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-next>] [day] [month] [year] [list]
Date:   Mon, 15 Aug 2022 12:32:25 +0800
From:   kernel test robot <oliver.sang@...el.com>
To:     Stefan Roesch <shr@...com>
CC:     Jens Axboe <axboe@...nel.dk>, Christoph Hellwig <hch@....de>,
        Jan Kara <jack@...e.cz>,
        Christian Brauner <brauner@...nel.org>,
        "Darrick J. Wong" <djwong@...nel.org>,
        LKML <linux-kernel@...r.kernel.org>,
        <linux-fsdevel@...r.kernel.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: [fs]  faf99b5635:  will-it-scale.per_thread_ops -9.0% regression



Greeting,

FYI, we noticed a -9.0% regression of will-it-scale.per_thread_ops due to commit:


commit: faf99b563558f74188b7ca34faae1c1da49a7261 ("fs: add __remove_file_privs() with flags parameter")
https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git master

in testcase: will-it-scale
on test machine: 48 threads 2 sockets Intel(R) Xeon(R) CPU E5-2697 v2 @ 2.70GHz with 112G memory
with following parameters:

	nr_task: 50%
	mode: thread
	test: pwrite1
	cpufreq_governor: performance
	ucode: 0x42e

test-description: Will It Scale takes a testcase and runs it from 1 through to n parallel copies to see if the testcase will scale. It builds both a process and threads based test in order to see any differences between the two.
test-url: https://github.com/antonblanchard/will-it-scale

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

+------------------+-------------------------------------------------------------------------------------+
| testcase: change | will-it-scale: will-it-scale.per_process_ops -9.4% regression                       |
| test machine     | 48 threads 2 sockets Intel(R) Xeon(R) CPU E5-2697 v2 @ 2.70GHz with 112G memory     |
| test parameters  | cpufreq_governor=performance                                                        |
|                  | mode=process                                                                        |
|                  | nr_task=16                                                                          |
|                  | test=pwrite1                                                                        |
|                  | ucode=0x42e                                                                         |
+------------------+-------------------------------------------------------------------------------------+
| testcase: change | fxmark: fxmark.ssd_btrfs_DWOM_72_bufferedio.works/sec -8.2% regression              |
| test machine     | 128 threads 2 sockets Intel(R) Xeon(R) Platinum 8358 CPU @ 2.60GHz with 128G memory |
| test parameters  | cpufreq_governor=performance                                                        |
|                  | directio=bufferedio                                                                 |
|                  | disk=1SSD                                                                           |
|                  | fstype=btrfs                                                                        |
|                  | media=ssd                                                                           |
|                  | test=DWOM                                                                           |
|                  | ucode=0xd000331                                                                     |
+------------------+-------------------------------------------------------------------------------------+


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/kconfig/mode/nr_task/rootfs/tbox_group/test/testcase/ucode:
  gcc-11/performance/x86_64-rhel-8.3/thread/50%/debian-11.1-x86_64-20220510.cgz/lkp-ivb-2ep1/pwrite1/will-it-scale/0x42e

commit: 
  8017553980 ("fs: add a FMODE_BUF_WASYNC flags for f_mode")
  faf99b5635 ("fs: add __remove_file_privs() with flags parameter")

