From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1759937Ab1LPAcD (ORCPT ); Thu, 15 Dec 2011 19:32:03 -0500 Received: from ipmail06.adl2.internode.on.net ([150.101.137.129]:17480 "EHLO ipmail06.adl2.internode.on.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756413Ab1LPAcB (ORCPT ); Thu, 15 Dec 2011 19:32:01 -0500 X-IronPort-Anti-Spam-Filtered: true X-IronPort-Anti-Spam-Result: Av0EAB6O6k55LOCn/2dsb2JhbABDq0CBBoFyAQEFOhwPFBAIAxguFCUDIRPBBBOLDmMElHWSQA Date: Fri, 16 Dec 2011 11:31:57 +1100 From: Dave Chinner To: Wu Fengguang Cc: linux-fsdevel@vger.kernel.org, LKML , Christoph Hellwig Subject: Re: XFS/btrfs performance after IO-less dirty throttling Message-ID: <20111216003157.GA23662@dastard> References: <20111214143156.GA22511@localhost> <20111215133137.GA14562@localhost> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20111215133137.GA14562@localhost> 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 Thu, Dec 15, 2011 at 09:31:37PM +0800, Wu Fengguang wrote: > > The other big regressions happen in the XFS UKEY-thresh=100M cases. > > > 3.1.0+ 3.2.0-rc3 > > ------------------------ ------------------------ > > 4.17 -37.8% 2.59 fat/UKEY-thresh=100M/xfs-100dd-1-3.1.0+ > > 4.14 -53.3% 1.94 fat/UKEY-thresh=100M/xfs-10dd-1-3.1.0+ > > 6.30 +0.4% 6.33 fat/UKEY-thresh=100M/xfs-1dd-1-3.1.0+ > > Here are more details for the 10dd case. The attached > balance_dirty_pages-pause.png shows small pause time (mostly in range > 10-50ms) and nr_dirtied_pause (mostly < 5), which may be the root cause. > > The iostat graphs show very unstable throughput and IO size often > drops low. And it's doing shitloads more allocation work. IOWs, the delayed allocation algorithms are being strangled by writeback, causing fragmentation and hence not allowing enough data per thread to be written at a time to maximise throughput. However, I'd argue that the performance of 10 concurrent writers to a slow USB key formatted with XFS is so *completely irrelevant* that I'd ignore it. Spend your time optimising writeback on XFS for high throughputs (e.g > 500MB/s), not for shitty $5 USB keys that are 2-3 orders of magnitude slower than the target market for XFS... Cheers, Dave. -- Dave Chinner david@fromorbit.com