Received-SPF: pass (google.com: domain of linux-kernel+bounces-9319-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:40f1:3f00::1 as permitted sender) client-ip=2604:1380:40f1:3f00::1;
Precedence: bulk
MIME-Version: 1.0
References: <CAJj2-QGqDWGVHEwU+=8+ywEAQtK9QKGZCOhkyEgp8LEWbXDggQ@mail.gmail.com>
 <20231222024458.12441-1-henry.hj@antgroup.com>
In-Reply-To: <20231222024458.12441-1-henry.hj@antgroup.com>
From: Yu Zhao <yuzhao@google.com>
Date: Thu, 21 Dec 2023 21:35:08 -0700
Message-ID: <CAOUHufZwXBs4x7GeawrjZNEwTBdV=mf-DYrZuF4j=10URHwQTw@mail.gmail.com>
Subject: Re: [RFC v2] mm: Multi-Gen LRU: fix use mm/page_idle/bitmap
To: Henry Huang <henry.hj@antgroup.com>
Cc: yuanchu@google.com, akpm@linux-foundation.org, 
	=?UTF-8?B?6LCI6Ym06ZSL?= <henry.tjf@antgroup.com>, 
	linux-kernel@vger.kernel.org, linux-mm@kvack.org, 
	=?UTF-8?B?5pyx6L6JKOiMtuawtCk=?= <teawater@antgroup.com>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable

On Thu, Dec 21, 2023 at 7:45=E2=80=AFPM Henry Huang <henry.hj@antgroup.com>=
 wrote:
>
> Thanks for replyting.
>
> On Fri, Dec 22, 2023 at 07:16=E2=80=AFAM Yuanchu Xie wrote:
> > How does the shared memory get charged to the cgroups?
> > Does it all go to cgroup A or B exclusively, or do some pages get
> > charged to each one?
>
> Some pages get charged to cgroup A, and the other get charged to cgroup B=
.

Just a side note:
We can potentially "fix" this, but it doesn't mean this is a good
practice. In fact, I think this is an anti-pattern to memcgs:
resources should be preferably isolated between memcgs, or if a
resource has to be shared between memcgs, it should be charged in a
predetermined way, not randomly to one of the memcgs sharing it.