From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751524Ab1JYTBz (ORCPT ); Tue, 25 Oct 2011 15:01:55 -0400 Received: from mx1.redhat.com ([209.132.183.28]:1652 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750755Ab1JYTBy (ORCPT ); Tue, 25 Oct 2011 15:01:54 -0400 Date: Tue, 25 Oct 2011 15:01:51 -0400 From: Vivek Goyal To: Jens Axboe Cc: Tejun Heo , "linux-kernel@vger.kernel.org" Subject: Re: [PATCH 2/2] blk-throttle: Take blkcg->lock while traversing blkcg->policy_list Message-ID: <20111025190151.GH23292@redhat.com> References: <1319144906-5066-1-git-send-email-vgoyal@redhat.com> <1319144906-5066-2-git-send-email-vgoyal@redhat.com> <20111020211140.GY25124@google.com> <20111020212021.GA2841@redhat.com> <20111020212958.GA25124@google.com> <20111021121043.GB6474@redhat.com> <4EA6C3F7.20604@fusionio.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <4EA6C3F7.20604@fusionio.com> User-Agent: Mutt/1.5.21 (2010-09-15) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Tue, Oct 25, 2011 at 04:13:11PM +0200, Jens Axboe wrote: > On 2011-10-21 14:10, Vivek Goyal wrote: > > On Thu, Oct 20, 2011 at 02:29:58PM -0700, Tejun Heo wrote: > >> Hello, > >> > >> On Thu, Oct 20, 2011 at 05:20:21PM -0400, Vivek Goyal wrote: > >>> The only problem with this approach is that it will cleanup per device > >>> weight rules also at elevator_exit() time which is not same as device > >>> removal and one might device to bring CFQ back on device and we will > >>> need the rules again. > >> > >> I actually think removoing those rules on elevator detach would be the > >> right thing to do. We don't try to keep cfq setting across elevator > >> switch. When we're switching from cfq, we're detaching iocg policy > >> too. The settings going away is perfectly fine. I actually think > >> it's a pretty bad idea to implement ad-hoc setting persistence in > >> kernel. Just making sure that userland is notified is far better > >> approach. Userland has all the facilities to deal with this type of > >> situations. > >> > >> When switching from cfq to deadline, we lose the whole proportional io > >> control. It's way more confusing to have lingering settings which > >> don't do anything. > > > > I am not so sure about this. Suppose tomorrow another IO sheduler starts > > taking into account the cgroup gloabl weight or cgroup per device weight > > to do some kind of IO prioritization, then removing the rules upon > > changing the IO schduler will not make sense. > > > > IOW, rules are per cgroup per device and not per cgroup per IO scheduler > > and more than one IO scheduler should be able to share the rules. > > FWIW, I agree with Tejun here. A switch operation is a reset, start from > scratch. We don't preserve other per IO-scheduler settings on a switch, > preserving _some_ settings is just confusing. Ok. But this is more of a per queue setting (per cgroup, per device) and not per IO scheduler one. That's a different thing that currently only CFQ makes use of it. If we start looking at them just as CFQ specific weigths, then it is a different story. My thought process about these files was per cgroup per device weights. Thanks Vivek