Finally, proof positive that PUE is garbage.


Vern Burke, SwiftWater Telecom
Biddeford, ME

I’ve just been reading a piece about Microsoft removing fans from their data center servers and that having a negative effect on their PUE numbers. I’ve written on this blog before about the problems with PUE, now we have proof that it needs to be put out of it’s misery.

In a nutshell, PUE is the ratio of power consumed by the IT equipment of the data center, versus the entire power consumed by the data center. A PUE of 1.0 would indicate a data center where all the power is being consumed by the IT equipment. A PUE greater that 1.0 indicates a data center where a certain amount of power is being consumed by other than IT equipment, the biggest chunk of which is cooling.

The problem I’ve written about before with PUE is the failure to take into account the actual work being accomplished by the IT equipment in the data center. Throw in a pile of extra servers just simply turned on and idling, not doing anything useful, and you’ve just gamed your PUE into looking better.

The problem shown here is even more damning. Microsoft determined that data center energy consumption could be reduced by removing the individual cooling fans from its servers and increasing the size of the data center cooling system. Since the increase in power for the data center cooling systems is less than the power required for the individual server fans, the data center accomplishes the same amount of work for less total energy consumption, an efficiency win in anyone’s book.

The side effect of this is that, even though the total energy consumption for the data center is reduced, transferring the energy usage from the fans (part of the IT equipment number) to the cooling (part of the non-IT equipment number) makes the PUE for the data center look WORSE.

Gaming the metric simply made it inaccurate, which was bad enough. Any efficiency metric that shows a net gain in data center efficiency (same amount of work accomplished for less energy consumed) as a NEGATIVE is hopelessly broken. This also has the side effect of making a mockery of the EPA’s Energy Star for data centers, since that award is based directly on the data center’s PUE.

Misleading, inaccurate, and now totally wrong, this sucker needs to go where all the other bad ideas go to die.

SwiftWater Telecom Green Eco Cabinet Filler Panels, insulated, lightweight, inexpensive

About these ads

8 responses to “Finally, proof positive that PUE is garbage.

  1. Good job on this article. I share your frustration with the “numbers game” people play. We see the same thing with performance ratings for portable air conditioners for server rooms. Going to share this on AirPac’s Facebook page. Thanks.

  2. PUE is but one metric to measure the efficiency of your data-center – just as gross profit margin is but one metric for running a business.
    Between two data centers with identical in all other respects, the one with the lowest PUE will be the most efficient and have the lowest energy bill.
    But comparing two data centers with different IT hardware risks to compare apples to oranges. You can read more here http://intel.ly/hKZzFp and here http://intel.ly/ho0ANw about that.
    So PUE is not so much misleading as it is open to misinterpretation, especially by those who aren’t familiar with the complexity of data centers. And you are right. A low PUE in and of itself does not an efficient data center make.

    • The “PUE shouldn’t be used to compare different data centers” argument went out the window the moment the EPA decided to use PUE as the basis for awarding data center Energy Star status.

      I know that doing the same amount of work for less energy is a “gain” in efficiency. When your “efficiency metric” sees that as a negative, it’s horrendously broken.

      Vern

  3. We have met with most of the Fortune 100 and discussed PUE with hundreds of folks. The prevailing comment we get is, we (the client) have one and track it (which if all PUE does is force people to measure at greater and greater levels of detail makes it a worthwhile metric in my opinion) but we don’t trust anyone else’s.

    I would love for you to take a look at our DCEEF (Data Center Energy Efficiency Framework) which focuses on actionable steps to reduce consumption. Feel free to contact me if you are interested in taking a look at it.
    Thanks,

    Derek Schwartz – dereks@greendca.org

  4. Many datacenter operators are providing facilities for customers, in the case of large-scale co-location providers like DRT, DFT, Equinix, etc. In that ballgame, they don’t have any control or say whatsoever on the IT equipment. So in that case, PUE is a fair comparison.

    In your example, Microsoft operates both the IT Equipment and the Datacenter, so they have a lot more variables and things they can change.

    • Actually, your example is entirely the opposite. If you don’t control the IT equipment in the data center, now you’re not measuring the data center operator’s efficiency but an aggregation of the data center operator and thousands or more of individual tenants who have some unknown level of impact and are quite likely not spread evenly between data centers.

      Regardless of that, the very fact that PUE can be easily gamed (and easily so) makes it an UNFAIR comparison for any data center. You want to truly compare data centers, come up with an honest metric. PUE doesn’t cut it.

      Vern

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s