8017553980d0bbfe faf99b563558f74188b7ca34faa 
---------------- --------------------------- 
         %stddev     %change         %stddev
             \          |                \  
  28551731            -9.0%   25983687        will-it-scale.24.threads
   1189655            -9.0%    1082653        will-it-scale.per_thread_ops
  28551731            -9.0%   25983687        will-it-scale.workload
  1.12e+10           +11.8%  1.252e+10        perf-stat.i.branch-instructions
      1.58            +0.1        1.71        perf-stat.i.branch-miss-rate%
 1.768e+08           +20.5%  2.129e+08        perf-stat.i.branch-misses
      4.11            -0.5        3.62 ±  6%  perf-stat.i.cache-miss-rate%
   4700198 ±  3%     +12.2%    5275824 ±  6%  perf-stat.i.cache-references
      1.33            -7.2%       1.23        perf-stat.i.cpi
      0.56 ±  2%      +0.2        0.71 ±  2%  perf-stat.i.dTLB-load-miss-rate%
 1.372e+08 ±  3%     +29.1%   1.77e+08 ±  2%  perf-stat.i.dTLB-load-misses
 2.433e+10            +1.1%  2.461e+10        perf-stat.i.dTLB-loads
      0.34            -0.0        0.32        perf-stat.i.dTLB-store-miss-rate%
  64856094 ±  2%     -10.2%   58254064        perf-stat.i.dTLB-store-misses
 1.895e+10            -3.9%  1.821e+10        perf-stat.i.dTLB-stores
  5.44e+10            +7.6%  5.852e+10        perf-stat.i.instructions
      0.75            +7.8%       0.81        perf-stat.i.ipc
      1136            +1.5%       1154        perf-stat.i.metric.M/sec
      1.58            +0.1        1.70        perf-stat.overall.branch-miss-rate%
      5.35 ±  4%      -0.7        4.62 ±  5%  perf-stat.overall.cache-miss-rate%
      1.33            -7.2%       1.23        perf-stat.overall.cpi
      0.56 ±  2%      +0.2        0.71 ±  2%  perf-stat.overall.dTLB-load-miss-rate%
      0.34            -0.0        0.32        perf-stat.overall.dTLB-store-miss-rate%
      0.75            +7.8%       0.81        perf-stat.overall.ipc
    575689           +18.2%     680311        perf-stat.overall.path-length
 1.117e+10           +11.8%  1.248e+10        perf-stat.ps.branch-instructions
 1.762e+08           +20.4%  2.122e+08        perf-stat.ps.branch-misses
   4686980 ±  3%     +12.2%    5259903 ±  6%  perf-stat.ps.cache-references
 1.367e+08 ±  3%     +29.1%  1.764e+08 ±  2%  perf-stat.ps.dTLB-load-misses
 2.425e+10            +1.1%  2.453e+10        perf-stat.ps.dTLB-loads
  64640648 ±  2%     -10.2%   58061132        perf-stat.ps.dTLB-store-misses
 1.889e+10            -3.9%  1.815e+10        perf-stat.ps.dTLB-stores
 5.422e+10            +7.6%  5.832e+10        perf-stat.ps.instructions
 1.644e+13            +7.5%  1.768e+13        perf-stat.total.instructions
      0.88 ±  6%      -0.2        0.70 ±  4%  perf-profile.calltrace.cycles-pp.file_update_time.__generic_file_write_iter.generic_file_write_iter.new_sync_write.vfs_write
      0.74 ±  7%      -0.2        0.58 ±  2%  perf-profile.calltrace.cycles-pp.up_write.generic_file_write_iter.new_sync_write.vfs_write.__x64_sys_pwrite64
      0.00            +0.6        0.60 ±  4%  perf-profile.calltrace.cycles-pp.strlen.xattr_full_name.shmem_xattr_handler_get.__vfs_getxattr.cap_inode_need_killpriv
      0.00            +0.8        0.80 ±  4%  perf-profile.calltrace.cycles-pp.xattr_full_name.shmem_xattr_handler_get.__vfs_getxattr.cap_inode_need_killpriv.security_inode_need_killpriv
      0.00            +1.1        1.12        perf-profile.calltrace.cycles-pp._raw_spin_lock.simple_xattr_get.__vfs_getxattr.cap_inode_need_killpriv.security_inode_need_killpriv
      0.00            +1.4        1.37        perf-profile.calltrace.cycles-pp.simple_xattr_get.__vfs_getxattr.cap_inode_need_killpriv.security_inode_need_killpriv.__file_remove_privs
      0.00            +1.5        1.54 ±  4%  perf-profile.calltrace.cycles-pp.shmem_xattr_handler_get.__vfs_getxattr.cap_inode_need_killpriv.security_inode_need_killpriv.__file_remove_privs
      0.00            +1.9        1.87 ±  2%  perf-profile.calltrace.cycles-pp.xattr_resolve_name.__vfs_getxattr.cap_inode_need_killpriv.security_inode_need_killpriv.__file_remove_privs
     37.39 ±  7%      +4.0       41.35 ±  2%  perf-profile.calltrace.cycles-pp.__x64_sys_pwrite64.do_syscall_64.entry_SYSCALL_64_after_hwframe.__libc_pwrite64
     33.79 ±  7%      +4.3       38.04 ±  2%  perf-profile.calltrace.cycles-pp.vfs_write.__x64_sys_pwrite64.do_syscall_64.entry_SYSCALL_64_after_hwframe.__libc_pwrite64
     28.94 ±  7%      +4.4       33.34 ±  2%  perf-profile.calltrace.cycles-pp.new_sync_write.vfs_write.__x64_sys_pwrite64.do_syscall_64.entry_SYSCALL_64_after_hwframe
