Greeting, FYI, we noticed a -6.8% regression of aim9.add_long.ops_per_sec due to commit: commit: dc280d93623927570da279e99393879dbbab39e7 ("cpu/hotplug: Prevent overwriting of callbacks") https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git master in testcase: aim9 on test machine: 80 threads Intel(R) Xeon(R) CPU E7- 8870 @ 2.40GHz with 128G memory with following parameters: testtime: 300s test: add_long cpufreq_governor: performance test-description: Suite IX is the "AIM Independent Resource Benchmark:" the famous synthetic benchmark. test-url: https://sourceforge.net/projects/aimbench/files/aim-suite9/ 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: aim9/300s-add_long-performance/lkp-wsx02 59fefd0890f12716 dc280d93623927570da279e993 ---------------- -------------------------- %stddev change %stddev \ | \ 6372000 -7% 5939700 aim9.add_long.ops_per_sec 302467 310046 interrupts.CAL:Function_call_interrupts 81197 82290 vmstat.system.in 252 -100% 0 turbostat.Avg_MHz 12.01 -100% 0.00 turbostat.%Busy 0 2e+04 16338 ± 58% latency_stats.avg.perf_event_alloc.SYSC_perf_event_open.SyS_perf_event_open.entry_SYSCALL_64_fastpath 0 2e+04 16338 ± 58% latency_stats.max.perf_event_alloc.SYSC_perf_event_open.SyS_perf_event_open.entry_SYSCALL_64_fastpath 0 2e+04 16338 ± 58% latency_stats.sum.perf_event_alloc.SYSC_perf_event_open.SyS_perf_event_open.entry_SYSCALL_64_fastpath 4622 ±104% -3e+03 1198 latency_stats.sum.kthread_park.watchdog_park_threads.watchdog_enable_all_cpus.proc_watchdog_update.proc_watchdog_common.proc_nmi_watchdog.proc_sys_call_handler.proc_sys_write.__vfs_write.vfs_write.SyS_write.entry_SYSCALL_64_fastpath 1.04 ± 3% 1953% 21.38 perf-stat.cache-miss-rate% 18504 29% 23868 ± 8% perf-stat.cpu-migrations 1889012 ± 14% 121% 4170802 perf-stat.node-load-misses 20313444 ± 3% 83% 37191142 perf-stat.node-stores 90065697 82% 1.641e+08 perf-stat.cache-misses 0.41 ± 7% 111% 0.87 ± 8% perf-stat.ipc 6119350 ± 7% 158% 15783978 perf-stat.node-store-misses 33409559 56% 52103995 perf-stat.node-loads 4.596e+08 -86% 65414036 ± 3% perf-stat.dTLB-load-misses 2.003e+10 -14% 1.728e+10 perf-stat.dTLB-stores 2.335e+11 ± 4% -77% 5.439e+10 perf-stat.dTLB-loads 2.36e+12 -35% 1.545e+12 perf-stat.iTLB-loads 2.328e+12 ± 9% -40% 1.406e+12 ± 17% perf-stat.instructions 3.84e+11 -49% 1.946e+11 perf-stat.branch-instructions 5.34 ± 13% 39% 7.41 perf-stat.node-load-miss-rate% 1.929e+08 -51% 94975374 perf-stat.iTLB-load-misses 1.698e+09 -81% 3.201e+08 perf-stat.branch-misses 23.14 ± 5% 29% 29.79 perf-stat.node-store-miss-rate% 0.01 -25% 0.01 perf-stat.iTLB-load-miss-rate% 8.652e+09 -91% 7.674e+08 perf-stat.cache-references 0.44 -63% 0.16 perf-stat.branch-miss-rate% 5.607e+12 -72% 1.596e+12 ± 8% perf-stat.cpu-cycles 3.087e+08 -96% 11205248 ± 4% perf-stat.dTLB-store-misses 0.20 ± 5% -39% 0.12 ± 3% perf-stat.dTLB-load-miss-rate% 1.52 -96% 0.06 ± 3% perf-stat.dTLB-store-miss-rate% perf-stat.cpu-cycles 7e+12 ++------------------------------------------------------------------+ | | 6e+12 ++* .**. *. .**. *. .**. .* *. | * * *. *. .* .**.*.* .**.* * * * * : *. .**. : **.* 5e+12 ++ * * * *.* * : * *.: | | : : * | 4e+12 ++ : : | | : : | 3e+12 ++ : : | | :: | 2e+12 ++ :: | O OO OO O OO O OO O OO O :: | 1e+12 ++ OO : | | : | 0 ++--------------------------------------------------*---------------+ perf-stat.cache-references 1e+10 ++------------------------------------------------------------------+ 9e+09 ++ .* .**. *. *.*. .* *.*.* .*.* | *. *. *.* *.* * *.* **.* .*. *.* .*. *.* * : * *.**.* 8e+09 ++* * * * * * : : | 7e+09 ++ : : | | : : | 6e+09 ++ : : | 5e+09 ++ : : | 4e+09 ++ :: | | :: | 3e+09 ++ :: | 2e+09 ++ : | | : | 1e+09 O+OO OO O OO O OO OO O OO O : | 0 ++--------------------------------------------------*---------------+ perf-stat.branch-instructions 4.5e+11 ++----------------------------------------------------------------+ |.