sched: Check for an idle shared cache in select_task_rq_fair()
authorMike Galbraith <efault@gmx.de>
Tue, 27 Oct 2009 14:35:38 +0000 (15:35 +0100)
committerIngo Molnar <mingo@elte.hu>
Wed, 4 Nov 2009 17:46:22 +0000 (18:46 +0100)
commita1f84a3ab8e002159498814eaa7e48c33752b04b
tree070b6c105c510460b314c20e17de4b5b89eb6a48
parentacc3f5d7cabbfd6cec71f0c1f9900621fa2d6ae7
sched: Check for an idle shared cache in select_task_rq_fair()

When waking affine, check for an idle shared cache, and if
found, wake to that CPU/sibling instead of the waker's CPU.

This improves pgsql+oltp ramp up by roughly 8%. Possibly more
for other loads, depending on overlap. The trade-off is a
roughly 1% peak downturn if tasks are truly synchronous.

Signed-off-by: Mike Galbraith <efault@gmx.de>
Cc: Arjan van de Ven <arjan@infradead.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: <stable@kernel.org>
LKML-Reference: <1256654138.17752.7.camel@marge.simson.net>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
kernel/sched_fair.c