From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from bombadil.infradead.org ([198.137.202.133]:43094 "EHLO bombadil.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1729992AbeIRVCo (ORCPT ); Tue, 18 Sep 2018 17:02:44 -0400 Date: Tue, 18 Sep 2018 08:29:35 -0700 From: Christoph Hellwig Subject: Re: dm-writecache issue Message-ID: <20180918152935.GA13016@infradead.org> References: <20180918123238.GI27618@dastard> <817349b8-b54e-a16a-276f-7a977f29b449@sandeen.net> <8975ad6d-bfde-0a50-e60c-59228493f1b2@sandeen.net> <128a77fc-dbcb-278f-115c-da4a3d63e58f@sandeen.net> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <128a77fc-dbcb-278f-115c-da4a3d63e58f@sandeen.net> Sender: linux-xfs-owner@vger.kernel.org List-ID: List-Id: xfs To: Eric Sandeen Cc: Mikulas Patocka , Dave Chinner , "Darrick J. Wong" , linux-xfs@vger.kernel.org, David Teigland On Tue, Sep 18, 2018 at 10:27:20AM -0500, Eric Sandeen wrote: > (this may be a bit uninformed on my part, Darrick reminds me that jbd2's > careful use of cache flushing & FUA probably means that it won't get burned > by a partial 4k metadata update if the power fails.) cache flushing and FUA is never going to help you with torn writes. > > I'll stop for now and see if Dave wants to chime in on xfs's reliance on > the actual atomic IO size for metadata IO. ;) What helps todays XFS (and probably ext4) is checksums on all metadata blocks, as that way we can check if we wrote the full "block". This doesn't help applications that rely on the sector size unless they have similar protections of their own.