Might be off topic

Tue May 9 20:03:25 IST 2006

I would certainly look at a blade cluster configuration, with a SAN on the backend, and RedHat GFS as the underlying filesystem.  That one if one
blade fails it can be swapped out easily.  Probably put a pair of Cisco CSS 11503 load balancers in front of it.

UxBoD

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