Need comments about cluster file systems

Rob Ross rross at mcs.anl.gov
Mon Nov 18 09:17:08 EST 2002


That sort of depends on what you think of as "good" throughput, what
application you are using, and what those 16 I/O nodes look like
hardware-wise.

It's certainly possible for 16 reasonable I/O servers to serve 100+
compute nodes without falling over.

Rob

On Mon, 18 Nov 2002, Philippe Blaise - GRENOBLE wrote:

> 24 compute nodes is a desk cluster :-) ; but the ratio 1.5 compute /
> IO nodes is quite high. What about 100 compute nodes : do you really
> need 60 I/O nodes to achieve a good throughput - or 16 I/O nodeswill
> be still ok ?
> 
>   Philippe
> 
> Kumaran Rajaram wrote:
> 
> >   More information regarding the PVFS performance can be obtained from the
> > site below:
> >
> > http://www.dell.com/us/en/esg/topics/power_ps4q02-kashyap.htm
> >
> >    It is interesting to note the read/write performance to scale well for
> > 16 I/O nodes.
> >
> > -Kums
> >
> > -- Kumaran Rajaram, Mississippi State University --
> > kums at cs.msstate.edu  <http://www.cs.msstate.edu/~kums>
> >
> > On Fri, 15 Nov 2002, Jeff Layton wrote:
> >
> > > Philippe Blaise - GRENOBLE wrote:
> > >
> > > >
> > > >
> > > > Are there some figures about PVFS perfs over SCI and/or Myrinet ?
> > >
> > > Sure (Myrinet):
> > >
> > > http://parlweb.parl.clemson.edu/pvfs/miami2000/miami2000_01.html
> > > http://parlweb.parl.clemson.edu/pvfs/el2000/extreme2000.html
> > >
> > >
> > >
> > > --
> > >
> > > Jeff Layton
> > > Senior Engineer
> > > Lockheed-Martin Aeronautical Company - Marietta
> > > Aerodynamics & CFD
> > >
> > > "Is it possible to overclock a cattle prod?" - Irv Mullins
> > >
> > > This email may contain confidential information. If you have received this
> > > email in error, please delete it immediately, and inform me of the mistake by
> > > return email. Any form of reproduction, or further dissemination of this
> > > email is strictly prohibited. Also, please note that opinions expressed in
> > > this email are those of the author, and are not necessarily those of the
> > > Lockheed-Martin Corporation.
> > >
> > >
> > >
> > > _______________________________________________
> > > Beowulf mailing list, Beowulf at beowulf.org
> > > To change your subscription (digest mode or unsubscribe) visit http://www.beowulf.org/mailman/listinfo/beowulf
> > >
> >
> > _______________________________________________
> > Beowulf mailing list, Beowulf at beowulf.org
> > To change your subscription (digest mode or unsubscribe) visit http://www.beowulf.org/mailman/listinfo/beowulf
> 
> 
> 
> _______________________________________________
> Beowulf mailing list, Beowulf at beowulf.org
> To change your subscription (digest mode or unsubscribe) visit http://www.beowulf.org/mailman/listinfo/beowulf
> 
> 

_______________________________________________
Beowulf mailing list, Beowulf at beowulf.org
To change your subscription (digest mode or unsubscribe) visit http://www.beowulf.org/mailman/listinfo/beowulf



More information about the Beowulf mailing list