40C (104F) in the Data Center

From Data Center Knowledge yesterday: Rackable Turns up the Heat, we see the beginnings of the next class of server innovations. This one is going to be important and have lasting impact. The industry will save millions of dollars and megawatts of power ignoring the capital expense reductions possible. Hat’s off to Rackable Systems to being the first to deliver. Yesterday they announced the CloudRack C2. CloudRack is very similar to the MicroSlice offering I mentioned in the Microslice Servers posting. These are very low cost, high efficiency and high density, server offerings targeting high scale services.

What makes the CloudRack C2 particularly notable is they have raised the standard operating temperature range to a full 40C (104F). Data center mechanical systems consume roughly 1/3 of all power brought into the data center:

Data center power consumption:

IT load (servers): 1/1.7=> 59%

Distribution Losses: 8%

Mechanical load(cooling): 33%

From: Where Does the Power Go?

The best way to make cooling more efficient is to stop doing so much of it. I’ve been asking all server producers including Rackable to commit to full warrantee coverage for servers operating with 35C (95F) inlet temperatures. Some think I’m nuts but a few innovators like Rackable and Dell fully understand the savings possible. Higher data center temperatures conserve energy and reduce costs. It’s good for the industry and good for the environment.

To fully realize these industry-wide savings we need all data center IT equipment certified for high temperature operations particularily top of rack and aggregation switches.


James Hamilton, Amazon Web Services

1200, 12th Ave. S., Seattle, WA, 98144
W:+1(425)703-9972 | C:+1(206)910-4692 | H:+1(206)201-1859 |

H:mvdirona.com | W:mvdirona.com/jrh/work | blog:http://perspectives.mvdirona.com

6 comments on “40C (104F) in the Data Center
  1. hairiy says:

    hai….Andrew,u are the best… :-)

  2. Woops Service free Systems URL missing from comment above: //perspectives.mvdirona.com/2008/03/13/ServiceFreeSystems.aspx


  3. Good hearing from you Jeff. Arguably I’m a bit "out there" on this one but my goal is reduce the time humans spend in data centers while they are operating to near zero. I love the fail in place model where a module or pod is run until it needs service, then taken down, and bulk serviced or recycled. See Service Free Systems.

    Less radical approaches have people in to switch servers or failed switch gear with repairs done on bench. The less time people spend in data centers, the happier they will be and remember where “human error” comes from. The data center should be hot, dark, and unpleasant.

  4. Jeff Barr says:

    Don’t we have to certify the humans working in the data centers for high temperature operation as well? Perhaps there will be a rise in demand for data center personnel from equatorial countries!

  5. Great hearing from you Andrew. I know you have long been committed to ferreting out high scale data center efficiencies. In my view, pushing the environmental limits represent our single largest opportunity right now.


  6. certainly a "hot topic" indeed :)

Leave a Reply

Your email address will not be published. Required fields are marked *

This site uses Akismet to reduce spam. Learn how your comment data is processed.