Re: [PATCH] mm: memcontrol: don't count limit-setting reclaim as memory pressure

2020-07-30 Thread Michal Hocko
On Tue 28-07-20 09:52:10, Johannes Weiner wrote: > When an outside process lowers one of the memory limits of a cgroup > (or uses the force_empty knob in cgroup1), direct reclaim is performed > in the context of the write(), in order to directly enforce the new > limit and have it being met by the

Re: [PATCH] mm: memcontrol: don't count limit-setting reclaim as memory pressure

2020-07-28 Thread Chris Down
Johannes Weiner writes: When an outside process lowers one of the memory limits of a cgroup (or uses the force_empty knob in cgroup1), direct reclaim is performed in the context of the write(), in order to directly enforce the new limit and have it being met by the time the write() returns.

Re: [PATCH] mm: memcontrol: don't count limit-setting reclaim as memory pressure

2020-07-28 Thread Roman Gushchin
On Tue, Jul 28, 2020 at 09:52:10AM -0400, Johannes Weiner wrote: > When an outside process lowers one of the memory limits of a cgroup > (or uses the force_empty knob in cgroup1), direct reclaim is performed > in the context of the write(), in order to directly enforce the new > limit and have it

Re: [PATCH] mm: memcontrol: don't count limit-setting reclaim as memory pressure

2020-07-28 Thread Shakeel Butt
On Tue, Jul 28, 2020 at 6:53 AM Johannes Weiner wrote: > > When an outside process lowers one of the memory limits of a cgroup > (or uses the force_empty knob in cgroup1), direct reclaim is performed > in the context of the write(), in order to directly enforce the new > limit and have it being

[PATCH] mm: memcontrol: don't count limit-setting reclaim as memory pressure

2020-07-28 Thread Johannes Weiner
When an outside process lowers one of the memory limits of a cgroup (or uses the force_empty knob in cgroup1), direct reclaim is performed in the context of the write(), in order to directly enforce the new limit and have it being met by the time the write() returns. Currently, this reclaim