From: Joel Fernandes <joel@joelfernandes.org>
To: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>,
LKML <linux-kernel@vger.kernel.org>,
Peter Zijlstra <peterz@infradead.org>,
Masami Hiramatsu <mhiramat@kernel.org>,
Alexei Starovoitov <ast@kernel.org>,
Mathieu Desnoyers <mathieu.desnoyers@efficios.com>,
"Paul E. McKenney" <paulmck@kernel.org>,
Frederic Weisbecker <frederic@kernel.org>,
Daniel Bristot de Oliveira <bristot@redhat.com>,
Valentin Schneider <valentin.schneider@arm.com>
Subject: Re: Instrumentation and RCU
Date: Mon, 9 Mar 2020 11:42:28 -0700 [thread overview]
Message-ID: <CAEXW_YQJ=vGxn5P=OtdkJT4NwE9+P0rAPEEQFdAUtyZ9Ck=qug@mail.gmail.com> (raw)
In-Reply-To: <20200309141546.5b574908@gandalf.local.home>
On Mon, Mar 9, 2020 at 11:15 AM Steven Rostedt <rostedt@goodmis.org> wrote:
>
> On Mon, 09 Mar 2020 18:02:32 +0100
> Thomas Gleixner <tglx@linutronix.de> wrote:
>
[...]
> > #3) RCU idle
> >
> > Being able to trace code inside RCU idle sections is very similar to
> > the question raised in #1.
> >
> > Assume all of the instrumentation would be doing conditional RCU
> > schemes, i.e.:
> >
> > if (rcuidle)
> > ....
> > else
> > rcu_read_lock_sched()
> >
> > before invoking the actual instrumentation functions and of course
> > undoing that right after it, that really begs the question whether
> > it's worth it.
> >
> > Especially constructs like:
> >
> > trace_hardirqs_off()
> > idx = srcu_read_lock()
> > rcu_irq_enter_irqson();
> > ...
> > rcu_irq_exit_irqson();
> > srcu_read_unlock(idx);
> >
> > if (user_mode)
> > user_exit_irqsoff();
> > else
> > rcu_irq_enter();
> >
> > are really more than questionable. For 99.9999% of instrumentation
> > users it's absolutely irrelevant whether this traces the interrupt
> > disabled time of user_exit_irqsoff() or rcu_irq_enter() or not.
> >
> > But what's relevant is the tracer overhead which is e.g. inflicted
> > with todays trace_hardirqs_off/on() implementation because that
> > unconditionally uses the rcuidle variant with the scru/rcu_irq dance
> > around every tracepoint.
> >
> > Even if the tracepoint sits in the ASM code it just covers about ~20
> > low level ASM instructions more. The tracer invocation, which is
> > even done twice when coming from user space on x86 (the second call
> > is optimized in the tracer C-code), costs definitely way more
> > cycles. When you take the scru/rcu_irq dance into account it's a
> > complete disaster performance wise.
>
> Is this specifically to do with the kernel/trace/trace_preemptirqs.c code
> that was added by Joel?
Just started a vacation here and will be back on January 12th. Will
take a detailed look at Thomas's email at that time.
Adding some more folks (Daniel, Valentin) who have used the
preempt/irq tracepoints.
I agree we should reorder things and avoid these circular
dependencies, it bothers me too. I am happy to help with any clean ups
related to it. Let us definitely discuss more and fix it. Thanks.
- Joel
next prev parent reply other threads:[~2020-03-09 18:42 UTC|newest]
Thread overview: 44+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-03-09 17:02 Instrumentation and RCU Thomas Gleixner
2020-03-09 18:15 ` Steven Rostedt
2020-03-09 18:42 ` Joel Fernandes [this message]
2020-03-09 19:07 ` Steven Rostedt
2020-03-09 19:20 ` Mathieu Desnoyers
2020-03-16 15:02 ` Joel Fernandes
2020-03-09 18:59 ` Thomas Gleixner
2020-03-10 8:09 ` Masami Hiramatsu
2020-03-10 11:43 ` Thomas Gleixner
2020-03-10 15:31 ` Mathieu Desnoyers
2020-03-10 15:46 ` Steven Rostedt
2020-03-10 16:21 ` Mathieu Desnoyers
2020-03-11 0:18 ` Masami Hiramatsu
2020-03-11 0:37 ` Mathieu Desnoyers
2020-03-11 7:48 ` Masami Hiramatsu
2020-03-10 16:06 ` Masami Hiramatsu
2020-03-12 13:53 ` Peter Zijlstra
2020-03-10 15:24 ` Mathieu Desnoyers
2020-03-10 17:05 ` Daniel Thompson
2020-03-09 18:37 ` Mathieu Desnoyers
2020-03-09 18:44 ` Steven Rostedt
2020-03-09 18:52 ` Mathieu Desnoyers
2020-03-09 19:09 ` Steven Rostedt
2020-03-09 19:25 ` Mathieu Desnoyers
2020-03-09 19:52 ` Thomas Gleixner
2020-03-10 15:03 ` Mathieu Desnoyers
2020-03-10 16:48 ` Thomas Gleixner
2020-03-10 17:40 ` Mathieu Desnoyers
2020-03-10 18:31 ` Thomas Gleixner
2020-03-10 18:37 ` Mathieu Desnoyers
2020-03-10 1:40 ` Alexei Starovoitov
2020-03-10 8:02 ` Thomas Gleixner
2020-03-10 16:54 ` Paul E. McKenney
2020-03-17 17:56 ` Joel Fernandes
2020-03-09 20:18 ` Peter Zijlstra
2020-03-09 20:47 ` Paul E. McKenney
2020-03-09 20:58 ` Steven Rostedt
2020-03-09 21:25 ` Paul E. McKenney
2020-03-09 23:52 ` Frederic Weisbecker
2020-03-10 2:26 ` Paul E. McKenney
2020-03-10 15:13 ` Mathieu Desnoyers
2020-03-10 16:49 ` Paul E. McKenney
2020-03-10 17:22 ` Mathieu Desnoyers
2020-03-10 17:26 ` Paul E. McKenney
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='CAEXW_YQJ=vGxn5P=OtdkJT4NwE9+P0rAPEEQFdAUtyZ9Ck=qug@mail.gmail.com' \
--to=joel@joelfernandes.org \
--cc=ast@kernel.org \
--cc=bristot@redhat.com \
--cc=frederic@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mathieu.desnoyers@efficios.com \
--cc=mhiramat@kernel.org \
--cc=paulmck@kernel.org \
--cc=peterz@infradead.org \
--cc=rostedt@goodmis.org \
--cc=tglx@linutronix.de \
--cc=valentin.schneider@arm.com \
/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;
as well as URLs for NNTP newsgroup(s).