     28.24 ±  7%      +4.4       32.69 ±  2%  perf-profile.calltrace.cycles-pp.generic_file_write_iter.new_sync_write.vfs_write.__x64_sys_pwrite64.do_syscall_64
     24.16 ±  8%      +4.9       29.03 ±  2%  perf-profile.calltrace.cycles-pp.__generic_file_write_iter.generic_file_write_iter.new_sync_write.vfs_write.__x64_sys_pwrite64
      0.00            +5.3        5.29 ±  2%  perf-profile.calltrace.cycles-pp.__vfs_getxattr.cap_inode_need_killpriv.security_inode_need_killpriv.__file_remove_privs.__generic_file_write_iter
      0.00            +6.1        6.12 ±  2%  perf-profile.calltrace.cycles-pp.cap_inode_need_killpriv.security_inode_need_killpriv.__file_remove_privs.__generic_file_write_iter.generic_file_write_iter
      0.00            +6.4        6.39 ±  2%  perf-profile.calltrace.cycles-pp.security_inode_need_killpriv.__file_remove_privs.__generic_file_write_iter.generic_file_write_iter.new_sync_write
      0.00            +6.8        6.82 ±  2%  perf-profile.calltrace.cycles-pp.__file_remove_privs.__generic_file_write_iter.generic_file_write_iter.new_sync_write.vfs_write
      0.93 ±  6%      -0.2        0.73 ±  4%  perf-profile.children.cycles-pp.file_update_time
      0.74 ±  7%      -0.2        0.58 ±  2%  perf-profile.children.cycles-pp.up_write
      0.50 ±  8%      -0.1        0.38 ±  4%  perf-profile.children.cycles-pp.current_time
      0.12 ± 13%      -0.1        0.06 ± 12%  perf-profile.children.cycles-pp.set_page_dirty
      0.00            +0.1        0.11 ±  9%  perf-profile.children.cycles-pp.should_remove_suid
      0.81 ±  9%      +0.2        1.04 ±  4%  perf-profile.children.cycles-pp.__x86_indirect_thunk_rax
      0.00            +0.7        0.71 ±  4%  perf-profile.children.cycles-pp.strlen
      0.00            +0.8        0.82 ±  4%  perf-profile.children.cycles-pp.xattr_full_name
      0.00            +1.1        1.12 ±  2%  perf-profile.children.cycles-pp._raw_spin_lock
      0.00            +1.4        1.42        perf-profile.children.cycles-pp.simple_xattr_get
      0.00            +1.6        1.57 ±  4%  perf-profile.children.cycles-pp.shmem_xattr_handler_get
      0.00            +1.9        1.90 ±  2%  perf-profile.children.cycles-pp.xattr_resolve_name
     37.47 ±  7%      +4.0       41.43 ±  2%  perf-profile.children.cycles-pp.__x64_sys_pwrite64
     33.90 ±  7%      +4.3       38.17 ±  2%  perf-profile.children.cycles-pp.vfs_write
     29.01 ±  7%      +4.4       33.42 ±  2%  perf-profile.children.cycles-pp.new_sync_write
     28.37 ±  7%      +4.5       32.84 ±  2%  perf-profile.children.cycles-pp.generic_file_write_iter
     24.29 ±  8%      +4.9       29.14 ±  2%  perf-profile.children.cycles-pp.__generic_file_write_iter
      0.00            +5.4        5.39 ±  2%  perf-profile.children.cycles-pp.__vfs_getxattr
      0.00            +6.2        6.23 ±  2%  perf-profile.children.cycles-pp.cap_inode_need_killpriv
      0.00            +6.4        6.39 ±  2%  perf-profile.children.cycles-pp.security_inode_need_killpriv
      0.00            +6.8        6.85 ±  2%  perf-profile.children.cycles-pp.__file_remove_privs
      0.73 ±  8%      -0.2        0.55 ±  2%  perf-profile.self.cycles-pp.up_write
      0.34 ±  7%      -0.1        0.24 ±  6%  perf-profile.self.cycles-pp.current_time
      0.40 ±  9%      -0.1        0.29 ±  3%  perf-profile.self.cycles-pp.folio_mark_dirty
      0.42 ±  7%      -0.1        0.33 ±  4%  perf-profile.self.cycles-pp.file_update_time
      0.00            +0.1        0.11 ±  9%  perf-profile.self.cycles-pp.should_remove_suid
      0.00            +0.1        0.11 ±  5%  perf-profile.self.cycles-pp.xattr_full_name
      0.00            +0.2        0.16 ±  7%  perf-profile.self.cycles-pp.security_inode_need_killpriv
      0.68 ±  8%      +0.3        0.94 ±  4%  perf-profile.self.cycles-pp.__x86_indirect_thunk_rax
      0.00            +0.3        0.34 ±  5%  perf-profile.self.cycles-pp.__file_remove_privs
      0.00            +0.4        0.35 ±  4%  perf-profile.self.cycles-pp.simple_xattr_get
      0.00            +0.5        0.50 ±  4%  perf-profile.self.cycles-pp.__vfs_getxattr
      0.00            +0.7        0.68 ±  4%  perf-profile.self.cycles-pp.strlen
      0.00            +0.7        0.71 ±  4%  perf-profile.self.cycles-pp.shmem_xattr_handler_get
      0.00            +0.8        0.79 ±  4%  perf-profile.self.cycles-pp.cap_inode_need_killpriv
      0.00            +1.1        1.06        perf-profile.self.cycles-pp._raw_spin_lock
      0.00            +1.8        1.78 ±  2%  perf-profile.self.cycles-pp.xattr_resolve_name


