Greeting, FYI, we noticed a 17454.7% improvement of stress-ng.af-alg.ops_per_sec due to commit: commit: beeb460cd12ac9b91640b484b6a52dcba9d9fc8f ("crypto: algapi - Avoid spurious modprobe on LOADED") https://git.kernel.org/cgit/linux/kernel/git/next/linux-next.git master in testcase: stress-ng on test machine: 88 threads Intel(R) Xeon(R) CPU E5-2699 v4 @ 2.20GHz with 128G memory with following parameters: nr_threads: 100% disk: 1HDD testtime: 1s class: cpu cpufreq_governor: performance ucode: 0xb000038 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 ========================================================================================= class/compiler/cpufreq_governor/disk/kconfig/nr_threads/rootfs/tbox_group/testcase/testtime/ucode: cpu/gcc-7/performance/1HDD/x86_64-rhel-7.6/100%/debian-x86_64-20191114.cgz/lkp-bdw-ep6/stress-ng/1s/0xb000038 commit: 56b80bdee4 ("crypto: sun8i-ss - Delete an error message in sun8i_ss_probe()") beeb460cd1 ("crypto: algapi - Avoid spurious modprobe on LOADED") 56b80bdee4a16cf3 beeb460cd12ac9b91640b484b6a ---------------- --------------------------- %stddev %change %stddev \ | \ 1099 ± 90% +4914.5% 55147 stress-ng.af-alg.ops 190.88 ± 88% +17454.7% 33508 ± 2% stress-ng.af-alg.ops_per_sec 112458 +13.6% 127769 ± 6% stress-ng.atomic.ops 112544 +13.6% 127847 ± 6% stress-ng.atomic.ops_per_sec 47.26 -7.5% 43.73 stress-ng.time.elapsed_time 47.26 -7.5% 43.73 stress-ng.time.elapsed_time.max 7336 +7.8% 7908 stress-ng.time.percent_of_cpu_this_job_got 55189 ± 18% +77.3% 97878 ± 7% stress-ng.time.voluntary_context_switches 0.80 +6.2% 0.85 ± 5% boot-time.smp_boot 46139 +21.1% 55857 ± 2% meminfo.Shmem 16.95 -6.0 10.91 ± 4% mpstat.cpu.all.idle% 6.843e+08 ± 6% -56.8% 2.956e+08 ± 34% cpuidle.C6.time 763608 -39.6% 460844 ± 7% cpuidle.C6.usage 32623 ± 3% -9.9% 29394 ± 2% softirqs.CPU54.TIMER 31389 ± 5% -8.3% 28775 softirqs.CPU61.TIMER 33888 ± 6% -13.0% 29487 softirqs.CPU70.TIMER 19.50 ± 2% -26.9% 14.25 ± 5% vmstat.cpu.id 65.75 +6.8% 70.25 vmstat.cpu.us 5444 ± 12% +67.5% 9120 ± 6% vmstat.system.cs 1730383 ± 10% +16.3% 2012737 ± 2% numa-numastat.node0.local_node 1785683 ± 9% +15.7% 2065187 ± 2% numa-numastat.node0.numa_hit 1827655 ± 7% +14.8% 2097849 ± 8% numa-numastat.node1.local_node 1857503 ± 7% +14.8% 2132540 ± 7% numa-numastat.node1.numa_hit 1218409 ± 9% +28.4% 1564653 ± 3% numa-vmstat.node0.numa_hit 1044425 ± 11% +36.7% 1427589 ± 7% numa-vmstat.node0.numa_local 1257153 ± 4% +25.5% 1577543 ± 6% numa-vmstat.node1.numa_hit 1226664 ± 3% +22.8% 1506818 ± 10% numa-vmstat.node1.numa_local 20.13 -28.0% 14.49 ± 4% iostat.cpu.idle 13.70 ± 2% +7.7% 14.76 ± 2% iostat.cpu.system 66.17 +6.9% 70.75 iostat.cpu.user 6.19 ±100% -100.0% 0.00 iostat.sda.await.max 6.19 ±100% -100.0% 0.00 iostat.sda.r_await.max 3.09 ±100% -100.0% 0.00 iostat.sda.svctm.max 7012 ± 18% +61.7% 11338 ± 8% slabinfo.cred_jar.active_objs 166.50 ± 18% +62.0% 269.75 ± 8% slabinfo.cred_jar.active_slabs 7012 ± 18% +61.7% 11338 ± 8% slabinfo.cred_jar.num_objs 166.50 ± 18% +62.0% 269.75 ± 8% slabinfo.cred_jar.num_slabs 22516 ± 6% +16.7% 26265 ± 6% slabinfo.filp.active_objs 727.75 ± 5% +16.9% 851.00 ± 6% slabinfo.filp.active_slabs 23308 ± 5% +16.9% 27243 ± 6% slabinfo.filp.num_objs 727.75 ± 5% +16.9% 851.00 ± 6% slabinfo.filp.num_slabs 