[gmx-users] Gromacs 4.6 crushes in PBS queue system

[Alexey Shvetsov]

Hi!

В письме от 16 февраля 2013 23:27:45 пользователь Tomek Wlodarski написал:
> Hi!
> 
> I have problem in running gromacs 4.6 in PBS queue...
> I end up with error:
> 
> 
> [n370:03036] [[19430,0],0]-[[19430,1],8] mca_oob_tcp_msg_recv: readv
> failed: Connection reset by peer (104)
> --------------------------------------------------------------------------
> mpirun noticed that process rank 18 with PID 616 on node n344 exited on
> signal 4 (Illegal instruction).

Aha. Your mdrun process got SIGILL. This means that your nodes have different 
instruction set then head node. So try to use different acceleration level. 
Can you share details about your hw?

> --------------------------------------------------------------------------
> [n370:03036] 3 more processes have sent help message
> help-opal-shmem-mmap.txt / mmap on nfs
> [n370:03036] Set MCA parameter "orte_base_help_aggregate" to 0 to see all
> help / error messages
> 3 total processes killed (some possibly by mpirun during cleanup)
> 
> I run the same pbs files with older gromacs 4.5.5 (installed with the same
> openmpi, gcc and fftw) and everything is working..
> 
> also when I am running gromacs directly on the access node:
> 
> mpirun -np 32 /home/users/didymos/gromacs/bin/mdrun_mpi -v -deffnm
> protein-EM-solvated -c protein-EM-solvated.gro
> 
> it is running OK.
> Any ideas?
> Thank you!
> Best!
> 
> tomek
-- 
Best Regards,
Alexey 'Alexxy' Shvetsov
Petersburg Nuclear Physics Institute, NRC Kurchatov Institute, 
Gatchina, Russia
Department of Molecular and Radiation Biophysics
Gentoo Team Ru
Gentoo Linux Dev
mailto:alexxyum at gmail.com
mailto:alexxy at gentoo.org
mailto:alexxy at omrb.pnpi.spb.ru
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 836 bytes
Desc: This is a digitally signed message part.
URL: <http://maillist.sys.kth.se/pipermail/gromacs.org_gmx-users/attachments/20130217/675574d4/attachment.sig>