Job not Exiting

Users/Site Administrators
1

A user is facing always an issue with job exiting, after successful completion of the wall time of a job i.e. 24hrs or 72hrs job is not getting exit and stays on R state, this issue is facing only one particular user. Other jobs are get exited after completion of requested wall time.

Request anyone to give a solution for the above issue to resolve.

2

Please

  1. check his job script of that specific user
  2. check and share tracejob output of this specific user job
  3. check the job information in the compute nodes ( $PBS_HOME/mom_logs/YYYYMMDD)
  4. check the difference in qstat -fx output of this specific user job and other jobs that exited correctly