Greeting, FYI, we noticed a 48.8% improvement of fsmark.files_per_sec due to commit: commit: e4f9eb2268da0eb6b706fe582ef34cbfc359c799 ("[RFC v3] writeback: add elastic bdi in cgwb bdp") url: https://github.com/0day-ci/linux/commits/Hillf-Danton/writeback-add-elastic-bdi-in-cgwb-bdp/20191113-060336 in testcase: fsmark on test machine: 96 threads Intel(R) Xeon(R) Gold 6252 CPU @ 2.10GHz with 256G memory with following parameters: iterations: 1x nr_threads: 32t disk: 1HDD fs: f2fs filesize: 16MB test_size: 60G sync_method: NoSync nr_directories: 16d nr_files_per_directory: 256fpd cpufreq_governor: performance ucode: 0x500002b test-description: The fsmark is a file system benchmark to test synchronous write workloads, for example, mail servers workload. test-url: https://sourceforge.net/projects/fsmark/ In addition to that, the commit also has significant impact on the following tests: +------------------+----------------------------------------------------------------------+ | testcase: change | fsmark: fsmark.files_per_sec 84.3% improvement | | test machine | 96 threads Intel(R) Xeon(R) Gold 6252 CPU @ 2.10GHz with 256G memory | | test parameters | cpufreq_governor=performance | | | disk=1SSD | | | filesize=16MB | | | fs=btrfs | | | iterations=1x | | | nr_directories=16d | | | nr_files_per_directory=256fpd | | | nr_threads=32t | | | sync_method=NoSync | | | test_size=60G | | | ucode=0x500002b | +------------------+----------------------------------------------------------------------+ | testcase: change | fsmark: fsmark.files_per_sec 39.4% improvement | | test machine | 96 threads Intel(R) Xeon(R) Gold 6252 CPU @ 2.10GHz with 256G memory | | test parameters | cpufreq_governor=performance | | | disk=1SSD | | | filesize=16MB | | | fs=f2fs | | | iterations=1x | | | nr_directories=16d | | | nr_files_per_directory=256fpd | | | nr_threads=32t | | | sync_method=NoSync | | | test_size=60G | | | ucode=0x500002b | +------------------+----------------------------------------------------------------------+ 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 ========================================================================================= compiler/cpufreq_governor/disk/filesize/fs/iterations/kconfig/nr_directories/nr_files_per_directory/nr_threads/rootfs/sync_method/tbox_group/test_size/testcase/ucode: gcc-7/performance/1HDD/16MB/f2fs/1x/x86_64-rhel-7.6/16d/256fpd/32t/debian-x86_64-2019-09-23.cgz/NoSync/lkp-csl-2sp7/60G/fsmark/0x500002b commit: eb094f0696 ("Merge branch 'x86-pti-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip") e4f9eb2268 ("writeback: add elastic bdi in cgwb bdp") eb094f06963bb0fd e4f9eb2268da0eb6b706fe582ef ---------------- --------------------------- fail:runs %reproduction fail:runs | | | :4 25% 1:4 dmesg.WARNING:stack_recursion %stddev %change %stddev \ | \ 206181 ± 3% -24.0% 156619 fsmark.app_overhead 36.85 +48.8% 54.85 ± 2% fsmark.files_per_sec 347.27 +5.2% 365.18 ± 4% fsmark.time.elapsed_time 347.27 +5.2% 365.18 ± 4% fsmark.time.elapsed_time.max 