[mvapich-discuss] MVAPICH-0.9.8 lockup with OFED-1.1-rc3

[Andrew Dobbie]

Hi Pavel,

It does appear that the problem was the hosts file.  Thanks for your
quick solution, it is much appreciated.  Would it be possible for future
versions to check for configuration mistakes such as these?

-Andrew

On Wed, 2006-09-13 at 18:10 +0300, Pavel Shamis (Pasha) wrote:
> > The hosts file is identical for all machines except for the 127.0.0.1
> > entry.  Will this cause a problem? 
> > 127.0.0.1       ND01    localhost.localdomain   localhost
> 
> I think the line is the exactly source of the problem.
> It should be:
> 127.0.0.1       localhost.localdomain   localhost
> 
> The hosts file should be:
> 127.0.0.1       localhost.localdomain   localhost
> 192.168.1.80    FLSRVR
> 192.168.8.1     ND01
> 192.168.8.2     ND02
> 192.168.8.3     ND03
> 192.168.8.4     ND04
> 192.168.8.5     ND05
> 192.168.8.6     ND06
> 
> Please copy the file to all nodes and I believe the mpi will run :)
>