From: nmm1@cus.cam.ac.uk (Nick Maclaren)
Newsgroups: comp.parallel.pvm,comp.parallel.mpi
Subject: Re: Switching HUB for beowulf cluster?
Date: 28 Jan 1999 11:50:38 GMT
Organization: University of Cambridge, England
Message-Id: <78piue$lrv$1@pegasus.csx.cam.ac.uk>
References: <78osd7$9ji$1@news.kren.nm.kr>
Originator: nmm1@taurus.cus.cam.ac.uk
Xref: ukc comp.parallel.pvm:7939 comp.parallel.mpi:4560


In article <78osd7$9ji$1@news.kren.nm.kr>, Sohn Jung-woo <logout@designer.snu.ac.kr> writes:
|> 
|> Can somebody recommend me any switching hub for a Beowulf cluster?
|> My laboratory plans to build a beowulf cluster with 10 ~ 16 pentium II
|> servers. While shuffling through some documentations on parallel
|> computing, I found that switching hub plays an important role
|> since network latency is the limiting factor for a beowulf cluster.
|> My questions are:
|> 
|> 1. Is there any specific switching hub product recommended for
|> a beowulf cluster? We are considering 3com's 100Mbps 24port switching
|> hub and Intel's 100Mbps 24port switching hub. One of them will
|> be ok?

For a system of that size, using MPI, the hardware letency is
negligible compared with the software latency.  Concentrate on
getting a tuned MPI implementation.

|> 2. How much is the need for 100Mbps bandwidth for a beowulf cluster?
|> Will 10M bps only switching hub be ok for clustering or
|> will 100M bps switching hub lead to better overall performance?

In terms of latency, there is no difference.  In terms of bandwidth,
a lot.  As the extra expense of 100M bps is now small, I advise
going for that.


Regards,
Nick Maclaren,
University of Cambridge Computing Service,
New Museums Site, Pembroke Street, Cambridge CB2 3QG, England.
Email:  nmm1@cam.ac.uk
Tel.:  +44 1223 334761    Fax:  +44 1223 334679