LKML Archive on lore.kernel.org
 help / color / Atom feed
From: Vincent Guittot <vincent.guittot@linaro.org>
To: Qais Yousef <qais.yousef@arm.com>
Cc: Mel Gorman <mgorman@suse.de>,
	Patrick Bellasi <patrick.bellasi@matbug.net>,
	Dietmar Eggemann <dietmar.eggemann@arm.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@redhat.com>,
	Randy Dunlap <rdunlap@infradead.org>,
	Jonathan Corbet <corbet@lwn.net>,
	Juri Lelli <juri.lelli@redhat.com>,
	Steven Rostedt <rostedt@goodmis.org>,
	Ben Segall <bsegall@google.com>,
	Luis Chamberlain <mcgrof@kernel.org>,
	Kees Cook <keescook@chromium.org>,
	Iurii Zaikin <yzaikin@google.com>,
	Quentin Perret <qperret@google.com>,
	Valentin Schneider <valentin.schneider@arm.com>,
	Pavan Kondeti <pkondeti@codeaurora.org>,
	linux-doc@vger.kernel.org,
	linux-kernel <linux-kernel@vger.kernel.org>,
	linux-fs <linux-fsdevel@vger.kernel.org>
Subject: Re: [PATCH 1/2] sched/uclamp: Add a new sysctl to control RT default boost value
Date: Thu, 11 Jun 2020 14:01:11 +0200
Message-ID: <CAKfTPtDnWuBOJxJP7ahX4Kzu+8jvPjAcE6XErMtG1SCJMdZZ-w@mail.gmail.com> (raw)
In-Reply-To: <20200611102407.vhy3zjexrhorx753@e107158-lin.cambridge.arm.com>

