Tsk lower than as given in the script

My job script looks like this:

#This job should be redirected to small queue
#PBS -N medium19.2
#PBS -l select=292:ncpus=24
#PBS -l walltime=01:00:00
#PBS -l place=scatter
#PBS -l accelerator_type=“None”
#PBS -S /bin/sh@sdb -V
. /opt/modules/default/init/sh
cd /mnt/lustre/ces2/ceskar/19.2
aprun -j 1 -n 7001 -N 24 python parallelization3.py >> log5Jan19.2.txt

Upon submission to the job queue, the tsk is shown to be 700, however I entered the no. of cores to be 7001.
Job ID Username Queue Jobname SessID NDS TSK Memory Time S Time

287614.sdb ceskar medium medium19.2 – 292 700 – 01:00 Q 17:54

What happened here? Is the no of cores requested not the same as tsk? I searched but didn’t find any explanation. The job status is queued and its expected to start later today. I want to use 7001 cores and I specified that, then why is the queue showing 700? Please help.


I’m using Cray XC60 supercomputer if its relevant.

  • Shivani.

Please check and share the output of this command : qstat -fx 287614
The qstat output might be truncating the core count.