82.25 ± 5% +28.9% 106.00 ± 7% fsmark.time.percent_of_cpu_this_job_got 286.02 ± 5% +35.5% 387.44 ± 4% fsmark.time.system_time 136907 -38.4% 84268 fsmark.time.voluntary_context_switches 5.109e+08 ±102% -74.3% 1.314e+08 ±168% cpuidle.C1.time 6376448 +7.8% 6874624 ± 6% meminfo.DirectMap2M 9.35 ± 3% -8.4 0.95 mpstat.cpu.all.iowait% 0.92 ± 4% +0.3 1.23 ± 7% mpstat.cpu.all.sys% 1.52 ±102% -1.2 0.37 ±168% turbostat.C1% 42.25 ± 3% -6.5% 39.50 ± 2% turbostat.PkgTmp 27542 ± 24% +34.9% 37156 ± 7% numa-vmstat.node1.nr_active_anon 27275 ± 25% +34.4% 36654 ± 8% numa-vmstat.node1.nr_anon_pages 27542 ± 24% +34.9% 37156 ± 7% numa-vmstat.node1.nr_zone_active_anon 89.25 +8.7% 97.00 vmstat.cpu.id 9.00 -100.0% 0.00 vmstat.procs.b 2180 ± 2% -15.6% 1841 vmstat.system.cs 89.63 +9.0% 97.68 iostat.cpu.idle 9.29 ± 3% -89.9% 0.94 iostat.cpu.iowait 0.97 ± 5% +31.0% 1.27 ± 7% iostat.cpu.system 222.75 ± 57% +436.4% 1194 ± 57% iostat.sda.r_await.max 331.50 ±173% -83.3% 55.25 ±173% iostat.sdb.r_await.max 229996 ± 8% -18.9% 186634 ± 12% numa-meminfo.node0.Active 130566 ± 17% -21.1% 103049 ± 17% numa-meminfo.node0.AnonHugePages 176121 ± 10% +25.1% 220255 ± 10% numa-meminfo.node1.Active 110144 ± 24% +34.9% 148629 ± 7% numa-meminfo.node1.Active(anon) 109070 ± 25% +34.4% 146622 ± 8% numa-meminfo.node1.AnonPages 2752 ± 8% +32.5% 3646 ± 4% sched_debug.cfs_rq:/.exec_clock.avg 3340 ± 6% +18.3% 3953 ± 4% sched_debug.cfs_rq:/.exec_clock.stddev 84751 ± 14% +32.3% 112168 ± 6% sched_debug.cfs_rq:/.min_vruntime.avg 254376 ± 4% +26.3% 321225 ± 4% sched_debug.cfs_rq:/.min_vruntime.max 85628 ± 7% +29.8% 111155 ± 7% sched_debug.cfs_rq:/.min_vruntime.stddev 0.08 ± 4% -9.0% 0.07 ± 9% sched_debug.cfs_rq:/.nr_running.avg 85629 ± 7% +29.8% 111155 ± 7% sched_debug.cfs_rq:/.spread0.stddev 6282 +6.8% 6708 ± 4% sched_debug.cpu.curr->pid.max 0.07 ± 2% -73.9% 0.02 ± 9% sched_debug.cpu.nr_uninterruptible.avg 2274 -12.6% 1987 ± 5% sched_debug.cpu.sched_goidle.avg 1129 -46.0% 610.16 ± 9% sched_debug.cpu.ttwu_local.avg 2157 ± 3% -16.0% 1811 perf-stat.i.context-switches 53.45 -2.9 50.56 ± 2% perf-stat.i.iTLB-load-miss-rate% 83.08 +4.7 87.75 ± 2% perf-stat.i.node-load-miss-rate% 231939 ± 10% +28.7% 298559 ± 7% perf-stat.i.node-load-misses 54.36 ± 17% +29.7 84.08 ± 7% perf-stat.i.node-store-miss-rate% 206288 ± 8% +43.9% 296880 ± 9% perf-stat.i.node-store-misses 145852 ± 10% -17.7% 120031 ± 12% perf-stat.i.node-stores 54.51 -2.8 51.70 ± 2% perf-stat.overall.iTLB-load-miss-rate% 83.92 +3.5 87.37 perf-stat.overall.node-load-miss-rate% 58.58 ± 4% +12.6 71.22 ± 2% perf-stat.overall.node-store-miss-rate% 2150 ± 3% -16.0% 1805 perf-stat.ps.context-switches 231136 ± 10% +28.7% 297572 ± 7% perf-stat.ps.node-load-misses 205545 ± 8% +43.9% 295793 ± 9% perf-stat.ps.node-store-misses 145378 ± 10% -17.6% 119740 ± 12% perf-stat.ps.node-stores 26510 +2.1% 27062 proc-vmstat.nr_active_file 7110246 +4.5% 7433121 ± 2% proc-vmstat.nr_dirty 14943233 +2.5% 15312986 proc-vmstat.nr_file_pages 14641262 +2.5% 15010784 proc-vmstat.nr_inactive_file 1231 -2.5% 1200 proc-vmstat.nr_page_table_pages 53598 +1.7% 54512 proc-vmstat.nr_slab_reclaimable 26510 +2.1% 27062 proc-vmstat.nr_zone_active_file 14641262 +2.5% 15010784 proc-vmstat.nr_zone_inactive_file 7132293 +4.5% 7455224 ± 2% proc-vmstat.nr_zone_write_pending 3382991 ± 16% +36.8% 4627644 ± 2% proc-vmstat.numa_foreign 13296658 ± 4% -9.2% 12077073 proc-vmstat.numa_hit 13265384 ± 4% -9.2% 12045787 proc-vmstat.numa_local 3382991 ± 16% +36.8% 4627644 ± 2% proc-vmstat.numa_miss 3414265 ± 16% +36.5% 4658931 ± 2% proc-vmstat.numa_other 58871 ± 26% -45.2% 32279 ± 31% proc-vmstat.numa_pte_updates 347.75 ± 30% -49.7% 174.75 ± 73% interrupts.CPU22.NMI:Non-maskable_interrupts 347.75 ± 30% -49.7% 174.75 ± 73% interrupts.CPU22.PMI:Performance_monitoring_interrupts 384.25 ± 25% -53.4% 179.00 ± 76% interrupts.CPU23.NMI:Non-maskable_interrupts 384.25 ± 25% -53.4% 179.00 ± 76% interrupts.CPU23.PMI:Performance_monitoring_interrupts 314.25 ± 27% -46.5% 168.00 ± 67% interrupts.CPU25.NMI:Non-maskable_interrupts 314.25 ± 27% -46.5% 168.00 ± 67% interrupts.CPU25.PMI:Performance_monitoring_interrupts 3620 ± 2% +88.1% 6810 ± 78% interrupts.CPU35.CAL:Function_call_interrupts 3603 ± 2% +33.3% 4801 ± 38% interrupts.CPU44.CAL:Function_call_interrupts 3516 ± 2% +7.1% 3764 ± 4% interrupts.CPU5.CAL:Function_call_interrupts 130.75 ±158% +871.7% 1270 ± 65% interrupts.CPU5.RES:Rescheduling_interrupts 336.25 ± 33% -43.3% 190.50 ± 65% interrupts.CPU52.NMI:Non-maskable_interrupts 336.25 ± 33% -43.3% 190.50 ± 65% interrupts.CPU52.PMI:Performance_monitoring_interrupts 3494 ± 2% +7.5% 3757 ± 4% interrupts.CPU6.CAL:Function_call_interrupts 457.25 ± 16% -54.8% 206.75 ± 64% interrupts.CPU60.NMI:Non-maskable_interrupts 457.25 ± 16% -54.8% 206.75 ± 64% interrupts.CPU60.PMI:Performance_monitoring_interrupts 359.75 ± 31% -44.6% 199.25 ± 59% interrupts.CPU62.NMI:Non-maskable_interrupts 359.75 ± 31% -44.6% 199.25 ± 59% interrupts.CPU62.PMI:Performance_monitoring_interrupts 3595 ± 3% +5.7% 3799 ± 3% interrupts.CPU77.CAL:Function_call_interrupts 3554 +9.8% 3902 ± 6% interrupts.CPU79.CAL:Function_call_interrupts 3571 ± 3% +6.3% 3797 ± 3% interrupts.CPU81.CAL:Function_call_interrupts 3568 ± 2% +6.6% 3802 ± 4% interrupts.CPU86.CAL:Function_call_interrupts 7.75 ± 93% +5029.0% 397.50 ±127% interrupts.CPU9.RES:Rescheduling_interrupts 7.25 ± 29% +2024.1% 154.00 ±152% interrupts.CPU92.RES:Rescheduling_interrupts 141969 ± 8% -15.8% 119489 ± 4% softirqs.CPU10.TIMER 144804 ± 7% -15.2% 122776 ± 5% softirqs.CPU14.TIMER 141762 ± 6% -15.9% 119169 ± 4% softirqs.CPU16.TIMER 141326 ± 4% -12.0% 124357 ± 7% softirqs.CPU17.TIMER 145957 ± 6% -15.2% 123724 ± 5% softirqs.CPU20.TIMER 142813 ± 6% -13.1% 124176 ± 6% softirqs.CPU21.TIMER 142851 ± 7% -13.6% 123373 ± 4% softirqs.CPU22.TIMER 149498 ± 6% -16.0% 125543 ± 8% softirqs.CPU4.TIMER 29806 ± 8% -18.1% 24404 ± 5% softirqs.CPU5.RCU 146049 ± 5% -17.3% 120793 ± 2% softirqs.CPU5.TIMER 149260 ± 7% -18.7% 121342 ± 5% softirqs.CPU51.TIMER 148165 ± 6% -17.4% 122323 ± 8% softirqs.CPU52.TIMER 144746 ± 5% -18.0% 118649 ± 3% softirqs.CPU53.TIMER 141387 ± 7% -16.4% 118229 ± 4% softirqs.CPU54.TIMER 147445 ± 7% -17.3% 121986 ± 8% softirqs.CPU56.TIMER 140489 ± 9% -17.3% 116198 ± 4% softirqs.CPU58.TIMER 142617 ± 7% -15.2% 120996 ± 3% softirqs.CPU6.TIMER 141828 ± 9% -14.9% 120757 ± 5% softirqs.CPU62.TIMER 140300 ± 7% -17.0% 116455 ± 4% softirqs.CPU64.TIMER 145431 ± 9% -15.5% 122932 ± 9% softirqs.CPU65.TIMER 134905 ± 9% -15.7% 113750 ± 4% softirqs.CPU67.TIMER 144366 ± 6% -16.2% 121011 ± 7% softirqs.CPU68.TIMER 142688 ± 6% -15.0% 121309 ± 6% softirqs.CPU69.TIMER 141441 ± 7% -15.8% 119130 ± 5% softirqs.CPU70.TIMER 150355 ± 12% -23.1% 115612 ± 4% softirqs.CPU71.TIMER 148522 ± 6% -16.0% 124752 ± 7% softirqs.CPU8.TIMER 55.67 ± 14% -12.8 42.92 ± 21% perf-profile.calltrace.cycles-pp.intel_idle.cpuidle_enter_state.cpuidle_enter.do_idle.cpu_startup_entry 1.13 ± 14% +0.5 1.59 ± 17% perf-profile.calltrace.cycles-pp.rebalance_domains.__softirqentry_text_start.irq_exit.smp_apic_timer_interrupt.apic_timer_interrupt 0.81 ±100% +1.5 2.27 ± 42% perf-profile.calltrace.cycles-pp.ktime_get.tick_nohz_irq_exit.irq_exit.smp_apic_timer_interrupt.apic_timer_interrupt 0.84 ± 97% +1.5 2.31 ± 42% perf-profile.calltrace.cycles-pp.tick_nohz_irq_exit.irq_exit.smp_apic_timer_interrupt.apic_timer_interrupt.cpuidle_enter_state 2.16 ± 69% +3.0 5.17 ± 40% perf-profile.calltrace.cycles-pp.ktime_get.clockevents_program_event.hrtimer_interrupt.smp_apic_timer_interrupt.apic_timer_interrupt 55.83 ± 14% -12.6 43.21 ± 21% perf-profile.children.cycles-pp.intel_idle 0.59 ± 21% -0.2 0.39 ± 34% perf-profile.children.cycles-pp.enqueue_hrtimer 0.48 ± 22% -0.2 0.28 ± 37% perf-profile.children.cycles-pp.timerqueue_del 0.52 ± 24% -0.2 0.34 ± 36% perf-profile.children.cycles-pp.timerqueue_add 0.60 ± 11% -0.2 0.45 ± 17% perf-profile.children.cycles-pp.cpuidle_governor_latency_req 0.32 ± 25% -0.1 0.19 ± 42% perf-profile.children.cycles-pp.update_ts_time_stats 0.19 ± 29% -0.1 0.10 ± 33% perf-profile.children.cycles-pp.run_posix_cpu_timers 0.20 ± 24% -0.1 0.11 ± 46% perf-profile.children.cycles-pp.pm_qos_request 0.11 ± 17% -0.1 0.04 ±107% perf-profile.children.cycles-pp.cpuidle_not_available 0.21 ± 23% -0.1 0.14 ± 23% perf-profile.children.cycles-pp.rb_insert_color 0.15 ± 14% -0.1 0.10 ± 15% perf-profile.children.cycles-pp.rb_erase 0.12 ± 26% +0.0 0.17 ± 14% perf-profile.children.cycles-pp.__x86_indirect_thunk_rax 0.01 ±173% +0.1 0.07 ± 23% perf-profile.children.cycles-pp.timer_clear_idle 0.25 ± 2% +0.1 0.37 ± 13% perf-profile.children.cycles-pp.rcu_eqs_enter 0.41 ± 16% +0.2 0.57 ± 14% perf-profile.children.cycles-pp.arch_cpu_idle_enter 0.39 ± 15% +0.2 0.56 ± 14% perf-profile.children.cycles-pp.tsc_verify_tsc_adjust 0.12 ± 11% +0.2 0.30 ± 39% perf-profile.children.cycles-pp.hrtimer_forward 0.29 ± 54% +0.4 0.68 ± 36% perf-profile.children.cycles-pp._raw_spin_trylock 0.98 ± 73% +1.4 2.35 ± 41% perf-profile.children.cycles-pp.tick_nohz_irq_exit 0.78 ± 99% +1.4 2.21 ± 46% perf-profile.children.cycles-pp.timekeeping_max_deferment 