Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]


Groups > linux.kernel > #1372993 > unrolled thread

[lkp] [mm] 6f25a14a70: will-it-scale.scalability -4.0% regression

Started bykernel test robot <xiaolong.ye@intel.com>
First post2016-04-07 03:10 +0200
Last post2016-04-07 04:50 +0200
Articles 2 — 2 participants

Back to article view | Back to linux.kernel


Contents

  [lkp] [mm] 6f25a14a70: will-it-scale.scalability -4.0% regression kernel test robot <xiaolong.ye@intel.com> - 2016-04-07 03:10 +0200
    Re: [lkp] [mm] 6f25a14a70: will-it-scale.scalability -4.0% regression Xishi Qiu <qiuxishi@huawei.com> - 2016-04-07 04:50 +0200

#1372993 — [lkp] [mm] 6f25a14a70: will-it-scale.scalability -4.0% regression

Fromkernel test robot <xiaolong.ye@intel.com>
Date2016-04-07 03:10 +0200
Subject[lkp] [mm] 6f25a14a70: will-it-scale.scalability -4.0% regression
Message-ID<rl6Cm-4fP-7@gated-at.bofh.it>

[Multipart message — attachments visible in raw view] — view raw

FYI, we noticed that will-it-scale.scalability -4.0% regression on

https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git master
commit 6f25a14a7053b69917e2ebea0d31dd444cd31fd5 ("mm: fix invalid node in alloc_migrate_target()")


=========================================================================================
compiler/cpufreq_governor/kconfig/rootfs/tbox_group/test/testcase:
  gcc-4.9/performance/x86_64-rhel/debian-x86_64-2015-02-07.cgz/lkp-ivb-d03/pthread_mutex1/will-it-scale

commit: 
  969e8d7e47f93ef693028667480558de8f70523f
  6f25a14a7053b69917e2ebea0d31dd444cd31fd5

969e8d7e47f93ef6 6f25a14a7053b69917e2ebea0d 
---------------- -------------------------- 
       fail:runs  %reproduction    fail:runs
         %stddev     %change         %stddev
             \          |                \  
 2.032e+08 ±  0%      -1.6%      2e+08 ±  0%  will-it-scale.per_process_ops
      0.83 ±  0%      -4.0%       0.79 ±  0%  will-it-scale.scalability
    214103 ± 14%     -20.2%     170884 ± 14%  sched_debug.cpu.ttwu_count.stddev
      3789 ±  7%     -10.3%       3398 ±  6%  slabinfo.anon_vma_chain.active_objs
      4660 ±  5%      +7.7%       5019 ±  2%  vmstat.system.in


lkp-ivb-d03: Ivy Bridge
Memory: 4G



To reproduce:

        git clone git://git.kernel.org/pub/scm/linux/kernel/git/wfg/lkp-tests.git
        cd lkp-tests
        bin/lkp install job.yaml  # job file is attached in this email
        bin/lkp run     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,
Xiaolong Ye

[toc] | [next] | [standalone]


#1373036

FromXishi Qiu <qiuxishi@huawei.com>
Date2016-04-07 04:50 +0200
Message-ID<rl8b7-5tm-13@gated-at.bofh.it>
In reply to#1372993
On 2016/4/7 9:06, kernel test robot wrote:

> FYI, we noticed that will-it-scale.scalability -4.0% regression on
> 
> https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git master
> commit 6f25a14a7053b69917e2ebea0d31dd444cd31fd5 ("mm: fix invalid node in alloc_migrate_target()")
> 

alloc_migrate_target() is called from cma or mem-offline.
I have no idea what's the relation between these, any ideas?

Thanks,
Xishi Qiu

> 
> =========================================================================================
> compiler/cpufreq_governor/kconfig/rootfs/tbox_group/test/testcase:
>   gcc-4.9/performance/x86_64-rhel/debian-x86_64-2015-02-07.cgz/lkp-ivb-d03/pthread_mutex1/will-it-scale
> 
> commit: 
>   969e8d7e47f93ef693028667480558de8f70523f
>   6f25a14a7053b69917e2ebea0d31dd444cd31fd5
> 
> 969e8d7e47f93ef6 6f25a14a7053b69917e2ebea0d 
> ---------------- -------------------------- 
>        fail:runs  %reproduction    fail:runs
>          %stddev     %change         %stddev
>              \          |                \  
>  2.032e+08 ±  0%      -1.6%      2e+08 ±  0%  will-it-scale.per_process_ops
>       0.83 ±  0%      -4.0%       0.79 ±  0%  will-it-scale.scalability
>     214103 ± 14%     -20.2%     170884 ± 14%  sched_debug.cpu.ttwu_count.stddev
>       3789 ±  7%     -10.3%       3398 ±  6%  slabinfo.anon_vma_chain.active_objs
>       4660 ±  5%      +7.7%       5019 ±  2%  vmstat.system.in
> 
> 
> lkp-ivb-d03: Ivy Bridge
> Memory: 4G
> 
> 
> 
> To reproduce:
> 
>         git clone git://git.kernel.org/pub/scm/linux/kernel/git/wfg/lkp-tests.git
>         cd lkp-tests
>         bin/lkp install job.yaml  # job file is attached in this email
>         bin/lkp run     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,
> Xiaolong Ye

[toc] | [prev] | [standalone]


Back to top | Article view | linux.kernel


csiph-web