Peter Zijlstra ffda12a17a sched: optimize group load balancer
I noticed that tg_shares_up() unconditionally takes rq-locks for all cpus
in the sched_domain. This hurts.

We need the rq-locks whenever we change the weight of the per-cpu group sched
entities. To allevate this a little, only change the weight when the new
weight is at least shares_thresh away from the old value.

This avoids the rq-lock for the top level entries, since those will never
be re-weighted, and fuzzes the lower level entries a little to gain performance
in semi-stable situations.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-10-20 14:05:02 +02:00
..
2008-08-14 14:58:01 +02:00
2008-10-16 11:21:30 -07:00
2008-07-26 20:53:20 -04:00
2008-10-13 09:51:40 -07:00
2008-03-30 14:18:41 -07:00
2008-07-28 14:37:38 +02:00
2007-07-16 09:05:50 -07:00
2008-07-26 12:00:09 -07:00
2008-08-13 12:55:10 +02:00
2008-10-16 11:21:32 -07:00
2008-09-02 19:21:40 -07:00
2008-10-20 14:05:02 +02:00
2007-07-16 09:05:50 -07:00
2008-08-19 20:37:07 -07:00
2008-10-16 11:21:31 -07:00
2008-02-06 10:41:02 -08:00
2008-10-16 11:21:51 -07:00
2008-10-16 11:21:31 -07:00
2008-07-25 10:53:45 -07:00
2008-10-20 14:05:02 +02:00
2008-08-11 13:46:53 +02:00
2008-10-16 11:21:47 -07:00
2008-10-16 11:21:31 -07:00