From: Juergen Beisert Subject: Re: High latencies on MPC5200 with patch-2.6.24-rc5-rt1 Date: Thu, 10 Jan 2008 16:48:05 +0100 Message-ID: <200801101648.05550.jbe@pengutronix.de> References: <47834CB7.1030102@grandegger.com> <20080110000124.GW3177@pengutronix.de> <47861ACE.9060301@grandegger.com> Mime-Version: 1.0 Content-Type: text/plain; charset=iso-8859-15 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: Wolfgang Grandegger , Robert Schwebel , Thomas Gleixner , John Stultz To: linux-rt-users@vger.kernel.org Return-path: Received: from metis.extern.pengutronix.de ([83.236.181.26]:51065 "EHLO metis.extern.pengutronix.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755146AbYAJPsN convert rfc822-to-8bit (ORCPT ); Thu, 10 Jan 2008 10:48:13 -0500 In-Reply-To: <47861ACE.9060301@grandegger.com> Content-Disposition: inline Sender: linux-rt-users-owner@vger.kernel.org List-ID: On Thursday 10 January 2008 14:17, Wolfgang Grandegger wrote: > Hi Robert, > > Robert Schwebel wrote: > > Wolfgang, > > > > On Wed, Jan 09, 2008 at 11:51:07PM +0100, Robert Schwebel wrote: > >> Throwing in the versions from 2.6.23.3-rt5 doesn't help, the effec= t > >> stays the same. So I assume it is a side effect. > > > > Can you test the following patch by John Stulz (thanks to John for = the > > quick help on irc!), which fixes the issues on my board: > > > > ----------8<---------- > > Index: linux-2.6.24-rc5/arch/powerpc/kernel/time.c > > =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D > > --- linux-2.6.24-rc5.orig/arch/powerpc/kernel/time.c > > +++ linux-2.6.24-rc5/arch/powerpc/kernel/time.c > > @@ -773,7 +773,7 @@ void update_vsyscall(struct timespec *wa > > stamp_xsec =3D (u64) xtime.tv_nsec * XSEC_PER_SEC; > > do_div(stamp_xsec, 1000000000); > > stamp_xsec +=3D (u64) xtime.tv_sec * XSEC_PER_SEC; > > - update_gtod(clock->cycle_last, stamp_xsec, t2x); > > + update_gtod(clock->cycle_last-clock->cycle_accumulated, stamp_xse= c, > > t2x); } > > > > void update_vsyscall_tz(void) > > ----------8<---------- > > > > With this patch ontop of 2.6.24-rc5-rt1 plus the board support patc= hes > > for the phyCORE-MPC5200B-tiny, I get this result from cyclictest, a= gain > > under "(while true; do hackbench 10; done) &" load: > > > > T: 0 ( 867) P:80 I: 10000 C: 105002 Min: 31 Act: 48 A= vg: =20 > > 51 Max: 92 > > Unfortunately, it doesn't really help on my Icecube board. > > bash-3.00# ./cyclictest -n -p80 -i1000 > 129.85 93.18 38.05 4/45 6354 > 130.41 162.23 83.05 3/49 8395 > T: 0 ( 4621) P:80 I:1000 C: 477097 Min: 25 Act: 64 Avg: 67 Ma= x: > 286 > > bash-3.00# ./hackbench 10 > Time: 95.402 > > Could you run your cyclictest much longer? > > And hackbench takes ages, already without running cyclictest: Did your read http://lkml.org/lkml/2007/12/7/181 ? Don't know if it is=20 relevant here. Juergen --=20 Dipl.-Ing. Juergen Beisert | http://www.pengutronix.de =A0Pengutronix - Linux Solutions for Science and Industry =A0 Handelsregister: Amtsgericht Hildesheim, HRA 2686 =A0 =A0 =A0 Vertretung Sued/Muenchen, Germany Phone: +49-8766-939 228 | Fax: +49-5121-206917-9