All of lore.kernel.org
 help / color / mirror / Atom feed
From: kernel test robot <oliver.sang@intel.com>
To: Ojaswin Mujoo <ojaswin@linux.ibm.com>
Cc: <oe-lkp@lists.linux.dev>, <lkp@intel.com>,
	<linux-kernel@vger.kernel.org>, Theodore Ts'o <tytso@mit.edu>,
	Jan Kara <jack@suse.cz>, Ritesh Harjani <ritesh.list@gmail.com>,
	Baokun Li <libaokun1@huawei.com>, <linux-ext4@vger.kernel.org>,
	<oliver.sang@intel.com>
Subject: [linus:master] [ext4]  896b02d0b9:  stress-ng.fiemap.ops_per_sec 15.8% regression
Date: Mon, 21 Apr 2025 13:56:07 +0800	[thread overview]
Message-ID: <202504211320.5025beac-lkp@intel.com> (raw)



Hello,

kernel test robot noticed a 15.8% regression of stress-ng.fiemap.ops_per_sec on:


commit: 896b02d0b9e7deb4a4eb365e13dd912b49916519 ("ext4: Make sb update interval tunable")
https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git master

[test failed on linus/master      1a1d569a75f3ab2923cb62daf356d102e4df2b86]
[test failed on linux-next/master f660850bc246fef15ba78c81f686860324396628]

testcase: stress-ng
config: x86_64-rhel-9.4
compiler: gcc-12
test machine: 64 threads 2 sockets Intel(R) Xeon(R) Gold 6346 CPU @ 3.10GHz (Ice Lake) with 256G memory
parameters:

	nr_threads: 100%
	disk: 1HDD
	testtime: 60s
	fs: ext4
	test: fiemap
	cpufreq_governor: performance




If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <oliver.sang@intel.com>
| Closes: https://lore.kernel.org/oe-lkp/202504211320.5025beac-lkp@intel.com


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


The kernel config and materials to reproduce are available at:
https://download.01.org/0day-ci/archive/20250421/202504211320.5025beac-lkp@intel.com

=========================================================================================
compiler/cpufreq_governor/disk/fs/kconfig/nr_threads/rootfs/tbox_group/test/testcase/testtime:
  gcc-12/performance/1HDD/ext4/x86_64-rhel-9.4/100%/debian-12-x86_64-20240206.cgz/lkp-icl-2sp8/fiemap/stress-ng/60s

commit: 
  ce2f26e737 ("ext4: avoid journaling sb update on error if journal is destroying")
  896b02d0b9 ("ext4: Make sb update interval tunable")

