[android-porting] Re: DispSync and power consumption

2014-05-06 Thread Maksym Kreshchuk
Hi again. I had wrong understanding of DispSync role. After removing define PRESENT_TIME_OFFSET_FROM_VSYNC_NS I got the same CPU time as without display fences. During video playback hardware vsync enables 10-30 times per minute. Is it normal value? Also I am interesting how to calculate values

[android-porting] Re: DispSync and power consumption

2014-05-05 Thread Maksym Kreshchuk
Hi Andy. I've checked power management component. It doesn't changes for a long time and works normal. > Without it, on every hardware VSYNC the system wake up SurfaceFlinger and > wakes up all apps. With it, you still do that, but instead of it all > happening at once it gets distributed.

[android-porting] Re: DispSync and power consumption

2014-05-02 Thread Maksym Kreshchuk
Hi Andy. Thank you for your answer. I understood that I shouldn't disable DispSync. > > > It calls a few trig functions every once in a while. That shouldn't be "a > lot". > It calls: 1. After every hardware vsync - 60 times per second. 2. After every displayed frame - for 30fps video it's 30

[android-porting] DispSync and power consumption

2014-05-01 Thread Maksym Kreshchuk
Hello community. I am porting Android 4.4 to OMAP4 platform. It was discovered that Android 4.4 has bigger power consumption that Android 4.3. After some investigation I found out that DispSync model does a lot of calculation on CPU. For example, in case of videoplayback I got next resul