卸载相关包

# 旧版docker
yum remove docker \
           docker-client \
           docker-client-latest \
           docker-common \
           docker-latest \
           docker-latest-logrotate \
           docker-logrotate \
           docker-selinux \
           docker-engine-selinux \
           docker-engine
           
# 新版docker(社区版)
yum remove docker-ce \
           docker-ce-cli \
           containerd

删除相关文件(备份好容器内的相关文件)

systemctl stop docker
rm -rf /etc/systemd/system/docker.service.d
rm -rf /etc/systemd/system/docker.service
rm -rf /var/lib/docker
rm -rf /var/run/docker
rm -rf /usr/local/docker
rm -rf /etc/docker
rm -rf /usr/bin/docker* /usr/bin/containerd* /usr/bin/runc /usr/bin/ctr

重新添加docker源

sudo yum-config-manager --add-repo=https://download.docker.com/linux/centos/docker-ce.repo
cat /etc/yum.repos.d/docker-ce.repo

下载安装包

repotrack docker-ce

# 安装docker 并设置开机自启
yum install ./*
systemctl  start docker
systemctl  enable docker

配置nvidia-docker的源

distribution=$(. /etc/os-release;echo $ID$VERSION_ID) && curl -s -L https://nvidia.github.io/nvidia-docker/$distribution/nvidia-docker.repo | sudo tee /etc/yum.repos.d/nvidia-docker.repo

cat /etc/yum.repos.d/nvidia-docker.repo

安装下载nvidia-docker

mkdir nvidia-docker2
cd nvidia-docker2
yum update -y
repotrack nvidia-docker2
yum install ./*

mkdir nvidia-container-toolkit
cd nvidia-container-toolkit
repotrack nvidia-container-toolkit
yum install ./*

下载镜像,并保存

docker pull nvidia/cuda:11.0-base
docker images
docker save -o cuda-11.0.tar nvidia/cuda:11.0-base
ls cuda-11.0.tar

在要测试的服务器上导入镜像

docker load -i cuda-11.0.tar
docker images | grep cuda

配置docker

# vim /etc/docker/daemon.json
{
    "runtimes": {
        "nvidia": {
            "path": "nvidia-container-runtime",
            "runtimeArgs": []
        }
    }
}
# 
systemctl daemon-reload
systemctl  restart docker

# 测试docker中的调用情况
sudo docker run --rm --gpus all nvidia/cuda:11.0-base nvidia-smi

*更改docker目录

systemctl stop docker
mkdir -p /home/docker
mv /var/lib/docker/* /home/docker	#将数据移至目标文件
rm -rf /var/lib/docker	
ln -s/home/docker /var/lib/docker	# 软链接
systemctl daemon-reload
systemctl restart docker
systemctl enable docker
Logo

魔乐社区(Modelers.cn) 是一个中立、公益的人工智能社区,提供人工智能工具、模型、数据的托管、展示与应用协同服务,为人工智能开发及爱好者搭建开放的学习交流平台。社区通过理事会方式运作,由全产业链共同建设、共同运营、共同享有,推动国产AI生态繁荣发展。

更多推荐