[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 13:09:36 EDT 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



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

-- 
This message has been scanned for viruses and
dangerous content by MailScanner, and is
believed to be clean.



More information about the Beowulf mailing list