linux-kernel - Re: [PATCH v4 1/2] sched/deadline: Fix bandwidth reclaim equation in GRUB

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <CAO7JXPit6snFM2oW-uSs-mtbmKr9wpbX2exqAUF0iAiaAO6hOg@mail.gmail.com>
Date:   Fri, 26 May 2023 11:58:50 -0400
From:   Vineeth Remanan Pillai <vineeth@...byteword.org>
To:     luca abeni <luca.abeni@...tannapisa.it>
Cc:     Juri Lelli <juri.lelli@...hat.com>,
        Daniel Bristot de Oliveira <bristot@...hat.com>,
        Peter Zijlstra <peterz@...radead.org>,
        Ingo Molnar <mingo@...hat.com>,
        Vincent Guittot <vincent.guittot@...aro.org>,
        Steven Rostedt <rostedt@...dmis.org>,
        Joel Fernandes <joel@...lfernandes.org>,
        youssefesmat@...gle.com,
        Dietmar Eggemann <dietmar.eggemann@....com>,
        Ben Segall <bsegall@...gle.com>, Mel Gorman <mgorman@...e.de>,
        Valentin Schneider <vschneid@...hat.com>,
        Jonathan Corbet <corbet@....net>, linux-kernel@...r.kernel.org,
        linux-doc@...r.kernel.org
Subject: Re: [PATCH v4 1/2] sched/deadline: Fix bandwidth reclaim equation in GRUB

Hi Luca,

>
> On Fri, May 26, 2023 at 11:30 AM luca abeni <luca.abeni@...tannapisa.it> wrote:
> > [...]
> > > + * but as "dq = -(max{u, (1 - Uinact - Uextra)} / Umax) dt",
> >
> > ...But I think this is wrong (should be "Umax - ...", not "1 - ...").
> > I think patch 2/2 has the same issue.
> >
> Oops sorry, I missed this. Will send the fixed patch as a
> reply to the original v4.
>
On looking again, I think the description is correct. That line
mentions the actual m-GRUB equation from the paper. And then the
comment explains why we use Umax(because of limiting the bandwidth
to RT capacity).

Does it seem correct to you?

Thanks,
Vineeth