sched: Fix vmark regression on big machines
authorMike Galbraith <efault@gmx.de>
Mon, 4 Jan 2010 13:44:56 +0000 (14:44 +0100)
committerIngo Molnar <mingo@elte.hu>
Thu, 21 Jan 2010 12:39:03 +0000 (13:39 +0100)
commit50b926e439620c469565e8be0f28be78f5fca1ce
tree3eb4b4aa89ed7c6d61457cdf745c5d52f577671a
parent24bc7347da73a9ed3383056c3d0f28c0e361621e
sched: Fix vmark regression on big machines

SD_PREFER_SIBLING is set at the CPU domain level if power saving isn't
enabled, leading to many cache misses on large machines as we traverse
looking for an idle shared cache to wake to.  Change the enabler of
select_idle_sibling() to SD_SHARE_PKG_RESOURCES, and enable same at the
sibling domain level.

Reported-by: Lin Ming <ming.m.lin@intel.com>
Signed-off-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1262612696.15495.15.camel@marge.simson.net>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
include/linux/topology.h
kernel/sched_fair.c