On Thu, 11 Jun 2020 at 12:24, Qais Yousef <qais.yousef@arm.com> wrote:
>
> On 06/09/20 19:10, Vincent Guittot wrote:
> > On Mon, 8 Jun 2020 at 14:31, Qais Yousef <qais.yousef@arm.com> wrote:
> > >
> > > On 06/04/20 14:14, Vincent Guittot wrote:
> > >
> > > [...]
> > >
> > > > I have tried your patch and I don't see any difference compared to
> > > > previous tests. Let me give you more details of my setup:
> > > > I create 3 levels of cgroups and usually run the tests in the 4 levels
> > > > (which includes root). The result above are for the root level
> > > >
> > > > But I see a difference at other levels:
> > > >
> > > >                            root           level 1       level 2       level 3
> > > >
> > > > /w patch uclamp disable     50097         46615         43806         41078
> > > > tip uclamp enable           48706(-2.78%) 45583(-2.21%) 42851(-2.18%)
> > > > 40313(-1.86%)
> > > > /w patch uclamp enable      48882(-2.43%) 45774(-1.80%) 43108(-1.59%)
> > > > 40667(-1.00%)
> > > >
> > > > Whereas tip with uclamp stays around 2% behind tip without uclamp, the
> > > > diff of uclamp with your patch tends to decrease when we increase the
> > > > number of level
> > >
> > > So I did try to dig more into this, but I think it's either not a good
> > > reproducer or what we're observing here is uArch level latencies caused by the
> > > new code that seem to produce a bigger knock on effect than what they really
> > > are.
> > >
> > > First, CONFIG_FAIR_GROUP_SCHED is 'expensive', for some definition of
> > > expensive..
> >
> > yes, enabling CONFIG_FAIR_GROUP_SCHED adds an overhead
> >
> > >
> > > *** uclamp disabled/fair group enabled ***
> > >
> > >         # Executed 50000 pipe operations between two threads
> > >
> > >              Total time: 0.958 [sec]
> > >
> > >               19.177100 usecs/op
> > >                   52145 ops/sec
> > >
> > > *** uclamp disabled/fair group disabled ***
> > >
> > >         # Executed 50000 pipe operations between two threads
> > >              Total time: 0.808 [sec]
> > >
> > >              16.176200 usecs/op
> > >                  61819 ops/sec
> > >
> > > So there's a 15.6% drop in ops/sec when enabling this option. I think it's good
> > > to look at the absolutely number of usecs/op, Fair group adds around
> > > 3 usecs/op.
> > >
> > > I dropped FAIR_GROUP_SCHED from my config to eliminate this overhead and focus
> > > on solely on uclamp overhead.
> >
> > Have you checked that both tests run at the root level ?
>
> I haven't actively moved tasks to cgroups. As I said that snippet was
> particularly bad and I didn't see that level of nesting in every call.
>
> > Your function-graph log below shows several calls to
> > update_cfs_group() which means that your trace below has not been made
> > at root level but most probably at the 3rd level and I wonder if you
> > used the same setup for running the benchmark above. This could
> > explain such huge difference because I don't have such difference on
> > my platform but more around 2%
>
> What promoted me to look at this is when you reported that even without uclamp
> the nested cgroup showed a drop at each level. I was just trying to understand
> how both affect the hot path in hope to understand the root cause of uclamp
> overhead.
>
> >
> > For uclamp disable/fair group enable/ function graph enable :  47994ops/sec
> > For uclamp disable/fair group disable/ function graph enable : 49107ops/sec
> >
> > >
> > > With uclamp enabled but no fair group I get
> > >
> > > *** uclamp enabled/fair group disabled ***
> > >
> > >         # Executed 50000 pipe operations between two threads
> > >              Total time: 0.856 [sec]
> > >
> > >              17.125740 usecs/op
> > >                  58391 ops/sec
> > >
> > > The drop is 5.5% in ops/sec. Or 1 usecs/op.
> > >
> > > I don't know what's the expectation here. 1 us could be a lot, but I don't
> > > think we expect the new code to take more than few 100s of ns anyway. If you
> > > add potential caching effects, reaching 1 us wouldn't be that hard.
> > >
> > > Note that in my runs I chose performance governor and use `taskset 0x2` to
> >
> > You might want to set 2 CPUs in your cpumask instead of 1 in order to
> > have 1 CPU for each thread
>
> I did try that but it didn't seem to change the number. I think the 2 tasks
> interleave so running in 2 CPUs doesn't change the result. But to ease ftrace
> capture, it's easier to monitor a single cpu.
>
> >
> > > force running on a big core to make sure the runs are repeatable.
> >
> > I also use performance governor but don't pinned tasks because I use smp.
>
> Is your arm platform SMP?

