On Tue, May 19, 2015 at 05:36:11PM +0800, Chao Yu wrote: > Hi Jaegeuk, > > > -----Original Message----- > > From: Jaegeuk Kim [mailto:jaeg...@kernel.org] > > Sent: Tuesday, May 19, 2015 1:51 PM > > To: Chao Yu > > Cc: Changman Lee; linux-f2fs-de...@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, -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
