[mvapich-discuss] mvapich2 and RDMA CM Address error

[Dhabaleswar Panda]

> > Hi Bryan,
> >
> > I believe you are still using the MPD/mpiexec environment. We are going
> > away from that environment because it is not scalable. Please start using
> > the new mpirun-rsh-based framwork which provides fast and scalable job
> > startup. Let us know if you see any issues when using the mpirun-rsh-based
> > framework.
>
> Hi DK,
>
> Actually, I'm not using MPD/mpiexec, but am using mpiexec.hydra from the
> mpich2 distribution. The mpirun_rsh (from mvapich2) does not work on our
> Chelsio cluster. I had reported the mpirun_rsh problem earlier, but I'll
> go ahead and send that in again.

We have not tested mpiexec.hydra. Let us know what issues you are facing
with the mpirun_rsh framework on your Chelsio cluster. We use this in our
Chelsio set-up here without any problem.

Thanks,

DK

> Thanks,
> Bryan
>
> >
> > Thanks,
> >
> > DK
> >
> >
> > On Wed, 4 Nov 2009, Bryan Putnam wrote:
> >
> > > We've been seeing with both mvapich2-1.4rc2 and mvapich2-1.4 the following
> > > error when attempting to use a large number of processors, for example
> > > 256 processors; 8 processors on each of 32 nodes.
> > >
> > > coates-a029 1005% mpiexec -np 256 ./helloc
> > > Hello from process 0!
> > > Hello from process 1!
> > > Hello from process 2!
> > > Hello from process 3!
> > > Hello from process 4!
> > > Hello from process 5!
> > > Hello from process 6!
> > > Hello from process 7!
> > > Hello from process 8!
> > > Hello from process 9!
> > > Hello from process 10!
> > > Hello from process 11!
> > > Hello from process 12!
> > > [247] Abort: RDMA CM Address error: rdma cma event 1, error -110
> > >  at line 341 in file rdma_cm.c
> > >
> > >
> > > I just wanted to check and see if this was a know problem with a solution.
> > >
> > > Thanks!
> > > Bryan
> > > _______________________________________________
> > > mvapich-discuss mailing list
> > > mvapich-discuss at cse.ohio-state.edu
> > > http://mail.cse.ohio-state.edu/mailman/listinfo/mvapich-discuss
> > >
> >
> >
>
>