Re: [PATCH 4/5] mm: release per-node memcg percpu data prematurely

2019-03-11 Thread Johannes Weiner
On Thu, Mar 07, 2019 at 03:00:32PM -0800, Roman Gushchin wrote: > Similar to memcg-level statistics, per-node data isn't expected > to be hot after cgroup removal. Switching over to atomics and > prematurely releasing percpu data helps to reduce the memory > footprint of dying cgroups. > >

[PATCH 4/5] mm: release per-node memcg percpu data prematurely

2019-03-07 Thread Roman Gushchin
Similar to memcg-level statistics, per-node data isn't expected to be hot after cgroup removal. Switching over to atomics and prematurely releasing percpu data helps to reduce the memory footprint of dying cgroups. Signed-off-by: Roman Gushchin --- include/linux/memcontrol.h | 1 +