***************************************************************************************************
lkp-ivb-2ep1: 48 threads 2 sockets Intel(R) Xeon(R) CPU E5-2697 v2 @ 2.70GHz with 112G memory
=========================================================================================
compiler/cpufreq_governor/kconfig/mode/nr_task/rootfs/tbox_group/test/testcase/ucode:
  gcc-11/performance/x86_64-rhel-8.3/process/16/debian-11.1-x86_64-20220510.cgz/lkp-ivb-2ep1/pwrite1/will-it-scale/0x42e

commit: 
  8017553980 ("fs: add a FMODE_BUF_WASYNC flags for f_mode")
  faf99b5635 ("fs: add __remove_file_privs() with flags parameter")

8017553980d0bbfe faf99b563558f74188b7ca34faa 
---------------- --------------------------- 
         %stddev     %change         %stddev
             \          |                \  
  19495625            -9.4%   17662665        will-it-scale.16.processes
   1218476            -9.4%    1103916        will-it-scale.per_process_ops
  19495625            -9.4%   17662665        will-it-scale.workload
     11.25            -1.0       10.21        mpstat.cpu.all.usr%
 7.336e+09           +12.2%  8.233e+09        perf-stat.i.branch-instructions
      1.72            +0.1        1.83        perf-stat.i.branch-miss-rate%
 1.259e+08           +19.6%  1.505e+08        perf-stat.i.branch-misses
      1.37            -7.2%       1.27        perf-stat.i.cpi
      0.51 ±  3%      +0.2        0.69 ±  2%  perf-stat.i.dTLB-load-miss-rate%
  83658097 ±  3%     +35.5%  1.133e+08 ±  2%  perf-stat.i.dTLB-load-misses
      0.31 ±  2%      -0.0        0.30        perf-stat.i.dTLB-store-miss-rate%
  39953707 ±  2%      -8.2%   36694148        perf-stat.i.dTLB-store-misses
 1.266e+10            -3.9%  1.217e+10        perf-stat.i.dTLB-stores
    948485 ±  2%      +5.4%     999860 ±  4%  perf-stat.i.iTLB-load-misses
 3.594e+10            +7.7%  3.872e+10        perf-stat.i.instructions
      0.73            +7.7%       0.78        perf-stat.i.ipc
    755.27            +1.5%     766.76        perf-stat.i.metric.M/sec
      1.72            +0.1        1.83        perf-stat.overall.branch-miss-rate%
      1.37            -7.2%       1.27        perf-stat.overall.cpi
      0.51 ±  3%      +0.2        0.69 ±  2%  perf-stat.overall.dTLB-load-miss-rate%
      0.31 ±  2%      -0.0        0.30        perf-stat.overall.dTLB-store-miss-rate%
      0.73            +7.7%       0.78        perf-stat.overall.ipc
    557238           +18.9%     662663        perf-stat.overall.path-length
 7.312e+09           +12.2%  8.206e+09        perf-stat.ps.branch-instructions
 1.254e+08           +19.6%    1.5e+08        perf-stat.ps.branch-misses
  83382244 ±  3%     +35.5%   1.13e+08 ±  2%  perf-stat.ps.dTLB-load-misses
  39822033 ±  2%      -8.2%   36573065        perf-stat.ps.dTLB-store-misses
 1.261e+10            -3.9%  1.213e+10        perf-stat.ps.dTLB-stores
    945340 ±  2%      +5.4%     996520 ±  4%  perf-stat.ps.iTLB-load-misses
 3.583e+10            +7.7%   3.86e+10        perf-stat.ps.instructions
 1.086e+13            +7.7%   1.17e+13        perf-stat.total.instructions
      2.60 ±  6%      -0.4        2.16 ±  8%  perf-profile.calltrace.cycles-pp.security_file_permission.vfs_write.__x64_sys_pwrite64.do_syscall_64.entry_SYSCALL_64_after_hwframe
      2.33 ±  6%      -0.4        1.90 ±  8%  perf-profile.calltrace.cycles-pp.apparmor_file_permission.security_file_permission.vfs_write.__x64_sys_pwrite64.do_syscall_64
      0.89 ±  8%      -0.3        0.56 ± 38%  perf-profile.calltrace.cycles-pp.file_update_time.__generic_file_write_iter.generic_file_write_iter.new_sync_write.vfs_write
      0.00            +0.7        0.70 ±  8%  perf-profile.calltrace.cycles-pp.xattr_full_name.shmem_xattr_handler_get.__vfs_getxattr.cap_inode_need_killpriv.security_inode_need_killpriv
      0.00            +1.0        1.02 ±  9%  perf-profile.calltrace.cycles-pp._raw_spin_lock.simple_xattr_get.__vfs_getxattr.cap_inode_need_killpriv.security_inode_need_killpriv
      0.00            +1.2        1.24 ±  9%  perf-profile.calltrace.cycles-pp.simple_xattr_get.__vfs_getxattr.cap_inode_need_killpriv.security_inode_need_killpriv.__file_remove_privs
      0.00            +1.4        1.39 ±  9%  perf-profile.calltrace.cycles-pp.shmem_xattr_handler_get.__vfs_getxattr.cap_inode_need_killpriv.security_inode_need_killpriv.__file_remove_privs
      0.00            +1.7        1.70 ±  9%  perf-profile.calltrace.cycles-pp.xattr_resolve_name.__vfs_getxattr.cap_inode_need_killpriv.security_inode_need_killpriv.__file_remove_privs
