On Feb 15, 2006, at 11:17 AM, BOYRIE Fabrice wrote:
> I've tried to strace lamd, lamboot and mpirun. The problem is I
> don't
> know how to strace the MPI processes.
You should be able to "mpirun C strace a.out ..."
Check out the LAM FAQ in the debugging section. strace isn't an
interactive debugger, but the issues are largely the same.
>> 1. That the names that appear in the file are correct and resolvable
>> on the nodes where MPI processes run
>> 2. That the file itself is readable on the nodes where MPI
>> processes run
>
> rsh gbnode27
> cat /usr/local/lam-7.1.2b31/etc/lam-hostmap.txt
> # Copyright (c) 2001-2003 The Trustees of Indiana University.
> # All rights reserved.
> [...]
> hostname
> node27.alineos.net
>
> cat /etc/hosts
> 127.0.0.1 localhost.localdomain localhost
> 192.168.1.150 master0.alineos.net master0
> 192.168.1.100 node0.alineos.net node0
> 192.168.1.101 node1.alineos.net node1
> 192.168.1.102 node2.alineos.net node2
> [...]
> 192.168.2.150 gbmaster0
> 192.168.2.100 gbnode0
> 192.168.2.101 gbnode1
>
> NB: The command host doesn't work because there isn't any DNS server
> reachable from the hosts.
What does your /etc/resolv.conf say -- is it looking at the /etc/
hosts file, or is it only looking at a DNS server (which doesn't exist)?
--
{+} Jeff Squyres
{+} The Open MPI Project
{+} http://www.open-mpi.org/
|
