Re: [External] Re: [PATCH v5] mm: memcontrol: Add the missing numa_stat interface for cgroup v2

From: Johannes Weiner <hannes@cmpxchg.org>
To: Muchun Song <songmuchun@bytedance.com>
Cc: Tejun Heo <tj@kernel.org>, Zefan Li <lizefan@huawei.com>,
	Jonathan Corbet <corbet@lwn.net>,
	Michal Hocko <mhocko@kernel.org>,
	Vladimir Davydov <vdavydov.dev@gmail.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	Shakeel Butt <shakeelb@google.com>, Roman Gushchin <guro@fb.com>,
	Randy Dunlap <rdunlap@infradead.org>,
	Cgroups <cgroups@vger.kernel.org>,
	linux-doc@vger.kernel.org, LKML <linux-kernel@vger.kernel.org>,
	Linux Memory Management List <linux-mm@kvack.org>
Subject: Re: [External] Re: [PATCH v5] mm: memcontrol: Add the missing numa_stat interface for cgroup v2
Date: Wed, 16 Sep 2020 10:40:57 -0400	[thread overview]
Message-ID: <20200916144057.GA194430@cmpxchg.org> (raw)
In-Reply-To: <CAMZfGtXOR1Ed2PyB4TB5mq=1mh7p7La-4BsoZ8oYhtgc8ZcqLQ@mail.gmail.com>

On Wed, Sep 16, 2020 at 12:14:49PM +0800, Muchun Song wrote:
> On Wed, Sep 16, 2020 at 5:50 AM Johannes Weiner <hannes@cmpxchg.org> wrote:
> >
> > On Wed, Sep 16, 2020 at 01:18:01AM +0800, Muchun Song wrote:
> > > In the cgroup v1, we have a numa_stat interface. This is useful for
> > > providing visibility into the numa locality information within an
> > > memcg since the pages are allowed to be allocated from any physical
> > > node. One of the use cases is evaluating application performance by
> > > combining this information with the application's CPU allocation.
> > > But the cgroup v2 does not. So this patch adds the missing information.
> > >
> > > Signed-off-by: Muchun Song <songmuchun@bytedance.com>
> > > Suggested-by: Shakeel Butt <shakeelb@google.com>
> > > Reviewed-by: Shakeel Butt <shakeelb@google.com>
> >
> > Yup, that would be useful information to have. Just a few comments on
> > the patch below:
> >
> > > @@ -1368,6 +1368,78 @@ PAGE_SIZE multiple when read back.
> > >               collapsing an existing range of pages. This counter is not
> > >               present when CONFIG_TRANSPARENT_HUGEPAGE is not set.
> > >
> > > +  memory.numa_stat
> > > +     A read-only flat-keyed file which exists on non-root cgroups.
> >
> > It's a nested key file, not flat.
> 
> This is just copied from memory.stat documentation.Is the memory.stat
> also a nested key file?

No, memory.stat is a different format. From higher up in the document:

  Flat keyed

	KEY0 VAL0\n
	KEY1 VAL1\n
	...

  Nested keyed

	KEY0 SUB_KEY0=VAL00 SUB_KEY1=VAL01...
	KEY1 SUB_KEY0=VAL10 SUB_KEY1=VAL11...
	...

> > Otherwise, this looks reasonable to me.
> 
> OK. Will do that.

Thanks!