From mboxrd@z Thu Jan 1 00:00:00 1970 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? From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932715AbYBHDH6 (ORCPT ); Thu, 7 Feb 2008 22:07:58 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1756910AbYBHDHu (ORCPT ); Thu, 7 Feb 2008 22:07:50 -0500 Received: from smtp2.linux-foundation.org ([207.189.120.14]:45655 "EHLO smtp2.linux-foundation.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756658AbYBHDHt (ORCPT ); Thu, 7 Feb 2008 22:07:49 -0500 Date: Thu, 7 Feb 2008 19:04:47 -0800 From: Andrew Morton 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.org, Milan Broz Subject: Re: [git pull] device-mapper update for 2.6.25 Message-Id: <20080207190447.b4dcfe0c.akpm@linux-foundation.org> In-Reply-To: <20080208024532.GC24157@agk.fab.redhat.com> References: <20080208024532.GC24157@agk.fab.redhat.com> X-Mailer: Sylpheed 2.4.1 (GTK+ 2.8.17; x86_64-unknown-linux-gnu) Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org 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?