From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753140AbZIXQ0E (ORCPT ); Thu, 24 Sep 2009 12:26:04 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752935AbZIXQ0E (ORCPT ); Thu, 24 Sep 2009 12:26:04 -0400 Received: from bombadil.infradead.org ([18.85.46.34]:39839 "EHLO bombadil.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752450AbZIXQ0C (ORCPT ); Thu, 24 Sep 2009 12:26:02 -0400 Subject: Re: [PATCH 03/10] writeback: stop background writeback when below background threshold From: Peter Zijlstra To: Jens Axboe Cc: linux-kernel@vger.kernel.org, fengguang.wu@intel.com, shaohua.li@intel.com, chris.mason@oracle.com, jack@suse.cz In-Reply-To: <20090924161357.GL23126@kernel.dk> References: <1253803236-20760-1-git-send-email-jens.axboe@oracle.com> <1253803236-20760-4-git-send-email-jens.axboe@oracle.com> <1253804615.18939.36.camel@laptop> <1253805536.18939.39.camel@laptop> <20090924161357.GL23126@kernel.dk> Content-Type: text/plain Date: Thu, 24 Sep 2009 18:26:00 +0200 Message-Id: <1253809560.18939.69.camel@laptop> Mime-Version: 1.0 X-Mailer: Evolution 2.26.1 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Thu, 2009-09-24 at 18:13 +0200, Jens Axboe wrote: > > > > for (;;) { > > > > /* > > > > + * Stop writeback when nr_pages has been consumed > > > > */ > > > > + if (args->nr_pages <= 0) > > > > break; > > > > > > > > /* > > > > + * For background writeout, stop when we are below the > > > > + * background dirty threshold > > > > */ > > > > + if (args->for_background && !over_bground_thresh()) > > > > break; > > > > > > > > > What I'm not getting is why this is conditional on for_background(), > > > shouldn't we always stop writeback when below the background threshold? > > > > Ah, that would be for things like sync, which need to write out > > everything, right? > > Yes, wb_writeback() handles any kind of writeback. The definition of our > background writeout is to stop when we are no longer over the background > writeout threshold. Right, ok Acked-by: Peter Zijlstra