From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756065AbbESRnx (ORCPT ); Tue, 19 May 2015 13:43:53 -0400 Received: from mail.kernel.org ([198.145.29.136]:57104 "EHLO mail.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756022AbbESRnt (ORCPT ); Tue, 19 May 2015 13:43:49 -0400 Date: Tue, 19 May 2015 10:43:44 -0700 From: Jaegeuk Kim To: Chao Yu Cc: "'Changman Lee'" , linux-f2fs-devel@lists.sourceforge.net, linux-kernel@vger.kernel.org Subject: Re: [PATCH 1/2] f2fs: support RENAME_WHITEOUT Message-ID: <20150519174344.GB42970@jaegeuk-mac02.mot.com> References: <002e01d0912f$30fc5cc0$92f51640$@samsung.com> <20150519055119.GA39478@jaegeuk-mac02.hsd1.ca.comcast.net> <005b01d09217$58302e00$08908a00$@samsung.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <005b01d09217$58302e00$08908a00$@samsung.com> 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 Tue, May 19, 2015 at 05:36:11PM +0800, Chao Yu wrote: > Hi Jaegeuk, > > > -----Original Message----- > > From: Jaegeuk Kim [mailto:jaegeuk@kernel.org] > > Sent: Tuesday, May 19, 2015 1:51 PM > > To: Chao Yu > > Cc: Changman Lee; linux-f2fs-devel@lists.sourceforge.net; linux-kernel@vger.kernel.org > > Subject: Re: [PATCH 1/2] f2fs: support RENAME_WHITEOUT > > > > Hi Chao, > > > > On Mon, May 18, 2015 at 01:54:22PM +0800, Chao Yu wrote: > > > As the description of rename in manual, RENAME_WHITEOUT is a special operation > > > that only makes sense for overlay/union type filesystem. > > > > > > When performing rename with RENAME_WHITEOUT, dst will be replace with src, and > > > meanwhile, a 'whiteout' will be create with name of src. > > > > > > A "whiteout" is designed to be a char device with 0,0 device number, it has > > > specially meaning for stackable filesystem. In these filesystems, there are > > > multiple layers exist, and only top of these can be modified. So a whiteout > > > in top layer is used to hide a corresponding file in lower layer, as well > > > removal of whiteout will make the file appear. > > > > > > Now in overlayfs, when we rename a file which is exist in lower layer, it > > > will be copied up to upper if it is not on upper layer yet, and then rename > > > it on upper layer, source file will be whiteouted to hide corresponding file > > > in lower layer at the same time. > > > > > > So in upper layer filesystem, implementation of RENAME_WHITEOUT provide a > > > atomic operation for stackable filesystem to support rename operation. > > > > > > There are multiple ways to implement RENAME_WHITEOUT in log of this commit: > > > 7dcf5c3e4527 ("xfs: add RENAME_WHITEOUT support") which pointed out by > > > Dave Chinner. > > > > > > For now, we just try to follow the way that xfs/ext4 use. > > > > Could you merge the two patches into one? > > OK. > > > And, after finishing xfstests, kernel reports missing inode objects. > > Do you mean this? > > BUG f2fs_inode_cache (Tainted: G B O ): > Objects remaining in f2fs_inode_cache on kmem_cache_close() > > Whenever rmmod f2fs module after tests/generic/078, system report this. Right. :) > > > Could you check it out? > > I find that the whiteout file is not be iput() after being linkated to > an entry. After fixing this issue, no exceptional report appears again. > > So can you please help to test the v2 patch? Great. Will do. Thanks,