[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <Y3yK78HMSVA/Q6CS@dhcp22.suse.cz>
Date: Tue, 22 Nov 2022 09:40:15 +0100
From: Michal Hocko <mhocko@...e.com>
To: Zhongkun He <hezhongkun.hzk@...edance.com>
Cc: Andrew Morton <akpm@...ux-foundation.org>, corbet@....net,
linux-mm@...ck.org, linux-kernel@...r.kernel.org,
linux-api@...r.kernel.org, linux-doc@...r.kernel.org
Subject: Re: [External] Re: [PATCH v2] mm: add new syscall
pidfd_set_mempolicy().
On Tue 22-11-22 16:33:09, Zhongkun He wrote:
> Hi Michal, thanks for your replay and suggestions.
>
> >
> > Yes the memory consumption is going to increase but the question is
> > whether this is something that is a real problem. Is it really common to
> > have many vmas with a dedicated policy?
>
> Yes, it does not a realy problem.
>
> >
> > What I am arguing here is that there are essentially 2 ways forward.
> > Either we continue to build up on top of the existing and arguably very
> > fragile code and make it even more subtle or follow a general pattern of
> > a proper reference counting (with usual tricks to reduce cache line
> > bouncing and similar issues). I do not really see why memory policies
> > should be any different and require very special treatment.
> >
>
> I got it. It is rather subtle and easy to get wrong if we push forward
> with the existing way and it is a good opportunity to get from the
> existing subtle model. I will try that on next version.
Thanks for being receptive to the review feedback!
--
Michal Hocko
SUSE Labs
Powered by blists - more mailing lists