livenessProbe: description: NVIDIA Driver container liveness probe settings properties: failureThreshold: description: |- Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. format: int32 minimum: 1 type: integer initialDelaySeconds: description: |- Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer periodSeconds: description: |- How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. format: int32 minimum: 1 type: integer successThreshold: description: |- Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. format: int32 minimum: 1 type: integer timeoutSeconds: description: |- Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 minimum: 1 type: integer type: object manager: description: Manager represents configuration for NVIDIA Driver Manager initContainer properties: env: description: 'Optional: List of environment variables' items: description: EnvVar represents an environment variable present in a Container. properties: name: description: Name of the environment variable. type: string value: description: Value of the environment variable. type: string required: - name type: object type: array image: description: Image represents NVIDIA Driver Manager image name pattern: '[a-zA-Z0-9\-]+' type: string imagePullPolicy: description: Image pull policy type: string imagePullSecrets: description: Image pull secrets items: type: string type: array repository: description: Repository represents Driver Managerrepository path type: string version: description: Version represents NVIDIA Driver Manager image tag(version) type: string type: object rdma: description: GPUDirectRDMASpec defines the properties for nvidia-peermem deployment properties: enabled: description: Enabled indicates if GPUDirect RDMA is enabled through GPU operator type: boolean useHostMofed: description: UseHostMOFED indicates to use MOFED drivers directly installed on the host to enable GPUDirect RDMA type: boolean type: object readinessProbe: description: NVIDIA Driver container readiness probe settings properties: failureThreshold: description: |- Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. format: int32 minimum: 1 type: integer initialDelaySeconds: description: |- Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer periodSeconds: description: |- How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. format: int32 minimum: 1 type: integer successThreshold: description: |- Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. format: int32 minimum: 1 type: integer timeoutSeconds: description: |- Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 minimum: 1 type: integer type: object repoConfig: description: 'Optional: Custom repo configuration for NVIDIA Driver container' properties: configMapName: type: string type: object repository: description: NVIDIA Driver image repository type: string resources: description: 'Optional: Define resources requests and limits for each pod' properties: limits: 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: |- Limits describes the maximum amount of compute resources allowed. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ type: object requests: 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: |- Requests describes the minimum amount of compute resources required. If Requests is omitted for a container, it defaults to Limits if that is explicitly specified, otherwise to an implementation-defined value. Requests cannot exceed Limits. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ type: object type: object secretEnv: description: 'Optional: SecretEnv represents the name of the Kubernetes Secret with secret environment variables for the NVIDIA Driver' type: string startupProbe: description: NVIDIA Driver container startup probe settings properties: failureThreshold: description: |- Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. format: int32 minimum: 1 type: integer initialDelaySeconds: description: |- Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer periodSeconds: description: |- How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. format: int32 minimum: 1 type: integer successThreshold: description: |- Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. format: int32 minimum: 1 type: integer timeoutSeconds: description: |- Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 minimum: 1 type: integer type: object upgradePolicy: description: Driver auto-upgrade settings properties: autoUpgrade: default: false description: |- AutoUpgrade is a global switch for automatic upgrade feature if set to false all other options are ignored type: boolean drain: description: DrainSpec describes configuration for node drain during automatic upgrade properties: deleteEmptyDir: default: false description: |- DeleteEmptyDir indicates if should continue even if there are pods using emptyDir (local data that will be deleted when the node is drained) type: boolean enable: default: false description: Enable indicates if node draining is allowed during upgrade type: boolean force: default: false description: Force indicates if force draining is allowed type: boolean podSelector: description: |- PodSelector specifies a label selector to filter pods on the node that need to be drained For more details on label selectors, see: https://kubernetes.io/docs/concepts/overview/working-with-objects/labels/#label-selectors type: string timeoutSeconds: default: 300 description: TimeoutSecond specifies the length of time in seconds to wait before giving up drain, zero means infinite minimum: 0 type: integer type: object maxParallelUpgrades: default: 1 description: |- MaxParallelUpgrades indicates how many nodes can be upgraded in parallel 0 means no limit, all nodes will be upgraded in parallel minimum: 0 type: integer maxUnavailable: anyOf: - type: integer - type: string default: 25% description: |- MaxUnavailable is the maximum number of nodes with the driver installed, that can be unavailable during the upgrade. Value can be an absolute number (ex: 5) or a percentage of total nodes at the start of upgrade (ex: 10%). Absolute number is calculated from percentage by rounding up. By default, a fixed value of 25% is used. x-kubernetes-int-or-string: true podDeletion: description: PodDeletionSpec describes configuration for deletion of pods using special resources during automatic upgrade properties: deleteEmptyDir: default: false description: |- DeleteEmptyDir indicates if should continue even if there are pods using emptyDir (local data that will be deleted when the pod is deleted) type: boolean force: default: false description: Force indicates if force deletion is allowed type: boolean timeoutSeconds: default: 300 description: |- TimeoutSecond specifies the length of time in seconds to wait before giving up on pod termination, zero means infinite minimum: 0 type: integer type: object waitForCompletion: description: WaitForCompletionSpec describes the configuration for waiting on job completions properties: podSelector: description: |- PodSelector specifies a label selector for the pods to wait for completion For more details on label selectors, see: https://kubernetes.io/docs/concepts/overview/working-with-objects/labels/#label-selectors type: string timeoutSeconds: default: 0 description: |- TimeoutSecond specifies the length of time in seconds to wait before giving up on pod termination, zero means infinite minimum: 0 type: integer type: object type: object useNvidiaDriverCRD: description: UseNvidiaDriverCRD indicates if the deployment of NVIDIA Driver is managed by the NVIDIADriver CRD type type: boolean useOpenKernelModules: description: |- Deprecated: This field is no longer honored by the gpu-operator. Please use KernelModuleType instead. UseOpenKernelModules indicates if the open GPU kernel modules should be used type: boolean usePrecompiled: description: UsePrecompiled indicates if deployment of NVIDIA Driver using pre-compiled modules is enabled type: boolean version: description: NVIDIA Driver image tag type: string virtualTopology: description: 'Optional: Virtual Topology Daemon configuration for NVIDIA vGPU drivers' properties: config: description: 'Optional: Config name representing virtual topology daemon configuration file nvidia-topologyd.conf' type: string type: object type: object gdrcopy: description: GDRCopy component spec properties: args: description: 'Optional: List of arguments' items: type: string type: array enabled: description: Enabled indicates if GDRCopy is enabled through GPU Operator type: boolean env: description: 'Optional: List of environment variables' items: description: EnvVar represents an environment variable present in a Container. properties: name: description: Name of the environment variable. type: string value: description: Value of the environment variable. type: string required: - name type: object type: array image: description: NVIDIA GDRCopy driver image name pattern: '[a-zA-Z0-9\-]+' type: string imagePullPolicy: description: Image pull policy type: string imagePullSecrets: description: Image pull secrets items: type: string type: array repository: description: NVIDIA GDRCopy driver image repository type: string version: description: NVIDIA GDRCopy driver image tag type: string type: object gds: description: GPUDirectStorage defines the spec for GDS components(Experimental) properties: args: description: 'Optional: List of arguments' items: type: string type: array enabled: description: Enabled indicates if GPUDirect Storage is enabled through GPU operator type: boolean env: description: 'Optional: List of environment variables' items: description: EnvVar represents an environment variable present in a Container. properties: name: description: Name of the environment variable. type: string value: description: Value of the environment variable. type: string required: - name type: object type: array image: description: NVIDIA GPUDirect Storage Driver image name pattern: '[a-zA-Z0-9\-]+' type: string imagePullPolicy: description: Image pull policy type: string imagePullSecrets: description: Image pull secrets items: type: string type: array repository: description: NVIDIA GPUDirect Storage Driver image repository type: string version: description: NVIDIA GPUDirect Storage Driver image tag type: string type: object gfd: description: GPUFeatureDiscovery spec properties: args: description: 'Optional: List of arguments' items: type: string type: array enabled: description: Enabled indicates if deployment of GPU Feature Discovery Plugin is enabled. type: boolean env: description: 'Optional: List of environment variables' items: description: EnvVar represents an environment variable present in a Container. properties: name: description: Name of the environment variable. type: string value: description: Value of the environment variable. type: string required: - name type: object type: array hostNetwork: description: HostNetwork indicates whether the GPU Feature Discovery pod uses the host's network namespace. type: boolean image: description: GFD image name pattern: '[a-zA-Z0-9\-]+' type: string imagePullPolicy: description: Image pull policy type: string imagePullSecrets: description: Image pull secrets items: type: string type: array repository: description: GFD image repository type: string resources: description: 'Optional: Define resources requests and limits for each pod' properties: limits: 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: |- Limits describes the maximum amount of compute resources allowed. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ type: object requests: 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: |- Requests describes the minimum amount of compute resources required. If Requests is omitted for a container, it defaults to Limits if that is explicitly specified, otherwise to an implementation-defined value. Requests cannot exceed Limits. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ type: object type: object version: description: GFD image tag type: string type: object hostPaths: description: HostPaths defines various paths on the host needed by GPU Operator components properties: driverInstallDir: description: |- DriverInstallDir represents the root at which driver files including libraries, config files, and executables can be found. type: string rootFS: description: |- RootFS represents the path to the root filesystem of the host. This is used by components that need to interact with the host filesystem and as such this must be a chroot-able filesystem. Examples include the MIG Manager and Toolkit Container which may need to stop, start, or restart systemd services. type: string type: object kataManager: description: KataManager component spec properties: args: description: 'Optional: List of arguments' items: type: string type: array config: description: Kata Manager config properties: artifactsDir: default: /opt/nvidia-gpu-operator/artifacts/runtimeclasses description: |- ArtifactsDir is the directory where kata artifacts (e.g. kernel / guest images, configuration, etc.) are placed on the local filesystem. type: string runtimeClasses: description: RuntimeClasses is a list of kata runtime classes to configure. items: description: RuntimeClass defines the configuration for a kata RuntimeClass properties: artifacts: description: Artifacts are the kata artifacts associated with the runtime class. properties: pullSecret: description: PullSecret is the secret used to pull the OCI artifact. type: string url: description: |- URL is the path to the OCI artifact (payload) containing all artifacts associated with a kata runtime class. type: string required: - url type: object name: description: Name is the name of the kata runtime class. type: string nodeSelector: additionalProperties: type: string description: |- NodeSelector specifies the nodeSelector for the RuntimeClass object. This ensures pods running with the RuntimeClass only get scheduled onto nodes which support it. type: object required: - artifacts - name type: object type: array type: object enabled: description: Enabled indicates if deployment of Kata Manager is enabled type: boolean env: description: 'Optional: List of environment variables' items: description: EnvVar represents an environment variable present in a Container. properties: name: description: Name of the environment variable. type: string value: description: Value of the environment variable. type: string required: - name type: object type: array hostNetwork: description: HostNetwork indicates whether the Kata Manager pod uses the host's network namespace. type: boolean image: description: Kata Manager image name pattern: '[a-zA-Z0-9\-]+' type: string imagePullPolicy: description: Image pull policy type: string imagePullSecrets: description: Image pull secrets items: type: string type: array repository: description: Kata Manager image repository type: string resources: description: 'Optional: Define resources requests and limits for each pod' properties: limits: 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: |- Limits describes the maximum amount of compute resources allowed. