[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <9eb70e53-0d8a-94e8-7da4-b577aaafd56e@redhat.com>
Date: Thu, 11 May 2017 19:07:01 +0200
From: Daniel Bristot de Oliveira <bristot@...hat.com>
To: Peter Zijlstra <peterz@...radead.org>
Cc: Ingo Molnar <mingo@...hat.com>, Xunlei Pang <xpang@...hat.com>,
Juri Lelli <juri.lelli@....com>,
Steven Rostedt <rostedt@...dmis.org>,
Luca Abeni <luca.abeni@...tannapisa.it>,
Tommaso Cucinotta <tommaso.cucinotta@...up.it>,
Romulo Silva de Oliveira <romulo.deoliveira@...c.br>,
linux-kernel@...r.kernel.org
Subject: Re: [PATCH RFC] sched/deadline: Use the revised wakeup rule for
suspending constrained dl tasks
On 05/04/2017 04:23 PM, Peter Zijlstra wrote:
> On Thu, May 04, 2017 at 04:17:21PM +0200, Peter Zijlstra wrote:
>> On Mon, Apr 24, 2017 at 05:18:35PM +0200, Daniel Bristot de Oliveira wrote:
>>> +static void
>>> +update_dl_revised_wakeup(struct sched_dl_entity *dl_se, struct rq *rq)
>>> +{
>>> + u64 density = div64_u64(dl_se->dl_runtime << 20, dl_se->dl_deadline);
>>> + u64 laxity = dl_se->deadline - rq_clock(rq);
>>> +
>>> + BUG_ON(laxity < 0);
>> Compiler will make that go away, by virtue of laxity being unsigned.
> Also, so we want that to BUG (or even WARN) in a soft RT setting.
> Remember, GEDF does not guarantee we make our deadlines.
The point is that, a task with laxity < 0 should be throttled before
this point by:
df8eac8cafce ("sched/deadline: Throttle a constrained deadline task
activated after the deadline")
Arrive here with (laxity < 0) meas that we skipped that check.
>> We use two difference CBS rules:
> _different_, clearly I cannot type anymore either ;-)
ops... :-)
-- Daniel
Powered by blists - more mailing lists