Ubuntu服务器配置docker

1、卸载原始docker和英伟达容器运行时（如有）

# 停止服务
sudo systemctl stop docker
sudo systemctl stop docker.socket
sudo systemctl disable docker

# 卸载Docker全家桶
sudo apt remove -y docker-ce docker-ce-cli containerd.io docker-buildx-plugin docker-compose-plugin

# 卸载所有nvidia-container相关包（匹配你当前已安装的组件）
sudo apt remove -y libnvidia-container-tools libnvidia-container1 nvidia-container-toolkit nvidia-container-toolkit-base

# 自动清理无用依赖
sudo apt autoremove -y

# 删除全部配置、镜像、容器持久化数据
sudo rm -rf /etc/docker
sudo rm -rf /var/lib/docker
sudo rm -rf /var/lib/containerd
sudo rm -rf ~/.docker /root/.docker
sudo rm -rf /etc/nvidia-container-runtime/

# 删除docker软件源与密钥
sudo rm -f /etc/apt/sources.list.d/docker.sources
sudo rm -f /etc/apt/keyrings/docker.asc

# 更新软件源缓存
sudo apt update

2、安装Docker

# 更新索引
sudo apt update 
 
# 安装Docker依赖
sudo apt install apt-transport-https ca-certificates curl gnupg2 software-properties-common  
 
# 添加Docker的官方GPG密钥(清华源)
curl -fsSL https://mirrors.tuna.tsinghua.edu.cn/docker-ce/linux/ubuntu/gpg | sudo gpg --dearmor -o /usr/share/keyrings/docker-archive-keyring.gpg 
 
# 添加Docker的官方APT仓库
echo "deb [arch=$(dpkg --print-architecture) signed-by=/usr/share/keyrings/docker-archive-keyring.gpg] https://mirrors.tuna.tsinghua.edu.cn/docker-ce/linux/ubuntu $(lsb_release -cs) stable" | sudo tee /etc/apt/sources.list.d/docker.list > /dev/null 
 
# 安装Docker Engine-Community
sudo apt-get update
sudo apt install docker-ce 
 
# 验证是否安装成功
sudo docker --version 
 
# 将当前用户添加到docker组（以便无需sudo运行Docker命令）
sudo groupadd docker
sudo gpasswd -a ${USER} docker
sudo service docker restart
newgrp - docker
 
# 安装 Docker Compose
sudo apt-get install -y docker-compose-plugin
 
# 如果遇到权限问题，尝试:
sudo chmod o+rw /var/run/docker.sock

3、安装Nvidia Container Runtime

# 添加Nidia仓库
curl -fsSL https://nvidia.github.io/libnvidia-container/gpgkey | sudo gpg --dearmor -o /usr/share/keyrings/nvidia-container-toolkit-keyring.gpg \
  && curl -s -L https://nvidia.github.io/libnvidia-container/stable/deb/nvidia-container-toolkit.list | \
    sed 's#deb https://#deb [signed-by=/usr/share/keyrings/nvidia-container-toolkit-keyring.gpg] https://#g' | \
    sudo tee /etc/apt/sources.list.d/nvidia-container-toolkit.list
 
# 更新索引
sudo apt-get update
 
# 安装ToolKit
sudo apt-get install -y nvidia-container-toolkit
 
# 配置Nvidia 容器运行时
sudo nvidia-ctk runtime configure --runtime=docker
 
# 安装完成后重启docker使nvidia生效. 使用下列命令重启docker
sudo systemctl restart docker.service
 
# option: 使用下列命令验证显卡是否docker中可备加载
sudo docker run --rm --runtime=nvidia --gpus all ubuntu nvidia-smi

（最后一步若失败）

sudo tee /etc/docker/daemon.json <<-'EOF'
{
  "runtimes": {
    "nvidia": {
      "path": "nvidia-container-runtime",
      "runtimeArgs": []
    }
  },
  "registry-mirrors": [
    "https://docker.m.daocloud.io",
    "https://mirror.baidubce.com",
    "https://docker.nju.edu.cn"
  ],
  "log-driver": "json-file",
  "log-opts": {
    "max-size": "100m",
    "max-file": "3"
  }
}
EOF

sudo systemctl daemon-reload
sudo systemctl restart docker

sudo docker run --rm --runtime=nvidia --gpus all ubuntu nvidia-smi