linux-kernel - Re: [linus:master] [timers/migration] 61f7fdf8fd: netperf.Throughput

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [day] [month] [year] [list]

Date: Thu, 16 May 2024 10:42:34 +0800
From: Oliver Sang <oliver.sang@...el.com>
To: Frederic Weisbecker <frederic@...nel.org>
CC: <oe-lkp@...ts.linux.dev>, <lkp@...el.com>, <linux-kernel@...r.kernel.org>,
	Thomas Gleixner <tglx@...utronix.de>, Anna-Maria Behnsen
	<anna-maria@...utronix.de>, <ying.huang@...el.com>, <feng.tang@...el.com>,
	<fengwei.yin@...el.com>, <oliver.sang@...el.com>
Subject: Re: [linus:master] [timers/migration]  61f7fdf8fd:
 netperf.Throughput_Mbps 2.7% improvement

hi, Frederic Weisbecker,

On Wed, May 15, 2024 at 04:14:14PM +0200, Frederic Weisbecker wrote:
> Le Wed, May 15, 2024 at 04:06:50PM +0800, kernel test robot a écrit :
> > 
> > 
> > Hello,
> > 
> > kernel test robot noticed a 2.7% improvement of netperf.Throughput_Mbps on:
> > 
> > 
> > commit: 61f7fdf8fd00ce33d30ca3fae8d643c0850ce945 ("timers/migration: Fix ignored event due to missing CPU update")
> > https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git master
> 
> Nice, so this means the previously reported regression with netperf due to the
> new timer migration code is gone, right?
> 
> For reference: https://lore.kernel.org/all/202403011511.24defbbd-oliver.sang@intel.com/

I believe so.
previous report is for 7ee9887703, the scores are:

=========================================================================================
cluster/compiler/cpufreq_governor/ip/kconfig/nr_threads/rootfs/runtime/tbox_group/test/testcase:
  cs-localhost/gcc-12/performance/ipv4/x86_64-rhel-8.3/200%/debian-12-x86_64-20240206.cgz/300s/lkp-icl-2sp2/SCTP_STREAM/netperf

<---- (1)
  
57e95a5c4117dc6a 7ee988770326fca440472200c3e 
---------------- --------------------------- 
         %stddev     %change         %stddev
             \          |                \  
      4.10            -1.2%       4.05        netperf.ThroughputBoth_Mbps
      1049            -1.2%       1037        netperf.ThroughputBoth_total_Mbps
      4.10            -1.2%       4.05        netperf.Throughput_Mbps
      1049            -1.2%       1037        netperf.Throughput_total_Mbps


for this report, we just have same test's score as:

=========================================================================================
cluster/compiler/cpufreq_governor/ip/kconfig/nr_threads/rootfs/runtime/tbox_group/test/testcase:
  cs-localhost/gcc-13/performance/ipv4/x86_64-rhel-8.3/200%/debian-12-x86_64-20240206.cgz/300s/lkp-icl-2sp2/SCTP_STREAM/netperf

<---- (2)
  
cffaefd15a8f423c 61f7fdf8fd00ce33d30ca3fae8d 
---------------- --------------------------- 
         %stddev     %change         %stddev
             \          |                \  
      4.05            +1.1%       4.10        netperf.ThroughputBoth_Mbps
      1037            +1.1%       1049        netperf.ThroughputBoth_total_Mbps
      4.05            +1.1%       4.10        netperf.Throughput_Mbps
      1037            +1.1%       1049        netperf.Throughput_total_Mbps


from option lines (1)(2), only diff is compiler version which we updated to use
gcc-13 recently. but seems no impact in this case.

what we can see from 2 tables above are, 7ee9887703 just has same scores as
parent of 61f7fdf8fd (cffaefd15a), and 61f7fdf8fd just has same scores as parent
of 7ee9887703 (57e95a5c41). these mean the regression is just resolved.


> 
> Thanks.
>