* Performance regression, please revert commit 441ef916ae6569c88b3d6abaf7fea4d69be49d76
@ 2013-01-13 10:09 Knut Petersen
2013-01-13 10:23 ` Chris Wilson
0 siblings, 1 reply; 5+ messages in thread
From: Knut Petersen @ 2013-01-13 10:09 UTC (permalink / raw)
To: Chris Wilson; +Cc: intel-gfx
There is a massive performance regression on i915GM hardware,
opening/closing/redrawing looks as if it is done in slow motion.
I bisected the problem to:
commit 441ef916ae6569c88b3d6abaf7fea4d69be49d76
Author: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu Jan 10 19:14:21 2013 +0000
intel: Throttle harder
Filling the rings is a very unpleasant user experience, so cap the
number of batches we allow to be inflight at any one time.
Interestingly, as also found with SNA, throttling can improve
performance by reducing RSS. However, typically throughput is improved
(at the expense of latency) by oversubscribing work to the GPU and a
10-20% slowdown is commonplace for cairo-traces. Notably, x11perf is
less affected and in particular application level benchmarks show no
change.
Note that this exposes another bug in libdrm-intel 2.4.40 on gen2/3.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Please revert 441ef (or limit the new code to hardware that benefits from it)
cu,
Knut
^ permalink raw reply [flat|nested] 5+ messages in thread
* Re: Performance regression, please revert commit 441ef916ae6569c88b3d6abaf7fea4d69be49d76
2013-01-13 10:09 Performance regression, please revert commit 441ef916ae6569c88b3d6abaf7fea4d69be49d76 Knut Petersen
@ 2013-01-13 10:23 ` Chris Wilson
2013-01-13 10:35 ` Knut Petersen
0 siblings, 1 reply; 5+ messages in thread
From: Chris Wilson @ 2013-01-13 10:23 UTC (permalink / raw)
To: Knut Petersen; +Cc: intel-gfx
On Sun, 13 Jan 2013 11:09:38 +0100, Knut Petersen <Knut_Petersen@t-online.de> wrote:
> There is a massive performance regression on i915GM hardware,
> opening/closing/redrawing looks as if it is done in slow motion.
gen2/3 benefits from it after applying the bugfix to libdrm.
-Chris
--
Chris Wilson, Intel Open Source Technology Centre
^ permalink raw reply [flat|nested] 5+ messages in thread
* Re: Performance regression, please revert commit 441ef916ae6569c88b3d6abaf7fea4d69be49d76
2013-01-13 10:23 ` Chris Wilson
@ 2013-01-13 10:35 ` Knut Petersen
2013-01-13 10:50 ` Chris Wilson
0 siblings, 1 reply; 5+ messages in thread
From: Knut Petersen @ 2013-01-13 10:35 UTC (permalink / raw)
To: Chris Wilson; +Cc: intel-gfx
On 13.01.2013 11:23, Chris Wilson wrote:
> On Sun, 13 Jan 2013 11:09:38 +0100, Knut Petersen <Knut_Petersen@t-online.de> wrote:
>> There is a massive performance regression on i915GM hardware,
>> opening/closing/redrawing looks as if it is done in slow motion.
> gen2/3 benefits from it after applying the bugfix to libdrm.
> -Chris
>
Which bugfix?
cu,
Knut
^ permalink raw reply [flat|nested] 5+ messages in thread
* Re: Performance regression, please revert commit 441ef916ae6569c88b3d6abaf7fea4d69be49d76
2013-01-13 10:35 ` Knut Petersen
@ 2013-01-13 10:50 ` Chris Wilson
2013-01-13 16:42 ` Knut Petersen
0 siblings, 1 reply; 5+ messages in thread
From: Chris Wilson @ 2013-01-13 10:50 UTC (permalink / raw)
To: Knut Petersen; +Cc: intel-gfx
On Sun, 13 Jan 2013 11:35:51 +0100, Knut Petersen <Knut_Petersen@t-online.de> wrote:
> On 13.01.2013 11:23, Chris Wilson wrote:
> > On Sun, 13 Jan 2013 11:09:38 +0100, Knut Petersen <Knut_Petersen@t-online.de> wrote:
> >> There is a massive performance regression on i915GM hardware,
> >> opening/closing/redrawing looks as if it is done in slow motion.
> > gen2/3 benefits from it after applying the bugfix to libdrm.
> > -Chris
> >
> Which bugfix?
https://patchwork.kernel.org/patch/1963391/
commit fdda97007b1dbf95beb16a0e3510fd36c89e8c33
Author: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri Jan 11 00:55:12 2013 +0000
intel: Remove the fence count contributions when clearing relocs
-Chris
--
Chris Wilson, Intel Open Source Technology Centre
^ permalink raw reply [flat|nested] 5+ messages in thread
* Re: Performance regression, please revert commit 441ef916ae6569c88b3d6abaf7fea4d69be49d76
2013-01-13 10:50 ` Chris Wilson
@ 2013-01-13 16:42 ` Knut Petersen
0 siblings, 0 replies; 5+ messages in thread
From: Knut Petersen @ 2013-01-13 16:42 UTC (permalink / raw)
To: Chris Wilson; +Cc: intel-gfx
On 13.01.2013 11:50, Chris Wilson wrote:
> On Sun, 13 Jan 2013 11:35:51 +0100, Knut Petersen <Knut_Petersen@t-online.de> wrote:
>> On 13.01.2013 11:23, Chris Wilson wrote:
>>> On Sun, 13 Jan 2013 11:09:38 +0100, Knut Petersen <Knut_Petersen@t-online.de> wrote:
>>>> There is a massive performance regression on i915GM hardware,
>>>> opening/closing/redrawing looks as if it is done in slow motion.
>>> gen2/3 benefits from it after applying the bugfix to libdrm.
>>> -Chris
>>>
>> Which bugfix?
> https://patchwork.kernel.org/patch/1963391/
>
> commit fdda97007b1dbf95beb16a0e3510fd36c89e8c33
> Author: Chris Wilson <chris@chris-wilson.co.uk>
> Date: Fri Jan 11 00:55:12 2013 +0000
>
> intel: Remove the fence count contributions when clearing relocs
> -Chris
>
Thanks, that indeed helps.
cu,
Knut
^ permalink raw reply [flat|nested] 5+ messages in thread
end of thread, other threads:[~2013-01-13 16:42 UTC | newest]
Thread overview: 5+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2013-01-13 10:09 Performance regression, please revert commit 441ef916ae6569c88b3d6abaf7fea4d69be49d76 Knut Petersen
2013-01-13 10:23 ` Chris Wilson
2013-01-13 10:35 ` Knut Petersen
2013-01-13 10:50 ` Chris Wilson
2013-01-13 16:42 ` Knut Petersen
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.