From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
To: Frederic Weisbecker <fweisbec@gmail.com>
Cc: LKML <linux-kernel@vger.kernel.org>,
Josh Triplett <josh@joshtriplett.org>,
Steven Rostedt <rostedt@goodmis.org>,
Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Subject: Re: [PATCH] rcu: Only pin GP kthread when full dynticks is actually used
Date: Thu, 12 Jun 2014 18:35:15 -0700 [thread overview]
Message-ID: <20140613013515.GA9589@linux.vnet.ibm.com> (raw)
In-Reply-To: <20140613012432.GH4581@linux.vnet.ibm.com>
On Thu, Jun 12, 2014 at 06:24:32PM -0700, Paul E. McKenney wrote:
> On Fri, Jun 13, 2014 at 02:16:59AM +0200, Frederic Weisbecker wrote:
> > CONFIG_NO_HZ_FULL may be enabled widely on distros nowadays but actual
> > users should be a tiny minority, if actually any.
> >
> > Also there is a risk that affining the GP kthread to a single CPU could
> > end up noticeably reducing RCU performances and increasing energy
> > consumption.
> >
> > So lets affine the GP kthread only when nohz full is actually used
> > (ie: when the nohz_full= parameter is filled or CONFIG_NO_HZ_FULL_ALL=y)
Which reminds me... Kernel-heavy workloads running NO_HZ_FULL_ALL=y
can see long RCU grace periods, as in about two seconds each. It is
not hard for me to detect this situation. Is there some way I can
call for a given CPU's scheduling-clock interrupt to be turned on?
I believe that the nsproxy guys were seeing something like this as well.
Thanx, Paul
> > Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
> > Cc: Josh Triplett <josh@joshtriplett.org>
> > Cc: Steven Rostedt <rostedt@goodmis.org>
> > Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
> > ---
> > kernel/rcu/tree_plugin.h | 10 +++++++---
> > 1 file changed, 7 insertions(+), 3 deletions(-)
> >
> > diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
> > index cbc2c45..726f52c 100644
> > --- a/kernel/rcu/tree_plugin.h
> > +++ b/kernel/rcu/tree_plugin.h
> > @@ -2843,12 +2843,16 @@ static bool rcu_nohz_full_cpu(struct rcu_state *rsp)
> > */
> > static void rcu_bind_gp_kthread(void)
> > {
> > -#ifdef CONFIG_NO_HZ_FULL
> > - int cpu = ACCESS_ONCE(tick_do_timer_cpu);
> > + int cpu;
> > +
> > + if (!tick_nohz_full_enabled())
> > + return;
> > +
> > + cpu = ACCESS_ONCE(tick_do_timer_cpu);
> >
> > if (cpu < 0 || cpu >= nr_cpu_ids)
> > return;
> > +
> > if (raw_smp_processor_id() != cpu)
> > set_cpus_allowed_ptr(current, cpumask_of(cpu));
> > -#endif /* #ifdef CONFIG_NO_HZ_FULL */
> > }
>
> Hello, Frederic,
>
> I have the following queued. Shall I port yours on top of mine, or is
> there an issue with mine?
>
> Thanx, Paul
>
> ------------------------------------------------------------------------
>
> rcu: Bind grace-period kthreads to non-NO_HZ_FULL CPUs
>
> Binding the grace-period kthreads to the timekeeping CPU resulted in
> significant performance decreases for some workloads. For more detail,
> see:
>
> https://lkml.org/lkml/2014/6/3/395 for benchmark numbers
>
> https://lkml.org/lkml/2014/6/4/218 for CPU statistics
>
> It turns out that it is necessary to bind the grace-period kthreads
> to the timekeeping CPU only when all but CPU 0 is a nohz_full CPU
> on the one hand or if CONFIG_NO_HZ_FULL_SYSIDLE=y on the other.
> In other cases, it suffices to bind the grace-period kthreads to the
> set of non-nohz_full CPUs.
>
> This commit therefore creates a tick_nohz_not_full_mask that is the
> complement of tick_nohz_full_mask, and then binds the grace-period
> kthread to the set of CPUs indicated by this new mask, which covers
> the CONFIG_NO_HZ_FULL_SYSIDLE=n case. The CONFIG_NO_HZ_FULL_SYSIDLE=y
> case still binds the grace-period kthreads to the timekeeping CPU.
