Open MPI logo

Open MPI User's Mailing List Archives

  |   Home   |   Support   |   FAQ   |   all Open MPI User's mailing list

Subject: Re: [OMPI users] More newbie question: --hostfile option
From: Tena Sakai (tsakai_at_[hidden])
Date: 2011-01-12 22:22:48


Thank you, David. That did it!

Tena Sakai
tsakai_at_[hidden]

On 1/12/11 6:40 PM, "David Zhang" <solarbikedz_at_[hidden]> wrote:

I think you just make a hostfile with

vixen
compute-0-0
...

and load the file in the first -H before the colon.

On Wed, Jan 12, 2011 at 6:23 PM, Tena Sakai <tsakai_at_[hidden]> wrote:
Hi,

I can execute the command below:
   $ mpirun -H vixen -np 1 hostname : -H compute-0-0,compute-0-1,compute-0-2 -np 3 hostname
and I get:
   vixen.egcrc.org <http://vixen.egcrc.org>
   compute-0-0.local
   compute-0-1.local
   compute-0-2.local

I have a file myhosts, which looks like:
   compute-0-0 slots=1
   compute-0-1 slots=1
   compute-0-2 slots=1
but when I execute:
   $ mpirun -H vixen -np 1 hostname : --hostfile myhosts -np 3 hostname
I get:
   There are no allocated resources for the application
     hostname
   that match the requested mapping:

   Verify that you have mapped the allocated resources properly using the
   --host or --hostfile specification.
   --------------------------------------------------------------------------
   --------------------------------------------------------------------------
   A daemon (pid unknown) died unexpectedly on signal 1 while attempting to
   launch so we are aborting.

   There may be more information reported by the environment (see above).

   This may be because the daemon was unable to find all the needed shared
   libraries on the remote node. You may set your LD_LIBRARY_PATH to have the
   location of the shared libraries on the remote nodes and this will
   automatically be forwarded to the remote nodes.
   --------------------------------------------------------------------------
   --------------------------------------------------------------------------
   mpirun noticed that the job aborted, but has no info as to the process
   that caused that situation.
   --------------------------------------------------------------------------
   mpirun: clean termination accomplished

Interestingly, this works:
   $ mpirun --hostfile myhosts -np 3 hostname
   compute-0-0.local
   compute-0-1.local
   compute-0-2.local
   $

Am I correct in concluding that –H and —hostfile cannot be issued in the
same mpirun command which contains a colon (:)? Or is there any trick
or work-around to have both –H and —hostfile?

Thank you.

Tena Sakai
tsakai_at_[hidden] <http://tsakai@gallo.ucsf.edu>

_______________________________________________
users mailing list
users_at_[hidden]
http://www.open-mpi.org/mailman/listinfo.cgi/users