281401 +1.0% 284257 proc-vmstat.nr_file_pages 6038 +4.7% 6321 ± 2% proc-vmstat.nr_inactive_anon 9715 +6.0% 10297 ± 2% proc-vmstat.nr_mapped 11522 +20.9% 13935 ± 3% proc-vmstat.nr_shmem 38248 +2.6% 39226 proc-vmstat.nr_slab_unreclaimable 6038 +4.7% 6321 ± 2% proc-vmstat.nr_zone_inactive_anon 3673028 ± 8% +14.9% 4220629 ± 5% proc-vmstat.numa_hit 3587869 ± 8% +15.2% 4133471 ± 5% proc-vmstat.numa_local 7827 +41.5% 11074 ± 2% proc-vmstat.pgactivate 3506649 ± 9% +15.3% 4043091 ± 5% proc-vmstat.pgfault 102330 ± 2% +9.2% 111707 ± 4% proc-vmstat.pgmigrate_success 4898 ± 6% -21.5% 3846 ± 22% sched_debug.cfs_rq:/.load.avg 3505 ± 8% +29.7% 4547 ± 17% sched_debug.cfs_rq:/.runnable_avg.max 2842 ± 62% -91.4% 245.06 ±443% sched_debug.cfs_rq:/.spread0.avg 16461 ± 11% -29.2% 11649 ± 24% sched_debug.cfs_rq:/.spread0.max -2942 +73.7% -5111 sched_debug.cfs_rq:/.spread0.min 40.84 ± 33% -49.8% 20.51 ± 28% sched_debug.cfs_rq:/.util_est_enqueued.avg 665.50 ± 29% -26.1% 492.00 ± 3% sched_debug.cfs_rq:/.util_est_enqueued.max 130.10 ± 21% -32.8% 87.38 ± 14% sched_debug.cfs_rq:/.util_est_enqueued.stddev 303.34 ± 8% -24.3% 229.64 ± 12% sched_debug.cpu.curr->pid.avg 674.10 ± 3% -12.5% 589.53 ± 5% sched_debug.cpu.curr->pid.stddev 0.17 ± 10% -23.0% 0.13 ± 12% sched_debug.cpu.nr_running.avg 62.75 ± 6% -25.9% 46.50 ± 20% sched_debug.cpu.nr_uninterruptible.max 3391 ± 28% +90.6% 6462 ± 4% interrupts.CPU0.NMI:Non-maskable_interrupts 3391 ± 28% +90.6% 6462 ± 4% interrupts.CPU0.PMI:Performance_monitoring_interrupts 3153 ± 24% +99.3% 6285 interrupts.CPU1.NMI:Non-maskable_interrupts 3153 ± 24% +99.3% 6285 interrupts.CPU1.PMI:Performance_monitoring_interrupts 3886 ± 10% +68.1% 6532 ± 6% interrupts.CPU10.NMI:Non-maskable_interrupts 3886 ± 10% +68.1% 6532 ± 6% interrupts.CPU10.PMI:Performance_monitoring_interrupts 3694 ± 4% +69.0% 6244 interrupts.CPU11.NMI:Non-maskable_interrupts 3694 ± 4% +69.0% 6244 interrupts.CPU11.PMI:Performance_monitoring_interrupts 3618 ± 2% +76.2% 6374 ± 3% interrupts.CPU12.NMI:Non-maskable_interrupts 3618 ± 2% +76.2% 6374 ± 3% interrupts.CPU12.PMI:Performance_monitoring_interrupts 3180 ± 25% +96.7% 6256 interrupts.CPU18.NMI:Non-maskable_interrupts 3180 ± 25% +96.7% 6256 interrupts.CPU18.PMI:Performance_monitoring_interrupts 2702 ± 32% +130.6% 6233 interrupts.CPU19.NMI:Non-maskable_interrupts 2702 ± 32% +130.6% 6233 interrupts.CPU19.PMI:Performance_monitoring_interrupts 154.50 ± 10% +29.4% 200.00 ± 6% interrupts.CPU19.RES:Rescheduling_interrupts 3384 ± 28% +85.5% 6276 interrupts.CPU2.NMI:Non-maskable_interrupts 3384 ± 28% +85.5% 6276 interrupts.CPU2.PMI:Performance_monitoring_interrupts 2797 ± 29% +123.4% 6247 interrupts.CPU20.NMI:Non-maskable_interrupts 2797 ± 29% +123.4% 6247 interrupts.CPU20.PMI:Performance_monitoring_interrupts 2879 ± 36% +121.5% 6378 ± 2% interrupts.CPU21.NMI:Non-maskable_interrupts 2879 ± 36% +121.5% 6378 ± 2% interrupts.CPU21.PMI:Performance_monitoring_interrupts 3039 ± 42% +110.9% 6408 ± 3% interrupts.CPU22.NMI:Non-maskable_interrupts 3039 ± 42% +110.9% 6408 ± 3% interrupts.CPU22.PMI:Performance_monitoring_interrupts 3145 ± 23% +99.3% 6269 interrupts.CPU23.NMI:Non-maskable_interrupts 3145 ± 23% +99.3% 6269 interrupts.CPU23.PMI:Performance_monitoring_interrupts 3156 ± 23% +99.5% 6298 