MIME-Version: 1.0
In-Reply-To: <20170708101700.4678-1-joelaf@google.com>
References: <20170708101700.4678-1-joelaf@google.com>
From: Joel Fernandes <joelaf@google.com>
Date: Sat, 8 Jul 2017 03:22:57 -0700
Message-ID: <CAJWu+opLARcOj1qpQmrAkjg7jrthYRqmmtLVASRG+aKmagxnRg@mail.gmail.com>
Subject: Re: [PATCH RFC v3] cpufreq: schedutil: Make iowait boost more energy efficient
To: LKML <linux-kernel@vger.kernel.org>
Cc: Patrick Bellasi <patrick.bellasi@arm.com>,
        Juri Lelli <juri.lelli@arm.com>,
        Andres Oportus <andresoportus@google.com>,
        Dietmar Eggemann <dietmar.eggemann@arm.com>,
        Joel Fernandes <joelaf@google.com>,
        Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>,
        Len Brown <lenb@kernel.org>, "Rafael J . Wysocki" <rjw@rjwysocki.net>,
        Viresh Kumar <viresh.kumar@linaro.org>, Ingo Molnar <mingo@redhat.com>,
        Peter Zijlstra <peterz@infradead.org>
Content-Type: text/plain; charset="UTF-8"
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 621
Lines: 18

Hi,

On Sat, Jul 8, 2017 at 3:17 AM, Joel Fernandes <joelaf@google.com> wrote:
> Currently the iowait_boost feature in schedutil makes the frequency go to max.
> This is to handle a case that Peter described where the through put of
> operations involving continuous I/O requests [1].

Apologies for the incomplete line here, I'll rewrite the commit
message in a subsequent patch.

I meant to say "This is to handle a case that Peter described where
the throughput of operations involving continuous I/O requests is a
victim of low-frequency and ends up getting 'stuck' in a loop as he
described in [1]."

thanks,

-Joel