[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20230511220336.05866e80@nowhere>
Date: Thu, 11 May 2023 22:03:36 +0200
From: luca abeni <luca.abeni@...tannapisa.it>
To: Vineeth Remanan Pillai <vineeth@...byteword.org>
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>,
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 1/2] sched/deadline: accurate reclaim bandwidth for GRUB
Hi,
first of all, thanks for your patience with my comments :)
On Thu, 11 May 2023 14:34:38 -0400
Vineeth Remanan Pillai <vineeth@...byteword.org> wrote:
[...]
> SMP GRUB paper has the equation for depreciating runtime as:
> dq_i = -max{u_i, 1 - (extra_bw + Uinact)} dt
>
> Since we are caping at Umax, the equation would be
> dq_i = -(max{u_i, Umax - (extra_bw + Uinact)} / Umax) dt (1)
>
> But existing implementation is:
> dq_i = -max{u_i/Umax, 1 - (extra_bw + Uinact)} dt (2)
>
> Here in (2), we factored Umax only to the first term "u_i" and the
> second term in max{} was as left as it is. What do you think?
I agree with you, (1) looks more correct. I do not know why I
implemented (2), but I agree with (1) now.
> Now with normal DL and SCHED_FLAG_RECLAIM tasks, equation (1) can be
> re-written as:
> dq_i =
> -(max{u_i, Ureclaim_max - (extra_bw + Uinact)}/Ureclaim_max)dt (3)
>
> I tested this equation (3) and it works as expected. What do you think
> about the correctness of equation (3)?
I agree with this too.
>
> I felt that, since we are using sequential reclaim mentioned in the
> paper and we isolate all parameters per-cpu(except for extra_bw) we
> could use the "-dq = -(U/Umax) dt" equation as it was simpler than
> equation (3).
This is the part I am not sure about...
Maybe the best way to go is to split the patch: first you implement (1)
(and use div64 to remove the approximation I used), then you implement
(3) in a second patch.
Finally, if removing the max{} is really needed you can do it in a
third patch (but I would try to go with Equation 3 before removing the
max{})
Thanks,
Luca
Powered by blists - more mailing lists