From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jens Axboe Subject: Re: [PATCH 00/19] periodic write-back timer optimization Date: Wed, 27 May 2009 14:33:20 +0200 Message-ID: <20090527123320.GF11363@kernel.dk> References: <20090527130503.4913.62042.sendpatchset@localhost.localdomain> <200905271323.29818.arnd@arndb.de> <4A1D31BA.6060903@nokia.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Arnd Bergmann , "linux-kernel@vger.kernel.org" , "linux-fsdevel@vger.kernel.org" , Christoph Hellwig To: Artem Bityutskiy Return-path: Received: from brick.kernel.dk ([93.163.65.50]:45801 "EHLO kernel.dk" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1757460AbZE0MdT (ORCPT ); Wed, 27 May 2009 08:33:19 -0400 Content-Disposition: inline In-Reply-To: <4A1D31BA.6060903@nokia.com> Sender: linux-fsdevel-owner@vger.kernel.org List-ID: On Wed, May 27 2009, Artem Bityutskiy wrote: > ext Arnd Bergmann wrote: >> On Wednesday 27 May 2009, Artem Bityutskiy wrote: >>> Hi, >>> >>> This is the second attempt. The first one was here: >>> http://marc.info/?l=linux-fsdevel&m=124301072305588&w=2 >>> It was very hacky and got no comments. >> >> How does this relate to the per-BDI writeback patches that >> Jens is working on? Doesn't that require a completely different >> (probably simpler) implementation of your patch? > > At a quick glance, our works do not intersect. He seems > to be changing the guts of write-back, while I only touch > the timer which wakes up the periodic write-back thread, > nothing else. I'll try to take Jens' patches and see. There's definitely overlap! The timer is gone with my patches and so is pdflush. For an idle (idle here meaning no background writeback activity) system, there should just be bdi-default running. And that will wake up every dirty_writeback_interval by default. -- Jens Axboe