[Beowulf] Repeated Dell SC1435 crash / hang. How to get the vendor to resolve the issue when 20% of the servers fail in first year?
Sellers, William A. (LARC-D205)[NCI INFORMATION SYSTEMS]
w.a.sellers at nasa.gov
Wed Apr 8 10:09:36 PDT 2009
-----Original Message-----
From: Skylar Thompson [mailto:skylar at cs.earlham.edu]
Sent: Wednesday, April 08, 2009 12:51 PM
To: Sellers, William A. (LARC-D205)[NCI INFORMATION SYSTEMS]
Cc: Beowulf Mailing List
Subject: Re: [Beowulf] Repeated Dell SC1435 crash / hang. How to get the
vendor to resolve the issue when 20% of the servers fail in first year?
Sellers, William A. (LARC-D205)[NCI INFORMATION SYSTEMS] wrote:
> To be perfectly fair to Dell, I have a rack of SC1435 and they are
> working perfectly under CentOS 5.2. Too bad I can't buy more. I'm
> having to strip down Dell 1950's to add a new rack of nodes, which
> costs significantly more. My gripe is that Dell has put the 1435 on
> end-of-sale, with the 1950 soon to follow, and no suitable replacement
> (from what I've seen & heard) for a diskless, dual CPU, 1 U footprint
> node available for sale for HPC use.
>
Have you tried the R200? We've only been using it for low-end web server
stuff so far (we still have our 1435 and 1950 based clusters) but it
seems like it's an upgrade of a 1435.
The R200 is a single CPU system. I just looked at the Dell site, and I
think the R610 might work.
Thanks,
Bill
More information about the Beowulf
mailing list