[PATCH] mm, memcg: add workingset_restore in memory.stat

[PATCH] mm, memcg: add workingset_restore in memory.stat

[Yafang Shao]

There's a new workingset counter introduced in commit 1899ad18c607 ("mm:
workingset: tell cache transitions from workingset thrashing"). With the
help of this counter we can know the workingset is transitioning or
thrashing. To leverage the benifit of this counter to memcg, we should
introduce it into memory.stat. Then we could know the workingset of the
workload inside a memcg better.

Bellow is the verification of this new counter in memory.stat.
Read a file into the memory and then read it again to make these pages be
active. The size of this file is 1G. (memory.max is greater than file size)
The counters in memory.stat will be,
	inactive_file 0
	active_file 1073639424

	workingset_refault 0
	workingset_activate 0
	workingset_restore 0
	workingset_nodereclaim 0
Trigger the memcg reclaim by setting a lower value to memory.high, and
then some pages will be demoted into inactive list, and then some pages
in the inactive list will be evicted into the storage.
	inactive_file 498094080
	active_file 310063104

	workingset_refault 0
	workingset_activate 0
	workingset_restore 0
	workingset_nodereclaim 0
Then recover the memory.high and read the file into memory again. As a
result of it, the transitioning will occur. Bellow is the result of this
transitioning,
	inactive_file 498094080
	active_file 575397888

	workingset_refault 64746
	workingset_activate 64746
	workingset_restore 64746
	workingset_nodereclaim 0

Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
---
 mm/memcontrol.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 5beea03dd58a..0395e479995b 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1451,6 +1451,8 @@ static char *memory_stat_format(struct mem_cgroup *memcg)
 		       memcg_page_state(memcg, WORKINGSET_REFAULT));
 	seq_buf_printf(&s, "workingset_activate %lu\n",
 		       memcg_page_state(memcg, WORKINGSET_ACTIVATE));
+	seq_buf_printf(&s, "workingset_restore %lu\n",
+		       memcg_page_state(memcg, WORKINGSET_RESTORE));
 	seq_buf_printf(&s, "workingset_nodereclaim %lu\n",
 		       memcg_page_state(memcg, WORKINGSET_NODERECLAIM));
 
-- 
2.18.2

Re: [PATCH] mm, memcg: add workingset_restore in memory.stat

[Johannes Weiner]

On Sat, May 02, 2020 at 10:18:49AM -0400, Yafang Shao wrote:
> There's a new workingset counter introduced in commit 1899ad18c607 ("mm:
> workingset: tell cache transitions from workingset thrashing"). With the
> help of this counter we can know the workingset is transitioning or
> thrashing. To leverage the benifit of this counter to memcg, we should
> introduce it into memory.stat. Then we could know the workingset of the
> workload inside a memcg better.
> 
> Bellow is the verification of this new counter in memory.stat.
>
> Read a file into the memory and then read it again to make these pages be
> active. The size of this file is 1G. (memory.max is greater than file size)
> The counters in memory.stat will be,
> 	inactive_file 0
> 	active_file 1073639424
> 
> 	workingset_refault 0
> 	workingset_activate 0
> 	workingset_restore 0
> 	workingset_nodereclaim 0
> Trigger the memcg reclaim by setting a lower value to memory.high, and
> then some pages will be demoted into inactive list, and then some pages
> in the inactive list will be evicted into the storage.
> 	inactive_file 498094080
> 	active_file 310063104
> 
> 	workingset_refault 0
> 	workingset_activate 0
> 	workingset_restore 0
> 	workingset_nodereclaim 0
> Then recover the memory.high and read the file into memory again. As a
> result of it, the transitioning will occur. Bellow is the result of this
> transitioning,
> 	inactive_file 498094080
> 	active_file 575397888
> 
> 	workingset_refault 64746
> 	workingset_activate 64746
> 	workingset_restore 64746
> 	workingset_nodereclaim 0
> 
> Signed-off-by: Yafang Shao <laoar.shao@gmail.com>

Thanks, yes, I've missed that counter a few times while debugging
something but never gotten around to actually adding it.

Acked-by: Johannes Weiner <hannes@cmpxchg.org>

Re: [PATCH] mm, memcg: add workingset_restore in memory.stat

[Michal Hocko]

On Sat 02-05-20 10:18:49, Yafang Shao wrote:
> There's a new workingset counter introduced in commit 1899ad18c607 ("mm:
> workingset: tell cache transitions from workingset thrashing"). With the
> help of this counter we can know the workingset is transitioning or
> thrashing. To leverage the benifit of this counter to memcg, we should
> introduce it into memory.stat. Then we could know the workingset of the
> workload inside a memcg better.
> 
> Bellow is the verification of this new counter in memory.stat.
> Read a file into the memory and then read it again to make these pages be
> active. The size of this file is 1G. (memory.max is greater than file size)
> The counters in memory.stat will be,
> 	inactive_file 0
> 	active_file 1073639424
> 
> 	workingset_refault 0
> 	workingset_activate 0
> 	workingset_restore 0
> 	workingset_nodereclaim 0
> Trigger the memcg reclaim by setting a lower value to memory.high, and
> then some pages will be demoted into inactive list, and then some pages
> in the inactive list will be evicted into the storage.
> 	inactive_file 498094080
> 	active_file 310063104
> 
> 	workingset_refault 0
> 	workingset_activate 0
> 	workingset_restore 0
> 	workingset_nodereclaim 0
> Then recover the memory.high and read the file into memory again. As a
> result of it, the transitioning will occur. Bellow is the result of this
> transitioning,
> 	inactive_file 498094080
> 	active_file 575397888
> 
> 	workingset_refault 64746
> 	workingset_activate 64746
> 	workingset_restore 64746
> 	workingset_nodereclaim 0

Could you update Documentation/admin-guide/cgroup-v2.rst as well please?