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ type: object requests: 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: |- Requests describes the minimum amount of compute resources required. If Requests is omitted for a container, it defaults to Limits if that is explicitly specified, otherwise to an implementation-defined value. Requests cannot exceed Limits. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ type: object type: object version: description: Kata Manager image tag type: string type: object kataSandboxDevicePlugin: description: KataSandboxDevicePlugin component spec properties: args: description: 'Optional: List of arguments' items: type: string type: array enabled: description: Enabled indicates if deployment of NVIDIA component through operator is enabled type: boolean env: description: 'Optional: List of environment variables' items: description: EnvVar represents an environment variable present in a Container. properties: name: description: Name of the environment variable. type: string value: description: Value of the environment variable. type: string required: - name type: object type: array hostNetwork: description: HostNetwork indicates whether the Kata Sandbox Device Plugin pod uses the host's network namespace. type: boolean image: description: NVIDIA component image name pattern: '[a-zA-Z0-9\-]+' type: string imagePullPolicy: description: Image pull policy type: string imagePullSecrets: description: Image pull secrets items: type: string type: array repository: description: NVIDIA component image repository type: string resources: description: 'Optional: Define resources requests and limits for each pod' properties: limits: 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: |- Limits describes the maximum amount of compute resources allowed. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ type: object requests: 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: |- Requests describes the minimum amount of compute resources required. If Requests is omitted for a container, it defaults to Limits if that is explicitly specified, otherwise to an implementation-defined value. Requests cannot exceed Limits. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ type: object type: object version: description: NVIDIA component image tag type: string type: object mig: description: MIG spec properties: strategy: description: 'Optional: MIGStrategy to apply for GFD and NVIDIA Device Plugin' enum: - none - single - mixed type: string type: object migManager: description: MIGManager for configuration to deploy MIG Manager properties: args: description: 'Optional: List of arguments' items: type: string type: array config: description: 'Optional: Custom mig-parted configuration for NVIDIA MIG Manager container' properties: default: default: all-disabled description: Default MIG config to be applied on the node, when there is no config specified with the node label nvidia.com/mig.config enum: - all-disabled - "" type: string name: description: ConfigMap name. If not specified, MIG configuration will be dynamically generated from hardware. type: string type: object enabled: description: Enabled indicates if deployment of NVIDIA MIG Manager is enabled type: boolean env: description: 'Optional: List of environment variables' items: description: EnvVar represents an environment variable present in a Container. properties: name: description: Name of the environment variable. type: string value: description: Value of the environment variable. type: string required: - name type: object type: array gpuClientsConfig: description: 'Optional: Custom gpu-clients configuration for NVIDIA MIG Manager container' properties: name: description: ConfigMap name type: string type: object hostNetwork: description: HostNetwork indicates whether the MIG Manager pod uses the host's network namespace. type: boolean image: description: NVIDIA MIG Manager image name pattern: '[a-zA-Z0-9\-]+' type: string imagePullPolicy: description: Image pull policy type: string imagePullSecrets: description: Image pull secrets items: type: string type: array repository: description: NVIDIA MIG Manager image repository type: string resources: description: 'Optional: Define resources requests and limits for each pod' properties: limits: 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: |- Limits describes the maximum amount of compute resources allowed. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ type: object requests: 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: |- Requests describes the minimum amount of compute resources required. If Requests is omitted for a container, it defaults to Limits if that is explicitly specified, otherwise to an implementation-defined value. Requests cannot exceed Limits. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ type: object type: object version: description: NVIDIA MIG Manager image tag type: string type: object nodeStatusExporter: description: NodeStatusExporter spec properties: args: description: 'Optional: List of arguments' items: type: string type: array enabled: description: Enabled indicates if deployment of Node Status Exporter is enabled. type: boolean env: description: 'Optional: List of environment variables' items: description: EnvVar represents an environment variable present in a Container. properties: name: description: Name of the environment variable. type: string value: description: Value of the environment variable. type: string required: - name type: object type: array hostNetwork: description: HostNetwork indicates whether the Node Status Exporter pod uses the host's network namespace. type: boolean image: description: Node Status Exporter image name pattern: '[a-zA-Z0-9\-]+' type: string imagePullPolicy: description: Image pull policy type: string imagePullSecrets: description: Image pull secrets items: type: string type: array repository: description: Node Status Exporterimage repository type: string resources: description: 'Optional: Define resources requests and limits for each pod' properties: limits: 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: |- Limits describes the maximum amount of compute resources allowed. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ type: object requests: 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: |- Requests describes the minimum amount of compute resources required. If Requests is omitted for a container, it defaults to Limits if that is explicitly specified, otherwise to an implementation-defined value. Requests cannot exceed Limits. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ type: object type: object version: description: Node Status Exporterimage tag type: string type: object operator: description: Operator component spec properties: annotations: additionalProperties: type: string description: |- Optional: Annotations is an unstructured key value map stored with a resource that may be set by external tools to store and retrieve arbitrary metadata. They are not queryable and should be preserved when modifying objects. type: object defaultRuntime: description: 'Deprecated: DefaultRuntime is no longer used by the gpu-operator. This is instead, detected at runtime.' type: string initContainer: description: 'Deprecated: InitContainerSpec describes configuration for initContainer image used with all components' properties: image: description: Image represents image name pattern: '[a-zA-Z0-9\-]+' type: string imagePullPolicy: description: Image pull policy type: string imagePullSecrets: description: Image pull secrets items: type: string type: array repository: description: Repository represents image repository path type: string version: description: Version represents image tag(version) type: string type: object labels: additionalProperties: type: string description: |- Optional: Map of string keys and values that can be used to organize and categorize (scope and select) objects. May match selectors of replication controllers and services. type: object runtimeClass: default: nvidia type: string use_ocp_driver_toolkit: description: UseOpenShiftDriverToolkit indicates if DriverToolkit image should be used on OpenShift to build and install driver modules type: boolean type: object psa: description: PSA defines spec for PodSecurityAdmission configuration properties: enabled: description: Enabled indicates if PodSecurityAdmission configuration needs to be enabled for all Pods type: boolean type: object psp: description: |- Deprecated: Pod Security Policies are no longer supported. Please use PodSecurityAdmission instead PSP defines spec for handling PodSecurityPolicies properties: enabled: description: Enabled indicates if PodSecurityPolicies needs to be enabled for all Pods type: boolean type: object sandboxDevicePlugin: description: SandboxDevicePlugin component spec properties: args: description: 'Optional: List of arguments' items: type: string type: array enabled: description: Enabled indicates if deployment of NVIDIA Sandbox Device Plugin through operator is enabled type: boolean env: description: 'Optional: List of environment variables' items: description: EnvVar represents an environment variable present in a Container. properties: name: description: Name of the environment variable. type: string value: description: Value of the environment variable. type: string required: - name type: object type: array hostNetwork: description: HostNetwork indicates whether the Sandbox Device Plugin pod uses the host's network namespace. type: boolean image: description: NVIDIA Sandbox Device Plugin image name pattern: '[a-zA-Z0-9\-]+' type: string imagePullPolicy: description: Image pull policy type: string imagePullSecrets: description: Image pull secrets items: type: string type: array repository: description: NVIDIA Sandbox Device Plugin image repository type: string resources: description: 'Optional: Define resources requests and limits for each pod' properties: limits: 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: |- Limits describes the maximum amount of compute resources allowed. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ type: object requests: 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: |- Requests describes the minimum amount of compute resources required. If Requests is omitted for a container, it defaults to Limits if that is explicitly specified, otherwise to an implementation-defined value. Requests cannot exceed Limits. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ type: object type: object version: description: NVIDIA Sandbox Device Plugin image tag type: string type: object sandboxWorkloads: description: SandboxWorkloads defines the spec for handling sandbox workloads (i.e. Virtual Machines) properties: defaultWorkload: default: container description: |- DefaultWorkload indicates the default GPU workload type to configure worker nodes in the cluster for enum: - container - vm-passthrough - vm-vgpu type: string enabled: description: |- Enabled indicates if the GPU Operator should manage additional operands required for sandbox workloads (i.e. VFIO Manager, vGPU Manager, and additional device plugins) type: boolean mode: default: kubevirt description: |- Mode indicates the sandbox mode. Accepted values are "kubevirt" and "kata". The default value is "kubevirt". enum: - kubevirt - kata type: string type: object toolkit: description: Toolkit component spec properties: args: description: 'Optional: List of arguments' items: type: string type: array enabled: description: Enabled indicates if deployment of NVIDIA Container Toolkit through operator is enabled type: boolean env: description: 'Optional: List of environment variables' items: description: EnvVar represents an environment variable present in a Container. properties: name: description: Name of the environment variable. type: string value: description: Value of the environment variable. type: string required: - name type: object type: array hostNetwork: description: HostNetwork indicates whether the Container Toolkit pod uses the host's network namespace. type: boolean image: description: NVIDIA Container Toolkit image name pattern: '[a-zA-Z0-9\-]+' type: string imagePullPolicy: description: Image pull policy type: string imagePullSecrets: description: Image pull secrets items: type: string type: array installDir: default: /usr/local/nvidia description: Toolkit install directory on the host type: string repository: description: NVIDIA Container Toolkit image repository type: string resources: description: 'Optional: Define resources requests and limits for each pod' properties: limits: 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: |- Limits describes the maximum amount of compute resources allowed. