[mpich-discuss] Possible setup problem

[Andy_Holland at URSCorp.com]

I'm trying to run the CMAQ air quality model (http://cmaq-model.org) using 
MPICH.  Many people have done this successfully, but I'm having some 
trouble that I believe is due to the way my system is setup.  We have two 
8 CPU HPs running RedHat Linux Enterprise 5.  These two machine each have 
data storage available to them and each machine can access the others data 
storage area.  I have installed MPICH on both machines.  I'm trying to run 
the model from one machine using all the CPUs on that machine and the CPUs 
on the other machine using a MACHINEFILE.  I'm running the model from the 
shared data space so that no matter which machine I run the model from, it 
is in the same directory.  When I run from either machine using CPUs from 
both machines the run stops with many mpi messages.  Below is the last 
message in the list:

main (/usr/local/mpich2-1.3.2p1/src/pm/hydra/ui/mpich/mpiexec.c:404): 
process manager error waiting for completion

If I run on either machine using the CPUs for that same machine the run 
completes with no errors.  If I run on either machine using only CPUs from 
the other machine, the run completes with no errors.

Does anybody know what might be wrong?  I really need to be able to run 
using all the CPUs from both machines.

Thank you,

Andy Holland
Air Quality Modeler
URS Corporation
1600 Perimeter Park Drive
Suite 400
Morrisville, NC 27560
Direct: (303) 796-4694
Cell: (919) 619-4218
Fax: (919) 461-1415
andy_holland at urscorp.com


This e-mail and any attachments contain URS Corporation confidential 
information that may be proprietary or privileged. If you receive this 
message in error or are not the intended recipient, you should not retain, 
distribute, disclose or use any of this information and you should destroy 
the e-mail and any attachments or copies.


-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mcs.anl.gov/pipermail/mpich-discuss/attachments/20110425/c500aa40/attachment.htm>