sched: Compute runnable load avg in cpu_load and cpu_avg_load_per_task
authorAlex Shi <alex.shi@intel.com>
Thu, 20 Jun 2013 02:18:50 +0000 (10:18 +0800)
committerIngo Molnar <mingo@kernel.org>
Thu, 27 Jun 2013 08:07:35 +0000 (10:07 +0200)
commitb92486cbf2aa230d00f160664858495c81d2b37b
tree293470662cb92417b45bb68bab46aa36f1ba27e0
parent83dfd5235ebd66c284b97befe6eabff7132333e6
sched: Compute runnable load avg in cpu_load and cpu_avg_load_per_task

They are the base values in load balance, update them with rq runnable
load average, then the load balance will consider runnable load avg
naturally.

We also try to include the blocked_load_avg as cpu load in balancing,
but that cause kbuild performance drop 6% on every Intel machine, and
aim7/oltp drop on some of 4 CPU sockets machines.
Or only add blocked_load_avg into get_rq_runable_load, hackbench still
drop a little on NHM EX.

Signed-off-by: Alex Shi <alex.shi@intel.com>
Reviewed-by: Gu Zheng <guz.fnst@cn.fujitsu.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1371694737-29336-7-git-send-email-alex.shi@intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
kernel/sched/fair.c
kernel/sched/proc.c