From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753248Ab0G0NJR (ORCPT ); Tue, 27 Jul 2010 09:09:17 -0400 Received: from mx1.redhat.com ([209.132.183.28]:48660 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751949Ab0G0NJP (ORCPT ); Tue, 27 Jul 2010 09:09:15 -0400 Date: Tue, 27 Jul 2010 09:09:07 -0400 From: Vivek Goyal To: Gui Jianfeng Cc: linux-kernel@vger.kernel.org, jaxboe@fusionio.com, nauman@google.com, dpshah@google.com, jmoyer@redhat.com, czoccolo@gmail.com Subject: Re: [PATCH 2/5] cfq-iosched: Implment IOPS mode for group scheduling Message-ID: <20100727130906.GA23118@redhat.com> References: <1279834172-4227-1-git-send-email-vgoyal@redhat.com> <1279834172-4227-3-git-send-email-vgoyal@redhat.com> <4C4E72FB.2080104@cn.fujitsu.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <4C4E72FB.2080104@cn.fujitsu.com> User-Agent: Mutt/1.5.20 (2009-12-10) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Tue, Jul 27, 2010 at 01:47:39PM +0800, Gui Jianfeng wrote: [..] > > @@ -913,19 +927,21 @@ static void cfq_group_served(struct cfq_data *cfqd, struct cfq_group *cfqg, > > struct cfq_queue *cfqq) > > { > > struct cfq_rb_root *st = &cfqd->grp_service_tree; > > - unsigned int used_sl, charge_sl; > > + unsigned int used_sl, charge; > > int nr_sync = cfqg->nr_cfqq - cfqg_busy_async_queues(cfqd, cfqg) > > - cfqg->service_tree_idle.count; > > > > BUG_ON(nr_sync < 0); > > - used_sl = charge_sl = cfq_cfqq_slice_usage(cfqq); > > + used_sl = charge = cfq_cfqq_slice_usage(cfqq); > > > > - if (!cfq_cfqq_sync(cfqq) && !nr_sync) > > - charge_sl = cfqq->allocated_slice; > > + if (iops_mode(cfqd)) > > + charge = cfqq->slice_dispatch; > > Hi Vivek, > > At this time, requests may still stay in dispatch list, shall we add a new variable > in cfqq to keep track of the number of requests that go into driver, and charging > this number? > Hi Gui, How does that help. Even if request is in dispatch list, sooner or later it will be dispatched. As long as we can make sure that requests in dispatch list are in proportion to group weights, things should be just fine. Thanks Vivek