Greeting, We noticed a +17.2% improvement of aim7.jobs-per-min due to commit: commit: bfd53afc3fa66703227288b158f739ded1a996e7 ("ext4: delayed inode insertion into transaction at write()") url: https://github.com/0day-ci/linux/commits/Seongbae-Son/ext4-delayed-inode-... base: https://git.kernel.org/cgit/linux/kernel/git/tytso/ext4.git dev in testcase: aim7 on test machine: 40 threads Intel(R) Xeon(R) CPU E5-2690 v2 @ 3.00GHz with 384G memory with following parameters: disk: 4BRD_12G md: RAID0 fs: ext4 test: disk_wrt load: 3000 cpufreq_governor: performance test-description: AIM7 is a traditional UNIX system level benchmark suite which is used to test and measure the performance of multiuser system. test-url: https://sourceforge.net/projects/aimbench/files/aim-suite7/ Details are as below: --------------------------------------------------------------------------------------------------> To reproduce: git clone git://git.kernel.org/pub/scm/linux/kernel/git/wfg/lkp-tests.git cd lkp-tests bin/lkp install job.yaml # job file is attached in this email bin/lkp run job.yaml testcase/path_params/tbox_group/run: aim7/4BRD_12G-RAID0-ext4-disk_wrt-3000-performance/lkp-ivb-ep01 cdd33b941b678ad6 bfd53afc3fa66703227288b158 ---------------- -------------------------- %stddev change %stddev \ | \ 138167 ± 1% +17.2% 161969 ± 0% aim7.jobs-per-min 46.06 ± 1% +17.2% 53.99 ± 0% aim7.jobs-per-min-per-task 130.76 ± 1% -14.7% 111.60 ± 0% aim7.time.elapsed_time 130.76 ± 1% -14.7% 111.60 ± 0% aim7.time.elapsed_time.max 677465 ± 1% -24.0% 514992 ± 2% aim7.time.involuntary_context_switches 4687 ± 1% -16.5% 3912 ± 0% aim7.time.system_time 17662 ± 3% +12.9% 19946 ± 1% iostat.md0.wkB/s 82385 ± 5% -23.3% 63216 ± 5% meminfo.Dirty 500210 ± 2% -19.9% 400692 ± 2% softirqs.RCU 1941048 ± 1% -14.0% 1670036 ± 0% softirqs.TIMER 13848 ± 0% +2.9% 14249 ± 1% vmstat.system.cs 48369 ± 2% +4.3% 50473 ± 2% vmstat.system.in 43076 ± 5% -21.0% 34012 ± 6% numa-meminfo.node0.Dirty 99678 ±134% -97.5% 2533 ±133% numa-meminfo.node0.Inactive(anon) 130132 ±136% -98.0% 2629 ±127% numa-meminfo.node0.Shmem 39842 ± 4% -18.8% 32363 ± 9% numa-meminfo.node1.Dirty 19917 ± 6% -15.2% 16888 ± 11% proc-vmstat.nr_dirty 64672 ± 9% -27.7% 46749 ± 16% proc-vmstat.nr_written 19918 ± 6% -15.2% 16888 ± 11% proc-vmstat.nr_zone_write_pending 2290 ± 22% +34.6% 3082 ± 1% proc-vmstat.numa_hint_faults_local 264090 ± 10% -28.1% 189820 ± 16% proc-vmstat.pgpgout 130.76 ± 1% -14.7% 111.60 ± 0% time.elapsed_time 130.76 ± 1% -14.7% 111.60 ± 0% time.elapsed_time.max 677465 ± 1% -24.0% 514992 ± 2% time.involuntary_context_switches 4687 ± 1% -16.5% 3912 ± 0% time.system_time 18.51 ± 0% -19.6% 14.89 ± 1% time.user_time aim7.jobs-per-min 180000 ++-----------------------------------------------------------------+ O O O O O O O O O O O OO | 160000 ++ O O | 140000 ++*. *.* **.*. * .** .*.**.*. .**.*.*. * *.**. .* *.*.* | : * : : * : * : * * *: : * : : | 120000 ++: : : : : : : : : : : : | 100000 ++ : : : :: : : : : : : : | |: : : : :: : : : : : : : | 80000 ++ : : : :: : : : : : : : | 60000 ++ : : :: : : : : : : :: | |: : : :: : : : : : : :: | 40000 ++ : : :: : : : : : : :: | 20000 ++ : : : : : : | | : : : : : : | 0 *+--O--O-*-O--O---O--O------*----------------------*----------*----+ [*] bisect-good sample [O] bisect-bad sample 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. Thanks, Xiaolong