ce2f26e73783b4a7 896b02d0b9e7deb4a4eb365e13d 
---------------- --------------------------- 
         %stddev     %change         %stddev
             \          |                \  
      2.29 ±  6%     -13.2%       1.99 ±  7%  iostat.cpu.user
   1688381 ±  2%     -16.4%    1411358 ±  4%  vmstat.system.cs
      0.01 ± 12%      -0.0        0.01 ± 10%  mpstat.cpu.all.soft%
      2.33 ±  6%      -0.3        2.01 ±  7%  mpstat.cpu.all.usr%
     28467 ± 22%     +39.4%      39676 ± 13%  numa-meminfo.node0.Inactive
     28467 ± 22%     +39.4%      39676 ± 13%  numa-meminfo.node0.Inactive(file)
      7099 ± 22%     +40.0%       9937 ± 13%  numa-vmstat.node0.nr_inactive_file
      7099 ± 22%     +40.0%       9937 ± 13%  numa-vmstat.node0.nr_zone_inactive_file
   3186734 ±  2%     -13.0%    2770907        meminfo.Active
   3186734 ±  2%     -13.0%    2770907        meminfo.Active(anon)
   2332511 ±  4%     -17.1%    1933636 ±  2%  meminfo.Shmem
    829642 ±  3%     -16.0%     696952 ±  4%  sched_debug.cpu.nr_switches.avg
    992823 ±  4%     -14.5%     849332 ±  6%  sched_debug.cpu.nr_switches.max
    153915 ±  5%     -15.2%     130547 ± 11%  sched_debug.cpu.nr_switches.stddev
  64971130 ±  3%     -15.8%   54708915 ±  4%  stress-ng.fiemap.ops
   1067456 ±  3%     -15.8%     898490 ±  4%  stress-ng.fiemap.ops_per_sec
 1.079e+08 ±  2%     -16.0%   90643140 ±  4%  stress-ng.time.involuntary_context_switches
     67.64 ±  9%     -16.5%      56.46 ±  9%  stress-ng.time.user_time
    797292 ±  2%     -13.2%     692413        proc-vmstat.nr_active_anon
   1499550            -6.7%    1398519        proc-vmstat.nr_file_pages
    583908 ±  4%     -17.3%     483006 ±  2%  proc-vmstat.nr_shmem
    797292 ±  2%     -13.2%     692413        proc-vmstat.nr_zone_active_anon
   1256873 ±  2%     -12.3%    1102563        proc-vmstat.numa_hit
   1190636 ±  2%     -13.0%    1036297        proc-vmstat.numa_local
   1367314 ±  2%     -11.3%    1212232 ±  2%  proc-vmstat.pgalloc_normal
    369155 ±  5%      -6.9%     343753 ±  2%  proc-vmstat.pgfault
 2.492e+10 ±  2%     -18.5%  2.031e+10        perf-stat.i.branch-instructions
 1.232e+08 ±  7%     -15.2%  1.045e+08 ±  6%  perf-stat.i.branch-misses
 3.895e+08 ±  2%      -8.8%  3.553e+08        perf-stat.i.cache-references
   1759358 ±  2%     -16.0%    1478535 ±  3%  perf-stat.i.context-switches
      1.80 ±  2%     +22.5%       2.20        perf-stat.i.cpi
 1.262e+11 ±  2%     -18.5%  1.028e+11        perf-stat.i.instructions
      0.56 ±  2%     -18.5%       0.46        perf-stat.i.ipc
     27.44 ±  2%     -15.8%      23.10 ±  3%  perf-stat.i.metric.K/sec
      4132 ±  5%      -8.9%       3766 ±  2%  perf-stat.i.minor-faults
      4132 ±  5%      -8.9%       3766 ±  2%  perf-stat.i.page-faults
      1.79 ±  2%     +22.8%       2.20        perf-stat.overall.cpi
      0.56 ±  2%     -18.6%       0.45        perf-stat.overall.ipc
  2.45e+10 ±  2%     -18.5%  1.998e+10        perf-stat.ps.branch-instructions
  1.21e+08 ±  7%     -15.0%  1.028e+08 ±  6%  perf-stat.ps.branch-misses
 3.828e+08 ±  2%      -8.7%  3.496e+08        perf-stat.ps.cache-references
   1729946 ±  2%     -15.9%    1454325 ±  3%  perf-stat.ps.context-switches
 1.241e+11 ±  2%     -18.5%  1.011e+11        perf-stat.ps.instructions
      4060 ±  5%      -8.8%       3703 ±  2%  perf-stat.ps.minor-faults
      4060 ±  5%      -8.8%       3703 ±  2%  perf-stat.ps.page-faults
 7.699e+12 ±  2%     -18.7%  6.262e+12 ±  2%  perf-stat.total.instructions
      0.02 ±194%   +3583.1%       0.80 ±127%  perf-sched.sch_delay.avg.ms.__cond_resched.zap_pte_range.zap_pmd_range.isra.0
      0.14 ±  5%     +21.4%       0.17 ±  2%  perf-sched.sch_delay.avg.ms.__x64_sys_sched_yield.do_syscall_64.entry_SYSCALL_64_after_hwframe.[unknown]
      0.02 ± 12%     +35.4%       0.03 ± 11%  perf-sched.sch_delay.avg.ms.schedule_timeout.kcompactd.kthread.ret_from_fork
