[PATCH v3 0/3] mm: improve zone->lock scalability

[Aaron Lu <aaron.lu@intel.com>]

Patch 1/3 is a small cleanup suggested by Matthew Wilcox which doesn't
affect scalability or performance;
Patch 2/3 moves some code in free_pcppages_bulk() outside of zone->lock
and has Mel Gorman's ack;
Patch 3/3 uses prefetch in free_pcppages_bulk() outside of zone->lock to
speedup page merging under zone->lock but Mel Gorman has some concerns.

For details, please see their changelogs.

Changes from v2:
Patch 1/3 is newly added;
Patch 2/3 is patch 1/2 in v2 and doesn't have any change except resolving
conflicts due to the newly added patch 1/3;
Patch 3/3 is patch 2/2 in v2 and only has some changelog updates on
concerns part.

v1 and v2 was here:
https://lkml.org/lkml/2018/1/23/879

Aaron Lu (3):
  mm/free_pcppages_bulk: update pcp->count inside
  mm/free_pcppages_bulk: do not hold lock when picking pages to free
  mm/free_pcppages_bulk: prefetch buddy while not holding lock

 mm/page_alloc.c | 56 +++++++++++++++++++++++++++++++++++---------------------
 1 file changed, 35 insertions(+), 21 deletions(-)

-- 
2.14.3

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>