« Hot Scalability Links For Sep 17, 2010 | Main | How Can the Large Hadron Collider Withstand One Petabyte of Data a Second? »
Thursday
Sep162010

Strategy: Buy New, Don't Fix the Old

This strategy is from the Large Hadron Collider project:
Improvements in performance per Watt have caused CERN to no longer sign hardware support contracts longer than three years. Machines run until they die. They have a very high utilization of equipment (‘duty cycle’, 7 x 24 x 365). Replacing hardware makes more sense because of the lower cost and the power savings of new hardware.

Reader Comments (4)

Do you mean 24h x 7d x 52w or 24h x 365d x 7y ?

But makes sense... they are probably run calcuations even on the desktops.

September 16, 2010 | Unregistered Commenterahm

I think it's 24 hours, 7 days a week. For all 365 days. Doesn't really work out as the equation they wrote it as, but of course they mean the the hardware is utilized constantly, until it dies.

September 16, 2010 | Unregistered Commentercam

It's an interesting idea but there is one catch - sorting out the financials.

Most "maintenance contracts" run at somewhere between 10% and 20% of the purchase price (well, at least the software ones I am used to, not sure about the average for commodity server hardware).

So I can see that it can make sense to say "I won't bother fixing it, just buy a new one, re-image, re-build, whatever".

You can afford to buy "10 or 20% more servers" in effect but only if you can get the money out of the accountants...

Getting a "maintenance contract" signed off is easy - the purchasing and accounting guys are used to these, they can haggle with the vendor, shave a bit of money off etc, make themselves feel good about their miserable existences etc ;-)

So if we skip the maintence contract we now want to park 10-20% of the order value in some type of holding account which Ops can draw down on to replace stuff as it breaks.

Cue fear & loathing in the Finance department as you try and do something new, red tape around who can authorise the release of funds, etc.

I still think its a good idea but just be prepared for some hassles in making it happen. Then again, anything worth doing is probably going to be difficult!

September 20, 2010 | Unregistered CommenterSteve Thair

Steve, sounds like you should say good-bye to corporate hell and join start-up heaven.

September 23, 2010 | Unregistered CommenterJens Begemann

PostPost a New Comment

Enter your information below to add a new comment.
Author Email (optional):
Author URL (optional):
Post:
 
Some HTML allowed: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <code> <em> <i> <strike> <strong>