memcg: replace ss->id_lock with a rwlock
While back-porting Johannes Weiner's patch "mm: memcg-aware global
reclaim" for an internal effort, we noticed a significant performance
regression during page-reclaim heavy workloads due to high contention of
the ss->id_lock. This lock protects idr map, and serializes calls to
idr_get_next() in css_get_next() (which is used during the memcg hierarchy
Since idr_get_next() is just doing a look up, we need only serialize it
with respect to idr_remove()/idr_get_new(). By making the ss->id_lock a
rwlock, contention is greatly reduced and performance improves.
Tested: cat a 256m file from a ramdisk in a 128m container 50 times on
each core (one file + container per core) in parallel on a NUMA machine.
Result is the time for the test to complete in 1 of the containers.
Both kernels included Johannes' memcg-aware global reclaim patches.
Before rwlock patch: 1710.778s
After rwlock patch: 152.227s
Signed-off-by: Andrew Bresticker <email@example.com>
Cc: Paul Menage <firstname.lastname@example.org>
Cc: Li Zefan <email@example.com>
Acked-by: KAMEZAWA Hiroyuki <firstname.lastname@example.org>
Cc: Ying Han <email@example.com>
Signed-off-by: Andrew Morton <firstname.lastname@example.org>
Signed-off-by: Linus Torvalds <email@example.com>
2 files changed