<div dir="ltr"><br><div class="gmail_extra"><br><br><div class="gmail_quote">On Mon, Aug 25, 2014 at 3:22 AM, Jani Nikula <span dir="ltr"><<a href="mailto:jani.nikula@intel.com" target="_blank">jani.nikula@intel.com</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><br>
[just moving from lkml to intel-gfx for a better fitting audience]<br>
<br>
On Mon, 25 Aug 2014, Jani Nikula <<a href="mailto:jani.nikula@intel.com">jani.nikula@intel.com</a>> wrote:<br>
> On Fri, 22 Aug 2014, Eric Rannaud <<a href="mailto:eric.rannaud@gmail.com">eric.rannaud@gmail.com</a>> wrote:<br>
>> Hi,<br>
>><br>
>> Between 3.15.4 and 3.15.8, there was an increase in idle power consumption on<br>
>> Apple Macbook Pro 15 (late 2013) on a freshly booted system (no wifi driver<br>
>> loaded; brightness set to 4/100; X running; no desktop environment, except<br>
>> Awesome), from 6.5W to about 10.5W, as reported by powertop.<br>
>><br>
>> In the stable tree, it bisects to:<br>
>> commit f4db98240ac2c6d9d2118c6f82d483ff5293f1ed<br>
>> Author: Chris Wilson <<a href="mailto:chris@chris-wilson.co.uk">chris@chris-wilson.co.uk</a>><br>
>> Date: Fri Jun 6 10:37:11 2014 +0100<br>
>><br>
>> drm/i915: Disable FBC by default also on Haswell and later<br>
>><br>
>> commit 0368920e51ae0cded0eb518c340a4dd17764d461 upstream.<br>
>><br>
>> It causes black screen on bootup and is approximately 100x<br>
>> slower than<br>
>> running with FBC disabled, so the GPU runs at a high<br>
>> frequency for much<br>
>> longer - completely contrary to the power saving claims.<br>
>> It also still<br>
>> has mutex deadlocks in multi-head scenarios, which can lead to a<br>
>> system/X lockup. These bugs were known before FBC was<br>
>> enabled by default<br>
>> on Haswell and still have not been fixed.<br>
>><br>
>> The issue is still present in Linus' tree (v3.17-rc1-22-g480cadc2b7e0).<br>
>><br>
>> With a 75Wh battery, that's a significant loss in battery life in normal use.<br>
>><br>
>> I'll be happy to help test any potential fix.<br>
><br>
> The earlier regression trumps, and in this case it was enabling FBC by<br>
> default on Haswell. Sorry.<br>
><br>
> You can enable FBC with i915.enable_fbc=1 module parameter, but all bets<br>
> are off. See the commit message you quoted above. I don't recommend.<br>
><br></blockquote></div><br><br></div><div class="gmail_extra">For what it's worth, I have a Mid-2014, Macbook Pro Retina (13inch display), running Archlinux with 3.16. <br><br></div><div class="gmail_extra">Definitely, enable_fbc is a win for me and I do manually enable it. But I am still seeing what I believe to be<br>
</div><div class="gmail_extra">a regression overall of about +4W even with fbc enabled. Still digging for clues.<br><br>Sean<br></div><div class="gmail_extra"><br></div><div class="gmail_extra"><br><br><br clear="all"><br>
-- <br>Sean V. Kelley <<a href="mailto:sean.v.kelley@intel.com" target="_blank">sean.v.kelley@intel.com</a>><br>Open Source Technology Center / SSG<br>Intel Corp.<br>
</div></div>