On Sat, 13 Jun 2015 16:41:18 +0000 Daniele Gregori <[email protected]> wrote:
> [e4user@hactar greg]$ qsub -pe mpi 2 sge.sh > > The problem is that the job doesn’t start, it is alwais in qw state: > > [e4user@hactar greg]$ qstat > job-ID prior name user state submit/start at queue > slots ja-task-ID > ----------------------------------------------------------------------------------------------------------------- > 961 0.60500 mpi_date.s e4user qw 06/12/2015 17:45:09 > 8 > 962 0.50500 sge.sh e4user qw 06/13/2015 18:24:30 > 2 > [e4user@hactar greg]$ > > mpi_date is a similar test job submitted before. > Any hint to start the job? First thing to do is to check why grid engine thinks it can't run (qalter -w v 962 and qalter -w p 962). One possibility is if there are lots of serial jobs in the queue it can't get started because there are never 2 slots free simultaneously. To prevent this you need to configure reservations (max_reservation in the scheduler configuration) and request one(qsub -R y) when submitting the job. William
pgpN2CgpQGriS.pgp
Description: PGP signature
_______________________________________________ users mailing list [email protected] https://gridengine.org/mailman/listinfo/users
