[Top] [All Lists]

Re: [PATCH 3/9] xfs: factor out everything but the filemap_write_and_wai

To: "Darrick J. Wong" <darrick.wong@xxxxxxxxxx>
Subject: Re: [PATCH 3/9] xfs: factor out everything but the filemap_write_and_wait from xfs_file_fsync
From: Christoph Hellwig <hch@xxxxxxxxxxxxx>
Date: Wed, 21 Nov 2012 05:09:13 -0500
Cc: axboe@xxxxxxxxx, tytso@xxxxxxx, david@xxxxxxxxxxxxx, jmoyer@xxxxxxxxxx, bpm@xxxxxxx, viro@xxxxxxxxxxxxxxxxxx, jack@xxxxxxx, linux-fsdevel@xxxxxxxxxxxxxxx, hch@xxxxxxxxxxxxx, linux-ext4@xxxxxxxxxxxxxxx, linux-kernel@xxxxxxxxxxxxxxx, xfs@xxxxxxxxxxx
In-reply-to: <20121120074138.24645.36708.stgit@xxxxxxxxxxxxxxxxxxx>
References: <20121120074116.24645.36369.stgit@xxxxxxxxxxxxxxxxxxx> <20121120074138.24645.36708.stgit@xxxxxxxxxxxxxxxxxxx>
User-agent: Mutt/1.5.21 (2010-09-15)
On Mon, Nov 19, 2012 at 11:41:38PM -0800, Darrick J. Wong wrote:
> Hi,
> Fsyncing is tricky business, so factor out the bits of the xfs_file_fsync
> function that can be used from the I/O post-processing path.

Why would we need to skip the filemap_write_and_wait_range call here?
If we're doing direct I/O we should not have any pages in this regions
anyway.  You're also not skipping it in the generic implementation as
far as I can see, so I see no point in doing it just in XFS.

<Prev in Thread] Current Thread [Next in Thread>