Date: Tue, 19 May 2015 10:43:44 -0700
From: Jaegeuk Kim <jaegeuk@kernel.org>
To: Chao Yu <chao2.yu@samsung.com>
Cc: "'Changman Lee'" <cm224.lee@samsung.com>,
        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
Content-Length: 2708
Lines: 70

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,
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/