From: Stefan Biereigel Subject: Re: Interrupt latency on some 945GM platforms Date: Sun, 26 Sep 2010 12:53:35 +0200 Message-ID: <4C9F262F.7030709@biereigel-wb.de> References: <201009132336.17310.anarsoul@gmail.com> <201009162306.59508.anarsoul@gmail.com> <20100924123901.243c85e1@jbarnes-desktop> <201009242248.36554.anarsoul@gmail.com> <20100924125153.4fdf0c1b@jbarnes-desktop> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: QUOTED-PRINTABLE Return-path: In-Reply-To: <20100924125153.4fdf0c1b@jbarnes-desktop> Sender: linux-kernel-owner@vger.kernel.org To: linux-kernel@vger.kernel.org Cc: Vasily Khoruzhick , Thomas Gleixner , Sitsofe Wheeler , Venkatesh Pallipadi , intel-gfx@lists.freedesktop.org, Len Brown , Jesse Barnes List-Id: intel-gfx@lists.freedesktop.org Am 24.09.2010 21:51, schrieb Jesse Barnes: > On Fri, 24 Sep 2010 22:48:36 +0300 > Vasily Khoruzhick wrote: > >> On 24 of September 2010 22:39:01 Jesse Barnes wrote: >>> On Thu, 16 Sep 2010 23:06:46 +0300 >>> >>> Vasily Khoruzhick wrote: >>>> =D0=92 =D1=81=D0=BE=D0=BE=D0=B1=D1=89=D0=B5=D0=BD=D0=B8=D0=B8 =D0=BE= =D1=82 16 of September 2010 21:50:50 =D0=B0=D0=B2=D1=82=D0=BE=D1=80 Tho= mas Gleixner >> =D0=BD=D0=B0=D0=BF=D0=B8=D1=81=D0=B0=D0=BB: >>>>> Ok. The problematic part of HPET was not the clocksource, it was = the >>>>> clock event device which failed to deliver interrupts occasionall= y. It >>>>> was worth a try at least. >>>> Hm, it seems that jerky glxgears is not related to jerky keyboard = events. >>>> Keyboard is jerky only in konsole (kde terminal emulator), it seem= s >>>> something happened it seems that font rendering performance is muc= h >>>> worse in latest xf86-video-intel than in xf86-video-intel-2.12.0. >>> Len just had me try a few things too: >>> - maxcpus=3D1 lets things work >>> - offlining cpu1 at runtime (echo 0 >>> >>> > /sys/devices/system/cpu/cpu1/online) lets things work >>> >>> - binding the i915 interrupt to cpu 0 does *not* help >>> >>> Vasily and Paolo, do you both have Atom CPUs with hyperthreading >>> enabled? >> Nope, I have Core2Duo T5500, dual-core, no hyperthreading :) > Hm, well there goes the theory about Atom HT... > Hello Everyone, just to add on to reports of this problem, there was a Thread here in=20 LKML some months ago targeting the same problem (but not really=20 attacking it at the Chipset driver). As I have one of those Laptops wit= h=20 a 945GM-Chipset and am stuck with the same Problem (disabled tickless=20 now as a workaround and set ticks to 1000) I could maybe do some testin= g=20 of patches. So what I can summarize is what the others did before: Disabling CPU1=20 helps, adding nohz=3Doff helps, changing the Clocksource afterwards hel= ps,=20 binding the Interrupt does NOT help. So here's the Link to the old Discussion with follow-ups, maybe you can= =20 get some furter information from there. http://linux.derkeiler.com/Mailing-Lists/Kernel/2010-05/msg03696.html We targeted the BIOS itself as everyone in this thread happened to own=20 an Phoenix BIOS with some special version string. best, Stefan