操作系统版本: rocky8.10, 相当于 cento8.5

安装 docker

参考: https://help.aliyun.com/zh/ecs/use-cases/install-and-use-docker

# 如果是非阿里云服务器
sudo wget -O /etc/yum.repos.d/docker-ce.repo https://mirrors.aliyun.com/docker-ce/linux/centos/docker-ce.repo

# 如果是阿里云的机器
#sudo wget -O /etc/yum.repos.d/docker-ce.repo http://mirrors.cloud.aliyuncs.com/docker-ce/linux/centos/docker-ce.repo
#sudo sed -i 's|https://mirrors.aliyun.com|http://mirrors.cloud.aliyuncs.com|g' /etc/yum.repos.d/docker-ce.repo

#安装Docker社区版本，容器运行时containerd.io，以及Docker构建和Compose插件
sudo dnf -y install docker-ce docker-ce-cli containerd.io docker-buildx-plugin docker-compose-plugin

# 查看 docker 版本
docker --version

#启动Docker
sudo systemctl start docker
#设置Docker守护进程在系统启动时自动启动
sudo systemctl enable docker

docker --version

nvidia-container-toolkit 安装

参考: https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html

# 添加 nvidia-container-toolkit 源
curl -s -L https://nvidia.github.io/libnvidia-container/stable/rpm/nvidia-container-toolkit.repo | \
  sudo tee /etc/yum.repos.d/nvidia-container-toolkit.repo

# 安装 nvidia-container-toolkit
sudo dnf install -y nvidia-container-toolkit
sudo nvidia-ctk runtime configure --runtime=docker

sudo systemctl restart docker

修改 docker 数据存储路径

/etc/docker/daemon.json 中增加配置 "data-root": "/new/docker/storage"
其中 runtimes.nvidia 是 nvidia-ctk 添加的, 内容如下
cat /etc/docker/daemon.json

{
    "data-root": "/new/docker/storage",
    "runtimes": {
        "nvidia": {
            "args": [],
            "path": "nvidia-container-runtime"
        }
    }
}

配置 docker 拉取镜像时的代理

sudo mkdir -p /etc/systemd/system/docker.service.d
sudo vim /etc/systemd/system/docker.service.d/http-proxy.conf

[Service]
Environment="HTTP_PROXY=http://proxy.example.com:port"
Environment="HTTPS_PROXY=http://proxy.example.com:port"
Environment="NO_PROXY=your-registry.com,10.10.10.10,*.example.com"

sudo systemctl daemon-reload
sudo systemctl restart docker

检查确认环境变量已经正确配置
sudo systemctl show --property=Environment docker

从 docker info 的结果中查看配置项,确认docker配置确实生效

image.png

参考: https://www.lfhacks.com/tech/pull-docker-images-behind-proxy/

拉取镜像,检查容器中使用显卡是否正确

sudo docker pull nvidia/cuda:12.6.3-base-ubuntu22.04

sudo docker run --rm --gpus all nvidia/cuda:12.6.3-base-ubuntu22.04 nvidia-smi

image.png

验证正常~