interrupts.CPU24.NMI:Non-maskable_interrupts 3156 ± 23% +99.5% 6298 interrupts.CPU24.PMI:Performance_monitoring_interrupts 3274 ± 25% +92.0% 6287 interrupts.CPU25.NMI:Non-maskable_interrupts 3274 ± 25% +92.0% 6287 interrupts.CPU25.PMI:Performance_monitoring_interrupts 3135 ± 23% +107.3% 6500 ± 6% interrupts.CPU26.NMI:Non-maskable_interrupts 3135 ± 23% +107.3% 6500 ± 6% interrupts.CPU26.PMI:Performance_monitoring_interrupts 3140 ± 23% +107.3% 6508 ± 6% interrupts.CPU27.NMI:Non-maskable_interrupts 3140 ± 23% +107.3% 6508 ± 6% interrupts.CPU27.PMI:Performance_monitoring_interrupts 164.25 ± 7% +27.2% 209.00 ± 8% interrupts.CPU29.RES:Rescheduling_interrupts 3620 ± 2% +78.4% 6458 ± 2% interrupts.CPU3.NMI:Non-maskable_interrupts 3620 ± 2% +78.4% 6458 ± 2% interrupts.CPU3.PMI:Performance_monitoring_interrupts 3201 ± 23% +95.5% 6257 interrupts.CPU37.NMI:Non-maskable_interrupts 3201 ± 23% +95.5% 6257 interrupts.CPU37.PMI:Performance_monitoring_interrupts 3142 ± 23% +101.3% 6325 interrupts.CPU38.NMI:Non-maskable_interrupts 3142 ± 23% +101.3% 6325 interrupts.CPU38.PMI:Performance_monitoring_interrupts 3139 ± 23% +102.8% 6366 ± 2% interrupts.CPU39.NMI:Non-maskable_interrupts 3139 ± 23% +102.8% 6366 ± 2% interrupts.CPU39.PMI:Performance_monitoring_interrupts 3180 ± 25% +97.3% 6274 interrupts.CPU40.NMI:Non-maskable_interrupts 3180 ± 25% +97.3% 6274 interrupts.CPU40.PMI:Performance_monitoring_interrupts 3175 ± 26% +97.6% 6273 interrupts.CPU41.NMI:Non-maskable_interrupts 3175 ± 26% +97.6% 6273 interrupts.CPU41.PMI:Performance_monitoring_interrupts 3796 ± 40% +65.0% 6265 interrupts.CPU42.NMI:Non-maskable_interrupts 3796 ± 40% +65.0% 6265 interrupts.CPU42.PMI:Performance_monitoring_interrupts 3285 ± 27% +92.8% 6333 interrupts.CPU43.NMI:Non-maskable_interrupts 3285 ± 27% +92.8% 6333 interrupts.CPU43.PMI:Performance_monitoring_interrupts 3310 ± 27% +98.4% 6568 ± 7% interrupts.CPU44.NMI:Non-maskable_interrupts 3310 ± 27% +98.4% 6568 ± 7% interrupts.CPU44.PMI:Performance_monitoring_interrupts 3178 ± 26% +97.5% 6276 interrupts.CPU45.NMI:Non-maskable_interrupts 3178 ± 26% +97.5% 6276 interrupts.CPU45.PMI:Performance_monitoring_interrupts 3415 ± 29% +83.9% 6279 interrupts.CPU46.NMI:Non-maskable_interrupts 3415 ± 29% +83.9% 6279 interrupts.CPU46.PMI:Performance_monitoring_interrupts 3178 ± 26% +105.0% 6514 ± 5% interrupts.CPU47.NMI:Non-maskable_interrupts 3178 ± 26% +105.0% 6514 ± 5% interrupts.CPU47.PMI:Performance_monitoring_interrupts 3171 ± 26% +97.9% 6276 interrupts.CPU48.NMI:Non-maskable_interrupts 3171 ± 26% +97.9% 6276 interrupts.CPU48.PMI:Performance_monitoring_interrupts 3163 ± 25% +97.7% 6253 interrupts.CPU49.NMI:Non-maskable_interrupts 3163 ± 25% +97.7% 6253 interrupts.CPU49.PMI:Performance_monitoring_interrupts 3617 ± 2% +76.2% 6371 ± 2% interrupts.CPU50.NMI:Non-maskable_interrupts 3617 ± 2% +76.2% 6371 ± 2% interrupts.CPU50.PMI:Performance_monitoring_interrupts 155.00 ± 9% +32.1% 204.75 ± 7% interrupts.CPU50.RES:Rescheduling_interrupts 3618 ± 2% +73.2% 6267 interrupts.CPU59.NMI:Non-maskable_interrupts 3618 ± 2% +73.2% 6267 interrupts.CPU59.PMI:Performance_monitoring_interrupts 157.25 ± 10% +25.4% 197.25 ± 12% interrupts.CPU59.RES:Rescheduling_interrupts 3620 ± 2% +73.2% 6271 interrupts.CPU63.NMI:Non-maskable_interrupts 3620 ± 2% +73.2% 