From: Ye Xiaolong <xiaolong.ye@intel.com>
To: lkp@lists.01.org
Subject: Re: [x86/copy_user] adb402cd14: will-it-scale.per_process_ops -12.7% regression
Date: Mon, 14 Nov 2016 22:19:31 +0800 [thread overview]
Message-ID: <20161114141931.GA27318@yexl-desktop> (raw)
In-Reply-To: <20161115100101.nzvhd5mlcb747n2h@pd.tnic>
[-- Attachment #1: Type: text/plain, Size: 2585 bytes --]
On 11/15, Borislav Petkov wrote:
>On Mon, Nov 14, 2016 at 10:37:11PM +0800, Ye Xiaolong wrote:
>> Below cmd should help on it:
>
>Right, before I go do this, can you please retest without
>
>CONFIG_DEBUG_ATOMIC_SLEEP=y
>
>?
Sorry for the late, here is the comparison, disable
CONFIG_DEBUG_ATOMIC_SLEEP helps to restore the performance back
according to the result.
=========================================================================================
commit/compiler/cpufreq_governor/rootfs/tbox_group/test/testcase:
adb402cd1461eef6e1a21db4532a3b9e6a6be853/gcc-6/performance/debian-x86_64-2016-08-31.cgz/xps/poll1/will-it-scale
kconfig:
x86_64-rhel-7.2
x86_64-rhel-7.2-CONFIG_DEBUG_ATOMIC_SLEEP
x86_64-rhel-7.2 x86_64-rhel-7.2-CONFIG_DEB
---------------- --------------------------
%stddev %change %stddev
\ | \
5899566 ± 2% +28.5% 7583094 ± 0% will-it-scale.per_process_ops
5121156 ± 0% +21.1% 6203340 ± 0% will-it-scale.per_thread_ops
49191 ±127% -79.8% 9938 ± 3% will-it-scale.time.involuntary_context_switches
588.63 ± 0% -4.1% 564.27 ± 0% will-it-scale.time.system_time
132.53 ± 0% +18.7% 157.26 ± 0% will-it-scale.time.user_time
23063 ± 0% -92.0% 1846 ± 0% interrupts.CAL:Function_call_interrupts
10336 ± 28% -66.1% 3499 ± 5% softirqs.NET_RX
444.00 ± 0% -24.3% 336.00 ± 0% vmstat.memory.buff
49191 ±127% -79.8% 9938 ± 3% time.involuntary_context_switches
132.53 ± 0% +18.7% 157.26 ± 0% time.user_time
4823 ± 1% -9.9% 4344 ± 0% proc-vmstat.nr_mapped
4994 ± 2% -13.2% 4336 ± 0% proc-vmstat.nr_shmem
2265 ± 7% -71.6% 642.67 ± 4% proc-vmstat.pgactivate
61.33 ± 0% -1.6% 60.33 ± 0% turbostat.%Busy
12.34 ± 7% -98.8% 0.15 ± 17% turbostat.CPU%c3
1.29 ± 6% +1004.7% 14.22 ± 5% turbostat.CPU%c6
113064 ± 1% -9.4% 102395 ± 2% meminfo.Active
196087 ± 0% -16.4% 163999 ± 0% meminfo.Committed_AS
19288 ± 1% -9.9% 17372 ± 0% meminfo.Mapped
19983 ± 2% -13.2% 17348 ± 0% meminfo.Shmem
15975 ± 27% -74.7% 4043 ± 10% latency_stats.avg.max
Thanks,
Xiaolong
>
>Thanks.
>
>--
>Regards/Gruss,
> Boris.
>
>Good mailing practices for 400: avoid top-posting and trim the reply.
next prev parent reply other threads:[~2016-11-14 14:19 UTC|newest]
Thread overview: 12+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-11-07 2:50 [x86/copy_user] adb402cd14: will-it-scale.per_process_ops -12.7% regression kernel test robot
2016-11-07 2:50 ` [lkp] " kernel test robot
2016-11-07 9:56 ` Borislav Petkov
2016-11-07 9:56 ` [lkp] " Borislav Petkov
2016-11-14 14:37 ` Ye Xiaolong
2016-11-15 10:01 ` Borislav Petkov
2016-11-14 14:19 ` Ye Xiaolong [this message]
2016-11-15 15:10 ` Borislav Petkov
2016-11-16 9:58 ` Borislav Petkov
2016-11-16 12:38 ` Ye Xiaolong
2016-11-09 12:42 ` Borislav Petkov
2016-11-09 12:42 ` [lkp] " Borislav Petkov
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=20161114141931.GA27318@yexl-desktop \
--to=xiaolong.ye@intel.com \
--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.