# Copyright (c) 2019, NVIDIA CORPORATION. All rights reserved. # # 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. apiVersion: apps/v1 kind: DaemonSet metadata: name: nvidia-device-plugin-daemonset namespace: kube-system spec: selector: matchLabels: name: nvidia-device-plugin-ds updateStrategy: type: RollingUpdate template: metadata: labels: name: nvidia-device-plugin-ds spec: # Schedule ONLY on the GPU node by hostname nodeSelector: kubernetes.io/hostname: k3s-worker-5-gpu tolerations: # Tolerate the gpu=true:NoSchedule taint on the GPU node - key: gpu operator: Equal value: "true" effect: NoSchedule # Also tolerate nvidia.com/gpu taint if present - 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" containers: - image: nvcr.io/nvidia/k8s-device-plugin:v0.15.0 name: nvidia-device-plugin-ctr env: - name: FAIL_ON_INIT_ERROR value: "false" securityContext: allowPrivilegeEscalation: false capabilities: drop: ["ALL"] volumeMounts: - name: device-plugin mountPath: /var/lib/kubelet/device-plugins - name: nvidia-libs mountPath: /usr/lib/x86_64-linux-gnu readOnly: true volumes: - name: device-plugin hostPath: path: /var/lib/kubelet/device-plugins - name: nvidia-libs hostPath: path: /usr/lib/x86_64-linux-gnu