rancher nividia docker 19.03

nvidia-docker.sh

#!/usr/bin/env bash

# this is the rancher docker installation script with nvidia support
# apply to NVIDIA GPU nodes only

# sources
# https://www.tensorflow.org/install/docker
# https://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html#pre-installation-actions
# https://github.com/NVIDIA/nvidia-docker/wiki/Frequently-Asked-Questions#how-do-i-install-the-nvidia-driver
# https://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html#ubuntu-installation
# https://github.com/NVIDIA/k8s-device-plugin/issues/166


# install docker from default rancher script
function install_docker() {
    curl -L https://releases.rancher.com/install-docker/19.03.sh -o install-docker.sh
    chmod +x install-docker.sh
    ./install-docker.sh
}

# install nvidia docker on top
function install_nvidia() {
    # pre-install
    lspci | grep -i nvidia
    uname -m && cat /etc/*release
    apt-get install -y gcc
    gcc --version
    sudo apt-get install linux-headers-$(uname -r)

    # install cuda
    wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64/cuda-ubuntu1804.pin
    sudo mv cuda-ubuntu1804.pin /etc/apt/preferences.d/cuda-repository-pin-600
    sudo apt-key adv --fetch-keys https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64/7fa2af80.pub
    sudo add-apt-repository "deb http://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64/ /"
    sudo apt-get update
    sudo apt-get -y install cuda

    # install nvidia docker
    # https://github.com/NVIDIA/nvidia-docker/blob/master/README.md#ubuntu-160418042004-debian-jessiestretchbuster
    curl -s -L https://nvidia.github.io/nvidia-docker/gpgkey | \
    sudo apt-key add - distribution=$(. /etc/os-release;echo $ID$VERSION_ID)
    curl -s -L https://nvidia.github.io/nvidia-docker/$distribution/nvidia-docker.list | \
      sudo tee /etc/apt/sources.list.d/nvidia-docker.list
    sudo apt-get update

    # install nvidia device plugin, still required
    # https://github.com/NVIDIA/k8s-device-plugin/issues/166
    # install the old nvidia-container-runtime for k8s
    curl -s -L https://nvidia.github.io/nvidia-container-runtime/gpgkey | \
      sudo apt-key add -
    distribution=$(. /etc/os-release;echo $ID$VERSION_ID)
    curl -s -L https://nvidia.github.io/nvidia-container-runtime/$distribution/nvidia-container-runtime.list | \
      sudo tee /etc/apt/sources.list.d/nvidia-container-runtime.list
    sudo apt-get update
    sudo apt-get update && sudo apt-get install -y nvidia-container-toolkit
    sudo apt-get install -y nvidia-container-runtime

    cat <<EOF > /etc/docker/daemon.json
{
    "default-runtime": "nvidia",
    "runtimes": {
        "nvidia": {
            "path": "/usr/bin/nvidia-container-runtime",
            "runtimeArgs": []
        }
    }
}
EOF
    echo "Restarting docker daemon"
    sudo systemctl restart docker
}

function check_docker_gpu() {
    echo "docker: checking with --gpus all flag"
    docker run --gpus all --rm nvidia/cuda nvidia-smi
    echo "docker: checking without --gpus all flag"
    docker run nvidia/cuda:10.2-runtime-ubuntu18.04 nvidia-smi
}

echo "nvidia-docker: installation starts ***"
install_docker
install_nvidia
check_docker_gpu
echo "nvidia-docker: installation ends ***"