      0.00            +4.8        4.84 ±  9%  perf-profile.calltrace.cycles-pp.__vfs_getxattr.cap_inode_need_killpriv.security_inode_need_killpriv.__file_remove_privs.__generic_file_write_iter
      0.00            +5.5        5.47 ±  8%  perf-profile.calltrace.cycles-pp.cap_inode_need_killpriv.security_inode_need_killpriv.__file_remove_privs.__generic_file_write_iter.generic_file_write_iter
      0.00            +5.7        5.70 ±  8%  perf-profile.calltrace.cycles-pp.security_inode_need_killpriv.__file_remove_privs.__generic_file_write_iter.generic_file_write_iter.new_sync_write
      0.00            +6.1        6.08 ±  8%  perf-profile.calltrace.cycles-pp.__file_remove_privs.__generic_file_write_iter.generic_file_write_iter.new_sync_write.vfs_write
      2.66 ±  6%      -0.5        2.20 ±  8%  perf-profile.children.cycles-pp.security_file_permission
      2.36 ±  6%      -0.4        1.92 ±  8%  perf-profile.children.cycles-pp.apparmor_file_permission
      0.94 ±  8%      -0.3        0.65 ± 10%  perf-profile.children.cycles-pp.file_update_time
      0.50 ±  9%      -0.2        0.34 ± 11%  perf-profile.children.cycles-pp.current_time
      0.62 ±  8%      -0.1        0.50 ± 10%  perf-profile.children.cycles-pp.folio_mark_dirty
      0.17 ± 11%      -0.1        0.06 ± 17%  perf-profile.children.cycles-pp.set_page_dirty
      0.46 ±  8%      -0.1        0.35 ±  8%  perf-profile.children.cycles-pp.__fsnotify_parent
      0.18 ±  9%      -0.1        0.10 ± 10%  perf-profile.children.cycles-pp.unlock_page
      0.25 ±  9%      -0.1        0.19 ± 11%  perf-profile.children.cycles-pp.exit_to_user_mode_prepare
      0.00            +0.1        0.10 ±  6%  perf-profile.children.cycles-pp.should_remove_suid
      0.00            +0.6        0.63 ±  8%  perf-profile.children.cycles-pp.strlen
      0.00            +0.7        0.73 ±  8%  perf-profile.children.cycles-pp.xattr_full_name
      0.00            +1.0        1.04 ±  9%  perf-profile.children.cycles-pp._raw_spin_lock
      0.00            +1.3        1.30 ±  9%  perf-profile.children.cycles-pp.simple_xattr_get
      0.00            +1.4        1.42 ±  8%  perf-profile.children.cycles-pp.shmem_xattr_handler_get
      0.00            +1.7        1.72 ±  9%  perf-profile.children.cycles-pp.xattr_resolve_name
      0.00            +4.9        4.87 ±  9%  perf-profile.children.cycles-pp.__vfs_getxattr
      0.00            +5.6        5.60 ±  9%  perf-profile.children.cycles-pp.cap_inode_need_killpriv
      0.00            +5.7        5.72 ±  8%  perf-profile.children.cycles-pp.security_inode_need_killpriv
      0.00            +6.1        6.11 ±  8%  perf-profile.children.cycles-pp.__file_remove_privs
      1.97 ±  6%      -0.4        1.60 ±  8%  perf-profile.self.cycles-pp.apparmor_file_permission
      1.09 ±  7%      -0.2        0.84 ±  8%  perf-profile.self.cycles-pp.generic_perform_write
      0.70 ±  6%      -0.2        0.55 ±  9%  perf-profile.self.cycles-pp.shmem_getpage_gfp
      0.42 ±  8%      -0.1        0.30 ± 10%  perf-profile.self.cycles-pp.file_update_time
      0.70 ±  6%      -0.1        0.58 ±  8%  perf-profile.self.cycles-pp.do_syscall_64
      0.41 ±  7%      -0.1        0.28 ± 11%  perf-profile.self.cycles-pp.folio_mark_dirty
      0.50 ±  7%      -0.1        0.38 ± 10%  perf-profile.self.cycles-pp.__generic_file_write_iter
      0.46 ±  8%      -0.1        0.34 ±  8%  perf-profile.self.cycles-pp.__fsnotify_parent
      0.33 ± 11%      -0.1        0.22 ±  9%  perf-profile.self.cycles-pp.current_time
      0.26 ±  9%      -0.1        0.20 ±  8%  perf-profile.self.cycles-pp.rcu_all_qs
      0.22 ± 10%      -0.1        0.16 ± 10%  perf-profile.self.cycles-pp.exit_to_user_mode_prepare
      0.00            +0.1        0.10 ± 15%  perf-profile.self.cycles-pp.xattr_full_name
      0.00            +0.1        0.10 ±  6%  perf-profile.self.cycles-pp.should_remove_suid
      0.00            +0.2        0.16 ± 11%  perf-profile.self.cycles-pp.security_inode_need_killpriv
      0.00            +0.3        0.31 ± 12%  perf-profile.self.cycles-pp.__file_remove_privs
      0.00            +0.3        0.33 ±  9%  perf-profile.self.cycles-pp.simple_xattr_get
      0.00            +0.4        0.38 ± 11%  perf-profile.self.cycles-pp.__vfs_getxattr
      0.00            +0.6        0.60 ±  8%  perf-profile.self.cycles-pp.strlen
      0.00            +0.6        0.63 ±  9%  perf-profile.self.cycles-pp.shmem_xattr_handler_get
      0.00            +0.7        0.69 ±  7%  perf-profile.self.cycles-pp.cap_inode_need_killpriv
      0.00            +1.0        0.98 ±  9%  perf-profile.self.cycles-pp._raw_spin_lock
      0.00            +1.7        1.68 ±  9%  perf-profile.self.cycles-pp.xattr_resolve_name



