From: Joel Fernandes <joel@joelfernandes.org>
To: "Paul E. McKenney" <paulmck@linux.ibm.com>
Cc: linux-kernel@vger.kernel.org,
Josh Triplett <josh@joshtriplett.org>,
kernel-team@android.com, Lai Jiangshan <jiangshanlai@gmail.com>,
linux-kselftest@vger.kernel.org,
Mathieu Desnoyers <mathieu.desnoyers@efficios.com>,
rcu@vger.kernel.org,
Sebastian Andrzej Siewior <bigeasy@linutronix.de>,
Shuah Khan <shuah@kernel.org>,
Steven Rostedt <rostedt@goodmis.org>
Subject: Re: [RFC 1/3] rcu: Expedite the rcu quiescent state reporting if help needed
Date: Tue, 2 Jul 2019 11:40:30 +0000 [thread overview]
Message-ID: <20190702114030.GA5429@localhost> (raw)
In-Reply-To: <20190702034730.GI26519@linux.ibm.com>
On Mon, Jul 01, 2019 at 08:47:30PM -0700, Paul E. McKenney wrote:
> On Mon, Jul 01, 2019 at 12:04:13AM -0400, Joel Fernandes (Google) wrote:
> > The t->rcu_read_unlock_special union's need_qs bit can be set by the
> > scheduler tick (in rcu_flavor_sched_clock_irq) to indicate that help is
> > needed from the rcu_read_unlock path. When this help arrives however, we
> > can do better to speed up the quiescent state reporting which if
> > rcu_read_unlock_special::need_qs is set might be quite urgent. Make use
> > of this information in deciding when to do heavy-weight softirq raising
> > where possible.
> >
> > Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
>
> Cute thought, but I am going to have to pass on this one. The reason
> is that by the time that ->rcu_read_unlock_special.b.need_qs gets set,
> the grace period is already one full second old. At that point, the
> extra tick of waiting is down in the noise.
>
> Right now, we do the extra work if we really are blocking an expedited
> grace period (the first two lines of the original condition) or we are
> running on a nohz_full CPU (which might never execute a scheduling clock
> tick, thus potentially delaying forever). And expedited grace periods
> are supposed to complete in tens or maybe hundreds of microseconds,
> assuming the RCU readers are being cooperative, which is a whole
> different level of urgent.
Makes sense, I agree the patch may not be that helpful right now. I mixed up
the different levels or urgencies. No problem dropping it.
>
> Nevertheless, thank you for looking into this!
My pleasure! Will keep them coming.
- Joel
>
> Thanx, Paul
>
> > ---
> > kernel/rcu/tree_plugin.h | 3 ++-
> > 1 file changed, 2 insertions(+), 1 deletion(-)
> >
> > diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
> > index c588ef98efd3..bff6410fac06 100644
> > --- a/kernel/rcu/tree_plugin.h
> > +++ b/kernel/rcu/tree_plugin.h
> > @@ -622,7 +622,8 @@ static void rcu_read_unlock_special(struct task_struct *t)
> > t->rcu_read_unlock_special.b.exp_hint = false;
> > exp = (t->rcu_blocked_node && t->rcu_blocked_node->exp_tasks) ||
> > (rdp->grpmask & rnp->expmask) ||
> > - tick_nohz_full_cpu(rdp->cpu);
> > + tick_nohz_full_cpu(rdp->cpu) ||
> > + t->rcu_read_unlock_special.b.need_qs;
> > // Need to defer quiescent state until everything is enabled.
> > if (irqs_were_disabled && use_softirq &&
> > (in_interrupt() ||
> > --
> > 2.22.0.410.gd8fdbe21b5-goog
> >
>
prev parent reply other threads:[~2019-07-02 11:40 UTC|newest]
Thread overview: 12+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-07-01 4:04 [RFC 1/3] rcu: Expedite the rcu quiescent state reporting if help needed Joel Fernandes (Google)
2019-07-01 4:04 ` [RFC 2/3] rcu: Simplify rcu_note_context_switch exit from critical section Joel Fernandes (Google)
2019-07-01 20:03 ` Paul E. McKenney
2019-07-01 21:33 ` Joel Fernandes
2019-07-01 21:42 ` Paul E. McKenney
2019-07-01 4:04 ` [RFC 3/3] Revert "rcutorture: Tweak kvm options" Joel Fernandes (Google)
2019-07-01 12:23 ` Sebastian Andrzej Siewior
2019-07-01 14:14 ` Joel Fernandes
2019-07-01 14:48 ` Dmitry Vyukov
2019-07-01 13:53 ` [RFC 1/3] rcu: Expedite the rcu quiescent state reporting if help needed Joel Fernandes
2019-07-02 3:47 ` Paul E. McKenney
2019-07-02 11:40 ` Joel Fernandes [this message]
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20190702114030.GA5429@localhost \
--to=joel@joelfernandes.org \
--cc=bigeasy@linutronix.de \
--cc=jiangshanlai@gmail.com \
--cc=josh@joshtriplett.org \
--cc=kernel-team@android.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-kselftest@vger.kernel.org \
--cc=mathieu.desnoyers@efficios.com \
--cc=paulmck@linux.ibm.com \
--cc=rcu@vger.kernel.org \
--cc=rostedt@goodmis.org \
--cc=shuah@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox