Greeting, FYI, we noticed a 4.9% improvement of will-it-scale.per_thread_ops due to commit: commit: 4389ee2a0b018bba7838240dc91f55a2e3cf88a9 ("mm/page_alloc: remove add_to_free_list check") git://bee.sh.intel.com/git/aaron/linux.git remove_add_to_list in testcase: will-it-scale on test machine: 16 threads Intel(R) Atom(R) CPU 3958 @ 2.00GHz with 64G memory with following parameters: nr_task: 100% mode: thread test: page_fault2 cpufreq_governor: performance test-description: Will It Scale takes a testcase and runs it from 1 through to n parallel copies to see if the testcase will scale. It builds both a process and threads based test in order to see any differences between the two. test-url: https://github.com/antonblanchard/will-it-scale Details are as below: --------------------------------------------------------------------------------------------------> To reproduce: git clone https://github.com/intel/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: will-it-scale/100%-thread-page_fault2-performance/lkp-denverton2 98b9f8a4549909c6 4389ee2a0b018bba7838240dc9 ---------------- -------------------------- 63754 5% 66885 will-it-scale.per_thread_ops 300882 5% 315437 will-it-scale.time.voluntary_context_switches 3.081e+08 5% 3.229e+08 will-it-scale.time.minor_page_faults 60.76 4% 63.42 will-it-scale.time.user_time 826 4% 862 will-it-scale.time.percent_of_cpu_this_job_got 2432 4% 2537 will-it-scale.time.system_time 1674576 3% 1727956 will-it-scale.time.involuntary_context_switches 28306 -5% 26868 ± 5% vmstat.system.in 10607 25% 13217 ± 13% perf-stat.cpu-migrations 5.136e+12 6% 5.419e+12 perf-stat.cpu-cycles 3.084e+08 5% 3.234e+08 perf-stat.minor-faults 3.084e+08 5% 3.234e+08 perf-stat.page-faults 1.188e+12 5% 1.244e+12 perf-stat.iTLB-loads 2.07e+11 4% 2.159e+11 perf-stat.branch-instructions 1.191e+12 4% 1.241e+12 perf-stat.instructions 1.998e+11 4% 2.081e+11 perf-stat.cache-references 4.784e+10 3% 4.944e+10 perf-stat.cache-misses 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