[linus:master] [jbd2] b5501f970d: fxmark.ssd_ext4_dbench_client_32_directio.works/sec 5.7% improvement

[kernel test robot]

Hello,

kernel test robot noticed a 5.7% improvement of fxmark.ssd_ext4_dbench_client_32_directio.works/sec on:


commit: b5501f970dbc039df1f7c720b7a481b62de125cd ("jbd2: avoid false sharing with j_state_lock") https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git master

testcase: fxmark
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:

	nr_threads: 2c
	disk: 1SSD
	media: ssd
	test: dbench_client
	fstype: ext4
	directio: directio
	cpufreq_governor: performance


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


The kernel config and materials to reproduce are available at:
https://download.01.org/0day-ci/archive/20261104/202611040245.a26ace73-lkp@xxxxxxxxx

=========================================================================================
compiler/cpufreq_governor/directio/disk/fstype/kconfig/media/nr_threads/rootfs/tbox_group/test/testcase:
  gcc-14/performance/directio/1SSD/ext4/x86_64-rhel-9.4/ssd/2c/debian-13-x86_64-20250902.cgz/lkp-icl-2sp8/dbench_client/fxmark

commit: 
  4a87cfb9b4 ("ext4: convert group-count barrier protocol to acquire/release")
  b5501f970d ("jbd2: avoid false sharing with j_state_lock")

4a87cfb9b45ae07c b5501f970dbc039df1f7c720b7a
---------------- --------------------------- 
         %stddev     %change         %stddev
             \          |                \  
    176.50            +7.0%     188.87        fxmark.ssd_ext4_dbench_client_32_directio.iowait_sec
      2.70           +13.7%       3.06 ± 18%  fxmark.ssd_ext4_dbench_client_32_directio.softirq_sec
    128.43            +6.9%     137.23 ±  2%  fxmark.ssd_ext4_dbench_client_32_directio.user_sec
     11759            +5.7%      12432        fxmark.ssd_ext4_dbench_client_32_directio.works/sec
  2.98e+08            +5.8%  3.153e+08        fxmark.time.file_system_outputs
    108.65            +7.4%     116.70        fxmark.time.user_time
   6468008            +5.2%    6803995        fxmark.time.voluntary_context_switches


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