public inbox for linux-ext4@vger.kernel.org
 help / color / mirror / Atom feed
* [linus:master] [ext4]  1ad0f42823:  fio.write_iops 23.8% improvement
@ 2026-04-30  5:38 kernel test robot
  0 siblings, 0 replies; only message in thread
From: kernel test robot @ 2026-04-30  5:38 UTC (permalink / raw)
  To: Zhang Yi
  Cc: oe-lkp, lkp, linux-kernel, Theodore Ts'o, Jan Kara,
	linux-ext4, oliver.sang



Hello,

kernel test robot noticed a 23.8% improvement of fio.write_iops on:


commit: 1ad0f42823291bcac371dafd37533f5e8d92acc3 ("ext4: move pagecache_isize_extended() out of active handle")
https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git master


testcase: fio-basic
config: x86_64-rhel-9.4
compiler: gcc-14
test machine: 64 threads 2 sockets Intel(R) Xeon(R) Gold 6346 CPU @ 3.10GHz (Ice Lake) with 256G memory
parameters:

	runtime: 300s
	disk: 1HDD
	fs: ext4
	nr_task: 1
	test_size: 128G
	rw: write
	bs: 4k
	ioengine: falloc
	cpufreq_governor: performance



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


The kernel config and materials to reproduce are available at:
https://download.01.org/0day-ci/archive/20260430/202604301021.faab1f8a-lkp@intel.com

=========================================================================================
bs/compiler/cpufreq_governor/disk/fs/ioengine/kconfig/nr_task/rootfs/runtime/rw/tbox_group/test_size/testcase:
  4k/gcc-14/performance/1HDD/ext4/falloc/x86_64-rhel-9.4/1/debian-13-x86_64-20250902.cgz/300s/write/lkp-icl-2sp9/128G/fio-basic

commit: 
  116c0bdac2 ("ext4: remove ctime/mtime update from ext4_alloc_file_blocks()")
  1ad0f42823 ("ext4: move pagecache_isize_extended() out of active handle")

