On Tuesday 25 March 2014 01:00 PM, Chris Wilson wrote:
On Tue, Mar 25, 2014 at 11:29:02AM +0530, Arun R Murthy wrote:
In wait for vblank use usleep_range, which will use hrtimers instead of
msleep. Using msleep(1~20) there are more chances of sleeping for 20ms.
Using usleep_range uses hrtimers and hence are precise, worst case will
trigger an interrupt at the higher/max timeout.
Change-log: On replacing msleep(1) with usleep_range(1000, 2000) we have
noticed the time consumed by wait for vblank is ~4ms to ~17ms.
Change-Id: I6672e5697b01987a6d069ab06e76d97287b1f7ae
Signed-off-by: Arun R Murthy <arun.r.mur...@intel.com>
No. I feel strongly that we do not want more wait_for_X() with strange
semantics.
http://sweng.the-davies.net/Home/rustys-api-design-manifesto
Will revert this additional wait_for_X.
Will update the existing _wait_for as per the kernel documentation for
timers.
Thanks and Regards,
Arun R Murthy
------------------
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
