Changes between Initial Version and Version 1 of cypress/GlobusInBarchJob

Timestamp:

04/03/25 16:38:41 (3 days ago)

Author:

fuji

Comment:

—

cypress/GlobusInBarchJob

@@ +1 @@
+= Example Pipeline for Data Transfer Using Globus and Computation in Batch Jobs =
+Here we consider a pipeline to do the following processes.
+1. Transfer data files from Box to the Cypress Lustre directory.
+2. Perform computation using the data.
+3. Transfer the results to Box.
+4. Delete files in Cypress Lustre.
+
+== Scripts ==
+=== Job Submission Script ===
+'''submitJob.sh'''
+{{{
+#
+# Pipeline for Data Transfer Using Globus and Computation
+#
+# Job name
+JOB_NAME="COMPUTING1"
+
+# Set path
+export BOX_DATA_DIR="/Test/"
+export CYPRESS_WORK_DIR="/lustre/project/group/userid/test/"
+export BOX_RESULT_DIR="/Test_result/"
+#
+# Submit a job to transfer data from Box to Cypress
+JOB1=`sbatch --job-name=${JOB_NAME}_DL ./transferData.sh DOWNLOAD KEEP | awk '{print $4}'`;
+echo $JOB1 "Submitted"
+
+# Submit a job to process data on Cypress
+JOB2=`sbatch --job-name=${JOB_NAME} --dependency=afterok:$JOB1 ./computing.sh | awk '{print $4}'`;
+echo $JOB2 "Submitted"
+
+# Submit a job to transfer data from Cypress to Box
+JOB3=`sbatch --job-name=${JOB_NAME}_UL --dependency=afterok:$JOB2 ./transferData.sh UPLOAD DELETE | awk '{print $4}'`;
+echo $JOB3 "Submitted"
+}}}
+'''JOB_NAME''' is the job name.
+
+'''BOX_DATA_DIR''' is the directory in Box where the source data is stored.
+
+'''CYPRESS_WORK_DIR''' is the directory where the downloaded data is stored.
+
+'''BOX_RESULT_DIR''' is the directory where results are uploaded in Box.
+
+=== Data Transfer Script ===
+'''transferData.sh'''
+{{{
+#!/bin/bash
+#SBATCH --partition=centos7
+#SBATCH --qos=long
+#SBATCH --time=7-00:00:00
+#SBATCH --nodes=1
+#SBATCH --ntasks-per-node=1
+#SBATCH --cpus-per-task=1
+
+# Check options
+if [ $# -ne 2 ]; then
+    echo 'Usage: transferData.sh [DOWNLOAD | UPLOAD] [KEEP | DELETE]'
+    exit 1
+fi
+
+# Check path
+if [[ -z "${BOX_DATA_DIR}" ]]; then
+    echo "ERROR!  BOX_DATA_DIR isn't set."
+    exit 1
+fi
+if [[ -z "${CYPRESS_WORK_DIR}" ]]; then
+    echo "ERROR!  CYPRESS_WORK_DIR isn't set."
+    exit 1
+fi
+if [[ -z "${BOX_RESULT_DIR}" ]]; then
+    echo "ERROR!  BOX_RESULT_DIR isn't set."
+    exit 1
+fi
+
+# Start Globus Connect
+module load globusconnectpersonal/3.2.5
+globusconnect -start &
+
+# Set up CLI environment
+source activate globus-cli
+
+# Obtain local UUID
+MY_UUID=$(globus endpoint local-id)
+uuid_code=$?
+if [ $uuid_code -ne 0 ]; then
+    echo "ERROR!  Globus Connect isn't activated."
+    globusconnect -stop
+    exit 1
+fi
+
+# Make the source and destination path
+if [[ "$1" == "DOWNLOAD" ]]; then
+    SOURCE_EP=$TULANE_BOX:$BOX_DATA_DIR
+    DEST_EP=$MY_UUID:$CYPRESS_WORK_DIR
+else
+    SOURCE_EP=$MY_UUID:$CYPRESS_WORK_DIR
+    DEST_EP=$TULANE_BOX:$BOX_DATA_DIR    
+fi
+
+# Check logged in to Globus
+output=$(globus whoami >/dev/null 2>&1)
+output_code=$?
+if [ $output_code -ne 0 ]; then
+    echo "ERROR!  Not logged in to Globus"
+    globusconnect -stop
+    exit 1
+fi
+
+task_id=$(globus transfer "$SOURCE_EP" "$DEST_EP" --label "$SLURM_JOB_NAME" | tail -1 | awk '{print $3}')
+output_code=$?
+if [ $output_code -ne 0 ]; then
+    echo "ERROR!  The transfer of data in could not be started."
+    globusconnect -stop
+    exit 1
+fi
+
+# wait util the task done.
+output=$(globus task wait $task_id)
+output_code=$?
+if [ $output_code -ne 0 ]; then
+    echo "ERROR!  The transfer of data was failed."
+    globus task cancel $task_id
+    globusconnect -stop
+    exit 1
+fi
+
+# Check if the delete option is set
+if [[ "$2" == "DELETE" ]]; then
+    task_id=$(globus rm --recursive $SOURCE_EP |& awk '{print $6}' | sed -e "s/\"//g")
+    globus task wait $task_id
+fi
+
+# done successfully
+source deactivate globus-cli
+globusconnect -stop
+exit 0
+}}}
+
+
+=== Computing Script ===
+'''computing.sh'''
+{{{
+#!/bin/bash
+#SBATCH --partition=defq
+#SBATCH --qos=normal
+#SBATCH --time=1-00:00:00
+#SBATCH --nodes=1
+#SBATCH --ntasks-per-node=1
+#SBATCH --cpus-per-task=20
+
+# cd to working directory
+cd ${CYPRESS_WORK_DIR}
+pwd
+
+# module load ... computing something
+touch RES
+sleep 5
+
+#done
+exit 0
+}}}
+
+
+== How to submit a job ==
+{{{
+sh ./SubmitJob.sh
+}}}