Datacenter Power Efficiency
perspectives.mvdirona.com
perspectives.mvdirona.com
It's interesting that in contrast to the likes of Google and HP who have been stating that the cost of power will soon be greater than the cost of servers — e.g. http://bits.blogs.nytimes.com/2008/11/03/kill-an-energy-hog-... Microsoft seem to be having a very different experience with servers making up 61% of the TCO and power consumption and distribution/cooling only taking up 16% and 14% respectively.
It's also interesting that they haven't (seemingly) adopted the Google strategy of shifting workloads from data centers based on the external weather conditions, e.g. http://www.datacenterknowledge.com/archives/2009/07/15/googl... — This sounded like an ingenious idea when I first heard about it and am surprised that everyone didn't copy it straight away.
http://www.youtube.com/watch?v=kHW-ayt_Urk
The numbers on the slides modify the assumptions on the spreadsheet at http://perspectives.mvdirona.com/2010/09/18/OverallDataCente...
Now, some people say 3 years, but some people say five or longer. The IRS says 5.
Personally, I also figure a 3 year life on servers, which puts my data center (power) costs at about the same as my hardware costs... but I probably pay a /whole lot/ more for data center space than Microsoft, as I buy that 'retail' and I imagine the difference in what we pay for hardware is rather smaller, as I self-assemble (at their scale, it's likely they are paying less for hardware than I am, too... but my operation is fairly efficient when it comes to hardware, and not very efficient at all when it comes to power.) so I can see how for someone who runs their own modern, efficient data center, and who replaces hardware every three years, hardware costs could dominate.