submit_mpi.sh

#!/bin/bash
echo "ip container: $(/sbin/ip -o -4 addr list eth0 | awk '{print $4}' | cut -d/ -f1)"
echo "ip host: $(curl -s "http://169.254.169.254/latest/meta-data/local-ipv4")"

# get shared dir
IFS=',' _shared_dirs=/shared
_shared_dir=${_shared_dirs[0]}
_job_dir="${_shared_dir}/${AWS_BATCH_JOB_ID%#*}-${AWS_BATCH_JOB_ATTEMPT}"
_exit_code_file="${_job_dir}/batch-exit-code"

if [[ "${AWS_BATCH_JOB_NODE_INDEX}" -eq  "${AWS_BATCH_JOB_MAIN_NODE_INDEX}" ]]; then
    echo "Hello I'm the main node $HOSTNAME! I run the mpi job!"

    mkdir -p "${_job_dir}"
    cp mpi_hello_world.c /shared

    echo "Compiling..."
    mpicc -o "${_job_dir}/mpi_hello_world" "${_shared_dir}/mpi_hello_world.c"

    echo "Running..."
    mpirun "${_job_dir}/mpi_hello_world"

    # Write exit status code
    echo "0" > "${_exit_code_file}"
    # Waiting for compute nodes to terminate
    sleep 30
else
    echo "Hello I'm the compute node $HOSTNAME! I let the main node orchestrate the mpi processing!"
    # Since mpi orchestration happens on the main node, we need to make sure the containers representing the compute
    # nodes are not terminated. A simple trick is to wait for a file containing the status code to be created.
    # All compute nodes are terminated by AWS Batch if the main node exits abruptly.
    while [ ! -f "${_exit_code_file}" ]; do
        sleep 2
    done
    exit $(cat "${_exit_code_file}")
fi