After last year discovering a major Linux kernel power regression that was widely debated until the Phoronix test automation software bisected the problem to get to the bottom of the situation, there's more active power regressions today on the Linux desktop. As I've mentioned on Twitter and in other articles in weeks prior there's a few regressions, but one of them for at least some notebooks is causing a very significant increase in power consumption. This situation that remains unresolved as of the Linux 3.7 kernel can cause the system to be going through about 20% more power.
There are a few unresolved Linux kernel power-related regressions I've spotted in the past few weeks that remain active even with the near-final Linux 3.7 kernel. Unfortunately, due to single-handedly writing hundreds of articles per month, doing various benchmark related work and test software development, and still also addressing other work, I haven't had the time to get to the bottom of all these regressions yet. However, as there's been many people emailing and asking about the state of these power problems, here's some more details for those interested. I have also alerted other select parties and stakeholders to the outstanding issues, but once again, there is little external activity until the problem is tossed into the public spotlight.
Since the Linux 3.6 kernel, the power consumption has risen noticeably for some newer Intel hardware configurations. For the problem being illustrated in this article, an Intel Core i5 laptop was used with running Ubuntu 12.10 x86_64. The only change between test runs while monitoring the power consumption rate was swapping the kernel. Other issues will be outlined in additional articles, but this 3.6 issue seems to be the biggest problem with easy ~20% differences in power consumption between kernels. The vanilla Linux 3.4, 3.5, and 3.6 kernels were tested. For the near-final Linux 3.7 kernel, the daily Git snapshot from 8 December 2012 was used. For easy reproducibility, the Ubuntu mainline kernel PPA was used for obtaining these four kernels. The Phoronix Test Suite measured the battery power consumption during testing in a variety of workloads.