Re: [PATCH 2/8] mm: clean up and clarify lruvec lookup procedure

2019-10-23 Thread Michal Hocko
On Tue 22-10-19 10:47:57, Johannes Weiner wrote: > There is a per-memcg lruvec and a NUMA node lruvec. Which one is being > used is somewhat confusing right now, and it's easy to make mistakes - > especially when it comes to global reclaim. > > How it works: when memory cgroups are enabled, we alw

Re: [PATCH 2/8] mm: clean up and clarify lruvec lookup procedure

2019-10-22 Thread Johannes Weiner
On Tue, Oct 22, 2019 at 07:25:01PM +, Roman Gushchin wrote: > On Tue, Oct 22, 2019 at 10:47:57AM -0400, Johannes Weiner wrote: > > There is a per-memcg lruvec and a NUMA node lruvec. Which one is being > > used is somewhat confusing right now, and it's easy to make mistakes - > > especially whe

Re: [PATCH 2/8] mm: clean up and clarify lruvec lookup procedure

2019-10-22 Thread Roman Gushchin
On Tue, Oct 22, 2019 at 10:47:57AM -0400, Johannes Weiner wrote: > There is a per-memcg lruvec and a NUMA node lruvec. Which one is being > used is somewhat confusing right now, and it's easy to make mistakes - > especially when it comes to global reclaim. > > How it works: when memory cgroups are

[PATCH 2/8] mm: clean up and clarify lruvec lookup procedure

2019-10-22 Thread Johannes Weiner
There is a per-memcg lruvec and a NUMA node lruvec. Which one is being used is somewhat confusing right now, and it's easy to make mistakes - especially when it comes to global reclaim. How it works: when memory cgroups are enabled, we always use the root_mem_cgroup's per-node lruvecs. When memory