      0.01 ±  3%     +14.8%       0.01 ±  6%  perf-sched.sch_delay.avg.ms.smpboot_thread_fn.kthread.ret_from_fork.ret_from_fork_asm
      2.90 ±107%    +259.8%      10.43 ± 35%  perf-sched.sch_delay.max.ms.__cond_resched.down_write.shmem_file_write_iter.vfs_write.ksys_write
      8.62 ± 28%     +69.3%      14.58 ±  8%  perf-sched.sch_delay.max.ms.__cond_resched.shmem_get_folio_gfp.shmem_write_begin.generic_perform_write.shmem_file_write_iter
      0.02 ±194%   +5175.4%       1.14 ± 88%  perf-sched.sch_delay.max.ms.__cond_resched.zap_pte_range.zap_pmd_range.isra.0
    395.95 ±185%     -99.6%       1.67 ± 45%  perf-sched.sch_delay.max.ms.do_nanosleep.hrtimer_nanosleep.common_nsleep.__x64_sys_clock_nanosleep
     10.22 ± 15%     +49.3%      15.26 ±  4%  perf-sched.sch_delay.max.ms.irqentry_exit_to_user_mode.asm_sysvec_apic_timer_interrupt.[unknown].[unknown]
      0.05 ± 10%     +29.0%       0.06 ± 13%  perf-sched.sch_delay.max.ms.schedule_timeout.kcompactd.kthread.ret_from_fork
      0.14 ±  5%     +20.6%       0.17 ±  2%  perf-sched.total_sch_delay.average.ms
      0.44 ±  3%     +19.7%       0.52 ±  3%  perf-sched.total_wait_and_delay.average.ms
   6639596 ±  3%     -17.7%    5461347 ±  3%  perf-sched.total_wait_and_delay.count.ms
      0.30 ±  2%     +19.3%       0.36 ±  3%  perf-sched.total_wait_time.average.ms
      0.28 ±  3%     +20.8%       0.34 ±  2%  perf-sched.wait_and_delay.avg.ms.__x64_sys_sched_yield.do_syscall_64.entry_SYSCALL_64_after_hwframe.[unknown]
   6614032 ±  3%     -17.8%    5436664 ±  3%  perf-sched.wait_and_delay.count.__x64_sys_sched_yield.do_syscall_64.entry_SYSCALL_64_after_hwframe.[unknown]
      5.80 ±107%    +259.8%      20.86 ± 35%  perf-sched.wait_and_delay.max.ms.__cond_resched.down_write.shmem_file_write_iter.vfs_write.ksys_write
     17.23 ± 28%     +69.3%      29.17 ±  8%  perf-sched.wait_and_delay.max.ms.__cond_resched.shmem_get_folio_gfp.shmem_write_begin.generic_perform_write.shmem_file_write_iter
     20.45 ± 15%     +63.4%      33.41 ± 21%  perf-sched.wait_and_delay.max.ms.irqentry_exit_to_user_mode.asm_sysvec_apic_timer_interrupt.[unknown].[unknown]
      0.02 ±223%   +4040.9%       0.79 ±127%  perf-sched.wait_time.avg.ms.__cond_resched.zap_pte_range.zap_pmd_range.isra.0
      0.15 ±  2%     +20.6%       0.18 ±  2%  perf-sched.wait_time.avg.ms.__x64_sys_sched_yield.do_syscall_64.entry_SYSCALL_64_after_hwframe.[unknown]
      2.90 ±107%    +259.8%      10.43 ± 35%  perf-sched.wait_time.max.ms.__cond_resched.down_write.shmem_file_write_iter.vfs_write.ksys_write
      8.62 ± 28%     +69.3%      14.58 ±  8%  perf-sched.wait_time.max.ms.__cond_resched.shmem_get_folio_gfp.shmem_write_begin.generic_perform_write.shmem_file_write_iter
      0.02 ±223%   +5863.5%       1.14 ± 88%  perf-sched.wait_time.max.ms.__cond_resched.zap_pte_range.zap_pmd_range.isra.0
     10.22 ± 15%    +103.2%      20.77 ± 61%  perf-sched.wait_time.max.ms.irqentry_exit_to_user_mode.asm_sysvec_apic_timer_interrupt.[unknown].[unknown]




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://github.com/intel/lkp-tests/wiki


             reply	other threads:[~2025-04-21  5:56 UTC|newest]

Thread overview: 2+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-04-21  5:56 kernel test robot [this message]
2025-04-22  8:51 ` [linus:master] [ext4] 896b02d0b9: stress-ng.fiemap.ops_per_sec 15.8% regression Ojaswin Mujoo

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=202504211320.5025beac-lkp@intel.com \
    --to=oliver.sang@intel.com \
    --cc=jack@suse.cz \
    --cc=libaokun1@huawei.com \
    --cc=linux-ext4@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=lkp@intel.com \
    --cc=oe-lkp@lists.linux.dev \
    --cc=ojaswin@linux.ibm.com \
    --cc=ritesh.list@gmail.com \
    --cc=tytso@mit.edu \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.