[Beowulf] RE: Capitalization Rates - How often should you replace a cluster? (resent - 1st sending wasn't posted ).

[Joe Landman]

Greg Lindahl wrote:

> To answer Joe's question, I think 365 Main (the one with the big

Yeah... that was it.

> outage) has been full for a while. I'm in a newish colo in Sunnyvale,
> an ex-Global Crossing building. From what my friends tell me, I'm
> paying the market rate.

Good colo isn't cheap.  Its easy to get used to someone else paying for 
your bandwidth/site/power/cooling.

This is IMO one of the great impediments to HPC-in-a-colo.  The 
infrastructure costs basically kill this as a business model, unless you 
own the colo and can amortize your costs across your customers machines. 
  There are a few folks whom are doing this successfully, but I believe 
they either own the colo or have a lower cost than most everyone else 
for some reason.

-- 
Joseph Landman, Ph.D
Founder and CEO
Scalable Informatics LLC,
email: landman at scalableinformatics.com
web  : http://www.scalableinformatics.com
        http://jackrabbit.scalableinformatics.com
phone: +1 734 786 8423 x121
fax  : +1 866 888 3112
cell : +1 734 612 4615