MIME-Version: 1.0
References: <20211213165342.74704-1-songmuchun@bytedance.com>
 <20211213165342.74704-2-songmuchun@bytedance.com> <YbieX3WCUt7hdZlW@cmpxchg.org>
In-Reply-To: <YbieX3WCUt7hdZlW@cmpxchg.org>
From:   Muchun Song <songmuchun@bytedance.com>
Date:   Wed, 15 Dec 2021 20:09:10 +0800
Message-ID: <CAMZfGtWPt2wk91Js6NRnw-wpMVQHc+ZRZo8OUyrkNAJBB3f8yQ@mail.gmail.com>
Subject: Re: [PATCH v4 01/17] mm: list_lru: optimize memory consumption of
 arrays of per cgroup lists
To:     Johannes Weiner <hannes@cmpxchg.org>
Cc:     Matthew Wilcox <willy@infradead.org>,
        Andrew Morton <akpm@linux-foundation.org>,
        Michal Hocko <mhocko@kernel.org>,
        Vladimir Davydov <vdavydov.dev@gmail.com>,
        Shakeel Butt <shakeelb@google.com>,
        Roman Gushchin <guro@fb.com>, Yang Shi <shy828301@gmail.com>,
        Alex Shi <alexs@kernel.org>,
        Wei Yang <richard.weiyang@gmail.com>,
        Dave Chinner <david@fromorbit.com>,
        trond.myklebust@hammerspace.com, anna.schumaker@netapp.com,
        jaegeuk@kernel.org, chao@kernel.org,
        Kari Argillander <kari.argillander@gmail.com>,
        linux-fsdevel <linux-fsdevel@vger.kernel.org>,
        LKML <linux-kernel@vger.kernel.org>,
        Linux Memory Management List <linux-mm@kvack.org>,
        linux-nfs@vger.kernel.org, Qi Zheng <zhengqi.arch@bytedance.com>,
        Xiongchun duan <duanxiongchun@bytedance.com>,
        fam.zheng@bytedance.com, Muchun Song <smuchun@gmail.com>
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

On Tue, Dec 14, 2021 at 9:38 PM Johannes Weiner <hannes@cmpxchg.org> wrote:
>
> On Tue, Dec 14, 2021 at 12:53:26AM +0800, Muchun Song wrote:
> > The list_lru uses an array (list_lru_memcg->lru) to store pointers
> > which point to the list_lru_one. And the array is per memcg per node.
> > Therefore, the size of the arrays will be 10K * number_of_node * 8 (
> > a pointer size on 64 bits system) when we run 10k containers in the
> > system. The memory consumption of the arrays becomes significant. The
> > more numa node, the more memory it consumes.
>
> The complexity for the lists themselves is still nrmemcgs * nrnodes
> right? But the rcu_head goes from that to nrmemcgs.

Right.

>
> > I have done a simple test, which creates 10K memcg and mount point
> > each in a two-node system. The memory consumption of the list_lru
> > will be 24464MB. After converting the array from per memcg per node
> > to per memcg, the memory consumption is going to be 21957MB. It is
> > reduces by 2.5GB. In our AMD servers, there are 8 numa nodes in
> > those system, the memory consumption could be more significant.
>
> The code looks good to me, but it would be useful to include a
> high-level overview of the new scheme, explain that the savings come
> from the rcu heads, that it simplifies the alloc/dealloc path etc.

Will do in the next version.

>
> With that,
>
> > Signed-off-by: Muchun Song <songmuchun@bytedance.com>

Thanks.

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