#!/bin/bash
# 空白机器安装 Docker 28.0.1。数据放在 /usr/cluster，默认运行时用 nvidia。
# 不要在已经跑着业务的 prod102 上执行。
set -eu
export DEBIAN_FRONTEND=noninteractive

if [ "$(hostname)" = "prod102" ] && [ -S /var/run/docker.sock ]; then
  echo "prod102 上 Docker 已经在跑。这份脚本是给空机器的，停在这里。"
  exit 1
fi

install -m 0755 -d /etc/apt/keyrings
curl -fsSL https://download.docker.com/linux/ubuntu/gpg \
  | gpg --dearmor --yes -o /etc/apt/keyrings/docker.gpg
echo "deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/docker.gpg] https://download.docker.com/linux/ubuntu jammy stable" \
  > /etc/apt/sources.list.d/docker.list
apt-get update
ver=$(apt-cache madison docker-ce | awk '/28.0.1/{print $3; exit}')
if [ -z "$ver" ]; then
  echo "apt 里没有 docker-ce 28.0.1"
  exit 1
fi
apt-get install -y "docker-ce=$ver" "docker-ce-cli=$ver" containerd.io

mkdir -p /usr/cluster/docker /etc/docker
cat > /etc/docker/daemon.json << 'EOF'
{
  "data-root": "/usr/cluster/docker",
  "exec-opts": ["native.cgroupdriver=systemd"],
  "default-runtime": "nvidia",
  "runtimes": {
    "nvidia": {
      "path": "nvidia-container-runtime"
    }
  },
  "registry-mirrors": [
    "https://docker.1ms.run",
    "https://docker.xuanyuan.me",
    "https://docker.m.daocloud.io",
    "https://hub-mirror.c.163.com"
  ]
}
EOF
systemctl enable docker
systemctl restart docker
docker info --format 'root={{.DockerRootDir}} cgroup={{.CgroupDriver}} runtime={{.DefaultRuntime}}'
echo DOCKER_OK