Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
MIME-Version: 1.0
References: <20200422112719.826676174@infradead.org> <20200422112831.988065598@infradead.org>
 <CAKfTPtB8NiKqggZN3v6u=Rdwj4grzRwn1mW31ov0y5ZhDBcvuw@mail.gmail.com>
 <20200422132923.GK20730@hirez.programming.kicks-ass.net> <CAKfTPtBsFDt8JyxjD39B2YP+kCN9nXWZxnaJys9sz2CjWzd1Zw@mail.gmail.com>
 <20200422135921.GL20730@hirez.programming.kicks-ass.net> <CAKfTPtDa2JPtc2qPSe=d187u8pp7AdvV4wKJiUJsDiAvUTE9hg@mail.gmail.com>
 <20200422153910.GN20730@hirez.programming.kicks-ass.net>
In-Reply-To: <20200422153910.GN20730@hirez.programming.kicks-ass.net>
From:   Vincent Guittot <vincent.guittot@linaro.org>
Date:   Wed, 22 Apr 2020 17:52:55 +0200
Message-ID: <CAKfTPtA=d6pnczmU8LFpV=d-9-KArO0qfQuvzod5xYo1pKjK5g@mail.gmail.com>
Subject: Re: [PATCH 13/23] sched,ion: Convert to sched_set_normal()
To:     Peter Zijlstra <peterz@infradead.org>
Cc:     Ingo Molnar <mingo@kernel.org>,
        linux-kernel <linux-kernel@vger.kernel.org>,
        Thomas Gleixner <tglx@linutronix.de>,
        Steven Rostedt <rostedt@goodmis.org>,
        Qais Yousef <qais.yousef@arm.com>,
        Juri Lelli <juri.lelli@redhat.com>,
        Dietmar Eggemann <dietmar.eggemann@arm.com>,
        Ben Segall <bsegall@google.com>, Mel Gorman <mgorman@suse.de>,
        John Stultz <john.stultz@linaro.org>
Content-Type: text/plain; charset="UTF-8"
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Wed, 22 Apr 2020 at 17:39, Peter Zijlstra <peterz@infradead.org> wrote:
>
> On Wed, Apr 22, 2020 at 05:09:15PM +0200, Vincent Guittot wrote:
> > > It's not unbounded, like a true idle-time scheduler would be, but it can
> > > still be pretty horrible. nice19 has some of that too of course, but
> > > idle has it worse, esp. also because it begs others to preempt it.
> >
> > Yeah... you have to pay the benefit of letting other tasks to preempt
> > faster. But both sched_idle and nice19 have the same weight
>
> #define WEIGHT_IDLEPRIO         3
>
>  /*  15 */        36,        29,        23,        18,        15,
>
> 15 != 3

Good point
Don't know why I thought they had same weight

>
> Also, like said elsewhere, idle is much more eager to let itself be
> preempted.