From: Christoph Hellwig Subject: Re: [PATCH] ext4: Set barrier=0 when block device does not advertise flush support Date: Mon, 6 Dec 2010 08:39:24 -0500 Message-ID: <20101206133924.GB9235@infradead.org> References: <20101203001659.GI18195@tux1.beaverton.ibm.com> <20101203070950.GA19071@infradead.org> <20101203091445.GK18195@tux1.beaverton.ibm.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Christoph Hellwig , Theodore Ts'o , linux-kernel , linux-ext4 To: "Darrick J. Wong" Return-path: Received: from bombadil.infradead.org ([18.85.46.34]:56470 "EHLO bombadil.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751560Ab0LFNj1 (ORCPT ); Mon, 6 Dec 2010 08:39:27 -0500 Content-Disposition: inline In-Reply-To: <20101203091445.GK18195@tux1.beaverton.ibm.com> Sender: linux-ext4-owner@vger.kernel.org List-ID: 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. > 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 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.