Messages in this thread | | | Date | Tue, 29 Jul 2014 10:55:52 -0700 | From | "Paul E. McKenney" <> | Subject | Re: [PATCH RFC tip/core/rcu 2/9] rcu: Provide cond_resched_rcu_qs() to force quiescent states in long loops |
| |
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
| |