What can Governor Adjustments do for your Battery Mileage?

After my previous post about Android saving power with Linux governor tweaking, I did some governor tweak testing on my netbook with a tweaked phoronix test suide (pts) and came up with these results:

The first two show the power usage in Watts, the third shows the frequencies used during the test.

The last two tests definitely seem off. I don't know why this happened but their numbers are certainly not to be relied upon, as you can see especially in the first and last graph - they stop way too early. But maybe ondemand with up 99 and powersave bias of 100 really is the ideal solution?

But I do think it's pretty reliable that the tuned ondemand (up 98, powersave bias 50) and conservative tuned (up 98, down 95, step 20) have very good results. And I mean 3.3 % difference in average power consumption just with a different scheduler is something to have or not to have.

I first idled for 15 seconds, then with mplayer played 15 seconds 720p video with xv, no sound, then with vaapi, no sound. Then I idled another 15 seconds with display off. What pts does during the test is determined only by this file: ~/.phoronix-test-suite/installed-tests/battery-power-usage/battery-power-usage.

Just check out the scripts I posted in my other entry, they should work out of the box. And then run the phoronix battery test with different options. Make sure to post your results! :)

If you liked this article, you might want to subscribe for more.

No comments:

Post a Comment

I appreciate comments. Feel free to write anything you wish. Selected comments and questions will be published.