* .* *. .* *. *. | 4e+11 *+ * *.* *. *.*. .* * *.* * *. *. .*. *.**.* 3.5e+11 ++ *.*.**.* * **.** * * ** * : | | : : *.* | 3e+11 ++ : : | 2.5e+11 ++ : : | | : : | 2e+11 O+OO OO OO O OO O O O OO : : | 1.5e+11 ++ O O :: | | :: | 1e+11 ++ :: | 5e+10 ++ : | | : | 0 ++------------------------------------------------*---------------+ perf-stat.branch-misses 1.8e+09 ++------------------*-*-**----------------------------------------+ *.**.**.**.*.**.**.* **.**.*.**.**.**.*.**.* **.*.**.**.**.* 1.6e+09 ++ : : | 1.4e+09 ++ : : | | : : | 1.2e+09 ++ : : | 1e+09 ++ : : | | : : | 8e+08 ++ :: | 6e+08 ++ :: | | :: | 4e+08 O+OO OO OO O OO OO O O : | 2e+08 ++ O O O : | | : | 0 ++------------------------------------------------*---------------+ perf-stat.dTLB-loads 3e+11 ++----------------------------------------------------------------+ |.* * * * * * | 2.5e+11 *+ :+ : * + + :.* + :+ *. | | * *.* .* + * * * *. *. *. : **.| | *.*.* *.** + .** * * * + * : * 2e+11 ++ *.* ** : :* : : | | : : *.* | 1.5e+11 ++ : : | | : : | 1e+11 ++ :: | | :: | O OO OO OO O O O O OO :: | 5e+10 ++ O O : | | O O : | 0 ++------------------------------------------------*---------------+ perf-stat.dTLB-load-misses 5e+08 ++---------*-*-----*---------------------------*----*-------------+ 4.5e+08 *+**.**.** *. * *.*.**.* .**.*.**.**.**.*.* * :*.*.**.**.**.* | * * : : | 4e+08 ++ : : | 3.5e+08 ++ : : | | : : | 3e+08 ++ : : | 2.5e+08 ++ : : | 2e+08 ++ :: | | :: | 1.5e+08 ++ :: | 1e+08 ++ O : | O OO O OO O OO OO OO O OO : | 5e+07 ++ : | 0 ++------------------------------------------------*---------------+ perf-stat.dTLB-stores 2.5e+10 ++----------------------------------------------------------------+ | | *.**.* .**.*.* .**.**. | 2e+10 ++ *.**.*.**.**.**.*.**.** * *.**.* **.*.**.**.**.* O OO O OO O OO OO OO O OO : : | | O : : | 1.5e+10 ++ : : | | : : | 1e+10 ++ : : | | :: | | :: | 5e+09 ++ :: | | : | | : | 0 ++------------------------------------------------*---------------+ perf-stat.dTLB-store-misses 3.5e+08 ++----------------------------------------------------------------+ *. *. .* .* .* *.* .*. | 3e+08 ++**.* **.* *.** *.*.**.** *.*.* *.** **.* **.*.**.**.**.* | : : | 2.5e+08 ++ : : | | : : | 2e+08 ++ : : | | : : | 1.5e+08 ++ :: | | :: | 1e+08 ++ :: | | :: | 5e+07 ++ : | O O O O O : | 0 ++-O--O-OO---O--OO-OO-O-OO------------------------*---------------+ perf-stat.iTLB-loads 3e+12 ++----------------------------------------------------------------+ | | 2.5e+12 ++* .* *. .* *. *. | * * *.* .*.* *.**.*. .**.* * *.* * *.**.* * .*. *.**.* | * *.* ** : :* **.* | 2e+12 ++ : : | | : : | 1.5e+12 O+OO OO OO O OO OO OO O OO : : | | : : | 1e+12 ++ :: | | :: | | :: | 5e+11 ++ : | | : | 0 ++------------------------------------------------*---------------+ perf-stat.iTLB-load-misses 2.5e+08 ++----------------------------------------------------------------+ | | *.**.**. .**.**.**.*.**.**.**.*. * | 2e+08 ++ **. .**.* * + .*.**.**.**.* | *.**.** * ** | | : : | 1.5e+08 ++ : : | | : : | 1e+08 O+ O OO O O : : | | O OO O OO O O O OO :: | | :: | 5e+07 ++ :: | | : | | : | 0 ++------------------------------------------------*---------------+ aim9.add_long.ops_per_sec 7e+06 ++------------------------------------------------------------------+ *.**.**.*.**.*.**.**.*.**.*.**.**.*.**.**.*.**.*.** *.*.**.*.**.**.* 6e+06 O+OO OO O OO O OO OO O OO O : : | | : : | 5e+06 ++ : : | | : : | 4e+06 ++ : : | | : : | 3e+06 ++ :: | | :: | 2e+06 ++ :: | | : | 1e+06 ++ : | | : | 0 ++--------------------------------------------------*---------------+ [*] 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