***************************************************************************************************
lkp-icl-2sp5: 128 threads 2 sockets Intel(R) Xeon(R) Platinum 8358 CPU @ 2.60GHz with 128G memory
=========================================================================================
compiler/cpufreq_governor/directio/disk/fstype/kconfig/media/rootfs/tbox_group/test/testcase/ucode:
  gcc-11/performance/bufferedio/1SSD/btrfs/x86_64-rhel-8.3/ssd/debian-11.1-x86_64-20220510.cgz/lkp-icl-2sp5/DWOM/fxmark/0xd000331

commit: 
  8017553980 ("fs: add a FMODE_BUF_WASYNC flags for f_mode")
  faf99b5635 ("fs: add __remove_file_privs() with flags parameter")

8017553980d0bbfe faf99b563558f74188b7ca34faa 
---------------- --------------------------- 
         %stddev     %change         %stddev
             \          |                \  
     16.96 ± 39%    +139.6%      40.65 ±  3%  fxmark.ssd_btrfs_DWOM_18_bufferedio.idle_sec
      1.88 ± 39%    +141.5%       4.55 ±  3%  fxmark.ssd_btrfs_DWOM_18_bufferedio.idle_util
      1.41 ±  6%     +16.1%       1.64 ±  5%  fxmark.ssd_btrfs_DWOM_18_bufferedio.user_sec
      0.16 ±  6%     +17.0%       0.18 ±  5%  fxmark.ssd_btrfs_DWOM_18_bufferedio.user_util
  34325041 ±  3%     -18.0%   28132939        fxmark.ssd_btrfs_DWOM_18_bufferedio.works
    686500 ±  3%     -18.0%     562658        fxmark.ssd_btrfs_DWOM_18_bufferedio.works/sec
      1.87 ±  3%     +28.7%       2.41 ±  4%  fxmark.ssd_btrfs_DWOM_1_bufferedio.user_sec
      3.74 ±  3%     +28.7%       4.81 ±  4%  fxmark.ssd_btrfs_DWOM_1_bufferedio.user_util
  49416836           -18.2%   40417244        fxmark.ssd_btrfs_DWOM_1_bufferedio.works
    988336           -18.2%     808344        fxmark.ssd_btrfs_DWOM_1_bufferedio.works/sec
      0.51 ±103%    +232.2%       1.68 ± 26%  fxmark.ssd_btrfs_DWOM_2_bufferedio.idle_sec
      0.51 ±103%    +234.0%       1.69 ± 26%  fxmark.ssd_btrfs_DWOM_2_bufferedio.idle_util
  39426231 ±  2%     -17.2%   32642756 ±  3%  fxmark.ssd_btrfs_DWOM_2_bufferedio.works
    788524 ±  2%     -17.2%     652855 ±  3%  fxmark.ssd_btrfs_DWOM_2_bufferedio.works/sec
      1.33 ±  5%     +21.3%       1.61 ±  5%  fxmark.ssd_btrfs_DWOM_36_bufferedio.user_sec
      0.07 ±  5%     +21.3%       0.09 ±  5%  fxmark.ssd_btrfs_DWOM_36_bufferedio.user_util
  27238066 ±  3%     -12.1%   23930983 ±  5%  fxmark.ssd_btrfs_DWOM_36_bufferedio.works
    544761 ±  3%     -12.1%     478619 ±  5%  fxmark.ssd_btrfs_DWOM_36_bufferedio.works/sec
      3.47 ± 32%    +299.6%      13.85 ± 18%  fxmark.ssd_btrfs_DWOM_4_bufferedio.idle_sec
      1.72 ± 32%    +309.5%       7.03 ± 18%  fxmark.ssd_btrfs_DWOM_4_bufferedio.idle_util
      1.31 ±  6%      +9.9%       1.44        fxmark.ssd_btrfs_DWOM_4_bufferedio.user_sec
      0.65 ±  7%     +12.5%       0.73        fxmark.ssd_btrfs_DWOM_4_bufferedio.user_util
  36520279 ±  4%     -16.9%   30343499 ±  3%  fxmark.ssd_btrfs_DWOM_4_bufferedio.works
    730405 ±  4%     -16.9%     606858 ±  3%  fxmark.ssd_btrfs_DWOM_4_bufferedio.works/sec
     74.92 ±  8%     +21.3%      90.85 ±  4%  fxmark.ssd_btrfs_DWOM_54_bufferedio.idle_sec
      2.77 ±  8%     +21.2%       3.36 ±  4%  fxmark.ssd_btrfs_DWOM_54_bufferedio.idle_util
      3.21 ±  3%      +8.3%       3.48 ±  2%  fxmark.ssd_btrfs_DWOM_54_bufferedio.user_sec
      0.12 ±  3%      +8.3%       0.13 ±  2%  fxmark.ssd_btrfs_DWOM_54_bufferedio.user_util
  23673951           -12.1%   20807656        fxmark.ssd_btrfs_DWOM_54_bufferedio.works
    473478           -12.1%     416152        fxmark.ssd_btrfs_DWOM_54_bufferedio.works/sec
      1.48 ±  7%     +12.6%       1.66        fxmark.ssd_btrfs_DWOM_72_bufferedio.user_sec
      0.04 ±  6%     +12.6%       0.05        fxmark.ssd_btrfs_DWOM_72_bufferedio.user_util
  20833152 ±  3%      -8.2%   19122984 ±  3%  fxmark.ssd_btrfs_DWOM_72_bufferedio.works
