linux-kernel - [io] c22368edfa: fxmark.ssd_ext4_MRPM_72_bufferedio.works/sec 27.0% improvement

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>] [day] [month] [year] [list]
Message-ID: <20220304014128.GA20556@xsang-OptiPlex-9020>
Date:   Fri, 4 Mar 2022 09:41:28 +0800
From:   kernel test robot <oliver.sang@...el.com>
To:     Stefan Roesch <shr@...com>
Cc:     Jens Axboe <axboe@...nel.dk>, LKML <linux-kernel@...r.kernel.org>,
        Linux Memory Management List <linux-mm@...ck.org>,
        lkp@...ts.01.org, lkp@...el.com, ying.huang@...el.com,
        feng.tang@...el.com, zhengjun.xing@...ux.intel.com,
        fengwei.yin@...el.com
Subject: [io]  c22368edfa:  fxmark.ssd_ext4_MRPM_72_bufferedio.works/sec
 27.0% improvement



Greeting,

FYI, we noticed a 27.0% improvement of fxmark.ssd_ext4_MRPM_72_bufferedio.works/sec due to commit:


commit: c22368edfa24ec033f9328b3328aaa0349c15e6c ("io-uring: Make statx API stable")
https://git.kernel.org/cgit/linux/kernel/git/next/linux-next.git master

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

	disk: 1SSD
	media: ssd
	test: MRPM
	fstype: ext4
	directio: bufferedio
	cpufreq_governor: performance
	ucode: 0xd000331

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





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-9/performance/bufferedio/1SSD/ext4/x86_64-rhel-8.3/ssd/debian-10.4-x86_64-20200603.cgz/lkp-icl-2sp5/MRPM/fxmark/0xd000331

commit: 
  6810a554d2 ("io_uring: documentation fixup")
  c22368edfa ("io-uring: Make statx API stable")

6810a554d2740bef c22368edfa24ec033f9328b3328 
---------------- --------------------------- 
         %stddev     %change         %stddev
             \          |                \  
      0.12 ±  4%     +18.1%       0.14 ±  4%  fxmark.ssd_ext4_MRPM_54_bufferedio.softirq_sec
      0.00 ±  4%     +18.1%       0.01 ±  4%  fxmark.ssd_ext4_MRPM_54_bufferedio.softirq_util
    519.84           +35.7%     705.50 ±  2%  fxmark.ssd_ext4_MRPM_54_bufferedio.user_sec
     19.24           +35.7%      26.11 ±  2%  fxmark.ssd_ext4_MRPM_54_bufferedio.user_util
 1.326e+09           +34.8%  1.787e+09        fxmark.ssd_ext4_MRPM_54_bufferedio.works
  26529596           +34.8%   35748793        fxmark.ssd_ext4_MRPM_54_bufferedio.works/sec
    530.72 ±  9%     +25.8%     667.85        fxmark.ssd_ext4_MRPM_72_bufferedio.user_sec
     14.73 ±  9%     +25.8%      18.54        fxmark.ssd_ext4_MRPM_72_bufferedio.user_util
 1.212e+09 ±  9%     +27.0%  1.539e+09        fxmark.ssd_ext4_MRPM_72_bufferedio.works
  24239035 ±  9%     +27.0%   30779008        fxmark.ssd_ext4_MRPM_72_bufferedio.works/sec
    257.01            -2.8%     249.70        fxmark.time.system_time
    128.39            +5.7%     135.70        fxmark.time.user_time
     23.54            +6.4%      25.04 ±  2%  iostat.cpu.user
      1235 ±  6%     +22.5%       1513 ±  8%  meminfo.Active(anon)
    142238 ± 96%     -73.4%      37870 ± 74%  turbostat.C1
    308.17 ±  6%     +22.6%     377.83 ±  8%  proc-vmstat.nr_active_anon
    308.17 ±  6%     +22.6%     377.83 ±  8%  proc-vmstat.nr_zone_active_anon
      0.00 ± 95%      -0.0        0.00 ±132%  perf-stat.i.dTLB-load-miss-rate%
      0.00 ± 84%      -0.0        0.00 ±111%  perf-stat.i.dTLB-store-miss-rate%
      0.11 ± 70%      -0.0        0.07 ± 80%  perf-stat.overall.dTLB-store-miss-rate%
      0.10 ±105%      +0.1        0.24 ± 60%  perf-profile.children.cycles-pp.folio_add_lru
      0.07 ±122%      +0.2        0.22 ± 48%  perf-profile.children.cycles-pp.rmqueue
      0.08 ±121%      +0.2        0.31 ± 46%  perf-profile.children.cycles-pp.__mod_lruvec_page_state
      0.00            +0.7        0.68 ± 33%  perf-profile.children.cycles-pp.vfs_fstatat




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.


---
0DAY/LKP+ Test Infrastructure                   Open Source Technology Center
https://lists.01.org/hyperkitty/list/lkp@lists.01.org       Intel Corporation

Thanks,
Oliver Sang


View attachment "config-5.17.0-rc3-00017-gc22368edfa24" of type "text/plain" (162108 bytes)

View attachment "job-script" of type "text/plain" (8130 bytes)

View attachment "job.yaml" of type "text/plain" (5593 bytes)

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