Add instructions to build a docker for GraphStorm-wholegraph on AWS

docker/build_docker_wholegraph.sh

@@ -0,0 +1,40 @@
+#!/bin/bash
+
+# process argument 1: graphstorm home folder
+if [ -z "$1" ]; then
+    echo "Please provide the graphstorm home folder that the graphstorm codes are cloned to."
+    echo "For example, ./build_docker_oss4local.sh /graph-storm/"
+    exit 1
+else
+    GSF_HOME="$1"
+fi
+
+# process argument 2: docker image name, default is graphstorm
+if [ -z "$2" ]; then
+    IMAGE_NAME="graphstorm-wholegraph"
+else
+    IMAGE_NAME="$2"
+fi
+
+# process argument 3: image's tag name, default is local
+if [ -z "$3" ]; then
+    TAG="local"
+else
+    TAG="$3"
+fi
+
+# Copy scripts and tools codes to the docker folder
+mkdir -p $GSF_HOME"/docker/code"
+cp -r $GSF_HOME"/python" $GSF_HOME"/docker/code/python"
+cp -r $GSF_HOME"/inference_scripts" $GSF_HOME"/docker/code/inference_scripts"
+cp -r $GSF_HOME"/tools" $GSF_HOME"/docker/code/tools"
+cp -r $GSF_HOME"/training_scripts" $GSF_HOME"/docker/code/training_scripts"
+
+# Build OSS docker for EC2 instances that an pull ECR docker images
+DOCKER_FULLNAME="${IMAGE_NAME}:${TAG}"
+
+echo "Build a local docker image ${DOCKER_FULLNAME}"
+docker build --no-cache -f $GSF_HOME"/docker/wholegraph/Dockerfile" . -t $DOCKER_FULLNAME
+
+# remove the temporary code folder
+rm -rf $GSF_HOME"/docker/code"

