Re: [RFC][PATCH 01/16] writeback: do not self-wakeup

From: Artem Bityutskiy
Date: Sun Jul 18 2010 - 05:43:21 EST


On Sun, 2010-07-18 at 02:44 -0400, Christoph Hellwig wrote:
> On Fri, Jul 16, 2010 at 03:44:57PM +0300, Artem Bityutskiy wrote:
> > From: Artem Bityutskiy <Artem.Bityutskiy@xxxxxxxxx>
> >
> > The bdi forker thread wakes up itself via 'bdi_add_to_pending()'.
> > And the thread is the only user of 'bdi_add_to_pending()'. Thus,
> > we can safely zap the unneeded 'wake_up_process()' call.
>
> At least right now it's called using call_rcu, which offloads the function
> to a RCU thread of some sorts.

Christoph, thanks for your review. I'll amend my series and re-send. And
I also have to think about some of your suggestions.

I did not CC you to spam your mailbox less, since I'm sure you would not
miss the series in the fsdevel ML. But if you prefer being CCed, let me
know.

--
Best Regards,
Artem Bityutskiy (ÐÑÑÑÐ ÐÐÑÑÑÐÐÐ)

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/