Files
linux/include/linux
Mel Gorman 0d5d823ab4 mm: move zone->pages_scanned into a vmstat counter
zone->pages_scanned is a write-intensive cache line during page reclaim
and it's also updated during page free.  Move the counter into vmstat to
take advantage of the per-cpu updates and do not update it in the free
paths unless necessary.

On a small UMA machine running tiobench the difference is marginal.  On
a 4-node machine the overhead is more noticable.  Note that automatic
NUMA balancing was disabled for this test as otherwise the system CPU
overhead is unpredictable.

          3.16.0-rc3  3.16.0-rc3  3.16.0-rc3
             vanillarearrange-v5   vmstat-v5
User          746.94      759.78      774.56
System      65336.22    58350.98    32847.27
Elapsed     27553.52    27282.02    27415.04

Note that the overhead reduction will vary depending on where exactly
pages are allocated and freed.

Signed-off-by: Mel Gorman <mgorman@suse.de>
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>
2014-08-06 18:01:20 -07:00
..
2014-06-03 23:12:20 +02:00
2014-08-01 22:35:55 +08:00
2014-07-08 13:36:52 -07:00
2014-06-04 13:34:30 +09:00
2014-07-13 21:38:49 -04:00
2014-08-06 18:01:19 -07:00
2014-06-06 16:08:13 -07:00
2014-06-02 16:05:24 -07:00
2014-06-02 14:56:01 -07:00
2014-07-08 09:40:06 +02:00
2014-06-16 16:26:54 +02:00
2014-06-25 17:45:43 -07:00
2014-07-22 21:55:45 +01:00
2014-07-09 14:58:37 +01:00
2014-06-04 16:54:07 -07:00
2014-06-04 16:54:21 -07:00
2014-06-04 16:54:12 -07:00
2014-06-06 16:08:12 -07:00
2014-06-12 00:21:11 -04:00
2014-06-04 16:53:57 -07:00
2014-06-04 16:53:56 -07:00
2014-05-30 11:35:54 -06:00
2014-06-04 16:53:57 -07:00
2014-06-04 16:53:57 -07:00