    416662 ±  3%      -8.2%     382458 ±  3%  fxmark.ssd_btrfs_DWOM_72_bufferedio.works/sec
    708206 ±  7%    +438.6%    3814521 ± 23%  fxmark.time.voluntary_context_switches
  13548657 ± 25%    +125.7%   30579685 ±  9%  cpuidle..usage
    775.00 ±105%    +233.2%       2582 ± 24%  meminfo.Dirty
      7.56 ±  4%      +1.1        8.70 ±  3%  mpstat.cpu.all.idle%
     70892 ± 29%    +124.1%     158847 ±  9%  vmstat.system.cs
    736.00 ±102%    +234.6%       2462 ± 28%  numa-meminfo.node0.Dirty
      1677 ± 11%     -21.2%       1320 ±  8%  numa-meminfo.node0.Writeback
    179.33 ±103%    +252.0%     631.33 ± 27%  numa-vmstat.node0.nr_dirty
    583.00 ± 41%     +65.1%     962.67 ± 21%  numa-vmstat.node0.nr_zone_write_pending
   8372809 ± 41%    +194.2%   24630154 ± 13%  turbostat.POLL
      0.03 ± 17%      +0.0        0.04 ± 10%  turbostat.POLL%
      6.06 ±  4%     +22.8%       7.45 ±  4%  iostat.cpu.idle
     89.97            -2.0%      88.14        iostat.cpu.system
      1.87 ±  2%      +8.1%       2.02 ±  2%  iostat.cpu.user
    187.33 ±103%    +216.0%     592.00 ± 28%  proc-vmstat.nr_dirty
     27467 ±  2%      +6.3%      29198        proc-vmstat.nr_shmem
    596.67 ± 39%     +57.4%     939.00 ± 23%  proc-vmstat.nr_zone_write_pending
   1556851            +1.0%    1572892        proc-vmstat.numa_hit
   1440188            +1.1%    1456241        proc-vmstat.numa_local
     35592 ±  3%      +5.8%      37641        proc-vmstat.pgdeactivate
     53525            +1.6%      54384        proc-vmstat.slabs_scanned
    113130 ±  9%     +21.2%     137083 ±  8%  sched_debug.cfs_rq:/.load.min
      1224 ±  7%     -10.8%       1092        sched_debug.cfs_rq:/.runnable_avg.max
     -1451           +44.5%      -2097        sched_debug.cfs_rq:/.spread0.min
     50.56 ±  5%     +13.8%      57.52 ±  7%  sched_debug.cfs_rq:/.util_avg.stddev
    270826 ±  8%     +30.4%     353103 ±  2%  sched_debug.cpu.avg_idle.avg
    537544 ±  7%     +37.1%     737049 ±  5%  sched_debug.cpu.avg_idle.max
     32771 ±  6%     +20.5%      39494 ±  5%  sched_debug.cpu.avg_idle.min
    143572 ± 10%     +51.2%     217113 ±  2%  sched_debug.cpu.avg_idle.stddev
    777.36 ± 46%     +42.6%       1108 ± 36%  sched_debug.cpu.clock_task.stddev
      1.90 ±  3%     -15.0%       1.62 ±  4%  sched_debug.cpu.nr_running.max
    751452 ± 20%    +267.0%    2758128 ± 17%  sched_debug.cpu.nr_switches.avg
    978379 ± 22%    +225.5%    3184540 ± 13%  sched_debug.cpu.nr_switches.max
    567505 ± 14%    +338.0%    2485802 ± 20%  sched_debug.cpu.nr_switches.min
    165188 ± 37%     +59.6%     263577 ± 18%  sched_debug.cpu.nr_switches.stddev
  20218908 ± 23%     +22.0%   24672368        perf-stat.i.branch-instructions
    744309 ± 18%     +15.8%     861797 ± 13%  perf-stat.i.branch-misses
     28048 ±  4%      +9.5%      30719 ±  4%  perf-stat.i.cache-misses
     69690 ± 29%    +123.6%     155804 ±  9%  perf-stat.i.context-switches
  20435635 ± 21%     +20.7%   24674017        perf-stat.i.dTLB-loads
   7546671 ± 15%     +15.9%    8748533        perf-stat.i.dTLB-stores
  98937391 ± 23%     +22.2%  1.209e+08        perf-stat.i.instructions
      1.70 ±  3%     +10.2%       1.87 ±  4%  perf-stat.i.major-faults
     11.67 ± 23%    +115.8%      25.18 ± 11%  perf-stat.i.metric.K/sec
      0.38 ± 20%     +20.7%       0.46        perf-stat.i.metric.M/sec
      1620 ± 11%     +19.6%       1939 ±  7%  perf-stat.i.node-loads
  20309256 ± 23%     +21.7%   24721820        perf-stat.ps.branch-instructions
    747449 ± 18%     +15.6%     863993 ± 13%  perf-stat.ps.branch-misses
     28031 ±  4%      +9.5%      30699 ±  4%  perf-stat.ps.cache-misses
     69502 ± 29%    +123.4%     155279 ±  9%  perf-stat.ps.context-switches
  20526738 ± 21%     +20.5%   24725699        perf-stat.ps.dTLB-loads
