The Tests Showing Ubuntu 11.04 On A Power Consumption Binge

Written by Michael Larabel in Operating Systems on 23 April 2011 at 08:18 AM EDT. Page 7 of 7. 19 Comments.

The Atom-powered Samsung NC10 trips up with Ubuntu 11.04 Beta 2 when it comes to the power consumption under a CPU/GPU-intensive workload of OpenGL gaming. Ubuntu Natty's power consumption went up by 18% just from Ubuntu 10.10.

Fortunately, at least, the OpenArena frame-rate performance is the best with Ubuntu 11.04.

When setting out to do this power consumption, the hope was that the power efficency had improved in Ubuntu 11.04 but not to regress so dramatically. For the four systems tested, the power regression was near universal. With the Atom netbook, the Ubuntu 11.04 release wasn't always worse than Ubuntu 10.10, but it was worse under graphics. With the other systems, the regressions occurred regardless of idling or load for the disk, CPU, or GPU. The extent of the mobile testing was limited to the hardware available, but spanned Intel Pentium M, Core Duo, Core 2 Duo, and Atom architectures.

What is the cause of Ubuntu 11.04 being so power hungry? Well, that is a good question. At first thought, it could be the Unity desktop to blame, which is the most visible change from Ubuntu 10.10 to Ubuntu 11.04 Beta. However, with the NVIDIA system where the Nouveau driver is not 3D capable out-of-the-box, the classic GNOME desktop is still used on Natty. Even with the classic non-3D desktop, it still had this power regression.

The actual OpenSSL / PostMark / OpenArena results are in line with what's expected, so it's not that there's some fundamental change in power management where the CPU clock is running in a vastly different state on some Ubuntu releases. It's also likely that Ubuntu 11.04 will also be consuming more power on desktops and servers too, but since my AC power meters have no USB interface or any other way for the Phoronix Test Suite to read the values without manual intervention, there are no results to publish on the desktop / server side.

It has been tracked down to being a mainline kernel regression as noted in that article on Friday. The investigation continues with the actual issue hopefully being determined by Sunday or Monday and an article to follow.

If you enjoyed this article consider joining Phoronix Premium to view this site ad-free, multi-page articles on a single page, and other benefits. PayPal or Stripe tips are also graciously accepted. Thanks for your support.


Related Articles
About The Author
Michael Larabel

Michael Larabel is the principal author of Phoronix.com and founded the site in 2004 with a focus on enriching the Linux hardware experience. Michael has written more than 20,000 articles covering the state of Linux hardware support, Linux performance, graphics drivers, and other topics. Michael is also the lead developer of the Phoronix Test Suite, Phoromatic, and OpenBenchmarking.org automated benchmarking software. He can be followed via Twitter, LinkedIn, or contacted via MichaelLarabel.com.