116c0bdac2ec059d 1ad0f42823291bcac371dafd375 
---------------- --------------------------- 
         %stddev     %change         %stddev
             \          |                \  
      0.11 ±  5%      -0.0        0.08 ±  7%  fio.latency_2us%
      0.07 ±  3%      -0.0        0.05 ±  6%  fio.latency_4us%
     34.79           -19.1%      28.14        fio.time.elapsed_time
     34.79           -19.1%      28.14        fio.time.elapsed_time.max
     24.17           -26.0%      17.90        fio.time.system_time
      3736           -18.7%       3037        fio.time.voluntary_context_switches
      3812           +23.8%       4720        fio.write_bw_MBps
    850.67           -22.7%     657.33        fio.write_clat_90%_ns
    857.33           -22.4%     665.33        fio.write_clat_95%_ns
    872.00           -22.5%     676.00        fio.write_clat_99%_ns
    835.45           -22.7%     645.60        fio.write_clat_mean_ns
    192.67 ± 28%    +122.3%     428.28 ± 20%  fio.write_clat_stddev
    975889           +23.8%    1208502        fio.write_iops
      1.13            -7.7%       1.05        iostat.cpu.system
    146867           -17.0%     121930        turbostat.IRQ
 2.317e+09           -17.6%  1.908e+09        cpuidle..time
    121665 ±  9%     -11.5%     107660 ±  5%  cpuidle..usage
      1.13            -0.1        1.04        mpstat.cpu.all.sys%
      0.54 ±  2%      +0.1        0.62 ±  2%  mpstat.cpu.all.usr%
    124.09 ±  2%      -6.1%     116.50        uptime.boot
      7577 ±  2%      -6.3%       7099        uptime.idle
      1507 ±  4%     +13.8%       1714        vmstat.io.bo
      1.58 ±  3%      +9.7%       1.73 ±  2%  vmstat.procs.r
    256506            -3.5%     247467        proc-vmstat.numa_hit
    281823            -4.4%     269466        proc-vmstat.pgalloc_normal
    166349            -7.9%     153190        proc-vmstat.pgfault
    159495            -7.7%     147154        proc-vmstat.pgfree
      7811 ± 20%     -45.1%       4288        proc-vmstat.pgpgout
      7649            -8.2%       7019 ±  2%  proc-vmstat.pgreuse
      4.74 ± 63%      -4.7        0.00        perf-profile.calltrace.cycles-pp.do_mprotect_pkey.__x64_sys_mprotect.do_syscall_64.entry_SYSCALL_64_after_hwframe
      3.64 ±104%      -3.1        0.56 ±223%  perf-profile.calltrace.cycles-pp.acpi_idle_do_entry.acpi_idle_enter.cpuidle_enter_state.cpuidle_enter.cpuidle_idle_call
      3.64 ±104%      -3.1        0.56 ±223%  perf-profile.calltrace.cycles-pp.acpi_idle_enter.cpuidle_enter_state.cpuidle_enter.cpuidle_idle_call.do_idle
      3.64 ±104%      -3.1        0.56 ±223%  perf-profile.calltrace.cycles-pp.acpi_safe_halt.acpi_idle_do_entry.acpi_idle_enter.cpuidle_enter_state.cpuidle_enter
      3.64 ±104%      -3.1        0.56 ±223%  perf-profile.calltrace.cycles-pp.cpuidle_enter.cpuidle_idle_call.do_idle.cpu_startup_entry.start_secondary
      3.64 ±104%      -3.1        0.56 ±223%  perf-profile.calltrace.cycles-pp.cpuidle_enter_state.cpuidle_enter.cpuidle_idle_call.do_idle.cpu_startup_entry
      3.64 ±104%      -3.1        0.56 ±223%  perf-profile.calltrace.cycles-pp.cpuidle_idle_call.do_idle.cpu_startup_entry.start_secondary.common_startup_64
      4.95 ± 81%      -3.4        1.54 ±149%  perf-profile.children.cycles-pp.__split_vma
      3.64 ±104%      -3.1        0.56 ±223%  perf-profile.children.cycles-pp.acpi_idle_do_entry
      3.64 ±104%      -3.1        0.56 ±223%  perf-profile.children.cycles-pp.acpi_idle_enter
      3.64 ±104%      -3.1        0.56 ±223%  perf-profile.children.cycles-pp.acpi_safe_halt
      3.64 ±104%      -3.1        0.56 ±223%  perf-profile.children.cycles-pp.cpuidle_enter
      3.64 ±104%      -3.1        0.56 ±223%  perf-profile.children.cycles-pp.cpuidle_enter_state
      3.64 ±104%      -3.1        0.56 ±223%  perf-profile.children.cycles-pp.cpuidle_idle_call
      3.64 ±104%      -3.1        0.56 ±223%  perf-profile.children.cycles-pp.pv_native_safe_halt
      1.82 ±148%      +5.8        7.59 ± 39%  perf-profile.children.cycles-pp.__mmap_region
      1.82 ±148%      +6.5        8.34 ± 44%  perf-profile.children.cycles-pp.do_mmap
      1.82 ±148%      +6.5        8.34 ± 44%  perf-profile.children.cycles-pp.vm_mmap_pgoff
      0.03 ±  7%     +21.8%       0.04 ±  4%  perf-stat.i.MPKI
      0.26            +0.1        0.32        perf-stat.i.branch-miss-rate%
   4548711           +21.7%    5537175        perf-stat.i.branch-misses
    274432 ±  6%     +20.4%     330549 ±  4%  perf-stat.i.cache-misses
   1860596            +8.1%    2011597        perf-stat.i.cache-references
      0.47            +2.1%       0.48        perf-stat.i.cpi
      2398            +3.0%       2470        perf-stat.i.minor-faults
      2398            +3.0%       2470        perf-stat.i.page-faults
      0.03 ±  6%     +22.3%       0.04 ±  4%  perf-stat.overall.MPKI
      0.26            +0.1        0.32        perf-stat.overall.branch-miss-rate%
     14.77 ±  6%      +1.7       16.46 ±  4%  perf-stat.overall.cache-miss-rate%
      0.47            +1.8%       0.48        perf-stat.overall.cpi
     14177 ±  6%     -16.9%      11783 ±  5%  perf-stat.overall.cycles-between-cache-misses
      2.12            -1.8%       2.08        perf-stat.overall.ipc
      8603           -19.7%       6911        perf-stat.overall.path-length
  1.69e+09            -1.7%  1.662e+09        perf-stat.ps.branch-instructions
   4424559           +21.0%    5353882        perf-stat.ps.branch-misses
    267376 ±  6%     +19.9%     320480 ±  4%  perf-stat.ps.cache-misses
   1810896            +7.5%    1947007        perf-stat.ps.cache-references
 7.998e+09            -2.0%  7.838e+09        perf-stat.ps.instructions
      2334            +2.5%       2393        perf-stat.ps.minor-faults
      2334            +2.5%       2393        perf-stat.ps.page-faults
 2.887e+11           -19.7%  2.319e+11        perf-stat.total.instructions




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


^ permalink raw reply	[flat|nested] only message in thread

only message in thread, other threads:[~2026-04-30  5:38 UTC | newest]

Thread overview: (only message) (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-04-30  5:38 [linus:master] [ext4] 1ad0f42823: fio.write_iops 23.8% improvement kernel test robot

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox