RLX blades (was Re: [Bioclusters] altivec-HMMER bechmark results from Erik Lindahl - 6x faster than dual Athlon)

James Cuff bioclusters@bioinformatics.org
Thu, 12 Dec 2002 08:24:46 +0000 (GMT)


On Wed, 11 Dec 2002, chris dagdigian wrote:

> Sanger Centre has ~800 RLX blades right now doing pipeline and blast
> work. Anyone from there (James Cuff, etc.?) on this list? I know there
> are RLX people here but it would be nice to hear from the sanger crew as
> to what their experiences have been.

We're good :-)  They might not be the fastest per blade, but I can manage
the whole lot with one FTE.  For me the best part is the ease of
management, and performance when you have many nodes is a given.  The RLX
support people are very, very solid too, which really helps.  Some of
their kernel stuff is pure magic to manage the console redirection...

J.

-- 
Dr. James Cuff
Group Leader - Informatics Systems Group
Wellcome Trust Sanger Institute, Hinxton, Cambridge, CB10 1SA, UK.
Tel: +44 (0) 1223-494880  Fax: +44 (0) 1223-494919