[Intel-gfx] Fwd: 2.6.36-rc5 i915 regression

[Chris Wilson]

On Tue, 26 Oct 2010 10:49:01 +0200, Seblu <seblu at seblu.net> wrote:
> On Tue, Oct 26, 2010 at 10:30 AM, Chris Wilson <chris at chris-wilson.co.uk> wrote:
> > Depending on where the tip was, at least one suspend regression was
> > recently fixed. It would be useful to recheck with 64193406.
> Yes i have this patch in, and the issue is still here.

Oh 6410. Yeah, that regression was pre-g4x. Do you have a good idea of the
precise range in which the regression was introduced, or is just another
eDP misery?
 
> Do you have seen this vmideo, which show the suspend to ram issue with
> ailine and drm-next and how it's functional with 2.6.35.7?
> 
> http://videobin.org/+2a5/2kp.ogg
> 
> >
> >> - after one day, applications become graphically slow.
> >
> > You're not alone. Eric has reported that writes to a GTT mapping become
> > glacially slow after some time, without any distortion in the CPU profile.
> > Can we collate what hardware we are seeing this effect on?
> lspci,lshw,cpuinfo, you did somthing more?

Just the chipset [Arrandale, in this case] for the time being, so I know
which machines to leave running to see if I can observe the effect here.
-Chris

-- 
Chris Wilson, Intel Open Source Technology Centre