[PATCH] slab: Use same schedule timeout for all cpus in cache_reap
commitcd61ef6268ac52d3dfa5626d1e0306a91b3b2608
authorManfred Spraul <manfred@colorfullife.com>
Mon, 7 Nov 2005 08:58:02 +0000 (7 00:58 -0800)
committerLinus Torvalds <torvalds@g5.osdl.org>
Mon, 7 Nov 2005 15:53:24 +0000 (7 07:53 -0800)
tree5df1bfd49f2e9be33505ba900d2ed153fed9a2af
parent2109a2d1b175dfcffbfdac693bdbe4c4ab62f11f
[PATCH] slab: Use same schedule timeout for all cpus in cache_reap

Chen noticed that cache_reap uses REAPTIMEOUT_CPUC+smp_processor_id() as
the timeout for rescheduling.

The "+smp_processor_id()" part is wrong, the timeout should be identical
for all cpus: start_cpu_timer already adds a cpu dependant offset to avoid
any clustering.

The attached patch removes smp_processor_id().

Signed-Off-By: Manfred Spraul <manfred@colorfullife.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
mm/slab.c