From mboxrd@z Thu Jan 1 00:00:00 1970 From: Gregory Haskins Subject: Re: [PATCH -v5][RFC]: mutex: implement adaptive spinning Date: Wed, 07 Jan 2009 23:00:18 -0500 Message-ID: <49657A52.2050702@novell.com> References: <1231281801.11687.125.camel@twins> <1231283778.11687.136.camel@twins> <1231329783.11687.287.camel@twins> <1231347442.11687.344.camel@twins> <20090107210923.GV2002@parisc-linux.org> <20090107213924.GP496@one.firstfloor.org> <49652C7C.3000909@novell.com> <49657297.9000708@novell.com> Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="------------enig5BEF5657D0E5E6EDEBEE4C8F" Cc: Linus Torvalds , Andi Kleen , Matthew Wilcox , Peter Zijlstra , paulmck@linux.vnet.ibm.com, Ingo Molnar , Chris Mason , Andrew Morton , Linux Kernel Mailing List , linux-fsdevel , linux-btrfs , Thomas Gleixner , Nick Piggin , Peter Morreale , Sven Dietrich To: Steven Rostedt Return-path: In-Reply-To: List-ID: This is an OpenPGP/MIME signed message (RFC 2440 and 3156) --------------enig5BEF5657D0E5E6EDEBEE4C8F Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable Steven Rostedt wrote: > On Wed, 7 Jan 2009, Gregory Haskins wrote: > =20 >> In my defense, the -rt versions of the patches guarantee this is ok >> based on a little hack: >> =20 > > The -rt versions worry about much more than what the mutex code in > mainline does. Linus is correct in his arguments. The adaptive mutex (a= s=20 > suppose to what -rt has), is only to help aid in preformance. There are= a=20 > lot of races that can happen in mainline version where lock taking may = not=20 > be fifo, or where we might start to schedule when we could have taken t= he=20 > lock. These races are not in -rt, but that is because -rt cares about=20 > these. But mainline cares more about performance over determinism. This= =20 > means that we have to look at the current code that Peter is submitting= =20 > with a different perspective than we do in -rt. > =20 Hey Steve, Understood, and agreed. I only mentioned it because I wanted to clear the record that I did not (to my knowledge) mess up the protocol design which first introduced the get/put-task pattern under discussion ;). I am fairly confident that at least the -rt version does not have any race conditions such as the one Linus mentioned in the mainline version. I am not advocating that the full protocol that we use in -rt should be carried forward, per se or anything like that. -Greg --------------enig5BEF5657D0E5E6EDEBEE4C8F Content-Type: application/pgp-signature; name="signature.asc" Content-Description: OpenPGP digital signature Content-Disposition: attachment; filename="signature.asc" -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.9 (GNU/Linux) Comment: Using GnuPG with SUSE - http://enigmail.mozdev.org iEYEARECAAYFAkllelIACgkQlOSOBdgZUxncEACeLmAFfg1k0t4QyWETbrWKJ3S8 nLUAnjftloyOFW7JhKpsVDSp+0prZDgc =wGal -----END PGP SIGNATURE----- --------------enig5BEF5657D0E5E6EDEBEE4C8F--