Re: [PATCH tip/core/rcu 0/5] Fix for cond_resched performance regression

2014-06-20 Thread Paul E. McKenney
On Fri, Jun 20, 2014 at 05:14:18PM -0700, Paul E. McKenney wrote: > On Fri, Jun 20, 2014 at 04:52:15PM -0700, j...@joshtriplett.org wrote: > > On Fri, Jun 20, 2014 at 04:30:33PM -0700, Paul E. McKenney wrote: > > > On Fri, Jun 20, 2014 at 03:39:51PM -0700, j...@joshtriplett.org wrote: > > > > On Fr

Re: [PATCH tip/core/rcu 0/5] Fix for cond_resched performance regression

2014-06-20 Thread Paul E. McKenney
On Fri, Jun 20, 2014 at 04:52:15PM -0700, j...@joshtriplett.org wrote: > On Fri, Jun 20, 2014 at 04:30:33PM -0700, Paul E. McKenney wrote: > > On Fri, Jun 20, 2014 at 03:39:51PM -0700, j...@joshtriplett.org wrote: > > > On Fri, Jun 20, 2014 at 03:11:20PM -0700, Paul E. McKenney wrote: > > > > On Fr

Re: [PATCH tip/core/rcu 0/5] Fix for cond_resched performance regression

2014-06-20 Thread josh
On Fri, Jun 20, 2014 at 04:30:33PM -0700, Paul E. McKenney wrote: > On Fri, Jun 20, 2014 at 03:39:51PM -0700, j...@joshtriplett.org wrote: > > On Fri, Jun 20, 2014 at 03:11:20PM -0700, Paul E. McKenney wrote: > > > On Fri, Jun 20, 2014 at 02:24:23PM -0700, j...@joshtriplett.org wrote: > > > > On Fr

Re: [PATCH tip/core/rcu 0/5] Fix for cond_resched performance regression

2014-06-20 Thread Paul E. McKenney
On Fri, Jun 20, 2014 at 03:39:51PM -0700, j...@joshtriplett.org wrote: > On Fri, Jun 20, 2014 at 03:11:20PM -0700, Paul E. McKenney wrote: > > On Fri, Jun 20, 2014 at 02:24:23PM -0700, j...@joshtriplett.org wrote: > > > On Fri, Jun 20, 2014 at 12:12:36PM -0700, Paul E. McKenney wrote: > > > > o

Re: [PATCH tip/core/rcu 0/5] Fix for cond_resched performance regression

2014-06-20 Thread josh
On Fri, Jun 20, 2014 at 03:11:20PM -0700, Paul E. McKenney wrote: > On Fri, Jun 20, 2014 at 02:24:23PM -0700, j...@joshtriplett.org wrote: > > On Fri, Jun 20, 2014 at 12:12:36PM -0700, Paul E. McKenney wrote: > > > o Make cond_resched() a no-op for PREEMPT=y. This might well turn > > > out to be

Re: [PATCH tip/core/rcu 0/5] Fix for cond_resched performance regression

2014-06-20 Thread Paul E. McKenney
On Fri, Jun 20, 2014 at 02:24:23PM -0700, j...@joshtriplett.org wrote: > On Fri, Jun 20, 2014 at 12:12:36PM -0700, Paul E. McKenney wrote: > > o Make cond_resched() a no-op for PREEMPT=y. This might well turn > > out to be a good thing, but it doesn't help give RCU the quiescent > > stat

Re: [PATCH tip/core/rcu 0/5] Fix for cond_resched performance regression

2014-06-20 Thread Paul E. McKenney
On Fri, Jun 20, 2014 at 12:04:34PM -0700, j...@joshtriplett.org wrote: > On Fri, Jun 20, 2014 at 11:32:49AM -0700, Paul E. McKenney wrote: > > Hello! > > > > This series contains changes to address the performance regressions > > introduced by commit ac1bea85781e (Make cond_resched() report RCU >

Re: [PATCH tip/core/rcu 0/5] Fix for cond_resched performance regression

2014-06-20 Thread josh
On Fri, Jun 20, 2014 at 12:12:36PM -0700, Paul E. McKenney wrote: > o Make cond_resched() a no-op for PREEMPT=y. This might well turn > out to be a good thing, but it doesn't help give RCU the quiescent > states that it needs. What about doing this, together with letting the fqs l

Re: [PATCH tip/core/rcu 0/5] Fix for cond_resched performance regression

2014-06-20 Thread Paul E. McKenney
On Fri, Jun 20, 2014 at 11:32:49AM -0700, Paul E. McKenney wrote: > Hello! > > This series contains changes to address the performance regressions > introduced by commit ac1bea85781e (Make cond_resched() report RCU > quiescent states), which was in turn fixing a problem where tasks looping > in th

Re: [PATCH tip/core/rcu 0/5] Fix for cond_resched performance regression

2014-06-20 Thread josh
On Fri, Jun 20, 2014 at 11:32:49AM -0700, Paul E. McKenney wrote: > Hello! > > This series contains changes to address the performance regressions > introduced by commit ac1bea85781e (Make cond_resched() report RCU > quiescent states), which was in turn fixing a problem where tasks looping > in th

[PATCH tip/core/rcu 0/5] Fix for cond_resched performance regression

2014-06-20 Thread Paul E. McKenney
Hello! This series contains changes to address the performance regressions introduced by commit ac1bea85781e (Make cond_resched() report RCU quiescent states), which was in turn fixing a problem where tasks looping in the kernel could delay RCU grace periods. The changes in this series are as fol