Re: [PATCH tip/core/rcu 19/19] rcu: Add fastpath bypassing funnel locking

2015-08-03 Thread Peter Zijlstra
On Mon, Aug 03, 2015 at 04:05:33PM -0400, Steven Rostedt wrote: > On Thu, 30 Jul 2015 17:40:01 +0200 > Peter Zijlstra wrote: > > > On Thu, Jul 30, 2015 at 08:34:52AM -0700, Paul E. McKenney wrote: > > > > If the extra read before the cmpxchg() does not hurt, we should do the > > > > same for mute

Re: [PATCH tip/core/rcu 19/19] rcu: Add fastpath bypassing funnel locking

2015-08-03 Thread Steven Rostedt
On Thu, 30 Jul 2015 17:40:01 +0200 Peter Zijlstra wrote: > On Thu, Jul 30, 2015 at 08:34:52AM -0700, Paul E. McKenney wrote: > > > If the extra read before the cmpxchg() does not hurt, we should do the > > > same for mutex and make the above redundant. > > > > I am pretty sure that different har

Re: [PATCH tip/core/rcu 19/19] rcu: Add fastpath bypassing funnel locking

2015-07-31 Thread Paul E. McKenney
On Thu, Jul 30, 2015 at 06:34:27PM +0200, Peter Zijlstra wrote: > On Thu, Jul 30, 2015 at 08:34:52AM -0700, Paul E. McKenney wrote: > > On Thu, Jul 30, 2015 at 04:44:55PM +0200, Peter Zijlstra wrote: > > > > If the extra read before the cmpxchg() does not hurt, we should do the > > > same for mute

Re: [PATCH tip/core/rcu 19/19] rcu: Add fastpath bypassing funnel locking

2015-07-30 Thread Waiman Long
On 07/30/2015 10:44 AM, Peter Zijlstra wrote: On Fri, Jul 17, 2015 at 04:29:24PM -0700, Paul E. McKenney wrote: /* +* First try directly acquiring the root lock in order to reduce +* latency in the common case where expedited grace periods are +* rare. We check

Re: [PATCH tip/core/rcu 19/19] rcu: Add fastpath bypassing funnel locking

2015-07-30 Thread Peter Zijlstra
On Thu, Jul 30, 2015 at 08:34:52AM -0700, Paul E. McKenney wrote: > On Thu, Jul 30, 2015 at 04:44:55PM +0200, Peter Zijlstra wrote: > > If the extra read before the cmpxchg() does not hurt, we should do the > > same for mutex and make the above redundant. > > I am pretty sure that different hardw

Re: [PATCH tip/core/rcu 19/19] rcu: Add fastpath bypassing funnel locking

2015-07-30 Thread Peter Zijlstra
On Thu, Jul 30, 2015 at 08:34:52AM -0700, Paul E. McKenney wrote: > > If the extra read before the cmpxchg() does not hurt, we should do the > > same for mutex and make the above redundant. > > I am pretty sure that different hardware wants it done differently. :-/ > So I agree that hard data wou

Re: [PATCH tip/core/rcu 19/19] rcu: Add fastpath bypassing funnel locking

2015-07-30 Thread Paul E. McKenney
On Thu, Jul 30, 2015 at 04:44:55PM +0200, Peter Zijlstra wrote: > On Fri, Jul 17, 2015 at 04:29:24PM -0700, Paul E. McKenney wrote: > > > /* > > +* First try directly acquiring the root lock in order to reduce > > +* latency in the common case where expedited grace periods are > > +

Re: [PATCH tip/core/rcu 19/19] rcu: Add fastpath bypassing funnel locking

2015-07-30 Thread Peter Zijlstra
On Fri, Jul 17, 2015 at 04:29:24PM -0700, Paul E. McKenney wrote: > /* > + * First try directly acquiring the root lock in order to reduce > + * latency in the common case where expedited grace periods are > + * rare. We check mutex_is_locked() to avoid pathological levels of