6271 interrupts.CPU63.PMI:Performance_monitoring_interrupts 152.25 ± 5% +15.9% 176.50 ± 4% interrupts.CPU64.RES:Rescheduling_interrupts 3159 ± 24% +98.6% 6275 interrupts.CPU67.NMI:Non-maskable_interrupts 3159 ± 24% +98.6% 6275 interrupts.CPU67.PMI:Performance_monitoring_interrupts 3610 ± 2% +73.5% 6264 interrupts.CPU7.NMI:Non-maskable_interrupts 3610 ± 2% +73.5% 6264 interrupts.CPU7.PMI:Performance_monitoring_interrupts 162.50 ± 4% +188.3% 468.50 ± 91% interrupts.CPU70.RES:Rescheduling_interrupts 3805 ± 8% +64.6% 6265 interrupts.CPU75.NMI:Non-maskable_interrupts 3805 ± 8% +64.6% 6265 interrupts.CPU75.PMI:Performance_monitoring_interrupts 171.00 ± 11% +51.3% 258.75 ± 35% interrupts.CPU77.RES:Rescheduling_interrupts 3612 ± 2% +73.8% 6277 interrupts.CPU8.NMI:Non-maskable_interrupts 3612 ± 2% +73.8% 6277 interrupts.CPU8.PMI:Performance_monitoring_interrupts 3171 ± 24% +97.7% 6269 interrupts.CPU85.NMI:Non-maskable_interrupts 3171 ± 24% +97.7% 6269 interrupts.CPU85.PMI:Performance_monitoring_interrupts 3469 ± 30% +80.4% 6257 interrupts.CPU86.NMI:Non-maskable_interrupts 3469 ± 30% +80.4% 6257 interrupts.CPU86.PMI:Performance_monitoring_interrupts 3332 ± 27% +88.9% 6294 interrupts.CPU87.NMI:Non-maskable_interrupts 3332 ± 27% +88.9% 6294 interrupts.CPU87.PMI:Performance_monitoring_interrupts 4234 ± 24% +47.6% 6251 interrupts.CPU9.NMI:Non-maskable_interrupts 4234 ± 24% +47.6% 6251 interrupts.CPU9.PMI:Performance_monitoring_interrupts 298153 +69.5% 505374 ± 4% interrupts.NMI:Non-maskable_interrupts 298153 +69.5% 505374 ± 4% interrupts.PMI:Performance_monitoring_interrupts 77.22 -28.8 48.43 perf-profile.calltrace.cycles-pp.swapcontext 37.82 -13.6 24.17 perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.swapcontext 37.15 -13.4 23.74 perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.swapcontext 16.94 ± 4% -11.1 5.83 ± 9% perf-profile.calltrace.cycles-pp.cpu_startup_entry.start_secondary.secondary_startup_64 16.94 ± 4% -11.1 5.83 ± 9% perf-profile.calltrace.cycles-pp.start_secondary.secondary_startup_64 17.12 ± 4% -11.1 6.01 ± 10% perf-profile.calltrace.cycles-pp.secondary_startup_64 16.93 ± 4% -11.1 5.83 ± 9% perf-profile.calltrace.cycles-pp.do_idle.cpu_startup_entry.start_secondary.secondary_startup_64 15.69 ± 3% -10.2 5.52 ± 9% perf-profile.calltrace.cycles-pp.cpuidle_enter.do_idle.cpu_startup_entry.start_secondary.secondary_startup_64 15.51 ± 3% -10.0 5.47 ± 9% perf-profile.calltrace.cycles-pp.cpuidle_enter_state.cpuidle_enter.do_idle.cpu_startup_entry.start_secondary 12.70 ± 3% -7.8 4.89 ± 11% perf-profile.calltrace.cycles-pp.intel_idle.cpuidle_enter_state.cpuidle_enter.do_idle.cpu_startup_entry 16.40 -6.7 9.68 perf-profile.calltrace.cycles-pp.entry_SYSCALL_64.swapcontext 6.46 -2.3 4.17 perf-profile.calltrace.cycles-pp.syscall_return_via_sysret.swapcontext 6.69 ± 3% -2.2 4.48 ± 4% perf-profile.calltrace.cycles-pp.__x64_sys_rt_sigprocmask.do_syscall_64.entry_SYSCALL_64_after_hwframe.swapcontext 2.65 ± 5% -2.0 0.63 ± 10% perf-profile.calltrace.cycles-pp.apic_timer_interrupt.cpuidle_enter_state.cpuidle_enter.do_idle.cpu_startup_entry 2.45 ± 5% -2.0 0.46 ± 57% perf-profile.calltrace.cycles-pp.smp_apic_timer_interrupt.apic_timer_interrupt.cpuidle_enter_state.cpuidle_enter.do_idle 2.70 ± 5% -0.9 1.82 ± 4% perf-profile.calltrace.cycles-pp._copy_from_user.