Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752641AbXLLMtU (ORCPT ); Wed, 12 Dec 2007 07:49:20 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1750847AbXLLMtM (ORCPT ); Wed, 12 Dec 2007 07:49:12 -0500 Received: from viefep18-int.chello.at ([213.46.255.22]:43068 "EHLO viefep12-int.chello.at" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1750786AbXLLMtL (ORCPT ); Wed, 12 Dec 2007 07:49:11 -0500 Subject: Re: Possible bug from kernel 2.6.22 and above, 2.6.24-rc4 From: Peter Zijlstra To: Jie Chen Cc: Ingo Molnar , linux-kernel@vger.kernel.org In-Reply-To: <475F0B07.2060303@jlab.org> References: <20071205210222.GA30089@elte.hu> <47572353.4040606@jlab.org> <20071206104318.GB30838@elte.hu> <47582367.6060602@jlab.org> <20071210105943.GA5370@elte.hu> <475D9BB5.20808@jlab.org> <20071211105149.GA24250@elte.hu> <475EAC81.1020408@jlab.org> <20071211155226.GA1056@elte.hu> <475EBD30.1010506@jlab.org> <20071211212352.GF6902@elte.hu> <475F0B07.2060303@jlab.org> Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="=-aghquV/EiD6MWW7kBRd9" Date: Wed, 12 Dec 2007 13:49:06 +0100 Message-Id: <1197463746.7042.2.camel@twins> Mime-Version: 1.0 X-Mailer: Evolution 2.12.0 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 2000 Lines: 70 --=-aghquV/EiD6MWW7kBRd9 Content-Type: text/plain Content-Transfer-Encoding: quoted-printable On Tue, 2007-12-11 at 17:11 -0500, Jie Chen wrote: > Ingo Molnar wrote: > > * Jie Chen wrote: > >=20 > >> The following is pthread_sync output for 2.6.21.7-cfs-v24 #1 SMP=20 > >> kernel. > >=20 > >> 2 threads: > >=20 > >> PARALLEL time =3D 11.106580 microseconds +/- 0.002460 > >> PARALLEL overhead =3D 0.617590 microseconds +/- 0.003409 > >=20 > >> Output for Kernel 2.6.24-rc4 #1 SMP > >=20 > >> PARALLEL time =3D 19.668450 microseconds +/- 0.015782 > >> PARALLEL overhead =3D 9.157945 microseconds +/- 0.018217 > >=20 > > ok, so the problem is that this PARALLEL time has an additional +9 usec= s=20 > > overhead, right? I dont see this myself on a Core2 CPU: > >=20 > > PARALLEL time =3D 10.446933 microseconds +/- = 0.078849 > > PARALLEL overhead =3D 0.751732 microseconds +/- 0= .177446 > >=20 On my dual socket AMD Athlon MP 2.6.20-13-generic PARALLEL time =3D 22.751875 microseconds +/- 21.3= 70942 PARALLEL overhead =3D 7.046595 microseconds +/- 24.37= 0040 2.6.24-rc5 PARALLEL time =3D 17.365543 microseconds +/- 3.29= 5133 PARALLEL overhead =3D 2.213722 microseconds +/- 4.797= 886 --=-aghquV/EiD6MWW7kBRd9 Content-Type: application/pgp-signature; name=signature.asc Content-Description: This is a digitally signed message part -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.6 (GNU/Linux) iD8DBQBHX9jCXA2jU0ANEf4RAnBjAJ99Iji2UkXzvwntBmBwu3oR0Nt4XQCfWh3U 5Fc05OYJe6yEVOpYEMAidcs= =fv/f -----END PGP SIGNATURE----- --=-aghquV/EiD6MWW7kBRd9-- -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/