Re: [OMPI users] I got "ssh_exchange_identification" errors when I mpirun over 1500 times almost at the same time

2013-06-03 Thread vacate
Dear Sabuj Pattanayek, After your reply, I try to disable my /etc/hosts.deny, but unfortunately, It didn't work still But I finally solve my problem, The reason is my "soft nofile" and "hard nofile" values aren't set large enough, so I can't open too much file like that Still thanks for your rep

Re: [OMPI users] I got "ssh_exchange_identification" errors when I mpirun over 1500 times almost at the same time

2013-06-03 Thread vacate
Dear Ralph Castain, Thank you for you reply!!! Actually, I have adjusted my /etc/security/limits.conf file, I modified the "soft nofile" and "hard nofile" values up to 65535, so these days I tried another possible limits settings another settings include "soft memlock" ,"hard memlock", and /proc/

Re: [OMPI users] Open MPI Checkpoint Restart

2013-06-03 Thread Neel Sunil Desai
Hi Ralph. I checked the errors. I do not understand what the fololowing means : The session directory location could not be parsed. ompi-checkpoint attempted to use the session directory: /tmp/openmpi-sessions-ndesai@vcainternmpi01_0 I opened the /tmp/openmpi-sessions-ndesai direct

Re: [OMPI users] 1.7.1 Hang with MPI_THREAD_MULTIPLE set

2013-06-03 Thread Paul Kapinos
Hello, It is more or less well-known that MPI_THREAD_MULTIPLE disable the OpenFabric / InfiniBand networking in Open MPI: http://www.open-mpi.org/faq/?category=supported-systems#thread-support http://www.open-mpi.org/community/lists/users/2010/03/12345.php On our system not only the 'openib'