Date:   Tue, 14 Dec 2021 14:38:39 +0100
From:   Johannes Weiner <hannes@cmpxchg.org>
To:     Muchun Song <songmuchun@bytedance.com>
Cc:     willy@infradead.org, akpm@linux-foundation.org, mhocko@kernel.org,
        vdavydov.dev@gmail.com, shakeelb@google.com, guro@fb.com,
        shy828301@gmail.com, alexs@kernel.org, richard.weiyang@gmail.com,
        david@fromorbit.com, trond.myklebust@hammerspace.com,
        anna.schumaker@netapp.com, jaegeuk@kernel.org, chao@kernel.org,
        kari.argillander@gmail.com, linux-fsdevel@vger.kernel.org,
        linux-kernel@vger.kernel.org, linux-mm@kvack.org,
        linux-nfs@vger.kernel.org, zhengqi.arch@bytedance.com,
        duanxiongchun@bytedance.com, fam.zheng@bytedance.com,
        smuchun@gmail.com
Subject: Re: [PATCH v4 01/17] mm: list_lru: optimize memory consumption of
 arrays of per cgroup lists
Message-ID: <YbieX3WCUt7hdZlW@cmpxchg.org>
References: <20211213165342.74704-1-songmuchun@bytedance.com>
 <20211213165342.74704-2-songmuchun@bytedance.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20211213165342.74704-2-songmuchun@bytedance.com>
Precedence: bulk

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.

> 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.

With that,

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

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