>
> Reported-by: Jet Chen <jet.chen@intel.com>
> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
>
> diff --git a/include/linux/tick.h b/include/linux/tick.h
> index b84773cb9f4c..1fe0c05eee39 100644
> --- a/include/linux/tick.h
> +++ b/include/linux/tick.h
> @@ -162,6 +162,7 @@ static inline u64 get_cpu_iowait_time_us(int cpu, u64 *unused) { return -1; }
> #ifdef CONFIG_NO_HZ_FULL
> extern bool tick_nohz_full_running;
> extern cpumask_var_t tick_nohz_full_mask;
> +extern cpumask_var_t tick_nohz_not_full_mask;
>
> static inline bool tick_nohz_full_enabled(void)
> {
> diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
> index 7ce734040a5e..ec7627becaf0 100644
> --- a/kernel/rcu/tree_plugin.h
> +++ b/kernel/rcu/tree_plugin.h
> @@ -2863,7 +2863,12 @@ static void rcu_bind_gp_kthread(void)
>
> if (cpu < 0 || cpu >= nr_cpu_ids)
> return;
> +#ifdef CONFIG_NO_HZ_FULL_SYSIDLE
> if (raw_smp_processor_id() != cpu)
> set_cpus_allowed_ptr(current, cpumask_of(cpu));
> +#else /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
> + if (!cpumask_test_cpu(raw_smp_processor_id(), tick_nohz_not_full_mask))
> + set_cpus_allowed_ptr(current, tick_nohz_not_full_mask);
> +#endif /* #else #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
> #endif /* #ifdef CONFIG_NO_HZ_FULL */
> }
> diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
> index 9f8af69c67ec..02209e957e76 100644
> --- a/kernel/time/tick-sched.c
> +++ b/kernel/time/tick-sched.c
> @@ -151,6 +151,7 @@ static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs)
>
> #ifdef CONFIG_NO_HZ_FULL
> cpumask_var_t tick_nohz_full_mask;
> +cpumask_var_t tick_nohz_not_full_mask;
> bool tick_nohz_full_running;
>
> static bool can_stop_full_tick(void)
> @@ -278,6 +279,7 @@ static int __init tick_nohz_full_setup(char *str)
> int cpu;
>
> alloc_bootmem_cpumask_var(&tick_nohz_full_mask);
> + alloc_bootmem_cpumask_var(&tick_nohz_not_full_mask);
> if (cpulist_parse(str, tick_nohz_full_mask) < 0) {
> pr_warning("NOHZ: Incorrect nohz_full cpumask\n");
> return 1;
> @@ -288,6 +290,8 @@ static int __init tick_nohz_full_setup(char *str)
> pr_warning("NO_HZ: Clearing %d from nohz_full range for timekeeping\n", cpu);
> cpumask_clear_cpu(cpu, tick_nohz_full_mask);
> }
> + cpumask_andnot(tick_nohz_not_full_mask,
> + cpu_possible_mask, tick_nohz_full_mask);
> tick_nohz_full_running = true;
>
> return 1;
> @@ -332,6 +336,8 @@ static int tick_nohz_init_all(void)
> err = 0;
> cpumask_setall(tick_nohz_full_mask);
> cpumask_clear_cpu(smp_processor_id(), tick_nohz_full_mask);
> + cpumask_clear(tick_nohz_not_full_mask);
> + cpumask_set_cpu(smp_processor_id(), tick_nohz_not_full_mask);
> tick_nohz_full_running = true;
> #endif
> return err;
next prev parent reply other threads:[~2014-06-13 1:35 UTC|newest]
Thread overview: 33+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-06-13 0:16 [PATCH] rcu: Only pin GP kthread when full dynticks is actually used Frederic Weisbecker
2014-06-13 1:24 ` Paul E. McKenney
2014-06-13 1:35 ` Paul E. McKenney [this message]
2014-06-13 12:47 ` Frederic Weisbecker
2014-06-13 15:52 ` Paul E. McKenney
2014-06-13 16:00 ` Frederic Weisbecker
2014-06-13 16:16 ` Paul E. McKenney
2014-06-13 16:21 ` Frederic Weisbecker
2014-06-13 16:44 ` Josh Triplett
2014-06-13 20:48 ` Paul E. McKenney
2014-06-13 21:10 ` Josh Triplett
2014-06-13 22:49 ` Paul E. McKenney
2014-06-13 23:10 ` Frederic Weisbecker
2014-06-13 23:27 ` Paul E. McKenney
2014-06-13 23:39 ` Frederic Weisbecker
2014-06-14 5:06 ` Paul E. McKenney
2014-06-14 11:26 ` Paul E. McKenney
2014-06-14 13:10 ` Frederic Weisbecker
2014-06-14 14:29 ` Paul E. McKenney
2014-06-14 13:05 ` Frederic Weisbecker
2014-06-13 20:49 ` Paul E. McKenney
2014-06-13 23:13 ` Frederic Weisbecker
2014-06-13 23:22 ` Paul E. McKenney
2014-06-13 2:05 ` Paul E. McKenney
2014-06-13 12:55 ` Frederic Weisbecker
2014-06-13 15:55 ` Paul E. McKenney
2014-06-13 16:03 ` Frederic Weisbecker
2014-06-13 16:20 ` Paul E. McKenney
2014-06-13 16:10 ` Paul E. McKenney
2014-06-13 12:42 ` Frederic Weisbecker
2014-06-13 15:58 ` Paul E. McKenney
2014-06-13 16:09 ` Frederic Weisbecker
2014-06-13 16:23 ` 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=20140613013515.GA9589@linux.vnet.ibm.com \
--to=paulmck@linux.vnet.ibm.com \
--cc=fweisbec@gmail.com \
--cc=josh@joshtriplett.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mathieu.desnoyers@efficios.com \
--cc=rostedt@goodmis.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).