# kubectl exec -it <容器名> /bin/bash
# mnist测试结果
一、环境介绍:阿里云新购4台vps(新加坡区),其中一台带GPU显卡
二、GPU驱动安装
wget http://cn.download.nvidia.com/tesla/384.66/nvidia-diag-driver-local-repo-ubuntu1604-384.66_1.0-1_amd64.deb
# 注意dpkg安装后,需要导入密钥
三、GPU node安装nvidia-docker
curl -s -L https://nvidia.github.io/nvidia-docker/gpgkey | apt-key add -
distribution=$(. /etc/os-release;echo $ID$VERSION_ID)
curl -s -L https://nvidia.github.io/nvidia-docker/$distribution/nvidia-docker.list | tee /etc/apt/sources.list.d/nvidia-docker.list
apt-get update
apt-get install -y nvidia-docker2
pkill -SIGHUP dockerd
四、修改/etc/docker/daemon.json
五、GPU node增加kubelet启动参数
--feature-gates=DevicePlugins=true
六、GPU node重启kubelet
systemctl daemon-reload
systemctl restart kubelet
七、开启GPU支持
kubectl create -f https://raw.githubusercontent.com/NVIDIA/k8s-device-plugin/v1.9/nvidia-device-plugin.yml
八、GPU node打label
kubectl label nodes node4 accelerator=nvidia-tesla-p100
九、测试