[Samba] 2.6.31-rc8: CIFS with 5 seconds hiccups

[Jeff Layton]

On Wed, 9 Sep 2009 13:28:24 -0400 (EDT)
Christoph Lameter <cl at linux-foundation.org> wrote:

> On Wed, 9 Sep 2009, Jeff Layton wrote:
> 
> > That'll stop your client from requesting oplocks, but that won't
> > prevent others from doing so. If my suspicion is correct, then another
> > client is holding an oplock and the server needs to break it before it
> > can reply to yours.
> >
> > Unfortunately I doubt there's much you can do from your client to
> > prevent that (if that is the case). There may be a way to turn off
> > oplocks on the server side, but that may very well be even worse for
> > performance.
> 
> Hmmm... We can look at that.
> 
> Another interesting tidbit is that I have never seen this from a 64 bit
> Linux kernel. Only occurs with 32 bit kernels it seems.
> 

That sounds rather strange. Maybe we do have a bug of some sort? The
thing to do might be to get a binary capture of the 32-bit traffic
around the time of the stalls. We could then inspect the packets and
see whether we have something wrong in there.

-- 
Jeff Layton <jlayton at redhat.com>