__x64_sys_rt_sigprocmask.do_syscall_64.entry_SYSCALL_64_after_hwframe.swapcontext 1.10 ± 5% -0.6 0.47 ± 58% perf-profile.calltrace.cycles-pp.worker_thread.kthread.ret_from_fork 1.09 ± 6% -0.6 0.46 ± 57% perf-profile.calltrace.cycles-pp.process_one_work.worker_thread.kthread.ret_from_fork 1.06 ± 6% -0.6 0.45 ± 57% perf-profile.calltrace.cycles-pp.drm_fb_helper_dirty_work.process_one_work.worker_thread.kthread.ret_from_fork 1.61 -0.6 1.04 perf-profile.calltrace.cycles-pp._copy_to_user.__x64_sys_rt_sigprocmask.do_syscall_64.entry_SYSCALL_64_after_hwframe.swapcontext 1.00 ± 6% -0.6 0.43 ± 58% perf-profile.calltrace.cycles-pp.memcpy_erms.drm_fb_helper_dirty_work.process_one_work.worker_thread.kthread 1.15 ± 5% -0.5 0.62 ± 11% perf-profile.calltrace.cycles-pp.ret_from_fork 1.14 ± 5% -0.5 0.61 ± 11% perf-profile.calltrace.cycles-pp.kthread.ret_from_fork 1.11 ± 7% -0.4 0.75 ± 4% perf-profile.calltrace.cycles-pp.__might_fault._copy_from_user.__x64_sys_rt_sigprocmask.do_syscall_64.entry_SYSCALL_64_after_hwframe 0.00 +6.5 6.53 perf-profile.calltrace.cycles-pp.fetestexcept 0.00 +31.1 31.14 perf-profile.calltrace.cycles-pp.feclearexcept 77.29 -28.4 48.89 perf-profile.children.cycles-pp.swapcontext 39.34 -13.7 25.60 perf-profile.children.cycles-pp.entry_SYSCALL_64_after_hwframe 38.74 -13.5 25.23 perf-profile.children.cycles-pp.do_syscall_64 17.12 ± 4% -11.1 6.01 ± 10% perf-profile.children.cycles-pp.do_idle 16.94 ± 4% -11.1 5.83 ± 9% perf-profile.children.cycles-pp.start_secondary 17.12 ± 4% -11.1 6.01 ± 10% perf-profile.children.cycles-pp.secondary_startup_64 17.12 ± 4% -11.1 6.01 ± 10% perf-profile.children.cycles-pp.cpu_startup_entry 15.85 ± 3% -10.2 5.69 ± 10% perf-profile.children.cycles-pp.cpuidle_enter 15.84 ± 3% -10.1 5.69 ± 10% perf-profile.children.cycles-pp.cpuidle_enter_state 12.83 ± 3% -7.9 4.92 ± 10% perf-profile.children.cycles-pp.intel_idle 15.73 -6.0 9.70 perf-profile.children.cycles-pp.entry_SYSCALL_64 7.14 -2.5 4.62 perf-profile.children.cycles-pp.syscall_return_via_sysret 6.74 ± 3% -2.2 4.51 ± 4% perf-profile.children.cycles-pp.__x64_sys_rt_sigprocmask 4.50 ± 4% -2.0 2.48 ± 5% perf-profile.children.cycles-pp.apic_timer_interrupt 4.12 ± 3% -1.9 2.23 ± 4% perf-profile.children.cycles-pp.smp_apic_timer_interrupt 2.96 ± 3% -1.2 1.75 ± 4% perf-profile.children.cycles-pp.hrtimer_interrupt 2.75 ± 5% -0.9 1.85 ± 4% perf-profile.children.cycles-pp._copy_from_user 2.04 ± 5% -0.8 1.21 ± 3% perf-profile.children.cycles-pp.__hrtimer_run_queues 0.92 ± 17% -0.7 0.22 ± 15% perf-profile.children.cycles-pp.menu_select 1.66 -0.6 1.08 perf-profile.children.cycles-pp._copy_to_user 1.74 ± 3% -0.6 1.16 ± 4% perf-profile.children.cycles-pp.__might_fault 1.15 ± 4% -0.5 0.63 ± 10% perf-profile.children.cycles-pp.ret_from_fork 1.14 ± 5% -0.5 0.61 ± 11% perf-profile.children.cycles-pp.kthread 1.10 ± 5% -0.5 0.59 ± 11% perf-profile.children.cycles-pp.worker_thread 1.09 ± 6% -0.5 0.58 ± 11% perf-profile.children.cycles-pp.process_one_work 1.06 ± 6% -0.5 0.57 ± 12% perf-profile.children.cycles-pp.drm_fb_helper_dirty_work 1.07 ± 6% -0.5 0.57 ± 12% perf-profile.children.cycles-pp.memcpy_erms 1.27 ± 8% -0.4 0.84 perf-profile.children.cycles-pp.tick_sched_timer 1.33 ± 3% -0.4 0.91 