2 posts tagged with "infra"

# Plugin configuration
# Only one of "name" or "map" should ever be set for a given deployment.
# Use "name" to point to an external ConfigMap with a list of configurations.
# Use "map" to build an integrated ConfigMap from a set of configurations as
# part of this helm chart. An example of setting "map" might be:
# config:
#   map:
#     default: |-
#       version: v1
#       flags:
#         migStrategy: none
#     mig-single: |-
#       version: v1
#       flags:
#         migStrategy: single
#     mig-mixed: |-
#       version: v1
#       flags:
#         migStrategy: mixed
config:
  # ConfigMap name if pulling from an external ConfigMap
  name: ""
  # Set of named configs to build an integrated ConfigMap from
  map:
    default: |-
      version: v1
        flags:
          migStrategy: mixed
        sharing:
          timeSlicing:
            renameByDefault: false
            failRequestsGreaterThanOne: false
            resources:
              - name: nvidia.com/gpu
                replicas: 4 # 主要是这里，加了个time slicing，然后replicas改成了4，就能同时调度四个pod了
  # Default config name within the ConfigMap
  default: ""
  # List of fallback strategies to attempt if no config is selected and no default is provided
  fallbackStrategies: [ "named", "single" ]

legacyDaemonsetAPI: null
compatWithCPUManager: null
migStrategy: null
failOnInitError: null
deviceListStrategy: null
deviceIDStrategy: null
nvidiaDriverRoot: null
gdsEnabled: null
mofedEnabled: null

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

allowDefaultNamespace: false

imagePullSecrets: []
image:
  repository: nvcr.io/nvidia/k8s-device-plugin
  pullPolicy: IfNotPresent
  # Overrides the image tag whose default is the chart appVersion.
  tag: ""

updateStrategy:
  type: RollingUpdate

podAnnotations: {}
podSecurityContext: {}
securityContext: {}

resources: {}
nodeSelector: {}
affinity: {}
tolerations:
  # This toleration is deprecated. Kept here for backward compatibility
  # See https://kubernetes.io/docs/tasks/administer-cluster/guaranteed-scheduling-critical-addon-pods/
  - key: CriticalAddonsOnly
    operator: Exists
  - key: nvidia.com/gpu
    operator: Exists
    effect: NoSchedule

# Mark this pod as a critical add-on; when enabled, the critical add-on
# scheduler reserves resources for critical add-on pods so that they can
# be rescheduled after a failure.
# See https://kubernetes.io/docs/tasks/administer-cluster/guaranteed-scheduling-critical-addon-pods/
priorityClassName: "system-node-critical"

runtimeClassName: null

# Subcharts
nfd:
  nameOverride: node-feature-discovery
  enableNodeFeatureApi: false
  master:
    extraLabelNs:
      - nvidia.com
    serviceAccount:
      name: node-feature-discovery

  worker:
    tolerations:
      - key: "node-role.kubernetes.io/master"
        operator: "Equal"
        value: ""
        effect: "NoSchedule"
      - key: "nvidia.com/gpu"
        operator: "Equal"
        value: "present"
        effect: "NoSchedule"
    config:
      sources:
        pci:
          deviceClassWhitelist:
            - "02"
            - "0200"
            - "0207"
            - "0300"
            - "0302"
          deviceLabelFields:
            - vendor
gfd:
  enabled: true
  nameOverride: gpu-feature-discovery
  namespaceOverride: ""

# kubectl describe node cluster-node0
Name:               cluster-node0
Roles:              <none>
Labels:             .......
                    nvidia.com/cuda.driver.major=470
                    nvidia.com/cuda.driver.minor=199
                    nvidia.com/cuda.driver.rev=02
                    nvidia.com/cuda.runtime.major=11
                    nvidia.com/cuda.runtime.minor=4
                    nvidia.com/gfd.timestamp=1695800061
                    nvidia.com/gpu.compute.major=6
                    nvidia.com/gpu.compute.minor=1
                    nvidia.com/gpu.count=1
                    nvidia.com/gpu.family=pascal
                    nvidia.com/gpu.memory=6080
                    nvidia.com/gpu.product=NVIDIA-P106-100-SHARED
                    nvidia.com/gpu.replicas=4
                    nvidia.com/mig.capable=false
                    nvidia.com/mig.strategy=mixed
......
Capacity:
  ......
  nvidia.com/gpu:     4