FYI, we noticed the below changes on commit aabfb57296e3dd9761e47736ec69305c95461d7d ("mm: memcontrol: do not kill uncharge batching in free_pages_and_swap_cache") 01c2965f0723a252 aabfb57296e3dd9761e47736ec testbox/testcase/testparams ---------------- -------------------------- --------------------------- %stddev %change %stddev \ | \ 2017 ± 3% -14.0% 1735 ± 2% lkp-hsw01/vm-scalability/performance-300s-16G-shm-pread-rand 2017 -14.0% 1735 GEO-MEAN time.system_time 01c2965f0723a252 aabfb57296e3dd9761e47736ec ---------------- -------------------------- 332 ± 0% -1.3% 328 ± 0% lkp-hsw01/vm-scalability/performance-300s-16G-shm-pread-rand 332 -1.3% 328 GEO-MEAN time.elapsed_time time.elapsed_time 334 ++--------------------------------------------------------------------+ *. .*.. .*.*.. .*..*.*..*.*.*..*. | 333 ++*..* * * *..*.*.*..*. .*.. .*..* | | *..* *.* + .* | 332 ++ *. | | | 331 ++ | | | 330 ++ | | | 329 ++ | | O O O O O O O O O O O O | 328 O+ O O O O O O O O O O O O O | O O O O | 327 ++--------------------------------------------------------------------+ [*] bisect-good sample [O] bisect-bad sample To reproduce: apt-get install ruby ruby-oj git clone git://git.kernel.org/pub/scm/linux/kernel/git/wfg/lkp-tests.git cd lkp-tests bin/setup-local job.yaml # the job file attached in this email bin/run-local job.yaml 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, Fengguang