From: Andrew Morton Subject: Re: [git pull] device-mapper update for 2.6.25 Date: Thu, 7 Feb 2008 19:04:47 -0800 Message-ID: <20080207190447.b4dcfe0c.akpm@linux-foundation.org> References: <20080208024532.GC24157@agk.fab.redhat.com> Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <20080208024532.GC24157@agk.fab.redhat.com> Sender: linux-kernel-owner@vger.kernel.org To: Alasdair G Kergon Cc: Linus Torvalds , Brian Wood , Daniel Walker , Herbert Xu , Jonathan Brassow , Jun'ichi Nomura , Milan Broz , Paul Jimenez , "Robert P. J. Day" , Vasily Averin , dm-devel@redhat.com, linux-kernel@vger.kernel.orgMilan Broz List-Id: dm-devel.ids On Fri, 8 Feb 2008 02:45:32 +0000 Alasdair G Kergon wrote: > dm: move deferred bio flushing to workqueue To my unpracticed eye this one looks fairly fundamental. Unfortunately the changelog: Add a single-thread workqueue for each mapped device and move flushing of the lists of pushback and deferred bios to this new workqueue. tells us nothing of the reasons for this change. (It should have done so!) It _looks_ pretty unscalable. Perhaps these deferred BIOs don't happen very often?