Commit cecf257b authored Mar 15, 2016 by Vladimir Davydov Committed by Linus Torvalds Mar 15, 2016

mm: vmscan: do not clear SHRINKER_NUMA_AWARE if nr_node_ids == 1



Currently, on shrinker registration we clear SHRINKER_NUMA_AWARE if
there's the only NUMA node present.  The comment states that this will
allow us to save some small loop time later.  It used to be true when
this code was added (see commit 1d3d4437 ("vmscan: per-node
deferred work")), but since commit 6b4f7799 ("mm: vmscan: invoke
slab shrinkers from shrink_zone()") it doesn't make any difference.
Anyway, running on non-NUMA machine shouldn't make a shrinker NUMA
unaware, so zap this hunk.

Signed-off-by: Vladimir Davydov <vdavydov@virtuozzo.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

parent 703fc13a

mm/vmscan.c

+0 −8

Original line number	Diff line number	Diff line
		@@ -228,14 +228,6 @@ int register_shrinker(struct shrinker *shrinker)
		{
		size_t size = sizeof(*shrinker->nr_deferred);

		/*
		* If we only have one possible node in the system anyway, save
		* ourselves the trouble and disable NUMA aware behavior. This way we
		* will save memory and some small loop time later.
		*/
		if (nr_node_ids == 1)
		shrinker->flags &= ~SHRINKER_NUMA_AWARE;

		if (shrinker->flags & SHRINKER_NUMA_AWARE)
		size *= nr_node_ids;

Admin message