From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Rafael J. Wysocki" Subject: Re: [Bug #12152] Huge wakeups number from i1915 Date: Mon, 8 Dec 2008 08:28:07 +0100 Message-ID: <200812080828.07683.rjw@sisk.pl> References: <6VnlupFpCsN.A.2rE.MsEPJB@chimera> <20081207151203.46c01a0d@infradead.org> <1228717448.9677.3.camel@hidalgo> Mime-Version: 1.0 Content-Transfer-Encoding: QUOTED-PRINTABLE Return-path: In-Reply-To: <1228717448.9677.3.camel@hidalgo> Content-Disposition: inline Sender: kernel-testers-owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org List-ID: Content-Type: text/plain; charset="utf-8" To: Yves-Alexis Perez Cc: Arjan van de Ven , Linux Kernel Mailing List , Kernel Testers List , Matthew Garrett On Monday, 8 of December 2008, Yves-Alexis Perez wrote: > On dim, 2008-12-07 at 15:12 -0800, Arjan van de Ven wrote: > >=20 > > > > at least in some of the cases where this has been seen the caus= e > > is > > > > the following: > > > > The i915 DRM driver used to do polling for completion, busy > > > > waiting. It moved to be interrupt driven, which is usually bett= er > > > > for power, but it will show up as more wakeups in powertop.... > > >=20 > > > IOW, this is not a regression? > >=20 > > I don't know about this specifc case (not enough information) but f= or > > the case I described it's not a regression. Going to interrupt driv= en > > from busy waiting is an improvement not a regression :) >=20 > Well, several thousand or more interrupts really seems like a > regression :). But it seems that's the same thing as the =E2=80=9CIRQ > spinning=E2=80=9D (there was a thread on dri-devel about that). >=20 > It seems fixed with a patch from Matthew Garrett applied to > drm-intel/for-airlied but I don't think this has been applied to Linu= s > master. Any pointers to the patch, please? Rafael