From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from ipmail06.adl2.internode.on.net ([150.101.137.129]:31494 "EHLO ipmail06.adl2.internode.on.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1730734AbeLNVU0 (ORCPT ); Fri, 14 Dec 2018 16:20:26 -0500 Date: Sat, 15 Dec 2018 08:20:22 +1100 From: Dave Chinner Subject: Re: XFS and RAID10 with o2 layout Message-ID: <20181214212022.GL6311@dastard> References: <20181213220533.GH6311@dastard> <3e0e8def-2bb4-5e8a-56c1-d010ede059d4@4net.rs> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <3e0e8def-2bb4-5e8a-56c1-d010ede059d4@4net.rs> Sender: linux-xfs-owner@vger.kernel.org List-ID: List-Id: xfs To: Sinisa Cc: linux-raid@vger.kernel.org, linux-xfs@vger.kernel.org On Fri, Dec 14, 2018 at 08:03:36AM +0100, Sinisa wrote: > On 12/13/18 11:05 PM, Dave Chinner wrote: > >On Wed, Dec 12, 2018 at 01:29:49PM +0100, Sinisa wrote: > >Basically, this looks and smells like a MD sync barrier race > >condition, not an XFs problem. > > But why don't we see the same issue with other filesystems? XFS has a lot more parallelism at the storage layer than other filesystems and has a different integrity synchronisation model (via IO completion processing rather than submission serialisation), so it stresses the underlying storage very differently to other filesystems. Cheers, Dave. -- Dave Chinner david@fromorbit.com