From: "Darrick J. Wong" Subject: Re: [PATCH] ext4: Set barrier=0 when block device does not advertise flush support Date: Mon, 6 Dec 2010 10:09:42 -0800 Message-ID: <20101206180942.GL18195@tux1.beaverton.ibm.com> References: <20101203001659.GI18195@tux1.beaverton.ibm.com> <20101203070950.GA19071@infradead.org> <20101203091445.GK18195@tux1.beaverton.ibm.com> <20101206133924.GB9235@infradead.org> Reply-To: djwong@us.ibm.com Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: "Theodore Ts'o" , linux-kernel , linux-ext4 To: Christoph Hellwig Return-path: Received: from e9.ny.us.ibm.com ([32.97.182.139]:56155 "EHLO e9.ny.us.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752778Ab0LFSJo (ORCPT ); Mon, 6 Dec 2010 13:09:44 -0500 Content-Disposition: inline In-Reply-To: <20101206133924.GB9235@infradead.org> Sender: linux-ext4-owner@vger.kernel.org List-ID: On Mon, Dec 06, 2010 at 08:39:24AM -0500, Christoph Hellwig wrote: > barrier=0 really means losemydata=1. The plan I discussed with Jens was > to allow to disable the flush and fua semantics in the block layer, so > we'll have one new tunable for that, which is documented to causes these > issues. Oh. I wasn't aware that anyone was planning to put in a tuning knob for flush/fua, red warning light or otherwise. What is the name of the tunable, and when will it appear? Or has it already? > > picks the safe option by default. However, I'd prefer /proc/mounts not > > misrepresent the status of flush support, to the best of ext4's knowledge. > > That's bullshit. The barrier option has traditionally meant that we Well then, let's remove the barrier= mount flag altogether. No need for strong language over a minor issue. :) When I see some patches I will push this through my testing setup and report back what data I collect. --D > sent barrier requests, and now means thatwe send flush+fua requests. > There's no reason for a warning and option mislabling just because you > got the most efficient implementation of it.