Johannes Weiner ce00a96737 mm: memcontrol: revert use of root_mem_cgroup res_counter
Dave Hansen reports a massive scalability regression in an uncontained
page fault benchmark with more than 30 concurrent threads, which he
bisected down to 05b843012335 ("mm: memcontrol: use root_mem_cgroup
res_counter") and pin-pointed on res_counter spinlock contention.

That change relied on the per-cpu charge caches to mostly swallow the
res_counter costs, but it's apparent that the caches don't scale yet.

Revert memcg back to bypassing res_counters on the root level in order
to restore performance for uncontained workloads.

Reported-by: Dave Hansen <dave@sr71.net>
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Tested-by: Dave Hansen <dave.hansen@intel.com>
Acked-by: Michal Hocko <mhocko@suse.cz>
Acked-by: Vladimir Davydov <vdavydov@parallels.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-09-05 08:19:02 -07:00
..
2014-08-06 18:01:16 -07:00
2012-01-03 22:54:56 -05:00
2011-07-26 16:49:47 -07:00
2014-08-06 18:01:16 -07:00
2014-08-06 18:01:23 -07:00
2014-08-08 15:57:17 -07:00
2014-01-27 21:02:39 -08:00
2012-06-20 14:39:36 -07:00
2014-08-08 15:57:17 -07:00
2014-08-08 15:57:17 -07:00
2014-08-29 16:28:16 -07:00
2014-08-29 16:28:16 -07:00