[Mesa-dev] [PATCH 1/3] vl/dri3: use external texture as back buffers

[Andy Furniss]

Nayan Deshmukh wrote:
> On Thu, Oct 27, 2016 at 11:52:13AM +0100, Andy Furniss wrote:
>> Andy Furniss wrote:
>>> Michel Dänzer wrote:
>>>> On 26/10/16 08:07 PM, Andy Furniss wrote:
>>>>>
>>>>> The bad = Starting with DRI3 (which is default) I still get trashed
>>>>> rendering full screen. Windowed including re-sizing seems OK.
>>>>>
>>>>> I use Fluxbox window manager, which does not use compositing -
>>>>> IIRC this has historically shown some ddx DRI2/3 issue that wasn't
>>>>> visible to those testing with compositing (but then the full screen
>>>>> case may avoid compositing anyway depending on settings).
>>>>
>>>> You may be running into a DDX driver issue fixed by
>>>> https://patchwork.freedesktop.org/patch/118514/ .
>>>
>>> Yes, that was it, OK with that patch.
>>
>> Though "OK", sub-optimal loosing pageflip on tonga, as a vsync test
>> fails top 5% of screen unless I force GPU perf high.
>
> This reason for this is that in case of single gpu, I have to recalculate
> its handle and get a pixmap from that buffer for each frame. This calulation
> is avoided due to the presence of a linear buffer in case of different gpu.

OK, possibly I misunderstand your answer, but I don't think any extra
calculation is the issue, it's purely that I loose pageflip. By which
I mean without your patches I can reproduce with R600_DEBUG=notiling.
Powerplay is not giving me enough on auto, but TBH I may not like it
if I had to be permanently higher/hotter to handle just one case.
Maybe the timing/efficiency of display copies is an issue - I don't know.


> Regards,
> Nayan
>>
>> Not related to this patch directly of course, but I am a bit surprised
>> that on auto powerplay the tonga is too slow to make 60Hz.
>>
>> Tested with CPU forced high, so it's not CPU freq.
>>
>>
>