Message-ID: <Yw8L7HTZ/dE2/o9C@xsang-OptiPlex-9020>
Date:   Wed, 31 Aug 2022 15:21:16 +0800
From:   kernel test robot <oliver.sang@...el.com>
To:     Mikulas Patocka <mpatocka@...hat.com>
CC:     <lkp@...ts.01.org>, <lkp@...el.com>,
        Linus Torvalds <torvalds@...ux-foundation.org>,
        Matthew Wilcox <willy@...radead.org>,
        <linux-kernel@...r.kernel.org>, <ying.huang@...el.com>,
        <feng.tang@...el.com>, <zhengjun.xing@...ux.intel.com>,
        <fengwei.yin@...el.com>, <regressions@...ts.linux.dev>
Subject: d4252071b9:  fxmark.ssd_ext4_no_jnl_DWTL_54_directio.works/sec
 -26.5% regression


hi, pleased be noted that we read this patch and understand it as a fix,
also what we understand is, since the patch itself adds some memory barrier,
some regression in block IO area is kind of expected.

after more internal review, we still decided to report out to share our finding
in our tests, and for your information that how this patch could impact
performance in some cases. please let us know if you have any concern.

Thanks a lot!

below is the full report.


Greeting,

FYI, we noticed a -26.5% regression of fxmark.ssd_ext4_no_jnl_DWTL_54_directio.works/sec due to commit:


commit: d4252071b97d2027d246f6a82cbee4d52f618b47 ("add barriers to buffer_uptodate and set_buffer_uptodate")
https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git master

in testcase: fxmark
on test machine: 128 threads 2 sockets Intel(R) Xeon(R) Platinum 8358 CPU @ 2.60GHz (Ice Lake) with 128G memory
with following parameters:

	disk: 1SSD
	media: ssd
	test: DWTL
	fstype: ext4_no_jnl
	directio: directio
	cpufreq_governor: performance
	ucode: 0xd000363

test-description: FxMark is a filesystem benchmark that test multicore scalability.
test-url: https://github.com/sslab-gatech/fxmark

In addition to that, the commit also has significant impact on the following tests:


If you fix the issue, kindly add following tag
Reported-by: kernel test robot <oliver.sang@...el.com>


Details are as below:
-------------------------------------------------------------------------------------------------->


To reproduce:

        git clone https://github.com/intel/lkp-tests.git
        cd lkp-tests
        sudo bin/lkp install job.yaml           # job file is attached in this email
        bin/lkp split-job --compatible job.yaml # generate the yaml file for lkp run
        sudo bin/lkp run generated-yaml-file

        # if come across any failure that blocks the test,
        # please remove ~/.lkp and /lkp dir to run from a clean state.

=========================================================================================
compiler/cpufreq_governor/directio/disk/fstype/kconfig/media/rootfs/tbox_group/test/testcase/ucode:
  gcc-11/performance/directio/1SSD/ext4_no_jnl/x86_64-rhel-8.3/ssd/debian-11.1-x86_64-20220510.cgz/lkp-icl-2sp5/DWTL/fxmark/0xd000363

commit: 
  e394ff83bb ("Merge tag 'nfsd-6.0' of git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux")
  d4252071b9 ("add barriers to buffer_uptodate and set_buffer_uptodate")

e394ff83bbca1c72 d4252071b97d2027d246f6a82cb 
---------------- --------------------------- 
         %stddev     %change         %stddev
             \          |                \  
      0.03           +15.9%       0.04 ±  2%  fxmark.ssd_ext4_no_jnl_DWTL_2_directio.secs
    733363           -13.7%     632887 ±  2%  fxmark.ssd_ext4_no_jnl_DWTL_2_directio.works/sec
      1.70 ± 38%     -46.9%       0.90 ± 32%  fxmark.ssd_ext4_no_jnl_DWTL_36_directio.irq_util
      0.00 ± 10%     +57.1%       0.01 ± 12%  fxmark.ssd_ext4_no_jnl_DWTL_36_directio.secs
      0.15 ± 49%     +84.3%       0.27 ± 11%  fxmark.ssd_ext4_no_jnl_DWTL_36_directio.sys_sec
     11.01 ± 46%     +68.6%      18.56 ±  8%  fxmark.ssd_ext4_no_jnl_DWTL_36_directio.sys_util
   5084846 ± 11%     -36.2%    3242280 ± 11%  fxmark.ssd_ext4_no_jnl_DWTL_36_directio.works/sec
      0.05 ±  5%     +10.5%       0.06 ±  3%  fxmark.ssd_ext4_no_jnl_DWTL_4_directio.real_sec
      0.02 ±  6%     +20.5%       0.03 ±  4%  fxmark.ssd_ext4_no_jnl_DWTL_4_directio.secs
      0.09 ±  7%     +18.2%       0.11 ±  3%  fxmark.ssd_ext4_no_jnl_DWTL_4_directio.sys_sec
     19.84 ±  6%     -11.5%      17.57 ±  5%  fxmark.ssd_ext4_no_jnl_DWTL_4_directio.user_util
   1105172 ±  6%     -17.2%     914623 ±  4%  fxmark.ssd_ext4_no_jnl_DWTL_4_directio.works/sec
      0.00 ±  8%     +37.2%       0.01 ± 12%  fxmark.ssd_ext4_no_jnl_DWTL_54_directio.secs
      0.22 ± 18%     +67.9%       0.38 ± 11%  fxmark.ssd_ext4_no_jnl_DWTL_54_directio.sys_sec
     11.60 ± 13%     +49.8%      17.38 ±  9%  fxmark.ssd_ext4_no_jnl_DWTL_54_directio.sys_util
   5081260 ±  8%     -26.5%    3734460 ± 12%  fxmark.ssd_ext4_no_jnl_DWTL_54_directio.works/sec


#regzbot introduced: d4252071b9


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.


-- 
0-DAY CI Kernel Test Service
https://01.org/lkp



View attachment "config-5.19.0-13322-gd4252071b97d" of type "text/plain" (164680 bytes)

View attachment "job-script" of type "text/plain" (8211 bytes)

View attachment "job.yaml" of type "text/plain" (5664 bytes)

View attachment "reproduce" of type "text/plain" (254 bytes)

Powered by blists - more mailing lists