All of lore.kernel.org
 help / color / mirror / Atom feed
From: Peter Zijlstra <peterz@infradead.org>
To: lkp@lists.01.org
Subject: Re: [sched/fair] 53d3bc773e: hackbench.throughput -32.9% regression
Date: Tue, 31 May 2016 14:41:51 +0200	[thread overview]
Message-ID: <20160531124151.GK3190@twins.programming.kicks-ass.net> (raw)
In-Reply-To: <87eg8id3s3.fsf@yhuang-dev.intel.com>

[-- Attachment #1: Type: text/plain, Size: 1061 bytes --]

On Tue, May 31, 2016 at 04:34:36PM +0800, Huang, Ying wrote:
> Hi, Ingo,
> 
> Part of the regression has been recovered in v4.7-rc1 from -32.9% to
> -9.8%.  But there is still some regression.  Is it possible for fully
> restore it?

after much searching on how you guys run hackbench... I figured
something like:

  perf bench sched messaging -g 20 --thread -l 60000

on my IVB-EP (2*10*2) is similar to your IVT thing.

And running something like:

  for i in /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor ; do echo performance > $i ; done
  perf stat --null --repeat 10 -- perf bench sched messaging -g 20 --thread -l 60000 | grep "seconds time elapsed"

gets me:

v4.6:

      36.786914089 seconds time elapsed ( +-  0.49% )
      37.054017355 seconds time elapsed ( +-  1.05% )


origin/master (v4.7-rc1-ish):

      34.757435264 seconds time elapsed ( +-  3.34% )
      35.396252515 seconds time elapsed ( +-  3.38% )


Which doesn't show a regression between v4.6 and HEAD; in fact it shows
an improvement.



WARNING: multiple messages have this Message-ID (diff)
From: Peter Zijlstra <peterz@infradead.org>
To: "Huang, Ying" <ying.huang@intel.com>
Cc: Ingo Molnar <mingo@kernel.org>,
	lkp@01.org, Mike Galbraith <efault@gmx.de>,
	linux-kernel@vger.kernel.org,
	Thomas Gleixner <tglx@linutronix.de>,
	Linus Torvalds <torvalds@linux-foundation.org>
Subject: Re: [LKP] [lkp] [sched/fair] 53d3bc773e: hackbench.throughput -32.9% regression
Date: Tue, 31 May 2016 14:41:51 +0200	[thread overview]
Message-ID: <20160531124151.GK3190@twins.programming.kicks-ass.net> (raw)
In-Reply-To: <87eg8id3s3.fsf@yhuang-dev.intel.com>

On Tue, May 31, 2016 at 04:34:36PM +0800, Huang, Ying wrote:
> Hi, Ingo,
> 
> Part of the regression has been recovered in v4.7-rc1 from -32.9% to
> -9.8%.  But there is still some regression.  Is it possible for fully
> restore it?

after much searching on how you guys run hackbench... I figured
something like:

  perf bench sched messaging -g 20 --thread -l 60000

on my IVB-EP (2*10*2) is similar to your IVT thing.

And running something like:

  for i in /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor ; do echo performance > $i ; done
  perf stat --null --repeat 10 -- perf bench sched messaging -g 20 --thread -l 60000 | grep "seconds time elapsed"

gets me:

v4.6:

      36.786914089 seconds time elapsed ( +-  0.49% )
      37.054017355 seconds time elapsed ( +-  1.05% )


origin/master (v4.7-rc1-ish):

      34.757435264 seconds time elapsed ( +-  3.34% )
      35.396252515 seconds time elapsed ( +-  3.38% )


Which doesn't show a regression between v4.6 and HEAD; in fact it shows
an improvement.

  reply	other threads:[~2016-05-31 12:41 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-05-31  8:20 [sched/fair] 53d3bc773e: hackbench.throughput -32.9% regression kernel test robot
2016-05-31  8:20 ` [lkp] " kernel test robot
2016-05-31  8:34 ` Huang, Ying
2016-05-31  8:34   ` [LKP] [lkp] " Huang, Ying
2016-05-31 12:41   ` Peter Zijlstra [this message]
2016-05-31 12:41     ` Peter Zijlstra
2016-06-01  5:00     ` Huang, Ying
2016-06-01  5:00       ` [LKP] [lkp] " Huang, Ying
2016-06-01  8:40       ` Peter Zijlstra
2016-06-01  8:40         ` [LKP] [lkp] " Peter Zijlstra
2016-06-01  8:53         ` Huang, Ying
2016-06-01  8:53           ` [LKP] [lkp] " Huang, Ying
2016-06-01  9:48           ` Mike Galbraith
2016-06-01  9:48             ` [LKP] [lkp] " Mike Galbraith
2016-06-02  0:28             ` Huang, Ying
2016-06-02  0:28               ` [LKP] [lkp] " Huang, Ying
2016-06-02  0:44               ` Mike Galbraith
2016-06-02  0:44                 ` [LKP] [lkp] " Mike Galbraith

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=20160531124151.GK3190@twins.programming.kicks-ass.net \
    --to=peterz@infradead.org \
    --cc=lkp@lists.01.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.