Re: [PATCH] Force rcutorture tasks to spread over CPUs

2007-06-27 Thread Paul E. McKenney
On Wed, Jun 27, 2007 at 08:30:55AM +0200, Ingo Molnar wrote: > > * Andrew Morton <[EMAIL PROTECTED]> wrote: > > > On Tue, 12 Jun 2007 21:28:04 -0700 > > "Paul E. McKenney" <[EMAIL PROTECTED]> wrote: > > > > > + while (!startwriters) > > > + barrier(); /* Force scheduler to spread

Re: [PATCH] Force rcutorture tasks to spread over CPUs

2007-06-27 Thread Ingo Molnar
* Andrew Morton <[EMAIL PROTECTED]> wrote: > On Tue, 12 Jun 2007 21:28:04 -0700 > "Paul E. McKenney" <[EMAIL PROTECTED]> wrote: > > > + while (!startwriters) > > + barrier(); /* Force scheduler to spread over CPUs. */ > > one wonders whether a cpu_relax() would be a bit nicer

Re: [PATCH] Force rcutorture tasks to spread over CPUs

2007-06-27 Thread Ingo Molnar
* Andrew Morton [EMAIL PROTECTED] wrote: On Tue, 12 Jun 2007 21:28:04 -0700 Paul E. McKenney [EMAIL PROTECTED] wrote: + while (!startwriters) + barrier(); /* Force scheduler to spread over CPUs. */ one wonders whether a cpu_relax() would be a bit nicer here. That

Re: [PATCH] Force rcutorture tasks to spread over CPUs

2007-06-27 Thread Paul E. McKenney
On Wed, Jun 27, 2007 at 08:30:55AM +0200, Ingo Molnar wrote: * Andrew Morton [EMAIL PROTECTED] wrote: On Tue, 12 Jun 2007 21:28:04 -0700 Paul E. McKenney [EMAIL PROTECTED] wrote: + while (!startwriters) + barrier(); /* Force scheduler to spread over CPUs. */ one

Re: [PATCH] Force rcutorture tasks to spread over CPUs

2007-06-26 Thread Andrew Morton
On Tue, 12 Jun 2007 21:28:04 -0700 "Paul E. McKenney" <[EMAIL PROTECTED]> wrote: > + while (!startwriters) > + barrier(); /* Force scheduler to spread over CPUs. */ one wonders whether a cpu_relax() would be a bit nicer here. That implicitly does a barrier(). This patch

Re: [PATCH] Force rcutorture tasks to spread over CPUs

2007-06-26 Thread Andrew Morton
On Tue, 12 Jun 2007 21:28:04 -0700 Paul E. McKenney [EMAIL PROTECTED] wrote: + while (!startwriters) + barrier(); /* Force scheduler to spread over CPUs. */ one wonders whether a cpu_relax() would be a bit nicer here. That implicitly does a barrier(). This patch doesn't

Re: [PATCH] Force rcutorture tasks to spread over CPUs

2007-06-13 Thread Josh Triplett
Paul E. McKenney wrote: > Of late, the scheduler seems to have decided to make things too easy for > RCU -- on some configurations, all of the rcutorture tasks end up on the > same CPU, which doesn't do a very good job of torturing RCU. This patch > helps the scheduler spread these tasks out by

Re: [PATCH] Force rcutorture tasks to spread over CPUs

2007-06-13 Thread Josh Triplett
Paul E. McKenney wrote: Of late, the scheduler seems to have decided to make things too easy for RCU -- on some configurations, all of the rcutorture tasks end up on the same CPU, which doesn't do a very good job of torturing RCU. This patch helps the scheduler spread these tasks out by

[PATCH] Force rcutorture tasks to spread over CPUs

2007-06-12 Thread Paul E. McKenney
Of late, the scheduler seems to have decided to make things too easy for RCU -- on some configurations, all of the rcutorture tasks end up on the same CPU, which doesn't do a very good job of torturing RCU. This patch helps the scheduler spread these tasks out by forcing a 20-millisecond burst of

[PATCH] Force rcutorture tasks to spread over CPUs

2007-06-12 Thread Paul E. McKenney
Of late, the scheduler seems to have decided to make things too easy for RCU -- on some configurations, all of the rcutorture tasks end up on the same CPU, which doesn't do a very good job of torturing RCU. This patch helps the scheduler spread these tasks out by forcing a 20-millisecond burst of