Messages in this thread | | | Subject | Re: [PATCH v2 1/5] mutex: In mutex_can_spin_on_owner(), return false if task need_resched() | From | Jason Low <> | Date | Tue, 28 Jan 2014 14:01:00 -0800 |
| |
On Tue, 2014-01-28 at 12:20 -0800, Paul E. McKenney wrote: > On Tue, Jan 28, 2014 at 11:13:12AM -0800, Jason Low wrote: > > The mutex_can_spin_on_owner() function should also return false if the > > task needs to be rescheduled to avoid entering the MCS queue when it > > needs to reschedule. > > > > Signed-off-by: Jason Low <jason.low2@hp.com> > > Reviewed-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> > > But I cannot help asking how this affects performance. (My guess is > "not much", but always good to know.)
Hi Paul,
In the past, when I tested this particular patch, I did not see any noticeable performance gains. Patch 1 is really more of a "correctness" change which was why I didn't retest this by itself. I can be sure to include the benchmarks numbers on this particular patch though next time.
Thanks.
| |