   7574374 ± 15%     +15.7%    8765053        perf-stat.ps.dTLB-stores
  99389556 ± 23%     +21.9%  1.212e+08        perf-stat.ps.instructions
      1.70 ±  3%     +10.8%       1.88 ±  3%  perf-stat.ps.major-faults
      1617 ± 11%     +19.8%       1938 ±  7%  perf-stat.ps.node-loads
  3.77e+10 ± 23%     +21.8%  4.593e+10        perf-stat.total.instructions
      1.55            +0.1        1.64        perf-profile.calltrace.cycles-pp.rwsem_spin_on_owner.rwsem_optimistic_spin.rwsem_down_write_slowpath.btrfs_inode_lock.btrfs_buffered_write
      0.41 ±  9%      -0.1        0.33        perf-profile.children.cycles-pp._raw_spin_lock
      0.27 ±  6%      -0.0        0.22 ± 11%  perf-profile.children.cycles-pp.__clear_extent_bit
      0.24 ±  8%      -0.0        0.20 ±  6%  perf-profile.children.cycles-pp.__reserve_bytes
      0.17 ±  8%      -0.0        0.13 ± 17%  perf-profile.children.cycles-pp.clear_state_bit
      0.07 ±  7%      -0.0        0.03 ± 70%  perf-profile.children.cycles-pp.__might_sleep
      0.15 ±  3%      -0.0        0.11 ± 11%  perf-profile.children.cycles-pp.btrfs_reserve_metadata_bytes
      0.11 ± 12%      -0.0        0.08 ±  5%  perf-profile.children.cycles-pp.up_write
      0.09 ±  5%      -0.0        0.07        perf-profile.children.cycles-pp.osq_unlock
      0.07 ±  6%      -0.0        0.06        perf-profile.children.cycles-pp.alloc_extent_state
      0.07 ±  7%      -0.0        0.05 ±  8%  perf-profile.children.cycles-pp.syscall_enter_from_user_mode
      0.06 ±  7%      +0.1        0.12 ± 15%  perf-profile.children.cycles-pp.kmem_cache_alloc
      1.55            +0.1        1.65        perf-profile.children.cycles-pp.rwsem_spin_on_owner
      0.00            +0.1        0.11 ± 14%  perf-profile.children.cycles-pp.btrfs_read_lock_root_node
      0.00            +0.1        0.15 ± 14%  perf-profile.children.cycles-pp.btrfs_search_slot
      0.00            +0.2        0.16 ± 13%  perf-profile.children.cycles-pp.btrfs_lookup_xattr
      0.16 ±  7%      +0.3        0.47 ±  5%  perf-profile.children.cycles-pp.btrfs_write_check
      0.00            +0.3        0.32 ±  2%  perf-profile.children.cycles-pp.btrfs_getxattr
      0.00            +0.3        0.33 ±  2%  perf-profile.children.cycles-pp.cap_inode_need_killpriv
      0.00            +0.3        0.33 ±  2%  perf-profile.children.cycles-pp.__vfs_getxattr
      0.00            +0.3        0.34 ±  2%  perf-profile.children.cycles-pp.security_inode_need_killpriv
      0.00            +0.3        0.34 ±  2%  perf-profile.children.cycles-pp.__file_remove_privs
      0.39 ±  9%      -0.1        0.32        perf-profile.self.cycles-pp._raw_spin_lock
      0.16 ±  7%      -0.0        0.12 ± 15%  perf-profile.self.cycles-pp.btrfs_write_check
      0.06            -0.0        0.03 ± 70%  perf-profile.self.cycles-pp.__might_sleep
      0.11 ±  8%      -0.0        0.08 ±  5%  perf-profile.self.cycles-pp.up_write
      0.09 ±  5%      -0.0        0.07        perf-profile.self.cycles-pp.osq_unlock
      0.07 ±  7%      -0.0        0.05 ±  8%  perf-profile.self.cycles-pp.syscall_enter_from_user_mode
      0.00            +0.1        0.06 ± 16%  perf-profile.self.cycles-pp.btrfs_getxattr
      0.00            +0.1        0.08 ± 22%  perf-profile.self.cycles-pp.kmem_cache_alloc
      1.54            +0.1        1.63        perf-profile.self.cycles-pp.rwsem_spin_on_owner





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-rc8-00180-gfaf99b563558" of type "text/plain" (164151 bytes)

View attachment "job-script" of type "text/plain" (7888 bytes)

View attachment "job.yaml" of type "text/plain" (5329 bytes)

View attachment "reproduce" of type "text/plain" (346 bytes)

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