perf-profile.children.cycles-pp.copy_user_generic_unrolled 0.72 ± 13% -0.4 0.32 ± 7% perf-profile.children.cycles-pp.vprintk_emit 0.70 ± 4% -0.4 0.31 ± 12% perf-profile.children.cycles-pp.irq_exit 0.72 ± 14% -0.4 0.33 ± 26% perf-profile.children.cycles-pp.console_unlock 0.48 ± 14% -0.4 0.11 ± 12% perf-profile.children.cycles-pp.tick_nohz_get_sleep_length 1.11 ± 6% -0.4 0.74 ± 2% perf-profile.children.cycles-pp.tick_sched_handle 0.64 ± 15% -0.4 0.28 ± 26% perf-profile.children.cycles-pp.serial8250_console_write 0.61 ± 15% -0.3 0.28 ± 26% perf-profile.children.cycles-pp.uart_console_write 1.06 ± 6% -0.3 0.73 ± 2% perf-profile.children.cycles-pp.update_process_times 0.54 ± 22% -0.3 0.22 ± 11% perf-profile.children.cycles-pp.io_serial_in 0.52 ± 14% -0.3 0.20 ± 10% perf-profile.children.cycles-pp._fini 0.52 ± 14% -0.3 0.20 ± 10% perf-profile.children.cycles-pp.devkmsg_write 0.52 ± 14% -0.3 0.20 ± 10% perf-profile.children.cycles-pp.devkmsg_emit 0.54 ± 13% -0.3 0.22 ± 11% perf-profile.children.cycles-pp.write 0.55 ± 21% -0.3 0.24 ± 28% perf-profile.children.cycles-pp.wait_for_xmitr 0.53 ± 20% -0.3 0.22 ± 15% perf-profile.children.cycles-pp.ktime_get 0.53 ± 14% -0.3 0.23 ± 9% perf-profile.children.cycles-pp.ksys_write 0.53 ± 14% -0.3 0.23 ± 9% perf-profile.children.cycles-pp.vfs_write 0.53 ± 14% -0.3 0.23 ± 9% perf-profile.children.cycles-pp.new_sync_write 0.54 ± 20% -0.3 0.24 ± 28% perf-profile.children.cycles-pp.serial8250_console_putchar 0.38 ± 11% -0.3 0.09 ± 12% perf-profile.children.cycles-pp.tick_nohz_next_event 0.55 ± 8% -0.3 0.26 ± 12% perf-profile.children.cycles-pp.__softirqentry_text_start 0.85 ± 2% -0.3 0.56 ± 6% perf-profile.children.cycles-pp.___might_sleep 0.75 ± 5% -0.3 0.48 ± 4% perf-profile.children.cycles-pp.copy_user_enhanced_fast_string 0.68 ± 2% -0.2 0.46 ± 3% perf-profile.children.cycles-pp.scheduler_tick 0.47 ± 8% -0.2 0.26 ± 17% perf-profile.children.cycles-pp.clockevents_program_event 0.27 ± 17% -0.2 0.06 ± 13% perf-profile.children.cycles-pp.get_next_timer_interrupt 0.28 ± 6% -0.2 0.08 ± 5% perf-profile.children.cycles-pp.irq_enter 0.22 ± 6% -0.2 0.03 ±100% perf-profile.children.cycles-pp.tick_irq_enter 0.19 ± 21% -0.2 0.03 ±100% perf-profile.children.cycles-pp.__next_timer_interrupt 0.35 ± 6% -0.2 0.18 ± 14% perf-profile.children.cycles-pp.perf_mux_hrtimer_handler 0.39 ± 11% -0.1 0.25 ± 15% perf-profile.children.cycles-pp.__x86_indirect_thunk_rax 0.32 ± 5% -0.1 0.19 ± 9% perf-profile.children.cycles-pp.sigprocmask 0.42 ± 4% -0.1 0.30 ± 6% perf-profile.children.cycles-pp.__might_sleep 0.18 ± 9% -0.1 0.09 ± 7% perf-profile.children.cycles-pp.read_tsc 0.11 ± 7% -0.1 0.03 ±100% perf-profile.children.cycles-pp.timerqueue_del 0.14 ± 5% -0.1 0.06 ± 13% perf-profile.children.cycles-pp.__remove_hrtimer 0.23 ± 17% -0.1 0.15 ± 10% perf-profile.children.cycles-pp.native_write_msr 0.14 ± 11% -0.1 0.07 ± 7% perf-profile.children.cycles-pp.run_timer_softirq 0.17 ± 6% -0.1 0.10 ± 17% perf-profile.children.cycles-pp._raw_spin_lock 0.17 ± 12% -0.1 0.11 ± 11% perf-profile.children.cycles-pp.ktime_get_update_offsets_now 0.13 ± 9% -0.1 0.08 ± 10% perf-profile.children.cycles-pp.