From: "Paul E. McKenney" <paulmck@linux.ibm.com>
To: Joel Fernandes <joel@joelfernandes.org>
Cc: rcu@vger.kernel.org
Subject: Re: need_heavy_qs flag for PREEMPT=y kernels
Date: Sun, 11 Aug 2019 14:13:18 -0700 [thread overview]
Message-ID: <20190811211318.GX28441@linux.ibm.com> (raw)
In-Reply-To: <20190811180852.GA128944@google.com>
On Sun, Aug 11, 2019 at 02:08:52PM -0400, Joel Fernandes wrote:
> Hi Paul, everyone,
>
> I noticed on reading code that the need_heavy_qs check and
> rcu_momentary_dyntick_idle() is only called for !PREEMPT kernels. Don't we
> need to call this for PREEMPT kernels for the benefit of nohz_full CPUs?
>
> Consider the following events:
> 1. Kernel is PREEMPT=y configuration.
> 2. CPU 2 is a nohz_full CPU running only a single task and the tick is off.
> 3. CPU 2 is running only in kernel mode and does not enter user mode or idle.
> 4. Grace period thread running on CPU 3 enter the fqs loop.
> 5. Enough time passes and it sets the need_heavy_qs for CPU2.
> 6. CPU 2 is still in kernel mode but does cond_resched().
> 7. cond_resched() does not call rcu_momentary_dyntick_idle() because PREEMPT=y.
>
> Is 7. not calling rcu_momentary_dyntick_idle() a lost opportunity for the FQS
> loop to detect that the CPU has crossed a quiescent point?
>
> Is this done so that cond_resched() is fast for PREEMPT=y kernels?
The problem is that the definiton of cond_resched() in PREEMPT=y
kernels is as follows:
static inline int _cond_resched(void) { return 0; }
If (but only if!) someone shows a problem in a PREEMPT=y kernel, the
code could be updated to do something like a resched_cpu() earlier
rather than later.
The reason that I do not expect a problem in NO_HZ_FULL=n&&PREEMPT=y
kernels is that the scheduling-clock tick will with high probability
happen when the CPU is not in an RCU read-side critical section, and
this quiescent state will be reported reasonably quickly.
This leaves NO_HZ_FULL=y&&PREEMPT=y kernels. In that case, RCU is
more aggressive about using resched_cpu() on CPUs that have not yet
reported a quiescent state for the current grace period.
So we should be good as is.
Or am I missing a key corner case here?
Thanx, Paul
next prev parent reply other threads:[~2019-08-11 21:13 UTC|newest]
Thread overview: 31+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-08-11 18:08 need_heavy_qs flag for PREEMPT=y kernels Joel Fernandes
2019-08-11 18:34 ` Joel Fernandes
2019-08-11 21:16 ` Paul E. McKenney
2019-08-11 21:25 ` Joel Fernandes
2019-08-11 23:30 ` Paul E. McKenney
2019-08-12 1:24 ` Joel Fernandes
2019-08-12 1:40 ` Joel Fernandes
2019-08-12 3:57 ` Paul E. McKenney
2019-08-11 21:13 ` Paul E. McKenney [this message]
2019-08-12 3:21 ` Joel Fernandes
2019-08-12 3:53 ` Paul E. McKenney
2019-08-12 21:20 ` Joel Fernandes
2019-08-12 23:01 ` Paul E. McKenney
2019-08-13 1:02 ` Joel Fernandes
2019-08-13 1:05 ` Joel Fernandes
2019-08-13 2:28 ` Paul E. McKenney
2019-08-13 2:27 ` Paul E. McKenney
2019-08-13 2:50 ` Paul E. McKenney
2019-08-15 17:17 ` Paul E. McKenney
2019-08-15 20:04 ` Joel Fernandes
2019-08-15 20:31 ` Paul E. McKenney
2019-08-15 21:22 ` Joel Fernandes
2019-08-15 21:27 ` Joel Fernandes
2019-08-15 21:34 ` Joel Fernandes
2019-08-15 21:57 ` Paul E. McKenney
2019-08-15 21:45 ` Paul E. McKenney
2019-08-16 0:02 ` Joel Fernandes
2019-08-19 12:34 ` Frederic Weisbecker
2019-08-19 12:09 ` Frederic Weisbecker
2019-08-19 16:57 ` Frederic Weisbecker
2019-08-19 22:31 ` 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=20190811211318.GX28441@linux.ibm.com \
--to=paulmck@linux.ibm.com \
--cc=joel@joelfernandes.org \
--cc=rcu@vger.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;
as well as URLs for NNTP newsgroup(s).