docker/wholegraph/Dockerfile

@@ -0,0 +1,113 @@
+# Docker file for building a docker image for running GraphStorm code on Amazon SageMaker
+# Note: Distributed graph partition will use another docker image which will come soon.
+
+ARG DEVICE=gpu
+
+FROM 763104351884.dkr.ecr.us-east-1.amazonaws.com/pytorch-training:2.0.1-gpu-py310-cu118-ubuntu20.04-ec2
+ENV dev_type=GPU
+# Install DGL GPU version
+RUN pip3 install dgl==1.0.4+cu117 -f https://data.dgl.ai/wheels/cu117/repo.html && rm -rf /root/.cache
+
+LABEL maintainer="Amazon AI Graph ML team"
+
+# Install related Python packages
+RUN pip3 install ogb==1.3.6 scipy pyarrow boto3 scikit-learn transformers
+
+# Install other dependencies
+RUN apt-get update
+RUN apt-get install -y apt-transport-https
+RUN apt-get install -y cython3 libicu-dev
+RUN pip3 install h5py psutil
+
+RUN apt-get install -y unzip
+
+# Install GraphStorm from source code
+RUN mkdir -p /graphstorm
+COPY code/python/graphstorm /graphstorm/python/graphstorm
+ENV PYTHONPATH="/graphstorm/python/:${PYTHONPATH}"
+
+# Copy GraphStorm scripts and tools
+COPY code/inference_scripts /graphstorm/inference_scripts
+COPY code/tools /graphstorm/tools
+COPY code/training_scripts /graphstorm/training_scripts
+
+RUN ls /usr/local/cuda*
+
+#################################################
+## Install NCCL
+RUN apt-get clean
+RUN apt-get reinstall ca-certificates
+RUN wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/libnccl2_2.15.1-1+cuda11.8_amd64.deb
+RUN dpkg -i libnccl2_2.15.1-1+cuda11.8_amd64.deb
+RUN wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/libnccl-dev_2.15.1-1+cuda11.8_amd64.deb
+RUN dpkg -i libnccl-dev_2.15.1-1+cuda11.8_amd64.deb
+
+#################################################
+## Install EFA installer
+ARG EFA_INSTALLER_VERSION=latest
+RUN cd $HOME \
+    && curl -O https://efa-installer.amazonaws.com/aws-efa-installer-${EFA_INSTALLER_VERSION}.tar.gz \
+    && tar -xf $HOME/aws-efa-installer-${EFA_INSTALLER_VERSION}.tar.gz \
+    && cd aws-efa-installer \
+    && apt-get update \
+    && apt-get install -y libhwloc-dev \
+    && ./efa_installer.sh -y -g -d --skip-kmod --skip-limit-conf --no-verify \
+    && rm -rf /var/lib/apt/lists/*
+
+
+
+RUN wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/3bf863cc.pub
+RUN apt-key add 3bf863cc.pub
+RUN wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/cuda-ubuntu2004.pin
+RUN mv cuda-ubuntu2004.pin /etc/apt/preferences.d/cuda-repository-pin-600
+RUN apt --fix-broken -y install
+RUN apt update
+RUN apt-get install -y software-properties-common
+RUN add-apt-repository "deb http://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/ /"
+RUN apt update
+RUN apt install -y cuda-11-8
+RUN apt install -y cuda-libraries-dev-11-8
+
+###################################################
+## Install AWS-OFI-NCCL plugin
+ARG AWS_OFI_NCCL_VERSION=v1.7.1-aws
+RUN git clone https://github.com/aws/aws-ofi-nccl.git /opt/aws-ofi-nccl \
+    && cd /opt/aws-ofi-nccl \
+    && git checkout ${AWS_OFI_NCCL_VERSION} \
+    && ./autogen.sh \
+    && ./configure --prefix=/opt/aws-ofi-nccl/ \
+       --with-libfabric=/opt/amazon/efa/ \
+       --with-cuda=/usr/local/cuda-11.8/  \
+    && make && make install
+
+ENV PATH "/opt/amazon/efa/bin:$PATH"
+
+# Install WholeGraph
+RUN apt install -y ninja-build
+RUN apt-get remove -y cmake
+RUN wget https://github.com/Kitware/CMake/releases/download/v3.27.6/cmake-3.27.6-linux-x86_64.sh
+RUN mv cmake-3.27.6-linux-x86_64.sh /opt/cmake-3.27.6-linux-x86_64.sh \
+    && cd /opt \
+    && chmod +x cmake-3.27.6-linux-x86_64.sh \
+    && yes | bash cmake-3.27.6-linux-x86_64.sh
+RUN pip3 install cmake==3.27.5
+
+COPY wholegraph/install-wholegraph.sh install-wg.sh
+RUN bash install-wg.sh
+
+# Increase nofile limit
+RUN echo "root                soft    nofile          1048576" >> /etc/security/limits.conf \
+    && echo "root                hard    nofile          1048576" >> /etc/security/limits.conf
+
+# Set up SSH
+RUN apt-get install -y openssh-client openssh-server
+ENV SSH_PORT=2222
+RUN cat /etc/ssh/sshd_config > /tmp/sshd_config && \
+    sed "0,/^#Port 22/s//Port ${SSH_PORT}/" /tmp/sshd_config > /etc/ssh/sshd_config
+ENV SSHDIR $HOME/.ssh
+RUN mkdir -p ${SSHDIR}
+RUN ssh-keygen -t rsa -f ${SSHDIR}/id_rsa -N ''
+RUN cp ${SSHDIR}/id_rsa.pub ${SSHDIR}/authorized_keys
+
+EXPOSE 2222
+CMD ["/usr/sbin/sshd", "-D"]

docker/wholegraph/install-wholegraph.sh

@@ -0,0 +1,31 @@
+#!/bin/bash
+which cmake
+cmake --version
+
+
+git clone https://github.com/fmtlib/fmt.git  /opt/fmt
+cd /opt/fmt
+git checkout 9.1.0
+mkdir build && cd build
+cmake -DCMAKE_POSITION_INDEPENDENT_CODE=TRUE ..
+make
+make install
+
+git clone https://github.com/gabime/spdlog.git  /opt/spdlog
+cd /opt/spdlog && mkdir build && cd build
+cmake .. && make -j
+cp libspdlog.a  /usr/lib/libspdlog.a
+export PYTHON=/usr/bin/python
+
+mkdir /opt/rapids/
+cd  /opt/rapids/
+git clone https://github.com/rapidsai/wholegraph.git -b refactoring
+cd /opt/rapids/wholegraph/
+pip install --upgrade pip
+pip install scikit-build
+export WHOLEGRAPH_CMAKE_CUDA_ARCHITECTURES="70-real;80-real;90"
+# fix a bug in CMakeList.txt when build pylibwholegraph
+old="import sysconfig; print(sysconfig.get_config_var('BINLIBDEST'))"
+string="import sysconfig; print(\"%s/%s\" % (sysconfig.get_config_var(\"LIBDIR\"), sysconfig.get_config_var(\"INSTSONAME\")))"
+sed -i "s|$old|$string|" /opt/rapids/wholegraph/python/pylibwholegraph/CMakeLists.txt
+PYTHON=python3 bash build.sh libwholegraph pylibwholegraph -v