xfs
[Top] [All Lists]

Re: [PATCH 2/3] ext4: honor the O_SYNC flag for aysnchronous direct I/O

To: Jeff Moyer <jmoyer@xxxxxxxxxx>
Subject: Re: [PATCH 2/3] ext4: honor the O_SYNC flag for aysnchronous direct I/O requests
From: Jan Kara <jack@xxxxxxx>
Date: Mon, 6 Feb 2012 17:58:36 +0100
Cc: Jan Kara <jack@xxxxxxx>, linux-ext4@xxxxxxxxxxxxxxx, xfs@xxxxxxxxxxx, linux-fsdevel@xxxxxxxxxxxxxxx
In-reply-to: <x49bopcq6gi.fsf@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx>
References: <1327698949-12616-1-git-send-email-jmoyer@xxxxxxxxxx> <1327698949-12616-3-git-send-email-jmoyer@xxxxxxxxxx> <20120202173120.GA6640@xxxxxxxxxxxxx> <x49bopcq6gi.fsf@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx>
User-agent: Mutt/1.5.20 (2009-06-14)
On Mon 06-02-12 11:20:29, Jeff Moyer wrote:
> Jan Kara <jack@xxxxxxx> writes:
> 
> >> +  /* workqueue for aio+dio+o_sync disk cache flushing */
> >> +  struct workqueue_struct *aio_dio_flush_wq;
> >> +
> >   Hmm, looking at the patch I'm wondering why did you introduce the new
> > workqueue? It seems dio_unwritten_wq would be enough? You just need to
> > rename it to something more appropriate ;)
> 
> I used a new workqueue as the operations are blocking, and I didn't want
> to hold up other progress.  If you think re-using the unwritten_wq is
> the right thing to do, I'm happy to comply.
  Ah, ok. Thinking about it, it's probably better to use a separate work
queue then.

                                                                Honza

-- 
Jan Kara <jack@xxxxxxx>
SUSE Labs, CR

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