From: Tejun Heo Subject: Re: [PATCH cgroup/for-4.3-fixes] cgroup, writeback: don't enable cgroup writeback on traditional hierarchies Date: Mon, 28 Sep 2015 17:39:13 -0400 Message-ID: <20150928213913.GH2589@mtj.duckdns.org> References: <1434495193-31182-1-git-send-email-tj@kernel.org> <1434495193-31182-3-git-send-email-tj@kernel.org> <20150722035620.GD2944@thunk.org> <1443012552.19983.209.camel@gmail.com> <20150923180934.GE26647@mtj.duckdns.org> <20150923185137.GJ26647@mtj.duckdns.org> <20150923210729.GA23180@mtj.duckdns.org> <1443082186.19983.234.camel@gmail.com> <20150924204736.GG25415@mtj.duckdns.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: "dedekind1@gmail.com" , Theodore Ts'o , "axboe@kernel.dk" , "linux-kernel@vger.kernel.org" , "linux-fsdevel@vger.kernel.org" , "lizefan@huawei.com" , "cgroups@vger.kernel.org" , "hannes@cmpxchg.org" , "kernel-team@fb.com" , "adilger.kernel@dilger.ca" , "linux-ext4@vger.kernel.org" To: Dexuan Cui Return-path: Content-Disposition: inline In-Reply-To: <20150924204736.GG25415@mtj.duckdns.org> Sender: linux-kernel-owner@vger.kernel.org List-Id: linux-ext4.vger.kernel.org Hello, On Thu, Sep 24, 2015 at 04:47:36PM -0400, Tejun Heo wrote: > On Thu, Sep 24, 2015 at 08:40:18AM +0000, Dexuan Cui wrote: > > I can confirm the patch fixes my "slow write" issue too. > > > > Tested-by: Dexuan Cui > > Yeah, this should make it go away w/o using cgroup writeback > explicitly; however, I think the proper solution for cgroup writeback > is moving bandwidth estimation from memory domain to io domain so that > two separate bw estimations wouldn't interfere with each other leading > to unexpected outcomes. I'll work on the changes. So, this one actually turns out to be mostly caused by enabling cgroup writeback when it shouldn't be. balance_dirty_pages() ended up looking at a different bdi_writeback from the actual writeback path so the throttling was completley off, so making sure that cgroup writeback doesn't get turned on traditional hierarchies is the right solution here. While auditing the behavior, I noticed a couple non-critical issues. Will post patches to fix them soon. Thanks. -- tejun