Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
MIME-Version: 1.0
References: <20220907043537.3457014-1-shakeelb@google.com> <20220907043537.3457014-2-shakeelb@google.com>
 <YxqIQOWzrsrPnff3@blackbook>
In-Reply-To: <YxqIQOWzrsrPnff3@blackbook>
From:   Shakeel Butt <shakeelb@google.com>
Date:   Fri, 9 Sep 2022 09:11:48 -0700
Message-ID: <CALvZod77qUb0XRJh3y3-GQevoKjcwdt-Gtq0u0Tp6zTxBe-4CA@mail.gmail.com>
Subject: Re: [PATCH 1/3] memcg: extract memcg_vmstats from struct mem_cgroup
To:     =?UTF-8?Q?Michal_Koutn=C3=BD?= <mkoutny@suse.com>
Cc:     Johannes Weiner <hannes@cmpxchg.org>,
        Michal Hocko <mhocko@kernel.org>,
        Roman Gushchin <roman.gushchin@linux.dev>,
        Muchun Song <songmuchun@bytedance.com>,
        Andrew Morton <akpm@linux-foundation.org>,
        Cgroups <cgroups@vger.kernel.org>, Linux MM <linux-mm@kvack.org>,
        LKML <linux-kernel@vger.kernel.org>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
Precedence: bulk

On Thu, Sep 8, 2022 at 5:26 PM Michal Koutn=C3=BD <mkoutny@suse.com> wrote:
>
> Hi.
>
> On Wed, Sep 07, 2022 at 04:35:35AM +0000, Shakeel Butt <shakeelb@google.c=
om> wrote:
> > This is a preparatory patch to reduce the memory overhead of memory
> > cgroup. The struct memcg_vmstats is the largest object embedded into th=
e
> > struct mem_cgroup.
> > This patch extracts struct memcg_vmstats from struct
> > mem_cgroup to ease the following patches in reducing the size of struct
> > memcg_vmstats.
>
> Is the reason for the extraction just moving things away from the header
> file?
> Or is the separate allocation+indirection somehow beneficial wrt, e.g.
> fragmentation?
>

The main reason was to move away from the head file. I have not yet
measured the performance impact of these changes. I am planning to
rearrange struct mem_cgroup and will do some performance tests after
that.