加入 Gitee
与超过 1200万 开发者一起发现、参与优秀开源项目,私有仓库也完全免费 :)
免费加入
文件
克隆/下载
volcano-vgpu-device-plugin.yml 3.73 KB
一键复制 编辑 原始数据 按行查看 历史
limengxuan 提交于 2023-12-25 18:23 . adjust ci and examples
# 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: v1
kind: ServiceAccount
metadata:
name: volcano-device-plugin
namespace: kube-system
---
kind: ClusterRole
apiVersion: rbac.authorization.k8s.io/v1
metadata:
name: volcano-device-plugin
rules:
- apiGroups: [""]
resources: ["nodes"]
verbs: ["get","list", "watch","update","patch"]
- apiGroups: [""]
resources: ["nodes/status"]
verbs: ["patch"]
- apiGroups: [""]
resources: ["pods"]
verbs: ["get", "list", "update","patch"]
---
kind: ClusterRoleBinding
apiVersion: rbac.authorization.k8s.io/v1
metadata:
name: volcano-device-plugin
subjects:
- kind: ServiceAccount
name: volcano-device-plugin
namespace: kube-system
roleRef:
kind: ClusterRole
name: volcano-device-plugin
apiGroup: rbac.authorization.k8s.io
---
apiVersion: apps/v1
kind: DaemonSet
metadata:
name: volcano-device-plugin
namespace: kube-system
spec:
selector:
matchLabels:
name: volcano-device-plugin
updateStrategy:
type: RollingUpdate
template:
metadata:
# This annotation is deprecated. Kept here for backward compatibility
# See https://kubernetes.io/docs/tasks/administer-cluster/guaranteed-scheduling-critical-addon-pods/
annotations:
scheduler.alpha.kubernetes.io/critical-pod: ""
labels:
name: volcano-device-plugin
spec:
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: volcano.sh/gpu-memory
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"
serviceAccount: volcano-device-plugin
containers:
- image: volcanosh/volcano-vgpu-device-plugin:dev-vgpu-1219
args: ["--device-split-count=10"]
lifecycle:
postStart:
exec:
command: ["/bin/sh","-c","cp -f /k8s-vgpu/lib/nvidia/* /usr/local/vgpu/"]
name: volcano-device-plugin
env:
- name: NODE_NAME
valueFrom:
fieldRef:
fieldPath: spec.nodeName
- name: HOOK_PATH
value: "/usr/local/vgpu"
securityContext:
allowPrivilegeEscalation: false
capabilities:
drop: ["ALL"]
add: ["SYS_ADMIN"]
volumeMounts:
- name: device-plugin
mountPath: /var/lib/kubelet/device-plugins
- name: lib
mountPath: /usr/local/vgpu
- name: hosttmp
mountPath: /tmp
volumes:
- name: device-plugin
hostPath:
path: /var/lib/kubelet/device-plugins
- name: lib
hostPath:
path: /usr/local/vgpu
- name: hosttmp
hostPath:
path: /tmp
马建仓 AI 助手
尝试更多
代码解读
代码找茬
代码优化