Yes, all my tests are done on the Arm64 octo core  smp system

>
> >
> > >
> > > On Juno-r2 I managed to scrap most of the 1 us with the below patch. It seems
> > > there was weird branching behavior that affects the I$ in my case. It'd be good
> > > to try it out to see if it makes a difference for you.
> >
> > The perf are slightly worse on my setup:
> > For uclamp enable/fair group disable/ function graph enable : 48413ops/sec
> > with patch  below : 47804os/sec
>
> I am not sure if the new code could just introduce worse cache performance
> in a platform dependent way. The evidences I have so far point in this
> direction.
>
> >
> > >
> > > The I$ effect is my best educated guess. Perf doesn't catch this path and
> > > I couldn't convince it to look at cache and branch misses between 2 specific
> > > points.
> > >
> > > Other subtle code shuffling did have weird effect on the result too. One worthy
> > > one is making uclamp_rq_dec() noinline gains back ~400 ns. Making
> > > uclamp_rq_inc() noinline *too* cancels this gain out :-/
> > >
> > >
> > > diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> > > index 0464569f26a7..0835ee20a3c7 100644
> > > --- a/kernel/sched/core.c
> > > +++ b/kernel/sched/core.c
> > > @@ -1071,13 +1071,11 @@ static inline void uclamp_rq_dec_id(struct rq *rq, struct task_struct *p,
> > >
> > >  static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p)
> > >  {
> > > -       enum uclamp_id clamp_id;
> > > -
> > >         if (unlikely(!p->sched_class->uclamp_enabled))
> > >                 return;
> > >
> > > -       for_each_clamp_id(clamp_id)
> > > -               uclamp_rq_inc_id(rq, p, clamp_id);
> > > +       uclamp_rq_inc_id(rq, p, UCLAMP_MIN);
> > > +       uclamp_rq_inc_id(rq, p, UCLAMP_MAX);
> > >
> > >         /* Reset clamp idle holding when there is one RUNNABLE task */
> > >         if (rq->uclamp_flags & UCLAMP_FLAG_IDLE)
> > > @@ -1086,13 +1084,11 @@ static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p)
> > >
> > >  static inline void uclamp_rq_dec(struct rq *rq, struct task_struct *p)
> > >  {
> > > -       enum uclamp_id clamp_id;
> > > -
> > >         if (unlikely(!p->sched_class->uclamp_enabled))
> > >                 return;
> > >
> > > -       for_each_clamp_id(clamp_id)
> > > -               uclamp_rq_dec_id(rq, p, clamp_id);
> > > +       uclamp_rq_dec_id(rq, p, UCLAMP_MIN);
> > > +       uclamp_rq_dec_id(rq, p, UCLAMP_MAX);
> > >  }
> > >
> > >  static inline void
> > >
> > >
> > > FWIW I fail to see activate/deactivate_task in perf record. They don't show up
> > > on the list which means this micro benchmark doesn't stress them as Mel's test
> > > does.
> >
> > Strange because I have been able to trace them.
>
> On your arm platform? I can certainly see them on x86.

yes on my arm platform

>
> Thanks

>
> --
> Qais Yousef

  reply index

Thread overview: 68+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-05-11 15:40 Qais Yousef
2020-05-11 15:40 ` [PATCH 2/2] Documentation/sysctl: Document uclamp sysctl knobs Qais Yousef
2020-05-11 17:18 ` [PATCH 1/2] sched/uclamp: Add a new sysctl to control RT default boost value Qais Yousef
2020-05-12  2:10 ` Pavan Kondeti
2020-05-12 11:46   ` Qais Yousef
2020-05-15 11:08 ` Patrick Bellasi
2020-05-18  8:31 ` Dietmar Eggemann
2020-05-18 16:49   ` Qais Yousef
2020-05-28 13:23 ` Peter Zijlstra
2020-05-28 15:58   ` Qais Yousef
2020-05-28 16:11     ` Peter Zijlstra
2020-05-28 16:51       ` Qais Yousef
2020-05-28 18:29         ` Peter Zijlstra
2020-05-28 19:08           ` Patrick Bellasi
2020-05-28 19:20           ` Dietmar Eggemann
2020-05-29  9:11           ` Qais Yousef
2020-05-29 10:21         ` Mel Gorman
2020-05-29 15:11           ` Qais Yousef
2020-05-29 16:02             ` Mel Gorman
2020-05-29 16:05               ` Qais Yousef
2020-05-29 10:08       ` Mel Gorman
2020-05-29 16:04         ` Qais Yousef
2020-05-29 16:57           ` Mel Gorman
2020-06-02 16:46         ` Dietmar Eggemann
2020-06-03  8:29           ` Patrick Bellasi
2020-06-03 10:10             ` Mel Gorman
2020-06-03 14:59               ` Vincent Guittot
2020-06-03 16:52                 ` Qais Yousef
2020-06-04 12:14                   ` Vincent Guittot
2020-06-05 10:45                     ` Qais Yousef
2020-06-09 15:29                       ` Vincent Guittot
2020-06-08 12:31                     ` Qais Yousef
2020-06-08 13:06                       ` Valentin Schneider
2020-06-08 14:44                       ` Steven Rostedt
2020-06-11 10:13                         ` Qais Yousef
2020-06-09 17:10                       ` Vincent Guittot
2020-06-11 10:24                         ` Qais Yousef
2020-06-11 12:01                           ` Vincent Guittot [this message]
2020-06-23 15:44                             ` Qais Yousef
2020-06-24  8:45                               ` Vincent Guittot
2020-06-05  7:55                   ` Patrick Bellasi
2020-06-05 11:32                     ` Qais Yousef
2020-06-05 13:27                       ` Patrick Bellasi
2020-06-03  9:40           ` Mel Gorman
2020-06-03 12:41             ` Qais Yousef
2020-06-04 13:40               ` Mel Gorman
2020-06-05 10:58                 ` Qais Yousef
2020-06-11 10:58                 ` Qais Yousef
2020-06-16 11:08                   ` Qais Yousef
2020-06-16 13:56                     ` Lukasz Luba
  -- strict thread matches above, loose matches on Subject: below --
2020-04-03 12:30 Qais Yousef
2020-04-14 18:21 ` Patrick Bellasi
2020-04-15  7:46   ` Patrick Bellasi
2020-04-20 15:04     ` Qais Yousef
2020-04-20  8:24   ` Dietmar Eggemann
2020-04-20 15:19     ` Qais Yousef
2020-04-21  0:52       ` Steven Rostedt
2020-04-21 11:16         ` Dietmar Eggemann
2020-04-21 11:23           ` Qais Yousef
2020-04-20 14:50   ` Qais Yousef
2020-04-15 10:11 ` Quentin Perret
2020-04-20 15:08   ` Qais Yousef
2020-04-20  8:29 ` Dietmar Eggemann
2020-04-20 15:13   ` Qais Yousef
2020-04-21 11:18     ` Dietmar Eggemann
2020-04-21 11:27       ` Qais Yousef
2020-04-22 10:59         ` Dietmar Eggemann
2020-04-22 13:13           ` Qais Yousef

