Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Message-ID: <7b782bc880a29eb7d37f2c2aff73c43e7f7d032f.camel@redhat.com>
Subject: Re: [PATCH] timers/nohz: Update nohz load even if tick already
 stopped
From:   Scott Wood <swood@redhat.com>
To:     Thomas Gleixner <tglx@linutronix.de>
Cc:     Peter Zijlstra <peterz@infradead.org>,
        Frederic Weisbecker <frederic@kernel.org>,
        Ingo Molnar <mingo@kernel.org>,
        LKML <linux-kernel@vger.kernel.org>
Date:   Tue, 05 Nov 2019 01:30:58 -0600
In-Reply-To: <alpine.DEB.2.21.1911050042250.17054@nanos.tec.linutronix.de>
References: <20191028150716.22890-1-frederic@kernel.org>
          <20191029100506.GJ4114@hirez.programming.kicks-ass.net>
          <52d963553deda810113accd8d69b6dffdb37144f.camel@redhat.com>
          <20191030133130.GY4097@hirez.programming.kicks-ass.net>
         <813ed21938aa47b15f35f8834ffd98ad4dd27771.camel@redhat.com>
         <alpine.DEB.2.21.1911042315390.17054@nanos.tec.linutronix.de>
         <alpine.DEB.2.21.1911050042250.17054@nanos.tec.linutronix.de>
Organization: Red Hat
User-Agent: Evolution 3.30.5 (3.30.5-1.fc29)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: quoted-printable
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Tue, 2019-11-05 at 00:43 +0100, Thomas Gleixner wrote:
> On Mon, 4 Nov 2019, Thomas Gleixner wrote:
> > On Fri, 1 Nov 2019, Scott Wood wrote:
> > > On Wed, 2019-10-30 at 14:31 +0100, Peter Zijlstra wrote:
> > > > Oh argh! that's a bit radical of the remote tick. The normal tick
> > > > runs
> > > > just fine on idle CPUs, so lets mirror that.
> > > >=20
> > > > How's this then?
> >=20
> > ....
> > =20
> > > Needs to be tick_nohz_tick_stopped_cpu(cpu)
> > >=20
> > > After fixing that, I get:
> > >=20
> > > [    7.439068] WARNING: CPU: 20 PID: 7 at
> > > /home/root/linux/kernel/sched/core.c:3681
> > > sched_tick_remote+0x132/0x150
> >=20
> > So I'm going to apply Scotts patch if nobody comes up with a better ide=
a
> > until tomorrow.
>=20
> As Peter pointed out to me privately we should rather go and analyze the
> real thing instead of just applying duct tape.
>=20
> /me drops the patch again.

The warning is due to kernel/sched/idle.c not updating curr->se.exec_start.

While debugging I noticed an issue with a particular load pattern.  The CPU
goes non-nohz for a brief time at an interval very close to twice=20
tick_period.  When the tick is started, the timer expiration is more than
tick_period in the past, so hrtimer_forward() tries to catch up by adding
2*tick_period to the expiration.  Then the tick is stopped before that new
expiration, and when the tick is woken up the expiry is again advanced by
2*tick_period with the timer never actually running.  sched_tick_remote()
does fire every second, but there are streaks of several seconds where it
keeps catching the CPU in a non-nohz state, so neither the normal nor remot=
e
ticks are calling calc_load_nohz_remote().

Is there a reason to not just remove the hrtimer_forward() from
tick_nohz_restart(), letting the timer fire if it's in the past, which will
take care of doing hrtimer_forward()?

As for the warning in sched_tick_remote(), it seems like a test for time
since the last tick on this cpu (remote or otherwise) would be better than
relying on curr->se.exec_start, in order to detect things like this.

-Scott