Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752789AbXIHJnc (ORCPT ); Sat, 8 Sep 2007 05:43:32 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752122AbXIHJnY (ORCPT ); Sat, 8 Sep 2007 05:43:24 -0400 Received: from mx1.Informatik.Uni-Tuebingen.De ([134.2.12.5]:39310 "EHLO mx1.informatik.uni-tuebingen.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752118AbXIHJnX (ORCPT ); Sat, 8 Sep 2007 05:43:23 -0400 From: Goswin von Brederlow To: Nick Piggin Cc: Goswin von Brederlow , Bernd Schubert , Randy Dunlap , linux-kernel@vger.kernel.org, "J. Bruce Fields" , brian@clusterfs.com Subject: Re: patch: improve generic_file_buffered_write() (2nd try 1/2) References: <200709051546.06224.bs@q-leap.de> <87d4wuch8y.fsf@informatik.uni-tuebingen.de> <200709081725.06343.nickpiggin@yahoo.com.au> <200709081731.51263.nickpiggin@yahoo.com.au> Date: Sat, 08 Sep 2007 11:43:03 +0200 In-Reply-To: <200709081731.51263.nickpiggin@yahoo.com.au> (Nick Piggin's message of "Sat, 8 Sep 2007 17:31:50 +1000") Message-ID: <874pi5cx20.fsf@informatik.uni-tuebingen.de> User-Agent: Gnus/5.110006 (No Gnus v0.6) XEmacs/21.4.19 (linux) MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1446 Lines: 35 Nick Piggin writes: > Lustre should probably have to be ported over to write_begin/write_end in > order to use it too. With the patches in -mm, if a filesystem is still using > prepare_write/commit_write, the vm reverts to a safe path which avoids > the deadlock (and allows multi-seg io copies), but copies the data twice. Not quite relevant for the performance problem. The situation is like this: lustre servers <-lustre network protocol-> lustre client <-NFS-> desktop The NFSd problem is on the lustre client that only plays gateway. That is not to say that the lustre servers or desktop loose performance due to fragmenting writes too but it isn't that noticeable there. > OTOH, this is very likely to go upstream, so your filesystem will need to be > ported over sooner or later anyway. Lustre copies the ext3 source from the kernel, patches in some extra features and renames them during build. So one the one hand it always breaks whenever someone meddles with the ext3 code. On the other hand improvement for ext3 get picked up by lustre semi automatically. In this case lustre would get the begin_write() function from ext3 and use it. MfG Goswin - 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/