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ type: object requests: 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: |- Requests describes the minimum amount of compute resources required. If Requests is omitted for a container, it defaults to Limits if that is explicitly specified, otherwise to an implementation-defined value. Requests cannot exceed Limits. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ type: object type: object version: description: NVIDIA Container Toolkit image tag type: string type: object validator: description: Validator defines the spec for operator-validator daemonset properties: args: description: 'Optional: List of arguments' items: type: string type: array cuda: description: CUDA validator spec properties: env: description: 'Optional: List of environment variables' items: description: EnvVar represents an environment variable present in a Container. properties: name: description: Name of the environment variable. type: string value: description: Value of the environment variable. type: string required: - name type: object type: array type: object driver: description: Toolkit validator spec properties: env: description: 'Optional: List of environment variables' items: description: EnvVar represents an environment variable present in a Container. properties: name: description: Name of the environment variable. type: string value: description: Value of the environment variable. type: string required: - name type: object type: array type: object env: description: 'Optional: List of environment variables' items: description: EnvVar represents an environment variable present in a Container. properties: name: description: Name of the environment variable. type: string value: description: Value of the environment variable. type: string required: - name type: object type: array hostNetwork: description: HostNetwork indicates whether the Validator pod uses the host's network namespace. type: boolean image: description: Validator image name pattern: '[a-zA-Z0-9\-]+' type: string imagePullPolicy: description: Image pull policy type: string imagePullSecrets: description: Image pull secrets items: type: string type: array plugin: description: Plugin validator spec properties: env: description: 'Optional: List of environment variables' items: description: EnvVar represents an environment variable present in a Container. properties: name: description: Name of the environment variable. type: string value: description: Value of the environment variable. type: string required: - name type: object type: array type: object repository: description: Validator image repository type: string resources: description: 'Optional: Define resources requests and limits for each pod' properties: limits: 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: |- Limits describes the maximum amount of compute resources allowed. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ type: object requests: 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: |- Requests describes the minimum amount of compute resources required. If Requests is omitted for a container, it defaults to Limits if that is explicitly specified, otherwise to an implementation-defined value. Requests cannot exceed Limits. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ type: object type: object toolkit: description: Toolkit validator spec properties: env: description: 'Optional: List of environment variables' items: description: EnvVar represents an environment variable present in a Container. properties: name: description: Name of the environment variable. type: string value: description: Value of the environment variable. type: string required: - name type: object type: array type: object version: description: Validator image tag type: string vfioPCI: description: VfioPCI validator spec properties: env: description: 'Optional: List of environment variables' items: description: EnvVar represents an environment variable present in a Container. properties: name: description: Name of the environment variable. type: string value: description: Value of the environment variable. type: string required: - name type: object type: array type: object vgpuDevices: description: VGPUDevices validator spec properties: env: description: 'Optional: List of environment variables' items: description: EnvVar represents an environment variable present in a Container. properties: name: description: Name of the environment variable. type: string value: description: Value of the environment variable. type: string required: - name type: object type: array type: object vgpuManager: description: VGPUManager validator spec properties: env: description: 'Optional: List of environment variables' items: description: EnvVar represents an environment variable present in a Container. properties: name: description: Name of the environment variable. type: string value: description: Value of the environment variable. type: string required: - name type: object type: array type: object type: object vfioManager: description: VFIOManager for configuration to deploy VFIO-PCI Manager properties: args: description: 'Optional: List of arguments' items: type: string type: array driverManager: description: DriverManager represents configuration for NVIDIA Driver Manager properties: env: description: 'Optional: List of environment variables' items: description: EnvVar represents an environment variable present in a Container. properties: name: description: Name of the environment variable. type: string value: description: Value of the environment variable. type: string required: - name type: object type: array image: description: Image represents NVIDIA Driver Manager image name pattern: '[a-zA-Z0-9\-]+' type: string imagePullPolicy: description: Image pull policy type: string imagePullSecrets: description: Image pull secrets items: type: string type: array repository: description: Repository represents Driver Managerrepository path type: string version: description: Version represents NVIDIA Driver Manager image tag(version) type: string type: object enabled: description: Enabled indicates if deployment of VFIO Manager is enabled type: boolean env: description: 'Optional: List of environment variables' items: description: EnvVar represents an environment variable present in a Container. properties: name: description: Name of the environment variable. type: string value: description: Value of the environment variable. type: string required: - name type: object type: array hostNetwork: description: HostNetwork indicates whether the VFIO Manager pod uses the host's network namespace. type: boolean image: description: VFIO Manager image name pattern: '[a-zA-Z0-9\-]+' type: string imagePullPolicy: description: Image pull policy type: string imagePullSecrets: description: Image pull secrets items: type: string type: array repository: description: VFIO Manager image repository type: string resources: description: 'Optional: Define resources requests and limits for each pod' properties: limits: 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: |- Limits describes the maximum amount of compute resources allowed. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ type: object requests: 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: |- Requests describes the minimum amount of compute resources required. If Requests is omitted for a container, it defaults to Limits if that is explicitly specified, otherwise to an implementation-defined value. Requests cannot exceed Limits. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ type: object type: object version: description: VFIO Manager image tag type: string type: object vgpuDeviceManager: description: VGPUDeviceManager spec properties: args: description: 'Optional: List of arguments' items: type: string type: array config: description: NVIDIA vGPU devices configuration for NVIDIA vGPU Device Manager container properties: default: default: default description: Default config name within the ConfigMap type: string name: description: ConfigMap name type: string type: object enabled: description: Enabled indicates if deployment of NVIDIA vGPU Device Manager is enabled type: boolean env: description: 'Optional: List of environment variables' items: description: EnvVar represents an environment variable present in a Container. properties: name: description: Name of the environment variable. type: string value: description: Value of the environment variable. type: string required: - name type: object type: array hostNetwork: description: HostNetwork indicates whether the vGPU Device Manager pod uses the host's network namespace. type: boolean image: description: NVIDIA vGPU Device Manager image name pattern: '[a-zA-Z0-9\-]+' type: string imagePullPolicy: description: Image pull policy type: string imagePullSecrets: description: Image pull secrets items: type: string type: array repository: description: NVIDIA vGPU Device Manager image repository type: string resources: description: 'Optional: Define resources requests and limits for each pod' properties: limits: 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: |- Limits describes the maximum amount of compute resources allowed. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ type: object requests: 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: |- Requests describes the minimum amount of compute resources required. If Requests is omitted for a container, it defaults to Limits if that is explicitly specified, otherwise to an implementation-defined value. Requests cannot exceed Limits. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ type: object type: object version: description: NVIDIA vGPU Device Manager image tag type: string type: object vgpuManager: description: VGPUManager component spec properties: args: description: 'Optional: List of arguments' items: type: string type: array driverManager: description: DriverManager represents configuration for NVIDIA Driver Manager initContainer properties: env: description: 'Optional: List of environment variables' items: description: EnvVar represents an environment variable present in a Container. properties: name: description: Name of the environment variable. type: string value: description: Value of the environment variable. type: string required: - name type: object type: array image: description: Image represents NVIDIA Driver Manager image name pattern: '[a-zA-Z0-9\-]+' type: string imagePullPolicy: description: Image pull policy type: string imagePullSecrets: description: Image pull secrets items: type: string type: array repository: description: Repository represents Driver Managerrepository path type: string version: description: Version represents NVIDIA Driver Manager image tag(version) type: string type: object enabled: description: Enabled indicates if deployment of NVIDIA vGPU Manager through operator is enabled type: boolean env: description: 'Optional: List of environment variables' items: description: EnvVar represents an environment variable present in a Container. properties: name: description: Name of the environment variable. type: string value: description: Value of the environment variable. type: string required: - name type: object type: array hostNetwork: description: HostNetwork indicates whether the vGPU Manager pod uses the host's network namespace. type: boolean image: description: NVIDIA vGPU Manager image name pattern: '[a-zA-Z0-9\-]+' type: string imagePullPolicy: description: Image pull policy type: string imagePullSecrets: description: Image pull secrets items: type: string type: array kernelModuleConfig: description: 'Optional: Kernel module configuration parameters for the vGPU manager' properties: name: type: string type: object repository: description: NVIDIA vGPU Manager image repository type: string resources: description: 'Optional: Define resources requests and limits for each pod' properties: limits: 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: |- Limits describes the maximum amount of compute resources allowed. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ type: object requests: 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: |- Requests describes the minimum amount of compute resources required. If Requests is omitted for a container, it defaults to Limits if that is explicitly specified, otherwise to an implementation-defined value. Requests cannot exceed Limits. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ type: object type: object version: description: NVIDIA vGPU Manager image tag type: string type: object required: - daemonsets - dcgm - dcgmExporter - devicePlugin - driver - gfd - nodeStatusExporter - operator - toolkit type: object status: description: ClusterPolicyStatus defines the observed state of ClusterPolicy properties: conditions: description: Conditions is a list of conditions representing the ClusterPolicy's current state. items: description: Condition contains details for one aspect of the current state of this API Resource. 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. 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 namespace: description: Namespace indicates a namespace in which the operator is installed type: string state: description: State indicates status of ClusterPolicy enum: - ignored - ready - notReady type: string required: - state type: object type: object served: true storage: true subresources: status: {} --- # Source: gpu-operator/crds/nvidia.com_nvidiadrivers.yaml --- apiVersion: apiextensions.k8s.io/v1 kind: CustomResourceDefinition metadata: annotations: controller-gen.kubebuilder.io/version: v0.20.1 name: nvidiadrivers.nvidia.com spec: group: nvidia.com names: kind: NVIDIADriver listKind: NVIDIADriverList plural: nvidiadrivers shortNames: - nvd - nvdriver - nvdrivers singular: nvidiadriver scope: Cluster versions: - additionalPrinterColumns: - jsonPath: .status.state name: Status type: string - jsonPath: .metadata.creationTimestamp name: Age type: string name: v1alpha1 schema: openAPIV3Schema: description: NVIDIADriver is the Schema for the nvidiadrivers 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: NVIDIADriverSpec defines the desired state of NVIDIADriver properties: annotations: additionalProperties: type: string description: |- Optional: Annotations is an unstructured key value map stored with a resource that may be set by external tools to store and retrieve arbitrary metadata. They are not queryable and should be preserved when modifying objects. type: object args: description: 'Optional: List of arguments' items: type: string type: array certConfig: description: 'Optional: Custom certificates configuration for NVIDIA Driver container' properties: name: type: string type: object driverType: default: gpu description: DriverType defines NVIDIA driver type enum: - gpu - vgpu - vgpu-host-manager type: string x-kubernetes-validations: - message: driverType is an immutable field. Please create a new NvidiaDriver resource instead when you want to change this setting. rule: self == oldSelf env: description: 'Optional: List of environment variables' items: description: EnvVar represents an environment variable present in a Container. properties: name: description: Name of the environment variable. type: string value: description: Value of the environment variable. type: string required: - name type: object type: array gdrcopy: description: GDRCopy defines the spec for GDRCopy driver properties: args: description: 'Optional: List of arguments' items: type: string type: array enabled: description: Enabled indicates if GDRCopy is enabled through GPU operator type: boolean env: description: 'Optional: List of environment variables' items: description: EnvVar represents an environment variable present in a Container. properties: name: description: Name of the environment variable. type: string value: description: Value of the environment variable. type: string required: - name type: object type: array image: description: GDRCopy driver image name pattern: '[a-zA-Z0-9\-]+' type: string imagePullPolicy: description: Image pull policy type: string imagePullSecrets: description: Image pull secrets items: type: string type: array repository: description: GDRCopy diver image repository type: string version: description: GDRCopy driver image tag type: string type: object gds: description: GPUDirectStorage defines the spec for GDS driver properties: args: description: 'Optional: List of arguments' items: type: string type: array enabled: description: Enabled indicates if GPUDirect Storage is enabled through GPU operator type: boolean env: description: 'Optional: List of environment variables' items: description: EnvVar represents an environment variable present in a Container. properties: name: description: Name of the environment variable. type: string value: description: Value of the environment variable. type: string required: - name type: object type: array image: description: NVIDIA GPUDirect Storage Driver image name pattern: '[a-zA-Z0-9\-]+' type: string imagePullPolicy: description: Image pull policy type: string imagePullSecrets: description: Image pull secrets items: type: string type: array repository: description: NVIDIA GPUDirect Storage Driver image repository type: string version: description: NVIDIA GPUDirect Storage Driver image tag type: string type: object hostNetwork: description: HostNetwork indicates whether the Driver pod uses the host's network namespace. type: boolean image: default: nvcr.io/nvidia/driver description: NVIDIA Driver container image name type: string imagePullPolicy: description: Image pull policy type: string imagePullSecrets: description: Image pull secrets items: type: string type: array kernelModuleConfig: description: 'Optional: Kernel module configuration parameters for the NVIDIA Driver' properties: name: type: string type: object kernelModuleType: default: auto description: |- KernelModuleType represents the type of driver kernel modules to be used when installing the GPU driver. Accepted values are auto, proprietary and open. NOTE: If auto is chosen, it means that the recommended kernel module type is chosen based on the GPU devices on the host and the driver branch used enum: - auto - open - proprietary type: string labels: additionalProperties: type: string description: |- Optional: Map of string keys and values that can be used to organize and categorize (scope and select) objects. May match selectors of replication controllers and services. type: object licensingConfig: description: 'Optional: Licensing configuration for NVIDIA vGPU licensing' properties: name: description: 'Deprecated: ConfigMapName has been deprecated in favour of SecretName. Please use secrets to handle the licensing server configuration more securely' type: string nlsEnabled: description: NLSEnabled indicates if NVIDIA Licensing System is used for licensing. type: boolean secretName: type: string type: object livenessProbe: description: NVIDIA Driver container liveness probe settings properties: failureThreshold: description: |- Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. format: int32 minimum: 1 type: integer initialDelaySeconds: description: |- Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer periodSeconds: description: |- How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. format: int32 minimum: 1 type: integer successThreshold: description: |- Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. format: int32 minimum: 1 type: integer timeoutSeconds: description: |- Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 minimum: 1 type: integer type: object manager: description: Manager represents configuration for NVIDIA Driver Manager initContainer properties: env: description: 'Optional: List of environment variables' items: description: EnvVar represents an environment variable present in a Container. properties: name: description: Name of the environment variable. type: string value: description: Value of the environment variable. type: string required: - name type: object type: array image: description: Image represents NVIDIA Driver Manager image name pattern: '[a-zA-Z0-9\-]+' type: string imagePullPolicy: description: Image pull policy type: string imagePullSecrets: description: Image pull secrets items: type: string type: array repository: description: Repository represents Driver Managerrepository path type: string version: description: Version represents NVIDIA Driver Manager image tag(version) type: string type: object nodeAffinity: description: Affinity specifies node affinity rules for driver pods properties: preferredDuringSchedulingIgnoredDuringExecution: description: |- The scheduler will prefer to schedule pods to nodes that satisfy the affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling affinity expressions, etc.), compute a sum by iterating through the elements of this field and adding "weight" to the sum if the node matches the corresponding matchExpressions; the node(s) with the highest sum are the most preferred. items: description: |- An empty preferred scheduling term matches all objects with implicit weight 0 (i.e. it's a no-op). A null preferred scheduling term matches no objects (i.e. is also a no-op). properties: preference: description: A node selector term, associated with the corresponding weight. properties: matchExpressions: description: A list of node selector requirements by node's labels. items: description: |- A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: The label key that the selector applies to. type: string operator: description: |- Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. type: string values: description: |- 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. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchFields: description: A list of node selector requirements by node's fields. items: description: |- A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: The label key that the selector applies to. type: string operator: description: |- Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. type: string values: description: |- 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. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic type: object x-kubernetes-map-type: atomic weight: description: Weight associated with matching the corresponding nodeSelectorTerm, in the range 1-100. format: int32 type: integer required: - preference - weight type: object type: array x-kubernetes-list-type: atomic requiredDuringSchedulingIgnoredDuringExecution: description: |- If the affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to an update), the system may or may not try to eventually evict the pod from its node. properties: nodeSelectorTerms: description: Required. A list of node selector terms. The terms are ORed. items: description: |- A null or empty node selector term matches no objects. The requirements of them are ANDed. The TopologySelectorTerm type implements a subset of the NodeSelectorTerm. properties: matchExpressions: description: A list of node selector requirements by node's labels. items: description: |- A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: The label key that the selector applies to. type: string operator: description: |- Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. type: string values: description: |- 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. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic matchFields: description: A list of node selector requirements by node's fields. items: description: |- A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. properties: key: description: The label key that the selector applies to. type: string operator: description: |- Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. type: string values: description: |- 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. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. items: type: string type: array x-kubernetes-list-type: atomic required: - key - operator type: object type: array x-kubernetes-list-type: atomic type: object x-kubernetes-map-type: atomic type: array x-kubernetes-list-type: atomic required: - nodeSelectorTerms type: object x-kubernetes-map-type: atomic type: object nodeSelector: additionalProperties: type: string description: NodeSelector specifies a selector for installation of NVIDIA driver type: object podSecurityContext: description: 'Optional: Set pod-level security context for driver pod' properties: appArmorProfile: description: |- appArmorProfile is the AppArmor options to use by the containers in this pod. Note that this field cannot be set when spec.os.name is windows. properties: localhostProfile: description: |- localhostProfile indicates a profile loaded on the node that should be used. The profile must be preconfigured on the node to work. Must match the loaded name of the profile. Must be set if and only if type is "Localhost". type: string type: description: |- type indicates which kind of AppArmor profile will be applied. Valid options are: Localhost - a profile pre-loaded on the node. RuntimeDefault - the container runtime's default profile. Unconfined - no AppArmor enforcement. type: string required: - type type: object fsGroup: description: |- A special supplemental group that applies to all containers in a pod. Some volume types allow the Kubelet to change the ownership of that volume to be owned by the pod: 1. The owning GID will be the FSGroup 2. The setgid bit is set (new files created in the volume will be owned by FSGroup) 3. The permission bits are OR'd with rw-rw---- If unset, the Kubelet will not modify the ownership and permissions of any volume. Note that this field cannot be set when spec.os.name is windows. format: int64 type: integer fsGroupChangePolicy: description: |- fsGroupChangePolicy defines behavior of changing ownership and permission of the volume before being exposed inside Pod. This field will only apply to volume types which support fsGroup based ownership(and permissions). It will have no effect on ephemeral volume types such as: secret, configmaps and emptydir. Valid values are "OnRootMismatch" and "Always". If not specified, "Always" is used. Note that