Open MPI logo

Open MPI User's Mailing List Archives

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

Subject: Re: [OMPI users] very bad parallel scaling of vasp using openmpi
From: Joe Landman (landman_at_[hidden])
Date: 2009-08-18 13:41:20


Craig Plaisance wrote:

> mpich2 now and post the results. So, does anyone know what causes the
> wild oscillations in the throughput at larger message sizes and higher
> network traffic? Thanks!

Your switch can't handle this amount of traffic on its backplane. We
have seen this often in similar situations.

The major differentiation between the costlier switches and the less
expensive switches are a) port to port latency, and b) backplane
bandwidth.

For login traffic and simple command and control, the inexpensive
switches are fine. For MPI across switches, I'd strongly urge you to
consider things like HP Procurve units, some Cisco units, and a few
others. Look for the sustained backplane bandwidth to be close to
N(ports) * duplex bandwidth per port 2Gbps). If the switch vendor isn't
reporting the backplane bandwidth, ask them.

Joe

-- 
Joseph Landman, Ph.D
Founder and CEO
Scalable Informatics Inc.
email: landman_at_[hidden]
web  : http://scalableinformatics.com
        http://scalableinformatics.com/jackrabbit
phone: +1 734 786 8423 x121
fax  : +1 866 888 3112
cell : +1 734 612 4615