From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751647Ab1HUR4b (ORCPT ); Sun, 21 Aug 2011 13:56:31 -0400 Received: from mx2.fusionio.com ([66.114.96.31]:42280 "EHLO mx2.fusionio.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750784Ab1HUR42 (ORCPT ); Sun, 21 Aug 2011 13:56:28 -0400 X-ASG-Debug-ID: 1313949381-01de284617058f0001-xx1T2L X-Barracuda-Envelope-From: JAxboe@fusionio.com Message-ID: <4E5146C1.508@fusionio.com> Date: Sun, 21 Aug 2011 19:56:17 +0200 From: Jens Axboe MIME-Version: 1.0 To: Christoph Hellwig CC: Linus Torvalds , "linux-kernel@vger.kernel.org" Subject: Re: [GIT PULL] block bits for 3.1-rc References: <4E4E6238.3080808@fusionio.com> <20110820174137.GA27243@infradead.org> X-ASG-Orig-Subj: Re: [GIT PULL] block bits for 3.1-rc In-Reply-To: <20110820174137.GA27243@infradead.org> Content-Type: text/plain; charset="ISO-8859-1" Content-Transfer-Encoding: 7bit X-Barracuda-Connect: mail1.int.fusionio.com[10.101.1.21] X-Barracuda-Start-Time: 1313949381 X-Barracuda-URL: http://10.101.1.181:8000/cgi-mod/mark.cgi X-Barracuda-Spam-Score: 0.00 X-Barracuda-Spam-Status: No, SCORE=0.00 using global scores of TAG_LEVEL=1000.0 QUARANTINE_LEVEL=1000.0 KILL_LEVEL=9.0 tests=BSF_SC5_SA210e X-Barracuda-Spam-Report: Code version 3.2, rules version 3.2.2.72424 Rule breakdown below pts rule name description ---- ---------------------- -------------------------------------------------- 0.00 BSF_SC5_SA210e Custom Rule SA210e Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 2011-08-20 19:41, Christoph Hellwig wrote: > On Fri, Aug 19, 2011 at 03:16:40PM +0200, Jens Axboe wrote: >> - Revert of the CFQ meta data special treatment patch, it's been shown >> to regress a kernel build workload by about 10%. More investigation >> is needed, for 3.1 lets just back it out. > > Sorry, but you can't simply do that without any coordination. We have > added that marker to xfs now that the stupid special casing stopped, > and turning it back on will cause us massive slowdows. Next time > please better coordinate this with its users. In fact I have never > seen this patch or a discussion on any mailinglist. The discussion was on lkml, as Mike points out. But yes, short time to react. Since I can't easily cater to both cases right now, how about we add a temporary second meta flag that is only used for tracing? REQ_META = (__REQ_META | __REQ_META_TRACE), RET_META_TRACE = __REQ_META_TRACE, You get the idea. Not super pretty, but it should solve the immediate issue. -- Jens Axboe