this field cannot be set when spec.os.name is windows. type: string runAsGroup: description: |- The GID to run the entrypoint of the container process. Uses runtime default if unset. May also be set in SecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence for that container. Note that this field cannot be set when spec.os.name is windows. format: int64 type: integer runAsNonRoot: description: |- Indicates that the container must run as a non-root user. If true, the Kubelet will validate the image at runtime to ensure that it does not run as UID 0 (root) and fail to start the container if it does. If unset or false, no such validation will be performed. May also be set in SecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. type: boolean runAsUser: description: |- The UID to run the entrypoint of the container process. Defaults to user specified in image metadata if unspecified. May also be set in SecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence for that container. Note that this field cannot be set when spec.os.name is windows. format: int64 type: integer seLinuxChangePolicy: description: |- seLinuxChangePolicy defines how the container's SELinux label is applied to all volumes used by the Pod. It has no effect on nodes that do not support SELinux or to volumes does not support SELinux. Valid values are "MountOption" and "Recursive". "Recursive" means relabeling of all files on all Pod volumes by the container runtime. This may be slow for large volumes, but allows mixing privileged and unprivileged Pods sharing the same volume on the same node. "MountOption" mounts all eligible Pod volumes with `-o context` mount option. This requires all Pods that share the same volume to use the same SELinux label. It is not possible to share the same volume among privileged and unprivileged Pods. Eligible volumes are in-tree FibreChannel and iSCSI volumes, and all CSI volumes whose CSI driver announces SELinux support by setting spec.seLinuxMount: true in their CSIDriver instance. Other volumes are always re-labelled recursively. "MountOption" value is allowed only when SELinuxMount feature gate is enabled. If not specified and SELinuxMount feature gate is enabled, "MountOption" is used. If not specified and SELinuxMount feature gate is disabled, "MountOption" is used for ReadWriteOncePod volumes and "Recursive" for all other volumes. This field affects only Pods that have SELinux label set, either in PodSecurityContext or in SecurityContext of all containers. All Pods that use the same volume should use the same seLinuxChangePolicy, otherwise some pods can get stuck in ContainerCreating state. Note that this field cannot be set when spec.os.name is windows. type: string seLinuxOptions: description: |- The SELinux context to be applied to all containers. If unspecified, the container runtime will allocate a random SELinux context for each container. May also be set in SecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence for that container. Note that this field cannot be set when spec.os.name is windows. properties: level: description: Level is SELinux level label that applies to the container. type: string role: description: Role is a SELinux role label that applies to the container. type: string type: description: Type is a SELinux type label that applies to the container. type: string user: description: User is a SELinux user label that applies to the container. type: string type: object seccompProfile: description: |- The seccomp options to use by the containers in this pod. Note that this field cannot be set when spec.os.name is windows. properties: localhostProfile: description: |- localhostProfile indicates a profile defined in a file on the node should be used. The profile must be preconfigured on the node to work. Must be a descending path, relative to the kubelet's configured seccomp profile location. Must be set if type is "Localhost". Must NOT be set for any other type. type: string type: description: |- type indicates which kind of seccomp profile will be applied. Valid options are: Localhost - a profile defined in a file on the node should be used. RuntimeDefault - the container runtime default profile should be used. Unconfined - no profile should be applied. type: string required: - type type: object supplementalGroups: description: |- A list of groups applied to the first process run in each container, in addition to the container's primary GID and fsGroup (if specified). If the SupplementalGroupsPolicy feature is enabled, the supplementalGroupsPolicy field determines whether these are in addition to or instead of any group memberships defined in the container image. If unspecified, no additional groups are added, though group memberships defined in the container image may still be used, depending on the supplementalGroupsPolicy field. Note that this field cannot be set when spec.os.name is windows. items: format: int64 type: integer type: array x-kubernetes-list-type: atomic supplementalGroupsPolicy: description: |- Defines how supplemental groups of the first container processes are calculated. Valid values are "Merge" and "Strict". If not specified, "Merge" is used. (Alpha) Using the field requires the SupplementalGroupsPolicy feature gate to be enabled and the container runtime must implement support for this feature. Note that this field cannot be set when spec.os.name is windows. type: string sysctls: description: |- Sysctls hold a list of namespaced sysctls used for the pod. Pods with unsupported sysctls (by the container runtime) might fail to launch. Note that this field cannot be set when spec.os.name is windows. items: description: Sysctl defines a kernel parameter to be set properties: name: description: Name of a property to set type: string value: description: Value of a property to set type: string required: - name - value type: object type: array x-kubernetes-list-type: atomic windowsOptions: description: |- The Windows specific settings applied to all containers. If unspecified, the options within a container's SecurityContext will be used. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. Note that this field cannot be set when spec.os.name is linux. properties: gmsaCredentialSpec: description: |- GMSACredentialSpec is where the GMSA admission webhook (https://github.com/kubernetes-sigs/windows-gmsa) inlines the contents of the GMSA credential spec named by the GMSACredentialSpecName field. type: string gmsaCredentialSpecName: description: GMSACredentialSpecName is the name of the GMSA credential spec to use. type: string hostProcess: description: |- HostProcess determines if a container should be run as a 'Host Process' container. All of a Pod's containers must have the same effective HostProcess value (it is not allowed to have a mix of HostProcess containers and non-HostProcess containers). In addition, if HostProcess is true then HostNetwork must also be set to true. type: boolean runAsUserName: description: |- The UserName in Windows to run the entrypoint of the container process. Defaults to the user specified in image metadata if unspecified. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. type: string type: object type: object priorityClassName: description: 'Optional: Set priorityClassName' type: string rdma: description: GPUDirectRDMA defines the spec for NVIDIA Peer Memory driver properties: enabled: description: Enabled indicates if GPUDirect RDMA is enabled through GPU operator type: boolean useHostMofed: description: UseHostMOFED indicates to use MOFED drivers directly installed on the host to enable GPUDirect RDMA type: boolean type: object readinessProbe: description: NVIDIA Driver container readiness probe settings properties: failureThreshold: description: |- Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. format: int32 minimum: 1 type: integer initialDelaySeconds: description: |- Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer periodSeconds: description: |- How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. format: int32 minimum: 1 type: integer successThreshold: description: |- Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. format: int32 minimum: 1 type: integer timeoutSeconds: description: |- Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 minimum: 1 type: integer type: object repoConfig: description: 'Optional: Custom repo configuration for NVIDIA Driver container' properties: name: type: string type: object repository: description: NVIDIA Driver repository type: string resources: description: 'Optional: Define resources requests and limits for each pod' properties: limits: 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: |- Limits describes the maximum amount of compute resources allowed. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ type: object requests: 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: |- Requests describes the minimum amount of compute resources required. If Requests is omitted for a container, it defaults to Limits if that is explicitly specified, otherwise to an implementation-defined value. Requests cannot exceed Limits. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/ type: object type: object secretEnv: description: 'Optional: SecretEnv represents the name of the Kubernetes Secret with secret environment variables for the NVIDIA Driver' type: string startupProbe: description: NVIDIA Driver container startup probe settings properties: failureThreshold: description: |- Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. format: int32 minimum: 1 type: integer initialDelaySeconds: description: |- Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 type: integer periodSeconds: description: |- How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. format: int32 minimum: 1 type: integer successThreshold: description: |- Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. format: int32 minimum: 1 type: integer timeoutSeconds: description: |- Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes format: int32 minimum: 1 type: integer type: object tolerations: description: 'Optional: Set tolerations' items: description: |- The pod this Toleration is attached to tolerates any taint that matches the triple using the matching operator . properties: effect: description: |- Effect indicates the taint effect to match. Empty means match all taint effects. When specified, allowed values are NoSchedule, PreferNoSchedule and NoExecute. type: string key: description: |- Key is the taint key that the toleration applies to. Empty means match all taint keys. If the key is empty, operator must be Exists; this combination means to match all values and all keys. type: string operator: description: |- Operator represents a key's relationship to the value. Valid operators are Exists, Equal, Lt, and Gt. Defaults to Equal. Exists is equivalent to wildcard for value, so that a pod can tolerate all taints of a particular category. Lt and Gt perform numeric comparisons (requires feature gate TaintTolerationComparisonOperators). type: string tolerationSeconds: description: |- TolerationSeconds represents the period of time the toleration (which must be of effect NoExecute, otherwise this field is ignored) tolerates the taint. By default, it is not set, which means tolerate the taint forever (do not evict). Zero and negative values will be treated as 0 (evict immediately) by the system. format: int64 type: integer value: description: |- Value is the taint value the toleration matches to. If the operator is Exists, the value should be empty, otherwise just a regular string. type: string type: object type: array useOpenKernelModules: description: |- Deprecated: This field is no longer honored by the gpu-operator. Please use KernelModuleType instead. UseOpenKernelModules indicates if the open GPU kernel modules should be used type: boolean usePrecompiled: description: UsePrecompiled indicates if deployment of NVIDIA Driver using pre-compiled modules is enabled type: boolean x-kubernetes-validations: - message: usePrecompiled is an immutable field. Please create a new NvidiaDriver resource instead when you want to change this setting. rule: self == oldSelf version: description: NVIDIA Driver version (or just branch for precompiled drivers) type: string virtualTopologyConfig: description: 'Optional: Virtual Topology Daemon configuration for NVIDIA vGPU drivers' properties: name: description: 'Optional: Config name representing virtual topology daemon configuration file nvidia-topologyd.conf' type: string type: object required: - driverType - image type: object status: description: NVIDIADriverStatus defines the observed state of NVIDIADriver properties: conditions: description: Conditions is a list of conditions representing the NVIDIADriver's current state. items: description: Condition contains details for one aspect of the current state of this API Resource. 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. 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 namespace: description: Namespace indicates a namespace in which the operator and driver are installed type: string state: description: |- INSERT ADDITIONAL STATUS FIELD - define observed state of cluster Important: Run "make" to regenerate code after modifying this file State indicates status of NVIDIADriver instance enum: - ignored - ready - notReady - disabled type: string required: - state type: object type: object served: true storage: true subresources: status: {} --- # Source: gpu-operator/charts/node-feature-discovery/crds/nfd-api-crds.yaml --- apiVersion: apiextensions.k8s.io/v1 kind: CustomResourceDefinition metadata: annotations: controller-gen.kubebuilder.io/version: v0.16.3 name: nodefeatures.nfd.k8s-sigs.io spec: group: nfd.k8s-sigs.io names: kind: NodeFeature listKind: NodeFeatureList plural: nodefeatures singular: nodefeature scope: Namespaced versions: - name: v1alpha1 schema: openAPIV3Schema: description: |- NodeFeature resource holds the features discovered for one node in the cluster. 