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;
MIME-Version: 1.0
References: <20230515025716.316888-1-vineeth@bitbyteword.org>
 <20230515025716.316888-3-vineeth@bitbyteword.org> <20230515100616.33ba5dd9@luca64>
 <CAO7JXPgq8V5yHM6F2+iXf4XJ9cyT30Hn4ot5b2k7srjsaPc3JQ@mail.gmail.com>
 <20230516093729.0771938c@luca64> <CAO7JXPh5uLV4QjAEi6bJXfAGSsZ=XsnCyzrvKS8m35BGbRPYJw@mail.gmail.com>
 <20230519115621.2b3f75e2@luca64> <20230519121804.6c85a3ed@luca64>
 <CAO7JXPhZPvzVRyL87qNT5VnaVOf=0wrRftFB-Rjx-vJc3JUMog@mail.gmail.com>
 <20230520115857.3838a7ea@nowhere> <CAO7JXPgXi8q02HBeBR_RLWmODd9uQBH_UMCYgVQwbf+FX=Qxkg@mail.gmail.com>
 <20230523225831.60d75b38@nowhere>
In-Reply-To: <20230523225831.60d75b38@nowhere>
From:   Vineeth Remanan Pillai <vineeth@bitbyteword.org>
Date:   Tue, 23 May 2023 22:11:23 -0400
Message-ID: <CAO7JXPihFGX5Dop=ox3YDQ=8aQbzZ-ka_1h3hT1G46vsbxpzNw@mail.gmail.com>
Subject: Re: [PATCH v3 2/5] sched/deadline: Fix reclaim inaccuracy with SMP
To:     luca abeni <luca.abeni@santannapisa.it>
Cc:     Juri Lelli <juri.lelli@redhat.com>,
        Daniel Bristot de Oliveira <bristot@redhat.com>,
        Peter Zijlstra <peterz@infradead.org>,
        Ingo Molnar <mingo@redhat.com>,
        Vincent Guittot <vincent.guittot@linaro.org>,
        Steven Rostedt <rostedt@goodmis.org>,
        Joel Fernandes <joel@joelfernandes.org>,
        Dietmar Eggemann <dietmar.eggemann@arm.com>,
        Ben Segall <bsegall@google.com>, Mel Gorman <mgorman@suse.de>,
        Valentin Schneider <vschneid@redhat.com>,
        Jonathan Corbet <corbet@lwn.net>, linux-kernel@vger.kernel.org,
        linux-doc@vger.kernel.org
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

Hi Luca,

> >
> > I think it probably makes sense to get the fix for the equation to go
> > in as a first step and then we can investigate more about the second
> > issue (less reclaiming with less load and different bandwidth) and
> > fix it separately. What do you think?
>
> I fully agree. If you split this change in a first patch, IMHO it
> can be applied.
>
Thanks, I shall have it as the first patch in the next iteration.

> BTW, I tried changing the equation without introducing div64, and it
> seems to me that it works well... So, if removing the bw_ratio
> approximation is needed, I think you can do it in a second patch (so,
> the first patch changes the reclaiming equation, and the second one
> introduces div64)
>
There was one more reason for removing the bw_ratio. The second patch
fixing the issue with mix of normal and SCHED_FLAG_RECLAIM tasks,
do not have a constant Umax, so we cannot calculate the bw_ratio in
advance and has to be calculated in grub_reclaim().

As you suggested, I shall remove the bw_ratio as the second patch and
then have the third patch to fix the case of SCHED_FLAG_RECLAIM and
normal deadline tasks. For the rest of the issues, I shall work on it as
a separate patch series once this goes in.

Will send it out tomorrow after a bit more testing.

Thanks again,
Vineeth