Return-Path: Received: from mx2.suse.de ([195.135.220.15]:36167 "EHLO mx1.suse.de" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1750823AbdFUKws (ORCPT ); Wed, 21 Jun 2017 06:52:48 -0400 Date: Wed, 21 Jun 2017 12:52:46 +0200 From: Jan Kara To: Andrew Perepechko Cc: linux-fsdevel@vger.kernel.org Subject: Re: quota: dqio_mutex design Message-ID: <20170621105246.GA31686@quack2.suse.cz> References: <10928956.Fla3vXZ7d9@panda> <20170303100842.GB4373@quack2.suse.cz> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20170303100842.GB4373@quack2.suse.cz> Sender: linux-fsdevel-owner@vger.kernel.org List-ID: On Fri 03-03-17 11:08:42, Jan Kara wrote: > Hello! > > On Thu 02-02-17 15:23:44, Andrew Perepechko wrote: > > We have a heavy metadata related workload (ext4, quota journalling) > > and profiling shows that there's significant dqio_mutex contention. > > > > From the quota code, it looks like every time dqio_mutex is taken > > it protects access to only one quota file. > > > > Is it possible to split dqio_mutex for each of MAXQUOTAS so that > > e.g. 2 parallel dquot_commit()'s can be running for user and group > > quota update? Am I missing any dqio_mutex function that requires > > dqio_mutex to be monolithic? > > So we can certainly make dqio_mutex less heavy. Making it per-quota-type > would OK but I suspect it will not bring a big benefit. What would likely > be more noticeable is if we avoided dqio_mutex for updates of quota > information - that should not be that hard to do since we update that > in-place and so don't really need the serialization for anything > substantial. However we will need some restructuring of the code to make > such locking scheme possible in a clean way... So I'm experimenting with some patches. However I have trouble creating a workload where quota updates would show significant overhead. Can you share which workload is problematic for you? Thanks! Honza -- Jan Kara SUSE Labs, CR