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 NodeFeature, containing features discovered for a node. properties: features: description: Features is the full "raw" features data that has been discovered. properties: attributes: additionalProperties: description: AttributeFeatureSet is a set of features having string value. properties: elements: additionalProperties: type: string description: Individual features of the feature set. type: object required: - elements type: object description: Attributes contains all the attribute-type features of the node. type: object flags: additionalProperties: description: FlagFeatureSet is a set of simple features only containing names without values. properties: elements: additionalProperties: description: |- Nil is a dummy empty struct for protobuf compatibility. NOTE: protobuf definitions have been removed but this is kept for API compatibility. type: object description: Individual features of the feature set. type: object required: - elements type: object description: Flags contains all the flag-type features of the node. type: object instances: additionalProperties: description: InstanceFeatureSet is a set of features each of which is an instance having multiple attributes. properties: elements: description: Individual features of the feature set. items: description: InstanceFeature represents one instance of a complex features, e.g. a device. properties: attributes: additionalProperties: type: string description: Attributes of the instance feature. type: object required: - attributes type: object type: array required: - elements type: object description: Instances contains all the instance-type features of the node. type: object type: object labels: additionalProperties: type: string description: Labels is the set of node labels that are requested to be created. type: object type: object required: - spec type: object served: true storage: true --- apiVersion: apiextensions.k8s.io/v1 kind: CustomResourceDefinition metadata: annotations: controller-gen.kubebuilder.io/version: v0.16.3 name: nodefeaturegroups.nfd.k8s-sigs.io spec: group: nfd.k8s-sigs.io names: kind: NodeFeatureGroup listKind: NodeFeatureGroupList plural: nodefeaturegroups shortNames: - nfg singular: nodefeaturegroup scope: Namespaced versions: - name: v1alpha1 schema: openAPIV3Schema: description: NodeFeatureGroup resource holds Node pools by featureGroup 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: Spec defines the rules to be evaluated. properties: featureGroupRules: description: List of rules to evaluate to determine nodes that belong in this group. items: description: GroupRule defines a rule for nodegroup filtering. properties: matchAny: description: MatchAny specifies a list of matchers one of which must match. items: description: MatchAnyElem specifies one sub-matcher of MatchAny. properties: matchFeatures: description: MatchFeatures specifies a set of matcher terms all of which must match. items: description: |- FeatureMatcherTerm defines requirements against one feature set. All requirements (specified as MatchExpressions) are evaluated against each element in the feature set. properties: feature: description: Feature is the name of the feature set to match against. type: string matchExpressions: additionalProperties: description: |- MatchExpression specifies an expression to evaluate against a set of input values. It contains an operator that is applied when matching the input and an array of values that the operator evaluates the input against. properties: op: description: Op is the operator to be applied. enum: - In - NotIn - InRegexp - Exists - DoesNotExist - Gt - Ge - Lt - Le - GtLt - GeLe - IsTrue - IsFalse type: string type: description: |- Type defines the value type for specific operators. The currently supported type is 'version' for Gt,Ge,Lt,Le,GtLt,GeLe operators. type: string value: description: |- Value is the list of values that the operand evaluates the input against. Value should be empty if the operator is Exists, DoesNotExist, IsTrue or IsFalse. Value should contain exactly one element if the operator is Gt or Lt and exactly two elements if the operator is GtLt. In other cases Value should contain at least one element. items: type: string type: array required: - op type: object description: |- MatchExpressions is the set of per-element expressions evaluated. These match against the value of the specified elements. type: object matchName: description: |- MatchName in an expression that is matched against the name of each element in the feature set. properties: op: description: Op is the operator to be applied. enum: - In - NotIn - InRegexp - Exists - DoesNotExist - Gt - Ge - Lt - Le - GtLt - GeLe - IsTrue - IsFalse type: string type: description: |- Type defines the value type for specific operators. The currently supported type is 'version' for Gt,Ge,Lt,Le,GtLt,GeLe operators. type: string value: description: |- Value is the list of values that the operand evaluates the input against. Value should be empty if the operator is Exists, DoesNotExist, IsTrue or IsFalse. Value should contain exactly one element if the operator is Gt or Lt and exactly two elements if the operator is GtLt. In other cases Value should contain at least one element. items: type: string type: array required: - op type: object required: - feature type: object type: array required: - matchFeatures type: object type: array matchFeatures: description: MatchFeatures specifies a set of matcher terms all of which must match. items: description: |- FeatureMatcherTerm defines requirements against one feature set. All requirements (specified as MatchExpressions) are evaluated against each element in the feature set. properties: feature: description: Feature is the name of the feature set to match against. type: string matchExpressions: additionalProperties: description: |- MatchExpression specifies an expression to evaluate against a set of input values. It contains an operator that is applied when matching the input and an array of values that the operator evaluates the input against. properties: op: description: Op is the operator to be applied. enum: - In - NotIn - InRegexp - Exists - DoesNotExist - Gt - Ge - Lt - Le - GtLt - GeLe - IsTrue - IsFalse type: string type: description: |- Type defines the value type for specific operators. The currently supported type is 'version' for Gt,Ge,Lt,Le,GtLt,GeLe operators. type: string value: description: |- Value is the list of values that the operand evaluates the input against. Value should be empty if the operator is Exists, DoesNotExist, IsTrue or IsFalse. Value should contain exactly one element if the operator is Gt or Lt and exactly two elements if the operator is GtLt. In other cases Value should contain at least one element. items: type: string type: array required: - op type: object description: |- MatchExpressions is the set of per-element expressions evaluated. These match against the value of the specified elements. type: object matchName: description: |- MatchName in an expression that is matched against the name of each element in the feature set. properties: op: description: Op is the operator to be applied. enum: - In - NotIn - InRegexp - Exists - DoesNotExist - Gt - Ge - Lt - Le - GtLt - GeLe - IsTrue - IsFalse type: string type: description: |- Type defines the value type for specific operators. The currently supported type is 'version' for Gt,Ge,Lt,Le,GtLt,GeLe operators. type: string value: description: |- Value is the list of values that the operand evaluates the input against. Value should be empty if the operator is Exists, DoesNotExist, IsTrue or IsFalse. Value should contain exactly one element if the operator is Gt or Lt and exactly two elements if the operator is GtLt. In other cases Value should contain at least one element. items: type: string type: array required: - op type: object required: - feature type: object type: array name: description: Name of the rule. type: string vars: additionalProperties: type: string description: |- Vars is the variables to store if the rule matches. Variables can be referenced from other rules enabling more complex rule hierarchies. type: object varsTemplate: description: |- VarsTemplate specifies a template to expand for dynamically generating multiple variables. Data (after template expansion) must be keys with an optional value ([=]) separated by newlines. type: string required: - name type: object type: array required: - featureGroupRules type: object status: description: |- Status of the NodeFeatureGroup after the most recent evaluation of the specification. properties: nodes: description: Nodes is a list of FeatureGroupNode in the cluster that match the featureGroupRules items: properties: name: description: Name of the node. type: string required: - name type: object type: array x-kubernetes-list-map-keys: - name x-kubernetes-list-type: map type: object required: - spec type: object served: true storage: true subresources: status: {} --- apiVersion: apiextensions.k8s.io/v1 kind: CustomResourceDefinition metadata: annotations: controller-gen.kubebuilder.io/version: v0.16.3 name: nodefeaturerules.nfd.k8s-sigs.io spec: group: nfd.k8s-sigs.io names: kind: NodeFeatureRule listKind: NodeFeatureRuleList plural: nodefeaturerules shortNames: - nfr singular: nodefeaturerule scope: Cluster versions: - name: v1alpha1 schema: openAPIV3Schema: description: |- NodeFeatureRule resource specifies a configuration for feature-based customization of node objects, such as node labeling. 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: Spec defines the rules to be evaluated. properties: rules: description: Rules is a list of node customization rules. items: description: Rule defines a rule for node customization such as labeling. properties: annotations: additionalProperties: type: string description: Annotations to create if the rule matches. type: object extendedResources: additionalProperties: type: string description: ExtendedResources to create if the rule matches. type: object labels: additionalProperties: type: string description: Labels to create if the rule matches. type: object labelsTemplate: description: |- LabelsTemplate specifies a template to expand for dynamically generating multiple labels. Data (after template expansion) must be keys with an optional value ([=]) separated by newlines. type: string matchAny: description: MatchAny specifies a list of matchers one of which must match. items: description: MatchAnyElem specifies one sub-matcher of MatchAny. properties: matchFeatures: description: MatchFeatures specifies a set of matcher terms all of which must match. items: description: |- FeatureMatcherTerm defines requirements against one feature set. All requirements (specified as MatchExpressions) are evaluated against each element in the feature set. properties: feature: description: Feature is the name of the feature set to match against. type: string matchExpressions: additionalProperties: description: |- MatchExpression specifies an expression to evaluate against a set of input values. It contains an operator that is applied when matching the input and an array of values that the operator evaluates the input against. properties: op: description: Op is the operator to be applied. enum: - In - NotIn - InRegexp - Exists - DoesNotExist - Gt - Ge - Lt - Le - GtLt - GeLe - IsTrue - IsFalse type: string type: description: |- Type defines the value type for specific operators. The currently supported type is 'version' for Gt,Ge,Lt,Le,GtLt,GeLe operators. type: string value: description: |- Value is the list of values that the operand evaluates the input against. Value should be empty if the operator is Exists, DoesNotExist, IsTrue or IsFalse. Value should contain exactly one element if the operator is Gt or Lt and exactly two elements if the operator is GtLt. In other cases Value should contain at least one element. items: type: string type: array required: - op type: object description: |- MatchExpressions is the set of per-element expressions evaluated. These match against the value of the specified elements. type: object matchName: description: |- MatchName in an expression that is matched against the name of each element in the feature set. properties: op: description: Op is the operator to be applied. enum: - In - NotIn - InRegexp - Exists - DoesNotExist - Gt - Ge - Lt - Le - GtLt - GeLe - IsTrue - IsFalse type: string type: description: |- Type defines the value type for specific operators. The currently supported type is 'version' for Gt,Ge,Lt,Le,GtLt,GeLe operators. type: string value: description: |- Value is the list of values that the operand evaluates the input against. Value should be empty if the operator is Exists, DoesNotExist, IsTrue or IsFalse. Value should contain exactly one element if the operator is Gt or Lt and exactly two elements if the operator is GtLt. In other cases Value should contain at least one element. items: type: string type: array required: - op type: