intel 2.6.0: EXA choppy, UXA has artifacts

[Khashayar Naderehvandi]

Meh, this ain't my day. Forgot to send to list...

On Sat, Jan 17, 2009 at 8:28 PM, Khashayar Naderehvandi
<khashayar.lists at gmail.com> wrote:
>> Strangely, after I restarted my computer, this issue seems to have disappeared.
>> I'll keep an eye on the log, and will post back here if the issue
>> returns and I find anything useful in the logs.
>>
> Sorry for spamming, but the issue returned almost immediately after I
> sent the message stating the issue was gone. It's very much there and
> there's nothing new in the logs.
>
> Regards,
> Khashayar
>



On Sat, Jan 17, 2009 at 8:11 PM, Khashayar Naderehvandi
<khashayar.lists at gmail.com> wrote:
> On Sat, Jan 17, 2009 at 7:21 PM, Ben Gamari <bgamari at gmail.com> wrote:
>> On Sat, 2009-01-17 at 18:48 +0100, Khashayar Naderehvandi wrote:
>>> Hi!
>>>
>>> I'm trying out the newly released intel driver on a X4500 chipset.
>>> The stack is composed of:
>>>
>>> * kernel 2.6.28 with the patches from
>>> http://intellinuxgraphics.org/2008Q4.html applied
>>> * libdrm 2.4.4
>>> * mesa 7.3rc1
>>> * xorg-server 1.5.99.901.
>>> * intel driver 2.6.0
>>>
>>> With EXA compiz becomes unusably choppy and slow. I don't know how to
>>> explain the behavior in a good way, but it's like everything is run
>>> through a stroboscope. Sort of.
>>
>> Does seem that redraws are occurring only when you move the mouse, use
>> the keyboard, or some other interrupt-generating event?
> Not exactly. I also saw this choppy behavior when I dragged a window
> over the screen edge, causing the compiz cube to rotate. The rotation
> was choppy although I was dragging the window.
>
>> Check dmesg for any odd messages.
> I'm gonna do this now, so far the only thing I've seen is
> "exaCopyDirty: Pending damage region empty!"
>
>> A few weeks ago, we were having issues with the GPU's
>> interrupt getting disabled such that the driver wouldn't be notified
>> when the chip was done drawing. This would cause unusably "choppy"
>> behavior.
>>
>> The problem is tricky, but it appears that enabling message signaled
>> interrupts generally works around it, although I think there are a few
>> people who can still reproduce it.
>>
> Strangely, after I restarted my computer, this issue seems to have disappeared.
> I'll keep an eye on the log, and will post back here if the issue
> returns and I find anything useful in the logs.
>
>>
>>> With UXA, on the other hand, everything's smooth and nice, but there
>>> are certain artifacts. Like this:
>>> http://dl.getdropbox.com/u/175461/uxa-artifacts.png.
>>>
>>> Are these issues known? Any workarounds?
>>>
>>> Regards,
>>> Khashayar
>>> _______________________________________________
>>> xorg mailing list
>>> xorg at lists.freedesktop.org
>>> http://lists.freedesktop.org/mailman/listinfo/xorg
>>
>>
>