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=CAKfTPtDnWuBOJxJP7ahX4Kzu+8jvPjAcE6XErMtG1SCJMdZZ-w@mail.gmail.com \
    --to=vincent.guittot@linaro.org \
    --cc=bsegall@google.com \
    --cc=corbet@lwn.net \
    --cc=dietmar.eggemann@arm.com \
    --cc=juri.lelli@redhat.com \
    --cc=keescook@chromium.org \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mcgrof@kernel.org \
    --cc=mgorman@suse.de \
    --cc=mingo@redhat.com \
    --cc=patrick.bellasi@matbug.net \
    --cc=peterz@infradead.org \
    --cc=pkondeti@codeaurora.org \
    --cc=qais.yousef@arm.com \
    --cc=qperret@google.com \
    --cc=rdunlap@infradead.org \
    --cc=rostedt@goodmis.org \
    --cc=valentin.schneider@arm.com \
    --cc=yzaikin@google.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

LKML Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/lkml/0 lkml/git/0.git
	git clone --mirror https://lore.kernel.org/lkml/1 lkml/git/1.git
	git clone --mirror https://lore.kernel.org/lkml/2 lkml/git/2.git
	git clone --mirror https://lore.kernel.org/lkml/3 lkml/git/3.git
	git clone --mirror https://lore.kernel.org/lkml/4 lkml/git/4.git
	git clone --mirror https://lore.kernel.org/lkml/5 lkml/git/5.git
	git clone --mirror https://lore.kernel.org/lkml/6 lkml/git/6.git
	git clone --mirror https://lore.kernel.org/lkml/7 lkml/git/7.git
	git clone --mirror https://lore.kernel.org/lkml/8 lkml/git/8.git
	git clone --mirror https://lore.kernel.org/lkml/9 lkml/git/9.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 lkml lkml/ https://lore.kernel.org/lkml \
		linux-kernel@vger.kernel.org
	public-inbox-index lkml

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-kernel


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git