Re: [PATCH RFC tip/core/rcu 2/9] rcu: Provide cond_resched_rcu_qs() to force quiescent states in long loops

["Paul E. McKenney" <paulmck@linux.vnet.ibm.com>]

On Tue, Jul 29, 2014 at 07:37:33PM +0200, Peter Zijlstra wrote:
> On Tue, Jul 29, 2014 at 07:36:00PM +0200, Peter Zijlstra wrote:
> > On Tue, Jul 29, 2014 at 10:33:18AM -0700, Paul E. McKenney wrote:
> > > > No, but why can't we make the regular cond_resched() do this?
> > > 
> > > Well, I got a lot of grief when I tried it a few weeks ago.
> > > 
> > > But from what I can see, you are the maintainer or cond_resched(), so
> > > if you are good with making the normal cond_resched() do this, I am
> > > more than happy to make it so!  ;-)
> > 
> > Well, its the 'obvious' thing to do. But clearly I haven't tried so I'm
> > blissfully unaware of any problems. And the Changelog didn't inform me
> > either (you had a link in there, which I didn't read :-)
> 
> Then again, last time we touched cond_resched() we had a scalability
> issue or somesuch, or am I misremembering things?

More overhead than scalability, but yes.  That said, that was a much
heavier weight touch.  A later version with only an access to per-CPU
variable turned out to have overhead below what could be measured.
But I am comfortable with the current approach that does not touch
cond_resched() as well.

							Thanx, Paul