lkml.org 
[lkml]   [2015]   [Feb]   [11]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
SubjectRe: 答复: [LKP] [sched/fair] 638476007d1: +1.1% unixbench.score
From
Date
On Wed, 2015-02-11 at 15:25 +0800, pang.xunlei@zte.com.cn wrote:
> Hello,
>
> Does "+1.1% unixbench.score" mean better or worse?
>
> Anyway, this is a load bug fix, does can affect the load balancing
> behavior a little.

I think this means something better :)

Best Regards,
Huang, Ying

> Regards,
> Xunlei
>
>
>
> Huang Ying <ying.huang@intel.com>
> 2015-02-09 上午 11:27
>
> 收件人
> Xunlei Pang <pang.xunlei@linaro.org>,
> 抄送
> Ingo Molnar <mingo@kernel.org>, LKML <linux-kernel@vger.kernel.org>, LKP
> ML <lkp@01.org>
> 主题
> [LKP] [sched/fair] 638476007d1: +1.1% unixbench.score
>
>
>
>
>
>
> FYI, we noticed the below changes on
>
> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git sched/core
> commit 638476007d13534b2ed4134bf0279ef44071140b ("sched/fair: Fix the
> dealing with decay_count in __synchronize_entity_decay()")
>
> It appears that your patch cause CPU usage increased a little, so that
> unixbench score increased.
>
> testbox/testcase/testparams: nhm-white/unixbench/spawn
>
> 7f1a169b88f513e3 638476007d13534b2ed4134bf0
> ---------------- --------------------------
> %stddev %change %stddev
> \ | \
> 268908 ± 0% +4.6% 281320 ± 0%
> unixbench.time.involuntary_context_switches
> 1.147e+08 ± 0% +1.5% 1.164e+08 ± 0%
> unixbench.time.minor_page_faults
> 3607 ± 0% +1.1% 3648 ± 0% unixbench.score
> 324 ± 0% +1.2% 328 ± 0%
> unixbench.time.percent_of_cpu_this_job_got
> 633 ± 0% +1.2% 641 ± 0% unixbench.time.system_time
> 54100 ± 3% +51.0% 81705 ± 21%
> sched_debug.cpu#4.ttwu_local
> 65678 ± 7% +49.5% 98187 ± 16%
> sched_debug.cpu#6.ttwu_local
> 5624 ± 31% +52.1% 8553 ± 11% sched_debug.cpu#6.curr->pid
> 58 ± 20% +37.6% 80 ± 7%
> sched_debug.cfs_rq[3]:/.runnable_load_avg
> 61 ± 10% +22.5% 74 ± 14%
> sched_debug.cpu#2.cpu_load[3]
> 218479 ± 5% +15.4% 252190 ± 5%
> sched_debug.cpu#6.ttwu_count
> 102 ± 17% -19.3% 82 ± 10%
> sched_debug.cpu#4.cpu_load[2]
> 423974 ± 4% +15.6% 490072 ± 5% sched_debug.cpu#5.avg_idle
> 62 ± 4% +16.9% 72 ± 9%
> sched_debug.cpu#2.cpu_load[4]
> 152298 ± 2% +9.7% 167037 ± 3%
> sched_debug.cfs_rq[5]:/.min_vruntime
> 156795 ± 1% +11.3% 174544 ± 1%
> sched_debug.cfs_rq[7]:/.min_vruntime
> 155535 ± 3% +11.8% 173813 ± 2%
> sched_debug.cfs_rq[6]:/.min_vruntime
> 9231 ± 0% +1.3% 9348 ± 0% vmstat.system.in
>
> nhm-white: Nehalem
> Memory: 6G
>
>
> unixbench.time.system_time
>
> 643
> ++---------------------------------------------------------------O----+
> 642 ++ O O O
> O O O O O O O O O O O O O O O O O O O O O O |
> 641 ++ O O O O |
> 640 ++ |
> | |
> 639 ++ |
> 638 ++ |
> 637 ++ |
> | |
> 636 ++ |
> 635 ++ .* |
> *.*.. .*..* + .*.. .*.*.. * |
> 634 ++ * *..*.*..* * + |
> 633
> ++--------------------------------*-----------------------------------+
>
>
> unixbench.time.involuntary_context_switches
>
> 286000
> ++-----------------------------------------------------------------+
> 284000 ++ O |
> | O O |
> 282000 ++ O O
> O
> 280000 O+O O O O O O O O O O O O |
> | O O O O O O O O |
> 278000 ++ O O O |
> 276000 ++ |
> 274000 ++ |
> | |
> 272000 ++ |
> 270000 ++ .*.*. *.*.. .* |
> *.*. *..*. .* : *.*.*. |
> 268000 ++ * + : |
> 266000
> ++----------------*--*---------------------------------------------+
>
>
> kmsg.tsc:Fast_TSC_calibration_failed
>
> 1
> ++-------------------------------------O--------O---------------------+
> | |
> | |
> 0.8 ++ |
> | |
> | |
> 0.6 ++ |
> | |
> 0.4 ++ |
> | |
> | |
> 0.2 ++ |
> | |
> | |
> 0
> O+O--O-O--O-O-O--O-O--O-O--O-O-O--O-O----O-O--O----O-O--O-O-O--O-O--O-O
>
> [*] bisect-good sample
> [O] bisect-bad sample
>
> To reproduce:
>
> apt-get install ruby ruby-oj
> git clone
> git://git.kernel.org/pub/scm/linux/kernel/git/wfg/lkp-tests.git
> cd lkp-tests
> bin/setup-local job.yaml # the job file attached in this email
> bin/run-local job.yaml
>
>
> Disclaimer:
> Results have been estimated based on internal Intel analysis and are
> provided
> for informational purposes only. Any difference in system hardware or
> software
> design or configuration may affect actual performance.
>
>
> Thanks,
> Huang, Ying
>
>
> [附件 "job.yaml" 被 庞训磊10110855/user/zte_ltd 删除][附件 "reproduce" 被
> 庞训磊10110855/user/zte_ltd 删除
> ]_______________________________________________
> LKP mailing list
> LKP@linux.intel.com
>
>
>
> --------------------------------------------------------
> ZTE Information Security Notice: The information contained in this mail (and any attachment transmitted herewith) is privileged and confidential and is intended for the exclusive use of the addressee(s). If you are not an intended recipient, any disclosure, reproduction, distribution or other dissemination or use of the information contained is strictly prohibited. If you have received this mail in error, please delete it and notify us immediately.
> --------------------------------------------------------
> ZTE Information Security Notice: The information contained in this mail (and any attachment transmitted herewith) is privileged and confidential and is intended for the exclusive use of the addressee(s). If you are not an intended recipient, any disclosure, reproduction, distribution or other dissemination or use of the information contained is strictly prohibited. If you have received this mail in error, please delete it and notify us immediately.
> --------------------------------------------------------
> ZTE Information Security Notice: The information contained in this mail (and any attachment transmitted herewith) is privileged and confidential and is intended for the exclusive use of the addressee(s). If you are not an intended recipient, any disclosure, reproduction, distribution or other dissemination or use of the information contained is strictly prohibited. If you have received this mail in error, please delete it and notify us immediately.




\
 
 \ /
  Last update: 2015-02-11 08:41    [W:0.068 / U:4.192 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site