__set_current_blocked 0.08 ± 26% -0.1 0.03 ±102% perf-profile.children.cycles-pp.fbcon_putcs 0.13 ± 6% -0.0 0.08 ± 10% perf-profile.children.cycles-pp.swapcontext@plt 0.10 ± 7% -0.0 0.06 ± 7% perf-profile.children.cycles-pp.arch_scale_freq_tick 0.09 ± 26% -0.0 0.04 ± 60% perf-profile.children.cycles-pp.vt_console_print 0.09 ± 26% -0.0 0.04 ± 60% perf-profile.children.cycles-pp.lf 0.09 ± 26% -0.0 0.04 ± 60% perf-profile.children.cycles-pp.con_scroll 0.09 ± 26% -0.0 0.04 ± 60% perf-profile.children.cycles-pp.fbcon_scroll 0.09 ± 26% -0.0 0.04 ± 60% perf-profile.children.cycles-pp.fbcon_redraw 0.08 ± 10% -0.0 0.04 ± 60% perf-profile.children.cycles-pp.ksys_read 0.11 ± 26% -0.0 0.08 ± 14% perf-profile.children.cycles-pp.crypto_alloc_tfm 0.11 ± 26% -0.0 0.08 ± 14% perf-profile.children.cycles-pp.crypto_alg_mod_lookup 0.11 ± 26% -0.0 0.08 ± 14% perf-profile.children.cycles-pp.__request_module 0.11 ± 26% -0.0 0.08 ± 10% perf-profile.children.cycles-pp.bind 0.11 ± 26% -0.0 0.08 ± 10% perf-profile.children.cycles-pp.__x64_sys_bind 0.11 ± 26% -0.0 0.08 ± 10% perf-profile.children.cycles-pp.__sys_bind 0.11 ± 26% -0.0 0.08 ± 10% perf-profile.children.cycles-pp.alg_bind 0.10 ± 10% -0.0 0.07 ± 17% perf-profile.children.cycles-pp._raw_spin_lock_irq 0.08 -0.0 0.05 ± 9% perf-profile.children.cycles-pp.__intel_pmu_enable_all 0.32 ± 3% -0.0 0.29 ± 3% perf-profile.children.cycles-pp.task_tick_fair 0.01 ±173% +0.0 0.06 ± 7% perf-profile.children.cycles-pp.cexp 0.00 +0.1 0.08 ± 5% perf-profile.children.cycles-pp.@plt 0.00 +0.1 0.11 ± 10% perf-profile.children.cycles-pp.memcpy@plt 0.00 +0.1 0.12 ± 5% perf-profile.children.cycles-pp.prepare_to_wait_event 0.00 +0.1 0.15 ± 7% perf-profile.children.cycles-pp.sqrt 0.00 +0.2 0.16 ± 7% perf-profile.children.cycles-pp.feclearexcept@plt 0.00 +0.2 0.17 ± 11% perf-profile.children.cycles-pp.fetestexcept@plt 0.00 +0.2 0.18 ± 4% perf-profile.children.cycles-pp.__errno_location@plt 0.03 ±100% +0.2 0.23 ± 36% perf-profile.children.cycles-pp.syscall 0.00 +0.2 0.20 ± 10% perf-profile.children.cycles-pp.finished_loading 0.00 +0.2 0.21 ± 2% perf-profile.children.cycles-pp.fegetround 0.00 +0.3 0.32 ± 15% perf-profile.children.cycles-pp.osq_lock 0.00 +0.3 0.33 ± 17% perf-profile.children.cycles-pp.__mutex_lock 0.00 +0.4 0.38 ± 4% perf-profile.children.cycles-pp.log2 0.00 +0.4 0.40 ± 6% perf-profile.children.cycles-pp.__errno_location 0.00 +0.4 0.40 ± 4% perf-profile.children.cycles-pp.log 0.03 ±100% +0.4 0.47 ± 20% perf-profile.children.cycles-pp.__do_sys_finit_module 0.03 ±100% +0.4 0.47 ± 20% perf-profile.children.cycles-pp.load_module 0.00 +0.5 0.51 perf-profile.children.cycles-pp.exp 0.00 +6.5 6.53 perf-profile.children.cycles-pp.fetestexcept 0.00 +31.2 31.16 perf-profile.children.cycles-pp.feclearexcept 30.34 -11.1 19.20 perf-profile.self.cycles-pp.do_syscall_64 12.80 ± 3% -7.9 4.92 ± 10% perf-profile.self.cycles-pp.intel_idle 16.64 ± 2% -6.2 10.41 ± 2% perf-profile.self.cycles-pp.swapcontext 15.04 -5.8 9.27 perf-profile.self.cycles-pp.entry_SYSCALL_64 7.13 -2.5 4.62 perf-profile.self.cycles-pp.syscall_return_via_sysret 1.96 ± 6% -0.6 1.36 ± 6% perf-profile.self.cycles-pp.__x64_sys_rt_sigprocmask 1.07 ± 6% -0.5 0.57 ± 12% perf-profile.self.cycles-pp.memcpy_erms 1.11 ± 3% -0.4 0.75 perf-profile.self.cycles-pp.copy_user_generic_unrolled 0.50 ± 15% -0.3 0.21 ± 9% perf-profile.self.cycles-pp.io_serial_in 0.82 ± 2% -0.3 0.55 ± 5% perf-profile.self.cycles-pp.