From ca0873840161ed22349dae9e827bb00a7ed14602 Mon Sep 17 00:00:00 2001 From: Felix Kleinert <f.kleinert@fz-juelich.de> Date: Thu, 9 Apr 2020 15:36:03 +0200 Subject: [PATCH] update run script generator and remve old runscript --- create_runscripts_HPC.sh | 49 +++++++++++++++++++--------------------- run_devgpu.bash | 15 ------------ 2 files changed, 23 insertions(+), 41 deletions(-) delete mode 100755 run_devgpu.bash diff --git a/create_runscripts_HPC.sh b/create_runscripts_HPC.sh index 21a60bc0..b2df1a25 100755 --- a/create_runscripts_HPC.sh +++ b/create_runscripts_HPC.sh @@ -5,6 +5,7 @@ echo "# #" echo "# user interaction required #" echo "# #" echo "############################################################" +echo echo "This script creates the HPC batch scripts to run mlt on compute nodes (gpus and develgpus)." echo "You can modify the created run scripts afterwards if needed." @@ -13,62 +14,58 @@ echo "You can modify the created run scripts afterwards if needed." budget='' while [[ $budget == '' ]] do + echo read -p "Enter project budget for --account flag: " budget done email=`jutil user show -o json | grep email | cut -f2 -d':' | cut -f1 -d',' | cut -f2 -d'"'` +echo read -p "Enter e-mail address for --mail-user (default: ${email}): " new_email if [[ -z "$new_email" ]]; then new_email=$email fi -cat <<EOT > run_develgpus.bash -#!/bin/bash -x -#SBATCH --account=${budget} -#SBATCH --nodes=1 -#SBATCH --output=mlt-out.%j -#SBATCH --error=mlt-err.%j -#SBATCH --time=02:00:00 -#SBATCH --partition=develgpus -#SBATCH --gres=gpu:2 -#SBATCH --mail-type=ALL -#SBATCH --mail-user=${email} - -source mlt_modules.sh -source venv/bin/activate +# create HPC_logging dir +hpclogging="HPC_logging/" +mkdir -p $hpclogging -export PYTHONPATH=\${PWD}/venv/lib/python3.6/site-packages:\${PYTHONPATH} -srun python run.py -EOT +# ordering for looping: +# "partition nGPUs timing" -echo "Created runscript: run_develgpus.bash" +for i in "develgpus 2 02:00:00" "gpus 4 08:00:00"; do + set -- $i -cat <<EOT > run_gpus.bash +cat <<EOT > run_$1.bash #!/bin/bash -x #SBATCH --account=${budget} #SBATCH --nodes=1 -#SBATCH --output=mlt-out.%j -#SBATCH --error=mlt-err.%j -#SBATCH --time=16:00:00 -#SBATCH --partition=gpus -#SBATCH --gres=gpu:4 +#SBATCH --output=${hpclogging}mlt-out.%j +#SBATCH --error=${hpclogging}/mlt-err.%j +#SBATCH --time=$3 +#SBATCH --partition=$1 +#SBATCH --gres=gpu:$2 #SBATCH --mail-type=ALL #SBATCH --mail-user=${email} source mlt_modules.sh source venv/bin/activate +timestamp=\`date +"%Y-%m-%d_%H%M-%S"\` + export PYTHONPATH=\${PWD}/venv/lib/python3.6/site-packages:\${PYTHONPATH} -srun python run.py +srun python run.py --experiment_date=\$timestamp EOT -echo "Created runscript: run_gpus.bash" +echo "Created runscript: run_$1.bash" +done +echo echo "You have to run the the following command on a login node to download data:" echo " \`python run.py'" +echo echo "Please execute the following command to check if the setup went well:" echo " \`sbatch run_develgpus.bash'" diff --git a/run_devgpu.bash b/run_devgpu.bash deleted file mode 100755 index 78db1186..00000000 --- a/run_devgpu.bash +++ /dev/null @@ -1,15 +0,0 @@ -#!/bin/bash -x -#SBATCH --account=deepacf -#SBATCH --nodes=1 -#SBATCH --output=mlt-out.%j -#SBATCH --error=mlt-err.%j -#SBATCH --time=02:00:00 -#SBATCH --partition=develgpus -#SBATCH --gres=gpu:2 -#SBATCH --mail-type=ALL -#SBATCH --mail-user=f.kleinert@fz-juelich.de - -source mlt_modules.sh -source venv/bin/activate -export PYTHONPATH=${PWD}/venv/lib/python3.6/site-packages:${PYTHONPATH} -srun python run.py -- GitLab