[mvapich-discuss] troubles in running MPI job over RoCE, with
mvapich2-1.6 shipped with OFED1.5.3.2
Jonathan Perkins
perkinjo at cse.ohio-state.edu
Thu Feb 21 09:53:46 EST 2013
On Thu, Feb 21, 2013 at 08:05:40PM +0530, Devesh Sharma wrote:
> Hi list,
>
> I am trying to run a simple mpi job over a 2 node cluster with RoCE adapter
> and OFED-1.5.3.2. I am facing following error. Please help
>
> [root at neo01 IMB-3.2]# /usr/mpi/gcc/mvapich2-1.6/bin/mpirun_rsh -ssh -debug
> -np 2 MV2_USE_RoCE-1 MV2_USE_RDMA_CM-1 -hostfile /opt/Work/hostfile
> /usr/mpi/gcc/mvapich2-1.6/tests/IMB-3.2/IMB-MPI1
> execv: No such file or directory
> /usr/bin/xterm -e /usr/bin/ssh -q MV2_USE_RoCE-1 cd
[snip]
Where do you have xterm installed? Is it at /usr/bin/xterm? If not you
can edit the line in src/pm/mpirun_rsh.h that defines XTERM to the
correct path of xterm. You can then run make && make install inside the
src/pm directory to just rebuild mpirun_rsh.
> /usr/mpi/gcc/mvapich2-1.6/bin/mpispawn 0 execv: No such file or directory
> (null) I��H��|5 (null)
> /usr/bin/xterm -e /usr/bin/ssh -q MV2_USE_RDMA_CM-1 cd
I'm not sure where the garbage values are coming from here. Perhaps
fixing the xterm issue will help here to.
--
Jonathan Perkins
http://www.cse.ohio-state.edu/~perkinjo
More information about the mvapich-discuss
mailing list