___might_sleep 0.71 ± 3% -0.3 0.44 ± 6% perf-profile.self.cycles-pp.entry_SYSCALL_64_after_hwframe 0.73 ± 5% -0.3 0.47 ± 4% perf-profile.self.cycles-pp.copy_user_enhanced_fast_string 0.34 ± 28% -0.3 0.09 ± 14% perf-profile.self.cycles-pp.menu_select 0.38 ± 31% -0.2 0.16 ± 20% perf-profile.self.cycles-pp.ktime_get 0.57 ± 7% -0.2 0.37 ± 5% perf-profile.self.cycles-pp._copy_from_user 0.26 ± 11% -0.2 0.07 perf-profile.self.cycles-pp.cpuidle_enter_state 0.50 ± 7% -0.2 0.33 perf-profile.self.cycles-pp.__might_fault 0.36 ± 5% -0.1 0.26 ± 7% perf-profile.self.cycles-pp.__might_sleep 0.28 ± 2% -0.1 0.19 ± 6% perf-profile.self.cycles-pp._copy_to_user 0.17 ± 9% -0.1 0.08 ± 10% perf-profile.self.cycles-pp.read_tsc 0.23 ± 7% -0.1 0.14 ± 16% perf-profile.self.cycles-pp.__x86_indirect_thunk_rax 0.23 ± 17% -0.1 0.15 ± 10% perf-profile.self.cycles-pp.native_write_msr 0.20 ± 5% -0.1 0.12 ± 10% perf-profile.self.cycles-pp.sigprocmask 0.15 ± 4% -0.1 0.10 ± 14% perf-profile.self.cycles-pp._raw_spin_lock 0.11 ± 17% -0.1 0.06 ± 26% perf-profile.self.cycles-pp._raw_spin_lock_irqsave 0.11 ± 7% -0.0 0.07 ± 7% perf-profile.self.cycles-pp.__set_current_blocked 0.13 ± 6% -0.0 0.08 ± 10% perf-profile.self.cycles-pp.swapcontext@plt 0.10 ± 11% -0.0 0.07 ± 6% perf-profile.self.cycles-pp.hrtimer_interrupt 0.00 +0.1 0.06 ± 9% perf-profile.self.cycles-pp.cexp 0.00 +0.1 0.11 ± 10% perf-profile.self.cycles-pp.memcpy@plt 0.00 +0.1 0.12 ± 11% perf-profile.self.cycles-pp.sqrt 0.00 +0.2 0.16 ± 7% perf-profile.self.cycles-pp.feclearexcept@plt 0.00 +0.2 0.17 ± 8% perf-profile.self.cycles-pp.fetestexcept@plt 0.00 +0.2 0.18 ± 4% perf-profile.self.cycles-pp.__errno_location@plt 0.00 +0.2 0.18 ± 2% perf-profile.self.cycles-pp.fegetround 0.00 +0.2 0.22 ± 9% perf-profile.self.cycles-pp.__errno_location 0.00 +0.3 0.31 ± 14% perf-profile.self.cycles-pp.osq_lock 0.00 +0.3 0.34 ± 5% perf-profile.self.cycles-pp.log2 0.00 +0.4 0.36 ± 4% perf-profile.self.cycles-pp.log 0.00 +0.5 0.47 perf-profile.self.cycles-pp.exp 0.00 +6.3 6.32 ± 2% perf-profile.self.cycles-pp.fetestexcept 0.00 +30.8 30.80 perf-profile.self.cycles-pp.feclearexcept stress-ng.time.percent_of_cpu_this_job_got 8000 +--------------------------------------------------------------------+ 7800 |-+O O O O O O O O O O O O O O O | | O O O O | 7600 |-+ | 7400 |.. .+. .+.. .+. | | +.+..+. + +.+. +.+..+..+.+..+.+..+. +..+ | 7200 |-+ : : | 7000 |-+ : : | 6800 |-+ : : | | : : | 6600 |-+ : : | 6400 |-+ : : | | : : | 6200 |-+ : | 6000 +--------------------------------------------------------------------+ stress-ng.af-alg.ops 60000 +-------------------------------------------------------------------+ | O O O O O O O O O O O O O O O O O O O O O O O O O | 50000 |-+ | | | | | 40000 |-+ | | | 30000 |-+ | | | 20000 |-+ | | + | | :+ | 10000 |-+ : + .+.. .+ | |.. .+. : + +. + .+.. | 0 +-------------------------------------------------------------------+ stress-ng.af-alg.ops_per_sec 40000 +-------------------------------------------------------------------+ | | 35000 |-+O O O O O O O O O O O O O O O O O O | 30000 |-+ O O O O O O O | | | 25000 |-+ | | | 20000 |-+ | | | 15000 |-+ | 10000 |-+ | | | 5000 |-+ | | .+.. | 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, Rong Chen