Computational Cluster Programs

Running Multiple Serial Jobs on a Single Node through SGE

In the event you want to request a complete node for your job and you want to run multiple serial jobs on that node at the same time please enter the execution commands in multiple lines inside the same script and send it to background. Last line in your script should contain the command "wait" An example script is given below. You may use this procedure when you are not sure how much memory your jobs are going to use and you don't want your jobs memory consumption to slow down another user's job running on the same node. At the same time you can run multiple jobs as well.

#!/bin/sh
#$ -o sleep.sh.joblog.$JOB_ID
#$ -j y
# request for an 8 core node
#$ -pe shared 8
# job duration is one hour
#$ -l h_data=4096M,h_rt=1:00:00
# Three serial jobs run at the same time
sleep.sh > sleep.sh.ouput 2>&1 &
sleep10.sh > sleep10.sh.ouput 2>&1 &
sleep20.sh > sleep20.sh.ouput 2>&1 &
# wait is important so that SGE waits for all jobs to finish
wait