charts/nvidia-dra-driver-gpu/values.yaml

# Copyright 2023 NVIDIA CORPORATION
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

# Default values for k8s-dra-driver-gpu.
# This is a YAML-formatted file.
# Declare variables to be passed into your templates.

# Specify the driver root on the host.
# If the NVIDIA GPU driver is managed using the NVIDIA GPU Driver Container,
# this is typically /run/nvidia/driver.
# For driver installed directly on a host, a value of `/` is used.
nvidiaDriverRoot: /

# Specify the path of CTK binary (nvidia-ctk) on the host,
# as it should appear in the the generated CDI specification.
# The path depends on the system that runs on the node.
nvidiaCtkPath: /usr/bin/nvidia-ctk

nameOverride: ""
fullnameOverride: ""
namespaceOverride: ""
selectorLabelsOverride: {}
gpuResourcesEnabledOverride: false

allowDefaultNamespace: false

imagePullSecrets: []
image:
  repository: nvcr.io/nvidia/k8s-dra-driver-gpu
  pullPolicy: IfNotPresent
  # Note: an empty string is translated to the `appVersion` string from
  # the Helm chart YAML (effectively implementing the default value to be
  # the current version). Also note that a "v" is prefixed to the
  # `appVersion` value.
  tag: ""

serviceAccount:
  # Specifies whether a service account should be created
  create: true
  # Annotations to add to the service account
  annotations: {}
  # The name of the service account to use.
  # If not set and create is true, a name is generated using the fullname template
  name: ""

resources:
  gpus:
    enabled: true
  computeDomains:
    enabled: true

controller:
  priorityClassName: "system-node-critical"
  podAnnotations: {}
  podSecurityContext: {}
  nodeSelector: {}
  tolerations:
  - key: node-role.kubernetes.io/control-plane
    operator: Exists
    effect: NoSchedule
  containers:
    computeDomain:
      securityContext: {}
      resources: {}
  affinity:
    nodeAffinity:
      requiredDuringSchedulingIgnoredDuringExecution:
        nodeSelectorTerms:
        - matchExpressions:
          - key: "node-role.kubernetes.io/control-plane"
            operator: "Exists"

kubeletPlugin:
  priorityClassName: "system-node-critical"
  updateStrategy:
    type: RollingUpdate
  podAnnotations: {}
  podSecurityContext: {}
  nodeSelector: {}
  tolerations: []
  containers:
    init:
      securityContext: {}
      resources: {}
    computeDomains:
      securityContext:
        privileged: true
      resources: {}
    gpus:
      securityContext:
        privileged: true
      resources: {}
  affinity:
    nodeAffinity:
      requiredDuringSchedulingIgnoredDuringExecution:
        nodeSelectorTerms:
        - matchExpressions:
          # On discrete-GPU based systems NFD adds the following label where 10de is the NVIDIA PCI vendor ID
          - key: feature.node.kubernetes.io/pci-10de.present
            operator: In
            values:
            - "true"
        - matchExpressions:
          # On some Tegra-based systems NFD detects the CPU vendor ID as NVIDIA
          - key: feature.node.kubernetes.io/cpu-model.vendor_id
            operator: In
            values:
            - "NVIDIA"
        - matchExpressions:
          # We allow a GPU deployment to be forced by setting the following label to "true"
          - key: "nvidia.com/gpu.present"
            operator: In
            values:
            - "true"