All of lore.kernel.org
 help / color / mirror / Atom feed
From: Brian Foster <bfoster@redhat.com>
To: Christoph Hellwig <hch@lst.de>
Cc: rpeterso@redhat.com, linux-fsdevel@vger.kernel.org, xfs@oss.sgi.com
Subject: Re: [PATCH 5/8] xfs: implement iomap based buffered write path
Date: Tue, 3 May 2016 11:02:19 -0400	[thread overview]
Message-ID: <20160503150217.GA8014@bfoster.bfoster> (raw)
In-Reply-To: <20160502182523.GB7077@lst.de>

On Mon, May 02, 2016 at 08:25:23PM +0200, Christoph Hellwig wrote:
> On Thu, Apr 14, 2016 at 08:58:14AM -0400, Brian Foster wrote:
> > > +static int
> > > +xfs_file_iomap_end_delalloc(
> > > +	struct xfs_inode	*ip,
> > > +	loff_t			offset,
> > > +	loff_t			length,
> > > +	ssize_t			written)
> > > +{
> > > +	struct xfs_mount	*mp = ip->i_mount;
> > > +	xfs_fileoff_t		start_fsb;
> > > +	xfs_fileoff_t		end_fsb;
> > > +	int			error = 0;
> > > +
> > > +	start_fsb = XFS_B_TO_FSB(mp, offset + written);
> > > +	end_fsb = XFS_B_TO_FSB(mp, offset + length - written);
> > > +
> > 
> > Just skimming over this series... but shouldn't this be offset + length?
> > Why walk back from the end of the allocated range?
> 
> Because the interface from the core iomap code need to pass the
> length of the actually mapped range, and the amount of bytes successfully
> written into it to the filesystem, as other filesystems will require
> this for their locking.  We need to convert it back at some point,
> and it seems more logical here than in the caller.
> 

I'm not asking about the interface... or at least I'm not following your
point. I'm just suggesting that the calculation of end_fsb is wrong.
E.g., if the intent is to punch out the range that was allocated but not
written to, shouldn't the range to punch be [offset + written, offset +
length]?

Brian

> _______________________________________________
> xfs mailing list
> xfs@oss.sgi.com
> http://oss.sgi.com/mailman/listinfo/xfs

_______________________________________________
xfs mailing list
xfs@oss.sgi.com
http://oss.sgi.com/mailman/listinfo/xfs

WARNING: multiple messages have this Message-ID (diff)
From: Brian Foster <bfoster@redhat.com>
To: Christoph Hellwig <hch@lst.de>
Cc: rpeterso@redhat.com, linux-fsdevel@vger.kernel.org, xfs@oss.sgi.com
Subject: Re: [PATCH 5/8] xfs: implement iomap based buffered write path
Date: Tue, 3 May 2016 11:02:19 -0400	[thread overview]
Message-ID: <20160503150217.GA8014@bfoster.bfoster> (raw)
In-Reply-To: <20160502182523.GB7077@lst.de>

On Mon, May 02, 2016 at 08:25:23PM +0200, Christoph Hellwig wrote:
> On Thu, Apr 14, 2016 at 08:58:14AM -0400, Brian Foster wrote:
> > > +static int
> > > +xfs_file_iomap_end_delalloc(
> > > +	struct xfs_inode	*ip,
> > > +	loff_t			offset,
> > > +	loff_t			length,
> > > +	ssize_t			written)
> > > +{
> > > +	struct xfs_mount	*mp = ip->i_mount;
> > > +	xfs_fileoff_t		start_fsb;
> > > +	xfs_fileoff_t		end_fsb;
> > > +	int			error = 0;
> > > +
> > > +	start_fsb = XFS_B_TO_FSB(mp, offset + written);
> > > +	end_fsb = XFS_B_TO_FSB(mp, offset + length - written);
> > > +
> > 
> > Just skimming over this series... but shouldn't this be offset + length?
> > Why walk back from the end of the allocated range?
> 
> Because the interface from the core iomap code need to pass the
> length of the actually mapped range, and the amount of bytes successfully
> written into it to the filesystem, as other filesystems will require
> this for their locking.  We need to convert it back at some point,
> and it seems more logical here than in the caller.
> 

I'm not asking about the interface... or at least I'm not following your
point. I'm just suggesting that the calculation of end_fsb is wrong.
E.g., if the intent is to punch out the range that was allocated but not
written to, shouldn't the range to punch be [offset + written, offset +
length]?

Brian

> _______________________________________________
> xfs mailing list
> xfs@oss.sgi.com
> http://oss.sgi.com/mailman/listinfo/xfs

  reply	other threads:[~2016-05-03 15:02 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-04-12 20:52 iomap infrastructure and multipage writes V2 Christoph Hellwig
2016-04-12 20:52 ` Christoph Hellwig
2016-04-12 20:52 ` [PATCH 1/8] fs: move struct iomap from exportfs.h to a separate header Christoph Hellwig
2016-04-12 20:52   ` Christoph Hellwig
2016-04-12 20:52 ` [PATCH 2/8] fs: introduce iomap infrastructure Christoph Hellwig
2016-04-12 20:52   ` Christoph Hellwig
2016-04-12 20:52 ` [PATCH 3/8] xfs: make xfs_bmbt_to_iomap available outside of xfs_pnfs.c Christoph Hellwig
2016-04-12 20:52   ` Christoph Hellwig
2016-04-12 20:52 ` [PATCH 4/8] xfs: reorder zeroing and flushing sequence in truncate Christoph Hellwig
2016-04-12 20:52   ` Christoph Hellwig
2016-04-12 20:52 ` [PATCH 5/8] xfs: implement iomap based buffered write path Christoph Hellwig
2016-04-12 20:52   ` Christoph Hellwig
2016-04-14 12:58   ` Brian Foster
2016-04-14 12:58     ` Brian Foster
2016-05-02 18:25     ` Christoph Hellwig
2016-05-02 18:25       ` Christoph Hellwig
2016-05-03 15:02       ` Brian Foster [this message]
2016-05-03 15:02         ` Brian Foster
2016-05-03 18:15         ` Christoph Hellwig
2016-05-03 18:15           ` Christoph Hellwig
2016-04-12 20:53 ` [PATCH 6/8] xfs: remove buffered write support from __xfs_get_blocks Christoph Hellwig
2016-04-12 20:53   ` Christoph Hellwig
2016-04-12 20:53 ` [PATCH 7/8] fs: iomap based fiemap implementation Christoph Hellwig
2016-04-12 20:53   ` Christoph Hellwig
2016-04-12 20:53 ` [PATCH 8/8] xfs: use iomap " Christoph Hellwig
2016-04-12 20:53   ` Christoph Hellwig
2016-04-13 21:54 ` iomap infrastructure and multipage writes V2 Dave Chinner
2016-04-13 21:54   ` Dave Chinner
2016-05-02 18:23   ` Christoph Hellwig
2016-05-02 18:23     ` Christoph Hellwig

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20160503150217.GA8014@bfoster.bfoster \
    --to=bfoster@redhat.com \
    --cc=hch@lst.de \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=rpeterso@redhat.com \
    --cc=xfs@oss.sgi.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.