From mboxrd@z Thu Jan 1 00:00:00 1970 From: =?ISO-8859-1?Q?S=E9bastien_Dugu=E9?= Subject: Re: [3/4] kevent: AIO, aio_sendfile() implementation. Date: Thu, 27 Jul 2006 08:49:14 +0200 Message-ID: <1153982954.3887.9.camel@frecb000686> References: <1153905495613@2ka.mipt.ru> <11539054952574@2ka.mipt.ru> <20060726100431.GA7518@infradead.org> <20060726101919.GB2715@2ka.mipt.ru> <20060726103001.GA10139@infradead.org> <44C77C23.7000803@redhat.com> <44C796C3.9030404@us.ibm.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-15 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: Ulrich Drepper , Christoph Hellwig , Evgeniy Polyakov , lkml , David Miller , netdev , Suparna Bhattacharya Return-path: Received: from ecfrec.frec.bull.fr ([129.183.4.8]:18073 "EHLO ecfrec.frec.bull.fr") by vger.kernel.org with ESMTP id S1750812AbWG0Gt0 convert rfc822-to-8bit (ORCPT ); Thu, 27 Jul 2006 02:49:26 -0400 To: Badari Pulavarty In-Reply-To: <44C796C3.9030404@us.ibm.com> Sender: netdev-owner@vger.kernel.org List-Id: netdev.vger.kernel.org On Wed, 2006-07-26 at 09:22 -0700, Badari Pulavarty wrote: > Ulrich Drepper wrote: > > Christoph Hellwig wrote: > > =20 > >>> My personal opinion on existing AIO is that it is not the right d= esign. > >>> Benjamin LaHaise agree with me (if I understood him right), > >>> =20 > >> I completely agree with that aswell. > >> =20 > > > > I agree, too, but the current code is not the last of the line. Su= parna > > has a st of patches which make the current kernel aio code work muc= h > > better and especially make it really usable to implement POSIX AIO. > > > > In Ottawa we were talking about submitting it and Suparna will. We= just > > thought about a little longer timeframe. I guess it could be > > accelerated since he mostly has the patch done. But I don't know h= er > > schedule. > > > > Important here is, don't base any decision on the current aio > > implementation. > > =20 > Ulrich, >=20 > Suparna mentioned your interest in making POSIX glibc aio work with=20 > kernel-aio at OLS. > We thought taking a re-look at the (kernel side) work BULL did, would= be=20 > a nice starting > point. I re-based those patches to 2.6.18-rc2 and sent it to Zach Bro= wn=20 > for review before > sending them out to list. >=20 > These patches does NOT make AIO any cleaner. All they do is add=20 > functionality to support > POSIX AIO easier. These are >=20 > [ PATCH 1/3 ] Adding signal notification for event completion >=20 > [ PATCH 2/3 ] lio (listio) completion semantics >=20 > [ PATCH 3/3 ] cancel_fd support Badari, Thanks for refreshing those patches, they have been sitting here for quite some time now and collected dust. I also think Suparna's patchset for doing buffered AIO would be a real plus here. >=20 > Suparna explained these in the following article: >=20 > http://lwn.net/Articles/148755/ >=20 > If you think, this is a reasonable direction/approach for the kernel = and=20 > you would take care > of glibc side of things - I can spend time on these patches, getting=20 > them to reasonable shape > and push for inclusion. Ulrich, I you want to have a look at how those patches are put to use in libposix-aio, have a look at http://sourceforge.net/projects/pai= ol. It could be a starting point for glibc. Thanks, S=E9bastien. --=20 ----------------------------------------------------- S=E9bastien Dugu=E9 BULL/FREC:B1-247 phone: (+33) 476 29 77 70 Bullcom: 229-7770 mailto:sebastien.dugue@bull.net Linux POSIX AIO: http://www.bullopensource.org/posix http://sourceforge.net/projects/paiol -----------------------------------------------------