Re: why xfs_write() race with O

xfs

Re: why xfs_write() race with O_DIRECT only?

To:	Curtis Doty <Curtis@xxxxxxxxxxxx>
Subject:	Re: why xfs_write() race with O_DIRECT only?
From:	Christoph Hellwig <hch@xxxxxxxxxxxxx>
Date:	Mon, 6 Apr 2009 13:38:55 -0400
Cc:	XFS <xfs@xxxxxxxxxxx>
In-reply-to:	<49CD7912.6080508@xxxxxxxxxxxx>
References:	<49CD7912.6080508@xxxxxxxxxxxx>
User-agent:	Mutt/1.5.18 (2008-05-17)

On Fri, Mar 27, 2009 at 06:10:42PM -0700, Curtis Doty wrote:
> I'm guessing this is the race fixed in 2.6.29.
> http://git.kernel.org/?p=linux/kernel/git/torvalds/linux-2.6.git;a=commit;h=25051158
> 
> But my app is running O_DIRECT and only calls pwrite(). Is there
> something I'm missing that explains the aio stuff etc.?

The aboe patch only matters when using dmapi.  Can you send a simple
sample program or other kind of testcases that reproduces the bug that
you see?

[More with this subject...]

<Prev in Thread]	Current Thread	[Next in Thread>
Re: why xfs_write() race with O_DIRECT only?, Curtis Doty Re: why xfs_write() race with O_DIRECT only?, Christoph Hellwig <=

Previous by Date:	Re: [PATCH] xfstests: fix async io error handling in fsx, Christoph Hellwig
Next by Date:	Re: xfs_trans_log_inode: OOPS in 2.6.28.7, Christoph Hellwig
Previous by Thread:	Re: why xfs_write() race with O_DIRECT only?, Curtis Doty
Next by Thread:	Re: [PATCH] xfs: validate quota log items during log recovery, Arkadiusz Miskiewicz
Indexes:	[Date] [Thread] [Top] [All Lists]