Archives


- Beowulf
- Beowulf Announce
- Scyld-users
- Beowulf on Debian

[Beowulf] How to configure a cluster network

Many of your questions may have already been answered in earlier discussions or in the FAQ. The search results page will indicate current discussions as well as past list serves, articles, and papers.

Search

Patrick Geoffray patrick at myri.com
Thu Jul 24 15:51:20 PDT 2008


Hi Jan,

Jan Heichler wrote:
> 1) most applications are latency driven - not bandwidth driven. That 
> means that half bisectional bandwidth is not cutting your application 
> performance down to 50%. For most applications the impact should be less 
> than 5% - for some it is really 0%.

If the app is purely latency driven, bandwidth (link or bisection) is 
indeed irrelevant. However, don't underestimate the impact of contention 
on collective communication: once you exceed the internal buffering in 
the crossbars, you will have back-pressure. Typically, each crossbar 
port can buffer in the order of 1-10K these days. So, the larger the 
message size for the collective and the larger the communicator, the 
greater the need for effective bisection. At this scale (ie 50 nodes), I 
agree it's not that important, unless you are bandwidth bounded to begin 
with.

> 2) Static routing in IB networks limits your bandwidth for many of the 
> possible communication patterns anyway. For completely random 
> communication it was like below 50%. So you buy a IB fabric with full 
> bisectional but can't use it anyway - reducing the bisectional bandwidth 
> is not impacting that much anymore (as far as i understood most whitepapers)

With static routing on Fat Tree or Clos and pseudo-random traffic (ie 
real world), you waste ~50% of the bisection you have (actually, the 
more hops the more waste, but it's not linear). So, if you start with 
half the theoretical bisection, your effective bisection will roughly be 
a quarter of that.

Patrick



More information about the Beowulf mailing list