> Signed-off-by: Yafang Shao <laoar.shao@gmail.com>

Acked-by: Michal Hocko <mhocko@suse.com>

> ---
>  mm/memcontrol.c | 2 ++
>  1 file changed, 2 insertions(+)
> 
> diff --git a/mm/memcontrol.c b/mm/memcontrol.c
> index 5beea03dd58a..0395e479995b 100644
> --- a/mm/memcontrol.c
> +++ b/mm/memcontrol.c
> @@ -1451,6 +1451,8 @@ static char *memory_stat_format(struct mem_cgroup *memcg)
>  		       memcg_page_state(memcg, WORKINGSET_REFAULT));
>  	seq_buf_printf(&s, "workingset_activate %lu\n",
>  		       memcg_page_state(memcg, WORKINGSET_ACTIVATE));
> +	seq_buf_printf(&s, "workingset_restore %lu\n",
> +		       memcg_page_state(memcg, WORKINGSET_RESTORE));
>  	seq_buf_printf(&s, "workingset_nodereclaim %lu\n",
>  		       memcg_page_state(memcg, WORKINGSET_NODERECLAIM));
>  
> -- 
> 2.18.2

-- 
Michal Hocko
SUSE Labs

Re: [PATCH] mm, memcg: add workingset_restore in memory.stat

[Yafang Shao]

On Mon, May 4, 2020 at 5:10 PM Michal Hocko <mhocko@kernel.org> wrote:
>
> On Sat 02-05-20 10:18:49, Yafang Shao wrote:
> > There's a new workingset counter introduced in commit 1899ad18c607 ("mm:
> > workingset: tell cache transitions from workingset thrashing"). With the
> > help of this counter we can know the workingset is transitioning or
> > thrashing. To leverage the benifit of this counter to memcg, we should
> > introduce it into memory.stat. Then we could know the workingset of the
> > workload inside a memcg better.
> >
> > Bellow is the verification of this new counter in memory.stat.
> > Read a file into the memory and then read it again to make these pages be
> > active. The size of this file is 1G. (memory.max is greater than file size)
> > The counters in memory.stat will be,
> >       inactive_file 0
> >       active_file 1073639424
> >
> >       workingset_refault 0
> >       workingset_activate 0
> >       workingset_restore 0
> >       workingset_nodereclaim 0
> > Trigger the memcg reclaim by setting a lower value to memory.high, and
> > then some pages will be demoted into inactive list, and then some pages
> > in the inactive list will be evicted into the storage.
> >       inactive_file 498094080
> >       active_file 310063104
> >
> >       workingset_refault 0
> >       workingset_activate 0
> >       workingset_restore 0
> >       workingset_nodereclaim 0
> > Then recover the memory.high and read the file into memory again. As a
> > result of it, the transitioning will occur. Bellow is the result of this
> > transitioning,
> >       inactive_file 498094080
> >       active_file 575397888
> >
> >       workingset_refault 64746
> >       workingset_activate 64746
> >       workingset_restore 64746
> >       workingset_nodereclaim 0
>
> Could you update Documentation/admin-guide/cgroup-v2.rst as well please?
>

Thanks for your reminder. I will update it.

> > Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
>
> Acked-by: Michal Hocko <mhocko@suse.com>
>

Thanks.

> > ---
> >  mm/memcontrol.c | 2 ++
> >  1 file changed, 2 insertions(+)
> >
> > diff --git a/mm/memcontrol.c b/mm/memcontrol.c
> > index 5beea03dd58a..0395e479995b 100644
> > --- a/mm/memcontrol.c
> > +++ b/mm/memcontrol.c
> > @@ -1451,6 +1451,8 @@ static char *memory_stat_format(struct mem_cgroup *memcg)
> >                      memcg_page_state(memcg, WORKINGSET_REFAULT));
> >       seq_buf_printf(&s, "workingset_activate %lu\n",
> >                      memcg_page_state(memcg, WORKINGSET_ACTIVATE));
> > +     seq_buf_printf(&s, "workingset_restore %lu\n",
> > +                    memcg_page_state(memcg, WORKINGSET_RESTORE));
> >       seq_buf_printf(&s, "workingset_nodereclaim %lu\n",
> >                      memcg_page_state(memcg, WORKINGSET_NODERECLAIM));
> >
> > --
> > 2.18.2
>
> --
> Michal Hocko
> SUSE Labs



-- 
Thanks
Yafang