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;
Date:   Mon, 26 Sep 2022 16:08:43 +0200
From:   Michal Hocko <mhocko@suse.com>
To:     Zhongkun He <hezhongkun.hzk@bytedance.com>
Cc:     corbet@lwn.net, akpm@linux-foundation.org, linux-mm@kvack.org,
        linux-kernel@vger.kernel.org, linux-doc@vger.kernel.org,
        wuyun.abel@bytedance.com
Subject: Re: [External] Re: [RFC] proc: Add a new isolated
 /proc/pid/mempolicy type.
Message-ID: <YzGya2Q3iuWS2WdM@dhcp22.suse.cz>
References: <20220926091033.340-1-hezhongkun.hzk@bytedance.com>
 <YzF3aaLvEvFhTQa3@dhcp22.suse.cz>
 <24b20953-eca9-eef7-8e60-301080a17d2d@bytedance.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <24b20953-eca9-eef7-8e60-301080a17d2d@bytedance.com>
Precedence: bulk

On Mon 26-09-22 20:53:19, Zhongkun He wrote:
> > [Cc linux-api - please do so for any patches making/updating
> > kernel<->user interfaces]
> > 
> > 
> > On Mon 26-09-22 17:10:33, hezhongkun wrote:
> > > From: Zhongkun He <hezhongkun.hzk@bytedance.com>
> > > 
> > > /proc/pid/mempolicy can be used to check and adjust the userspace task's
> > > mempolicy dynamically.In many case, the application and the control plane
> > > are two separate systems. When the application is created, it doesn't know
> > > how to use memory, and it doesn't care. The control plane will decide the
> > > memory usage policy based on different reasons.In that case, we can
> > > dynamically adjust the mempolicy using /proc/pid/mempolicy interface.
> > 
> > Is there any reason to make it procfs interface rather than pidfd one?
> 
> Hi michal,  thanks for your reply.
> 
> I just think that it is easy to display and adjust the mempolicy using
> procfs. But it may not be suitable, I will send a pidfd_set_mempolicy patch
> later.

proc interface has many usability issues. That is why pidfd has been
introduced. So I would rather go with the pidfd interface than repeating
old proc API mistakes.

> Btw.in order to add per-thread-group mempolicy, is it possible to add
> mempolicy in mm_struct?

I dunno. This would make the mempolicy interface even more confusing.
Per mm behavior makes a lot of sense but we already do have per-thread
semantic so I would stick to it rather than introducing a new semantic.

Why is this really important?
-- 
Michal Hocko
SUSE Labs