Re: [regression, 3.16-rc] rwsem: optimistic spinning causing performance degradation

[Dave Chinner <david@fromorbit.com>]

On Fri, Jul 04, 2014 at 12:06:19AM -0700, Jason Low wrote:
> On Fri, 2014-07-04 at 16:13 +1000, Dave Chinner wrote:
> > On Thu, Jul 03, 2014 at 06:54:50PM -0700, Jason Low wrote:
> > > On Thu, 2014-07-03 at 18:46 -0700, Jason Low wrote:
> > > > On Fri, 2014-07-04 at 11:01 +1000, Dave Chinner wrote:
> > > 
> > > > > FWIW, the rwsems in the struct xfs_inode are often heavily
> > > > > read/write contended, so there are lots of IO related workloads that
> > > > > are going to regress on XFS without this optimisation...
> > > > > 
> > > > > Anyway, consider the patch:
> > > > > 
> > > > > Tested-by: Dave Chinner <dchinner@redhat.com>
> > > > 
> > > > Hi Dave,
> > > > 
> > > > Thanks for testing. I'll update the patch with an actual changelog.
> > > 
> > > ---
> > > Subject: [PATCH] rwsem: In rwsem_can_spin_on_owner(), return false if no owner
> > > 
> > > It was found that the rwsem optimistic spinning feature can potentially degrade
> > > performance when there are readers. Perf profiles indicate in some workloads
> > > that significant time can be spent spinning on !owner. This is because we don't
> > > set the lock owner when readers(s) obtain the rwsem.
> > 
> > I don't think you're being a little shifty with the truth here.
> > There's no "potentially degrade performance" here - I reported a
> > massive real world performance regression caused by optimistic
> > spinning.
> 
> Sure, though I mainly used the word "potentially" since there can be
> other workloads out there where spinning even when readers have the lock
> is a positive thing.
> 
> And agreed that the changelog can be modified to try reflecting more on
> it being a "regression fix" then a "new performance" addition.
> 
> So how about the following?

Looks good. Thanks!

-Dave.
-- 
Dave Chinner
david@fromorbit.com