From mboxrd@z Thu Jan  1 00:00:00 1970
From: Christoph Hellwig <hch@infradead.org>
Date: Wed, 16 Nov 2011 11:16:12 -0500
Subject: [Cluster-devel] fallocate vs O_(D)SYNC
In-Reply-To: <20111116155755.GA22284@quack.suse.cz>
References: <20111116084256.GA22963@infradead.org>
	<1321436588.2713.5.camel@menhir>
	<20111116105413.GA2916@quack.suse.cz>
	<20111116124550.GA11650@infradead.org>
	<20111116133915.GD8195@quack.suse.cz>
	<20111116134234.GA24258@infradead.org>
	<20111116155755.GA22284@quack.suse.cz>
Message-ID: <20111116161612.GA17008@infradead.org>
List-Id: <cluster-devel.redhat.com>
To: cluster-devel.redhat.com
MIME-Version: 1.0
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: 7bit

On Wed, Nov 16, 2011 at 04:57:55PM +0100, Jan Kara wrote:
>   I agree with you that userspace shouldn't have to call fsync. What I
> meant is that sys_fallocate() or do_fallocate() can call
> generic_write_sync(file, pos, len), and that would be completely
> transparent to userspace.

That's different from how everything else in the I/O path works.
If filessystem want to use it, that's fine, but I suspect most could
do it more efficiently.