If you were hoping that the Linux 3.1 kernel would fix the big power regression problem that's caused by PCI Express Active State Power Management (ASPM) being disabled on more systems since the release of the Linux 2.6.38 kernel, you're not in luck. There has not been any active work in this area. Making things worse though for mobile Linux users interested in a long lasting battery is another new regression in the Linux 3.1 kernel. Affected systems can easily see a 30% increase in power consumption simply when comparing the Linux 3.0 kernel to the current code being assembled for Linux 3.1. For an Intel Sandy Bridge notebook, the power consumption is up by 76% just over the course of this year from Linux kernel regressions.
Besides the new Linux 3.1 kernel power regression, there's also a power regression introduced in the Linux 3.0 kernel that has previously not been talked about on Phoronix. The Linux 3.0 power draw is up by 24% over the Linux 2.6.39 kernel. With all of these regressions, going from the Linux 2.6.38 to 3.1 kernel on an Intel Sandy Bridge notebook increases the power consumption by 76% under Ubuntu Linux and a dramatically shorter battery life.
The notebook where this regression was spotted has an Intel Core i5 2520M quad-core Sandy Bridge CPU, Intel HD 3000 integrated graphics, 4GB of RAM, and 160GB Intel X-25 Extreme SSD. On the software side was the x86_64 Ubuntu 11.10 development snapshot as of 21 August with Unity 4.8.2, X.Org Server 1.10.3 RC2, xf86-video-intel 2.15.901, GCC 4.6.1, and an EXT4 file-system. The Linux 2.6.38, 2.6.39, 3.0, and 3.1 kernels were obtained from the Ubuntu mainline kernel repository. The Linux 3.1 kernel was a daily snapshot as of 21 August with a post-rc2 kernel.
The Phoronix Test Suite was used for benchmarking the system on each kernel release in an automated manner, complete with battery polling.
The Linux 2.6.38 kernel had an average power consumption of 13.2 Watts, Linux 2.6.39 was at 13.9 Watts, Linux 3.0 up to 17.3 Watts, and the Linux 3.1 kernel Git is now at 22.8 Watts. These are rather depressing numbers especially as the very latest kernel needs to be used if wishing to maximize the performance of the integrated Intel Sandy Bridge graphics. Here are the results on OpenBenchmarking.org.