109 lines
4.6 KiB
Plaintext
109 lines
4.6 KiB
Plaintext
FROM nvidia/cuda:12.1.1-cudnn8-devel-ubuntu20.04
|
|
ENV DEBIAN_FRONTEND=noninteractive
|
|
|
|
WORKDIR /workspace
|
|
|
|
# Temporary Installation Directory
|
|
ENV STAGE_DIR=/tmp
|
|
RUN mkdir -p ${STAGE_DIR}
|
|
|
|
# Installation/Basic Utilities
|
|
RUN cp /etc/apt/sources.list /etc/apt/sources.list.bak && \
|
|
apt-get update && \
|
|
apt-get install -y --no-install-recommends \
|
|
software-properties-common build-essential autotools-dev \
|
|
nfs-common pdsh \
|
|
cmake g++ gcc \
|
|
curl wget vim tmux emacs less unzip \
|
|
htop iftop iotop ca-certificates openssh-client openssh-server \
|
|
rsync iputils-ping net-tools sudo \
|
|
llvm-dev
|
|
|
|
# Installation Latest Git
|
|
# RUN add-apt-repository ppa:git-core/ppa -y && \
|
|
RUN \
|
|
apt-get update && \
|
|
apt-get install -y git && \
|
|
git --version
|
|
|
|
# Client Liveness & Uncomment Port 22 for SSH Daemon
|
|
# Keep SSH client alive from server side
|
|
RUN echo "ClientAliveInterval 30" >> /etc/ssh/sshd_config
|
|
RUN cp /etc/ssh/sshd_config ${STAGE_DIR}/sshd_config && \
|
|
sed "0,/^#Port 22/s//Port 22/" ${STAGE_DIR}/sshd_config > /etc/ssh/sshd_config
|
|
|
|
# Mellanox OFED
|
|
ENV MLNX_OFED_VERSION=4.9-7.1.0.0
|
|
RUN apt-get install -y libnuma-dev
|
|
RUN cd ${STAGE_DIR} && \
|
|
wget -q -O - http://www.mellanox.com/downloads/ofed/MLNX_OFED-${MLNX_OFED_VERSION}/MLNX_OFED_LINUX-${MLNX_OFED_VERSION}-ubuntu20.04-x86_64.tgz | tar xzf - && \
|
|
cd MLNX_OFED_LINUX-${MLNX_OFED_VERSION}-ubuntu20.04-x86_64 && \
|
|
./mlnxofedinstall --user-space-only --without-fw-update --all -q && \
|
|
cd ${STAGE_DIR} && \
|
|
rm -rf ${STAGE_DIR}/MLNX_OFED_LINUX-${MLNX_OFED_VERSION}-ubuntu20.04-x86_64*
|
|
|
|
# nv_peer_mem
|
|
ENV NV_PEER_MEM_VERSION=1.2
|
|
ENV NV_PEER_MEM_TAG=${NV_PEER_MEM_VERSION}-0
|
|
RUN mkdir -p ${STAGE_DIR} && \
|
|
git clone https://github.com/Mellanox/nv_peer_memory.git --branch ${NV_PEER_MEM_TAG} ${STAGE_DIR}/nv_peer_memory && \
|
|
cd ${STAGE_DIR}/nv_peer_memory && \
|
|
./build_module.sh && \
|
|
cd ${STAGE_DIR} && \
|
|
tar xzf ${STAGE_DIR}/nvidia-peer-memory_${NV_PEER_MEM_VERSION}.orig.tar.gz && \
|
|
cd ${STAGE_DIR}/nvidia-peer-memory-${NV_PEER_MEM_VERSION} && \
|
|
apt-get update && \
|
|
apt-get install -y dkms && \
|
|
dpkg-buildpackage -us -uc && \
|
|
dpkg -i ${STAGE_DIR}/nvidia-peer-memory_${NV_PEER_MEM_TAG}_all.deb
|
|
|
|
# OPENMPI
|
|
ENV OPENMPI_BASEVERSION=4.1
|
|
ENV OPENMPI_VERSION=${OPENMPI_BASEVERSION}.6
|
|
RUN cd ${STAGE_DIR} && \
|
|
wget -q -O - https://download.open-mpi.org/release/open-mpi/v${OPENMPI_BASEVERSION}/openmpi-${OPENMPI_VERSION}.tar.gz | tar xzf - && \
|
|
cd openmpi-${OPENMPI_VERSION} && \
|
|
./configure --prefix=/usr/local/openmpi-${OPENMPI_VERSION} && \
|
|
make -j"$(nproc)" install && \
|
|
ln -s /usr/local/openmpi-${OPENMPI_VERSION} /usr/local/mpi && \
|
|
# Sanity check:
|
|
test -f /usr/local/mpi/bin/mpic++ && \
|
|
cd ${STAGE_DIR} && \
|
|
rm -r ${STAGE_DIR}/openmpi-${OPENMPI_VERSION}
|
|
ENV PATH=/usr/local/mpi/bin:${PATH} \
|
|
LD_LIBRARY_PATH=/usr/local/lib:/usr/local/mpi/lib:/usr/local/mpi/lib64:${LD_LIBRARY_PATH}
|
|
# Create a wrapper for OpenMPI to allow running as root by default
|
|
RUN mv /usr/local/mpi/bin/mpirun /usr/local/mpi/bin/mpirun.real && \
|
|
echo '#!/bin/bash' > /usr/local/mpi/bin/mpirun && \
|
|
echo 'mpirun.real --allow-run-as-root --prefix /usr/local/mpi "$@"' >> /usr/local/mpi/bin/mpirun && \
|
|
chmod a+x /usr/local/mpi/bin/mpirun
|
|
|
|
RUN apt-get update && \
|
|
apt-get install -y --no-install-recommends \
|
|
libsndfile-dev \
|
|
libcupti-dev \
|
|
libjpeg-dev \
|
|
libpng-dev \
|
|
screen \
|
|
libaio-dev
|
|
|
|
RUN wget -qO- https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh -O /${STAGE_DIR}/miniconda.sh && \
|
|
bash /tmp/miniconda.sh -b -p /opt/conda && \
|
|
rm /tmp/miniconda.sh && \
|
|
/opt/conda/bin/conda init bash
|
|
|
|
ENV PATH /opt/conda/bin:$PATH
|
|
COPY environment.yaml /workspace/environment.yaml
|
|
RUN conda env create -n ldh -f /workspace/environment.yaml
|
|
|
|
RUN conda run -n ldh pip config set global.index-url http://mirrors.aliyun.com/pypi/simple && \
|
|
conda run -n ldh pip config set install.trusted-host mirrors.aliyun.com && \
|
|
conda run -n ldh pip install -U pip && \
|
|
echo 'root:root' | chpasswd && \
|
|
sed -i 's/#PermitRootLogin prohibit-password/PermitRootLogin yes/' /etc/ssh/sshd_config && \
|
|
sed -i 's/#PasswordAuthentication yes/PasswordAuthentication yes/' /etc/ssh/sshd_config && \
|
|
rm -rf /usr/lib/python3/dist-packages/yaml && \
|
|
rm -rf /usr/lib/python3/dist-packages/PyYAML-*
|
|
|
|
CMD ["/bin/bash", "-c", "/usr/sbin/sshd -D"]
|