mm: don't avoid high-priority reclaim on memcg limit reclaim
authorJohannes Weiner <hannes@cmpxchg.org>
Wed, 3 May 2017 21:52:07 +0000 (14:52 -0700)
committerLinus Torvalds <torvalds@linux-foundation.org>
Wed, 3 May 2017 22:52:08 +0000 (15:52 -0700)
commit688035f729dcd9a98152c827338805a061f5c6fa
tree2c2def8c77d297e36d4a757f12c1b12211b38eee
parenta2d7f8e461881394167bafb616112a96f5f567d0
mm: don't avoid high-priority reclaim on memcg limit reclaim

Commit 246e87a93934 ("memcg: fix get_scan_count() for small targets")
sought to avoid high reclaim priorities for memcg by forcing it to scan
a minimum amount of pages when lru_pages >> priority yielded nothing.
This was done at a time when reclaim decisions like dirty throttling
were tied to the priority level.

Nowadays, the only meaningful thing still tied to priority dropping
below DEF_PRIORITY - 2 is gating whether laptop_mode=1 is generally
allowed to write.  But that is from an era where direct reclaim was
still allowed to call ->writepage, and kswapd nowadays avoids writes
until it's scanned every clean page in the system.  Potential changes to
how quick sc->may_writepage could trigger are of little concern.

Remove the force_scan stuff, as well as the ugly multi-pass target
calculation that it necessitated.

Link: http://lkml.kernel.org/r/20170228214007.5621-7-hannes@cmpxchg.org
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Jia He <hejianet@gmail.com>
Cc: Mel Gorman <mgorman@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
mm/vmscan.c