object required: - feature type: object type: array required: - matchFeatures type: object type: array matchFeatures: description: MatchFeatures specifies a set of matcher terms all of which must match. items: description: |- FeatureMatcherTerm defines requirements against one feature set. All requirements (specified as MatchExpressions) are evaluated against each element in the feature set. properties: feature: description: Feature is the name of the feature set to match against. type: string matchExpressions: additionalProperties: description: |- MatchExpression specifies an expression to evaluate against a set of input values. It contains an operator that is applied when matching the input and an array of values that the operator evaluates the input against. properties: op: description: Op is the operator to be applied. enum: - In - NotIn - InRegexp - Exists - DoesNotExist - Gt - Ge - Lt - Le - GtLt - GeLe - IsTrue - IsFalse type: string type: description: |- Type defines the value type for specific operators. The currently supported type is 'version' for Gt,Ge,Lt,Le,GtLt,GeLe operators. type: string value: description: |- Value is the list of values that the operand evaluates the input against. Value should be empty if the operator is Exists, DoesNotExist, IsTrue or IsFalse. Value should contain exactly one element if the operator is Gt or Lt and exactly two elements if the operator is GtLt. In other cases Value should contain at least one element. items: type: string type: array required: - op type: object description: |- MatchExpressions is the set of per-element expressions evaluated. These match against the value of the specified elements. type: object matchName: description: |- MatchName in an expression that is matched against the name of each element in the feature set. properties: op: description: Op is the operator to be applied. enum: - In - NotIn - InRegexp - Exists - DoesNotExist - Gt - Ge - Lt - Le - GtLt - GeLe - IsTrue - IsFalse type: string type: description: |- Type defines the value type for specific operators. The currently supported type is 'version' for Gt,Ge,Lt,Le,GtLt,GeLe operators. type: string value: description: |- Value is the list of values that the operand evaluates the input against. Value should be empty if the operator is Exists, DoesNotExist, IsTrue or IsFalse. Value should contain exactly one element if the operator is Gt or Lt and exactly two elements if the operator is GtLt. In other cases Value should contain at least one element. items: type: string type: array required: - op type: object required: - feature type: object type: array name: description: Name of the rule. type: string taints: description: Taints to create if the rule matches. 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 vars: additionalProperties: type: string description: |- Vars is the variables to store if the rule matches. Variables do not directly inflict any changes in the node object. However, they can be referenced from other rules enabling more complex rule hierarchies, without exposing intermediary output values as labels. type: object varsTemplate: description: |- VarsTemplate specifies a template to expand for dynamically generating multiple variables. Data (after template expansion) must be keys with an optional value ([=]) separated by newlines. type: string required: - name type: object type: array required: - rules type: object required: - spec type: object served: true storage: true --- # Source: gpu-operator/charts/node-feature-discovery/templates/serviceaccount.yaml apiVersion: v1 kind: ServiceAccount metadata: name: node-feature-discovery namespace: gpu-operator labels: helm.sh/chart: node-feature-discovery-0.18.3 app.kubernetes.io/name: node-feature-discovery app.kubernetes.io/instance: gpu-operator app.kubernetes.io/version: "v0.18.3" app.kubernetes.io/managed-by: Helm --- # Source: gpu-operator/templates/serviceaccount.yaml apiVersion: v1 kind: ServiceAccount metadata: name: gpu-operator namespace: gpu-operator labels: app.kubernetes.io/name: gpu-operator helm.sh/chart: gpu-operator-v26.3.2 app.kubernetes.io/instance: gpu-operator app.kubernetes.io/version: "v26.3.2" app.kubernetes.io/managed-by: Helm app.kubernetes.io/component: "gpu-operator" --- # Source: gpu-operator/charts/node-feature-discovery/templates/nfd-master-conf.yaml apiVersion: v1 kind: ConfigMap metadata: name: gpu-operator-node-feature-discovery-master-conf namespace: gpu-operator labels: helm.sh/chart: node-feature-discovery-0.18.3 app.kubernetes.io/name: node-feature-discovery app.kubernetes.io/instance: gpu-operator app.kubernetes.io/version: "v0.18.3" app.kubernetes.io/managed-by: Helm data: nfd-master.conf: |- extraLabelNs: - nvidia.com --- # Source: gpu-operator/charts/node-feature-discovery/templates/nfd-worker-conf.yaml apiVersion: v1 kind: ConfigMap metadata: name: gpu-operator-node-feature-discovery-worker-conf namespace: gpu-operator labels: helm.sh/chart: node-feature-discovery-0.18.3 app.kubernetes.io/name: node-feature-discovery app.kubernetes.io/instance: gpu-operator app.kubernetes.io/version: "v0.18.3" app.kubernetes.io/managed-by: Helm data: nfd-worker.conf: |- sources: pci: deviceClassWhitelist: - "02" - "0200" - "0207" - "0300" - "0302" deviceLabelFields: - vendor --- # Source: gpu-operator/charts/node-feature-discovery/templates/clusterrole.yaml apiVersion: rbac.authorization.k8s.io/v1 kind: ClusterRole metadata: name: gpu-operator-node-feature-discovery labels: helm.sh/chart: node-feature-discovery-0.18.3 app.kubernetes.io/name: node-feature-discovery app.kubernetes.io/instance: gpu-operator app.kubernetes.io/version: "v0.18.3" app.kubernetes.io/managed-by: Helm rules: - apiGroups: - "" resources: - namespaces verbs: - watch - list - apiGroups: - "" resources: - nodes - nodes/status verbs: - get - patch - update - list - apiGroups: - nfd.k8s-sigs.io resources: - nodefeatures - nodefeaturerules - nodefeaturegroups verbs: - get - list - watch - apiGroups: - nfd.k8s-sigs.io resources: - nodefeaturegroups/status verbs: - patch - update - apiGroups: - coordination.k8s.io resources: - leases verbs: - create - apiGroups: - coordination.k8s.io resources: - leases resourceNames: - "nfd-master.nfd.kubernetes.io" verbs: - get - update --- # Source: gpu-operator/charts/node-feature-discovery/templates/clusterrole.yaml apiVersion: rbac.authorization.k8s.io/v1 kind: ClusterRole metadata: name: gpu-operator-node-feature-discovery-gc labels: helm.sh/chart: node-feature-discovery-0.18.3 app.kubernetes.io/name: node-feature-discovery app.kubernetes.io/instance: gpu-operator app.kubernetes.io/version: "v0.18.3" app.kubernetes.io/managed-by: Helm rules: - apiGroups: - "" resources: - nodes verbs: - list - watch - apiGroups: - "" resources: - nodes/proxy verbs: - get - apiGroups: - topology.node.k8s.io resources: - noderesourcetopologies verbs: - delete - list - apiGroups: - nfd.k8s-sigs.io resources: - nodefeatures verbs: - delete - list --- # Source: gpu-operator/templates/clusterrole.yaml apiVersion: rbac.authorization.k8s.io/v1 kind: ClusterRole metadata: name: gpu-operator labels: app.kubernetes.io/name: gpu-operator helm.sh/chart: gpu-operator-v26.3.2 app.kubernetes.io/instance: gpu-operator app.kubernetes.io/version: "v26.3.2" app.kubernetes.io/managed-by: Helm app.kubernetes.io/component: "gpu-operator" rules: - apiGroups: - config.openshift.io resources: - clusterversions - proxies verbs: - get - list - watch - apiGroups: - image.openshift.io resources: - imagestreams verbs: - get - list - watch - apiGroups: - security.openshift.io resources: - securitycontextconstraints verbs: - create - get - list - watch - update - patch - delete - use - apiGroups: - rbac.authorization.k8s.io resources: - clusterroles - clusterrolebindings verbs: - create - get - list - watch - update - patch - delete - apiGroups: - "" resources: - nodes verbs: - get - list - watch - update - patch - apiGroups: - "" resources: - namespaces verbs: - get - list - watch - update - patch - apiGroups: - "" resources: - events verbs: - create - get - list - watch - delete - apiGroups: - "" resources: - pods verbs: - get - list - watch - apiGroups: - "" resources: - pods/eviction verbs: - create - apiGroups: - apps resources: - daemonsets verbs: - get - list - watch - apiGroups: - nvidia.com resources: - clusterpolicies - clusterpolicies/finalizers - clusterpolicies/status - nvidiadrivers - nvidiadrivers/finalizers - nvidiadrivers/status verbs: - create - get - list - watch - update - patch - delete - deletecollection - apiGroups: - scheduling.k8s.io resources: - priorityclasses verbs: - get - list - watch - create - apiGroups: - node.k8s.io resources: - runtimeclasses verbs: - get - list - create - update - watch - delete - apiGroups: - apiextensions.k8s.io resources: - customresourcedefinitions verbs: - get - list - watch - update - patch - create --- # Source: gpu-operator/charts/node-feature-discovery/templates/clusterrolebinding.yaml apiVersion: rbac.authorization.k8s.io/v1 kind: ClusterRoleBinding metadata: name: gpu-operator-node-feature-discovery labels: helm.sh/chart: node-feature-discovery-0.18.3 app.kubernetes.io/name: node-feature-discovery app.kubernetes.io/instance: gpu-operator app.kubernetes.io/version: "v0.18.3" app.kubernetes.io/managed-by: Helm roleRef: apiGroup: rbac.authorization.k8s.io kind: ClusterRole name: gpu-operator-node-feature-discovery subjects: - kind: ServiceAccount name: node-feature-discovery namespace: gpu-operator --- # Source: gpu-operator/charts/node-feature-discovery/templates/clusterrolebinding.yaml apiVersion: rbac.authorization.k8s.io/v1 kind: ClusterRoleBinding metadata: name: gpu-operator-node-feature-discovery-gc labels: helm.sh/chart: node-feature-discovery-0.18.3 app.kubernetes.io/name: node-feature-discovery app.kubernetes.io/instance: gpu-operator app.kubernetes.io/version: "v0.18.3" app.kubernetes.io/managed-by: Helm roleRef: apiGroup: rbac.authorization.k8s.io kind: ClusterRole name: gpu-operator-node-feature-discovery-gc subjects: - kind: ServiceAccount name: node-feature-discovery namespace: gpu-operator --- # Source: gpu-operator/templates/clusterrolebinding.yaml kind: ClusterRoleBinding apiVersion: rbac.authorization.k8s.io/v1 metadata: name: gpu-operator labels: app.kubernetes.io/name: gpu-operator helm.sh/chart: gpu-operator-v26.3.2 app.kubernetes.io/instance: gpu-operator app.kubernetes.io/version: "v26.3.2" app.kubernetes.io/managed-by: Helm app.kubernetes.io/component: "gpu-operator" subjects: - kind: ServiceAccount name: gpu-operator namespace: gpu-operator roleRef: kind: ClusterRole name: gpu-operator apiGroup: rbac.authorization.k8s.io --- # Source: gpu-operator/charts/node-feature-discovery/templates/role.yaml apiVersion: rbac.authorization.k8s.io/v1 kind: Role metadata: name: gpu-operator-node-feature-discovery-worker namespace: gpu-operator labels: helm.sh/chart: node-feature-discovery-0.18.3 app.kubernetes.io/name: node-feature-discovery app.kubernetes.io/instance: gpu-operator app.kubernetes.io/version: "v0.18.3" app.kubernetes.io/managed-by: Helm rules: - apiGroups: - nfd.k8s-sigs.io resources: - nodefeatures verbs: - create - get - update - delete - apiGroups: - "" resources: - pods verbs: - get --- # Source: gpu-operator/templates/role.yaml apiVersion: rbac.authorization.k8s.io/v1 kind: Role metadata: name: gpu-operator namespace: gpu-operator labels: app.kubernetes.io/name: gpu-operator helm.sh/chart: gpu-operator-v26.3.2 app.kubernetes.io/instance: gpu-operator app.kubernetes.io/version: "v26.3.2" app.kubernetes.io/managed-by: Helm app.kubernetes.io/component: "gpu-operator" rules: - apiGroups: - rbac.authorization.k8s.io resources: - roles - rolebindings verbs: - create - get - list - watch - update - patch - delete - apiGroups: - apps resources: - controllerrevisions verbs: - get - list - watch - apiGroups: - apps resources: - daemonsets verbs: - create - get - list - watch - update - patch - delete - apiGroups: - "" resources: - configmaps - endpoints - pods - pods/eviction - secrets - services - services/finalizers - serviceaccounts verbs: - create - get - list - watch - update - patch - delete - apiGroups: - coordination.k8s.io resources: - leases verbs: - get - list - watch - create - update - patch - delete - apiGroups: - monitoring.coreos.com resources: - servicemonitors - prometheusrules verbs: - get - list - create - watch - update - delete - apiGroups: - "nfd.k8s-sigs.io" resources: - "nodefeatures" verbs: - get - list - watch - create - update --- # Source: gpu-operator/charts/node-feature-discovery/templates/rolebinding.yaml apiVersion: rbac.authorization.k8s.io/v1 kind: RoleBinding metadata: name: gpu-operator-node-feature-discovery-worker namespace: gpu-operator labels: helm.sh/chart: node-feature-discovery-0.18.3 app.kubernetes.io/name: node-feature-discovery app.kubernetes.io/instance: gpu-operator app.kubernetes.io/version: "v0.18.3" app.kubernetes.io/managed-by: Helm roleRef: apiGroup: rbac.authorization.k8s.io kind: Role name: gpu-operator-node-feature-discovery-worker subjects: - kind: ServiceAccount name: node-feature-discovery namespace: gpu-operator --- # Source: gpu-operator/templates/rolebinding.yaml kind: RoleBinding apiVersion: rbac.authorization.k8s.io/v1 metadata: name: gpu-operator namespace: gpu-operator labels: app.kubernetes.io/name: gpu-operator helm.sh/chart: gpu-operator-v26.3.2 app.kubernetes.io/instance: gpu-operator app.kubernetes.io/version: "v26.3.2" app.kubernetes.io/managed-by: Helm app.kubernetes.io/component: "gpu-operator" subjects: - kind: ServiceAccount name: gpu-operator namespace: gpu-operator roleRef: kind: Role name: gpu-operator apiGroup: rbac.authorization.k8s.io --- # Source: gpu-operator/charts/node-feature-discovery/templates/worker.yaml apiVersion: apps/v1 kind: DaemonSet metadata: name: gpu-operator-node-feature-discovery-worker namespace: gpu-operator labels: helm.sh/chart: node-feature-discovery-0.18.3 app.kubernetes.io/name: node-feature-discovery app.kubernetes.io/instance: gpu-operator app.kubernetes.io/version: "v0.18.3" app.kubernetes.io/managed-by: Helm role: worker spec: revisionHistoryLimit: selector: matchLabels: app.kubernetes.io/name: node-feature-discovery app.kubernetes.io/instance: gpu-operator role: worker template: metadata: labels: app.kubernetes.io/name: node-feature-discovery app.kubernetes.io/instance: gpu-operator role: worker annotations: checksum/config: 49927da7921fd67923a64b7824f4ea87369321dfb619f890e2d5f6545e800416 spec: dnsPolicy: ClusterFirstWithHostNet priorityClassName: system-node-critical imagePullSecrets: serviceAccountName: node-feature-discovery securityContext: {} hostNetwork: false containers: - name: worker securityContext: allowPrivilegeEscalation: false capabilities: drop: - ALL readOnlyRootFilesystem: true runAsNonRoot: true image: "registry.k8s.io/nfd/node-feature-discovery:v0.18.3" imagePullPolicy: IfNotPresent livenessProbe: httpGet: path: /healthz port: http initialDelaySeconds: 10 readinessProbe: httpGet: path: /healthz port: http initialDelaySeconds: 5 failureThreshold: 10 env: - name: NODE_NAME valueFrom: fieldRef: fieldPath: spec.nodeName - name: POD_NAME valueFrom: fieldRef: fieldPath: metadata.name - name: POD_UID valueFrom: fieldRef: fieldPath: metadata.uid resources: limits: memory: 512Mi requests: cpu: 5m memory: 64Mi command: - "nfd-worker" args: # Go over featureGate and add the feature-gate flag - "-feature-gates=NodeFeatureGroupAPI=false" - "-port=8080" ports: - containerPort: 8080 name: http volumeMounts: - name: host-boot mountPath: "/host-boot" readOnly: true - name: host-os-release mountPath: "/host-etc/os-release" readOnly: true - name: host-sys mountPath: "/host-sys" readOnly: true - name: host-usr-lib mountPath: "/host-usr/lib" readOnly: true - name: host-lib mountPath: "/host-lib" readOnly: true - name: host-proc-swaps mountPath: "/host-proc/swaps" readOnly: true - name: features-d mountPath: "/etc/kubernetes/node-feature-discovery/features.d/" readOnly: true - name: nfd-worker-conf mountPath: "/etc/kubernetes/node-feature-discovery" readOnly: true volumes: - name: host-boot hostPath: path: "/boot" - name: host-os-release hostPath: path: "/etc/os-release" - name: host-sys hostPath: path: "/sys" - name: host-usr-lib hostPath: path: "/usr/lib" - name: host-lib hostPath: path: "/lib" - name: host-proc-swaps hostPath: path: "/proc/swaps" - name: features-d hostPath: path: "/etc/kubernetes/node-feature-discovery/features.d/" - name: nfd-worker-conf configMap: name: gpu-operator-node-feature-discovery-worker-conf items: - key: nfd-worker.conf path: nfd-worker.conf tolerations: - effect: NoSchedule key: node-role.kubernetes.io/control-plane operator: Equal value: "" - effect: NoSchedule key: nvidia.com/gpu operator: Exists --- # Source: gpu-operator/charts/node-feature-discovery/templates/master.yaml apiVersion: apps/v1 kind: Deployment metadata: name: gpu-operator-node-feature-discovery-master namespace: gpu-operator labels: helm.sh/chart: node-feature-discovery-0.18.3 app.kubernetes.io/name: node-feature-discovery app.kubernetes.io/instance: gpu-operator app.kubernetes.io/version: "v0.18.3" app.kubernetes.io/managed-by: Helm role: master spec: replicas: 1 revisionHistoryLimit: selector: matchLabels: app.kubernetes.io/name: node-feature-discovery app.kubernetes.io/instance: gpu-operator role: master template: metadata: labels: app.kubernetes.io/name: node-feature-discovery app.kubernetes.io/instance: gpu-operator role: master annotations: checksum/config: 4c75beab900dd5a0d37d2f52bab62d584835356434381fb0661f828a03b5935d spec: dnsPolicy: ClusterFirstWithHostNet priorityClassName: system-node-critical imagePullSecrets: serviceAccountName: node-feature-discovery enableServiceLinks: false securityContext: {} hostNetwork: false containers: - name: master securityContext: allowPrivilegeEscalation: false capabilities: drop: - ALL readOnlyRootFilesystem: true runAsNonRoot: true image: "registry.k8s.io/nfd/node-feature-discovery:v0.18.3" imagePullPolicy: IfNotPresent startupProbe: httpGet: path: /healthz port: http failureThreshold: 30 livenessProbe: httpGet: path: /healthz port: http readinessProbe: httpGet: path: /healthz port: http failureThreshold: 10 ports: - containerPort: 8080 name: http env: - name: NODE_NAME valueFrom: fieldRef: fieldPath: spec.nodeName command: - "nfd-master" resources: limits: memory: 4Gi requests: cpu: 100m memory: 128Mi args: - "-enable-leader-election" # Go over featureGates and add the feature-gate flag - "-feature-gates=NodeFeatureGroupAPI=false" - "-port=8080" volumeMounts: - name: nfd-master-conf mountPath: "/etc/kubernetes/node-feature-discovery" readOnly: true volumes: - name: nfd-master-conf configMap: name: gpu-operator-node-feature-discovery-master-conf items: - key: nfd-master.conf path: nfd-master.conf affinity: nodeAffinity: preferredDuringSchedulingIgnoredDuringExecution: - preference: matchExpressions: - key: node-role.kubernetes.io/control-plane operator: In values: - "" weight: 1 tolerations: - effect: NoSchedule key: node-role.kubernetes.io/control-plane operator: Equal value: "" --- # Source: gpu-operator/charts/node-feature-discovery/templates/nfd-gc.yaml apiVersion: apps/v1 kind: Deployment metadata: name: gpu-operator-node-feature-discovery-gc namespace: gpu-operator labels: helm.sh/chart: node-feature-discovery-0.18.3 app.kubernetes.io/name: node-feature-discovery app.kubernetes.io/instance: gpu-operator app.kubernetes.io/version: "v0.18.3" app.kubernetes.io/managed-by: Helm role: gc spec: replicas: 1 revisionHistoryLimit: selector: matchLabels: app.kubernetes.io/name: node-feature-discovery app.kubernetes.io/instance: gpu-operator role: gc template: metadata: labels: app.kubernetes.io/name: node-feature-discovery app.kubernetes.io/instance: gpu-operator role: gc spec: serviceAccountName: node-feature-discovery dnsPolicy: ClusterFirstWithHostNet priorityClassName: system-node-critical imagePullSecrets: securityContext: {} hostNetwork: false containers: - name: gc image: "registry.k8s.io/nfd/node-feature-discovery:v0.18.3" imagePullPolicy: "IfNotPresent" livenessProbe: httpGet: path: /healthz port: http initialDelaySeconds: 10 readinessProbe: httpGet: path: /healthz port: http initialDelaySeconds: 5 env: - name: NODE_NAME valueFrom: fieldRef: fieldPath: spec.nodeName command: - "nfd-gc" args: - "-gc-interval=1h" resources: limits: memory: 1Gi requests: cpu: 10m memory: 128Mi securityContext: allowPrivilegeEscalation: false capabilities: drop: [ "ALL" ] readOnlyRootFilesystem: true runAsNonRoot: true ports: - name: http containerPort: 8080 --- # Source: gpu-operator/templates/operator.yaml apiVersion: apps/v1 kind: Deployment metadata: name: gpu-operator namespace: gpu-operator labels: app.kubernetes.io/name: gpu-operator helm.sh/chart: gpu-operator-v26.3.2 app.kubernetes.io/instance: gpu-operator app.kubernetes.io/version: "v26.3.2" app.kubernetes.io/managed-by: Helm app.kubernetes.io/component: "gpu-operator" nvidia.com/gpu-driver-upgrade-drain.skip: "true" spec: replicas: 1 selector: matchLabels: app.kubernetes.io/component: "gpu-operator" app: "gpu-operator" template: metadata: labels: app.kubernetes.io/name: gpu-operator helm.sh/chart: gpu-operator-v26.3.2 app.kubernetes.io/instance: gpu-operator app.kubernetes.io/version: "v26.3.2" app.kubernetes.io/managed-by: Helm app.kubernetes.io/component: "gpu-operator" app: "gpu-operator" nvidia.com/gpu-driver-upgrade-drain.skip: "true" annotations: openshift.io/scc: restricted-readonly spec: serviceAccountName: gpu-operator priorityClassName: system-node-critical containers: - name: gpu-operator image: nvcr.io/nvidia/gpu-operator:v26.3.2 imagePullPolicy: IfNotPresent command: ["gpu-operator"] args: - --leader-elect - --zap-time-encoding=epoch - --zap-log-level=info env: - name: WATCH_NAMESPACE value: "" - name: OPERATOR_NAMESPACE valueFrom: fieldRef: fieldPath: metadata.namespace - name: "DRIVER_MANAGER_IMAGE" value: "nvcr.io/nvidia/cloud-native/k8s-driver-manager:v0.11.0" livenessProbe: httpGet: path: /healthz port: 8081 initialDelaySeconds: 15 periodSeconds: 20 readinessProbe: httpGet: path: /readyz port: 8081 initialDelaySeconds: 5 periodSeconds: 10 resources: limits: cpu: 500m memory: 350Mi requests: cpu: 200m memory: 100Mi ports: - name: metrics containerPort: 8080 affinity: nodeAffinity: preferredDuringSchedulingIgnoredDuringExecution: - preference: matchExpressions: - key: node-role.kubernetes.io/control-plane operator: In values: - "" weight: 1 tolerations: - effect: NoSchedule key: node-role.kubernetes.io/control-plane operator: Equal value: "" --- # Source: gpu-operator/templates/clusterpolicy.yaml apiVersion: nvidia.com/v1 kind: ClusterPolicy metadata: name: cluster-policy labels: app.kubernetes.io/name: gpu-operator helm.sh/chart: gpu-operator-v26.3.2 app.kubernetes.io/instance: gpu-operator app.kubernetes.io/version: "v26.3.2" app.kubernetes.io/managed-by: Helm app.kubernetes.io/component: "gpu-operator" spec: hostPaths: rootFS: / driverInstallDir: /run/nvidia/driver operator: runtimeClass: nvidia daemonsets: labels: helm.sh/chart: gpu-operator-v26.3.2 app.kubernetes.io/managed-by: gpu-operator tolerations: - effect: NoSchedule key: nvidia.com/gpu operator: Exists priorityClassName: system-node-critical updateStrategy: RollingUpdate rollingUpdate: maxUnavailable: "1" validator: repository: nvcr.io/nvidia image: gpu-operator version: "v26.3.2" imagePullPolicy: IfNotPresent plugin: env: [] mig: strategy: single psa: enabled: false cdi: enabled: true driver: enabled: true useNvidiaDriverCRD: false kernelModuleType: auto usePrecompiled: false repository: nvcr.io/nvidia image: driver version: "595.91.07" imagePullPolicy: IfNotPresent startupProbe: failureThreshold: 120 initialDelaySeconds: 60 periodSeconds: 10 timeoutSeconds: 60 rdma: enabled: false useHostMofed: false manager: repository: nvcr.io/nvidia/cloud-native image: k8s-driver-manager version: "v0.11.0" imagePullPolicy: IfNotPresent repoConfig: configMapName: "" certConfig: name: "" licensingConfig: nlsEnabled: true secretName: "" virtualTopology: config: "" kernelModuleConfig: name: "" upgradePolicy: autoUpgrade: true maxParallelUpgrades: 1 maxUnavailable : 25% waitForCompletion: timeoutSeconds: 0 podDeletion: force: false timeoutSeconds: 300 deleteEmptyDir: false drain: enable: false force: false timeoutSeconds: 300 deleteEmptyDir: false vgpuManager: enabled: false image: vgpu-manager imagePullPolicy: IfNotPresent kernelModuleConfig: name: "" driverManager: repository: nvcr.io/nvidia/cloud-native image: k8s-driver-manager version: "v0.11.0" imagePullPolicy: IfNotPresent kataManager: enabled: false imagePullPolicy: IfNotPresent vfioManager: enabled: true repository: nvcr.io/nvidia/cloud-native image: k8s-driver-manager version: "v0.11.0" imagePullPolicy: IfNotPresent driverManager: repository: nvcr.io/nvidia/cloud-native image: k8s-driver-manager version: "v0.11.0" imagePullPolicy: IfNotPresent vgpuDeviceManager: enabled: true repository: nvcr.io/nvidia/cloud-native image: vgpu-device-manager version: "v0.4.2" imagePullPolicy: IfNotPresent config: default: default name: "" ccManager: enabled: true defaultMode: "on" repository: nvcr.io/nvidia/cloud-native image: k8s-cc-manager version: "v0.4.0" imagePullPolicy: IfNotPresent toolkit: enabled: true repository: nvcr.io/nvidia/k8s image: container-toolkit version: "v1.19.1" imagePullPolicy: IfNotPresent installDir: /usr/local/nvidia devicePlugin: enabled: true repository: nvcr.io/nvidia image: k8s-device-plugin version: "v0.19.2" imagePullPolicy: IfNotPresent dcgm: enabled: false repository: nvcr.io/nvidia/cloud-native image: dcgm version: "4.5.2-1-ubuntu22.04" imagePullPolicy: IfNotPresent dcgmExporter: enabled: true repository: nvcr.io/nvidia/k8s image: dcgm-exporter version: "4.5.3-4.8.2-distroless" imagePullPolicy: IfNotPresent serviceMonitor: additionalLabels: {} enabled: false honorLabels: false interval: 15s relabelings: [] service: internalTrafficPolicy: Cluster gfd: enabled: true repository: nvcr.io/nvidia image: k8s-device-plugin version: "v0.19.2" imagePullPolicy: IfNotPresent migManager: enabled: true repository: nvcr.io/nvidia/cloud-native image: k8s-mig-manager version: "v0.14.2" imagePullPolicy: IfNotPresent config: default: "all-disabled" gpuClientsConfig: name: "" nodeStatusExporter: enabled: false repository: nvcr.io/nvidia image: gpu-operator version: "v26.3.2" imagePullPolicy: IfNotPresent gds: enabled: false repository: nvcr.io/nvidia/cloud-native image: nvidia-fs version: "2.27.3" imagePullPolicy: IfNotPresent gdrcopy: enabled: false repository: nvcr.io/nvidia/cloud-native image: gdrdrv version: "v2.5.2" imagePullPolicy: IfNotPresent sandboxWorkloads: enabled: false defaultWorkload: container mode: "kubevirt" sandboxDevicePlugin: enabled: true repository: nvcr.io/nvidia image: kubevirt-gpu-device-plugin version: "v1.5.0" imagePullPolicy: IfNotPresent kataSandboxDevicePlugin: enabled: true repository: nvcr.io/nvidia/cloud-native image: nvidia-sandbox-device-plugin version: "v0.0.3" imagePullPolicy: IfNotPresent