xfs
[Top] [All Lists]

Re: [PATCH, RFC] Move AIL pushing into a separate thread

To: Lachlan McIlroy <lachlan@xxxxxxx>
Subject: Re: [PATCH, RFC] Move AIL pushing into a separate thread
From: David Chinner <dgc@xxxxxxx>
Date: Fri, 9 Nov 2007 14:16:55 +1100
Cc: David Chinner <dgc@xxxxxxx>, xfs-oss <xfs@xxxxxxxxxxx>, xfs-dev <xfs-dev@xxxxxxx>
In-reply-to: <4733AB27.70208@sgi.com>
References: <20071105050706.GW66820511@sgi.com> <4733AB27.70208@sgi.com>
Sender: xfs-bounce@xxxxxxxxxxx
User-agent: Mutt/1.4.2.1i
On Fri, Nov 09, 2007 at 11:34:47AM +1100, Lachlan McIlroy wrote:
> I like the sound of this Dave.  I'm still going through the code in
> detail.
> 
> Could we convert the ail lock into a mutex to ease the load?  I know
> it may not improve throughput but it would at least relieve the CPUs
> to do other stuff.

Most of the time the ail lock is used for very short periods of
time, (e.g.  less than ten lines of code) so a spin lock is
appropriate. What we are seeing here is too many CPUs holding it for
to long trying to do the work one CPU could easily do.

i.e. the bug we are seeing here is the contention on the lock, not
the type of lock. If we change to a sleeping lock, all ppl will see
is a slowdown and that is much, much harder to diagnose on a
production system than spin lock contention....

Cheers,

Dave.
-- 
Dave Chinner
Principal Engineer
SGI Australian Software Group


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