5.04 ± 47% +5.0 10.07 ± 34% perf-profile.children.cycles-pp.ktime_get 55.70 ± 13% -12.5 43.17 ± 21% perf-profile.self.cycles-pp.intel_idle 0.19 ± 29% -0.1 0.10 ± 33% perf-profile.self.cycles-pp.run_posix_cpu_timers 0.11 ± 20% -0.1 0.04 ±107% perf-profile.self.cycles-pp.cpuidle_not_available 0.19 ± 22% -0.1 0.12 ± 25% perf-profile.self.cycles-pp.rb_insert_color 0.13 ± 19% -0.0 0.08 ± 17% perf-profile.self.cycles-pp.rb_erase 0.01 ±173% +0.1 0.07 ± 23% perf-profile.self.cycles-pp.timer_clear_idle 0.21 ± 10% +0.1 0.27 ± 18% perf-profile.self.cycles-pp.get_next_timer_interrupt 0.24 +0.1 0.35 ± 13% perf-profile.self.cycles-pp.rcu_eqs_enter 0.12 ± 11% +0.2 0.29 ± 39% perf-profile.self.cycles-pp.hrtimer_forward 0.32 ± 30% +0.2 0.53 ± 19% perf-profile.self.cycles-pp.tsc_verify_tsc_adjust 0.57 ± 34% +0.3 0.82 ± 17% perf-profile.self.cycles-pp.tick_nohz_next_event 0.25 ± 36% +0.4 0.68 ± 36% perf-profile.self.cycles-pp._raw_spin_trylock 0.77 ±102% +1.4 2.21 ± 47% perf-profile.self.cycles-pp.timekeeping_max_deferment 4.14 ± 55% +4.7 8.84 ± 36% perf-profile.self.cycles-pp.ktime_get fsmark.time.system_time 450 +-+-------------------------------------------------------------------+ | O O | 400 O-O O O O OO O O O O O O | 350 +-+ O O O | | .+. .+. | 300 +-+.++. .+ ++.+.+.+.++ +.+.++.+.+.++.+. .+.++.+.+. .++.+.+.+.++.+.| 250 +-+ + + + | | | 200 +-+ | 150 +-+ | | | 100 +-+ | 50 +-+ | | | 0 +-+------O------------------------------------------------------------+ fsmark.time.voluntary_context_switches 160000 +-+----------------------------------------------------------------+ | | 140000 +-++.+.+.++.+.++.+.+.++.+.+ +.+.++.+.+.++.+.++.+.+.++.+.++.+.+.++.| 120000 +-+ :+ | | + | 100000 +-+ | | | 80000 O-OO O O O OO O O OO O OO O O | | | 60000 +-+ | 40000 +-+ | | O | 20000 +-+ | | | 0 +-+------O---------------------------------------------------------+ fsmark.files_per_sec 60 +-+----------O---------------------------------------------------------+ O O OO O O OO O O OO O O O | 50 +-+ O O | | | | | 40 +-+ .+.+.+.+.++.+.+.+.+ .+.+.+. .+.+ .++.+.+.+.+.++. .| |.+.++ + +.++.+.+.+ +.+.+.+ + | 30 +-+ | | | 20 +-+ | | | | | 10 +-+ | | | 0 +-+------O-------------------------------------------------------------+ [*] bisect-good sample [O] bisect-bad sample *************************************************************************************************** lkp-csl-2sp7: 96 threads Intel(R) Xeon(R) Gold 6252 CPU @ 2.10GHz with 256G memory ========================================================================================= compiler/cpufreq_governor/disk/filesize/fs/iterations/kconfig/nr_directories/nr_files_per_directory/nr_threads/rootfs/sync_method/tbox_group/test_size/testcase/ucode: gcc-7/performance/1SSD/16MB/btrfs/1x/x86_64-rhel-7.6/16d/256fpd/32t/debian-x86_64-2019-09-23.cgz/NoSync/lkp-csl-2sp7/60G/fsmark/0x500002b commit: eb094f0696 ("Merge branch 'x86-pti-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip") e4f9eb2268 ("writeback: add elastic bdi in cgwb bdp") eb094f06963bb0fd e4f9eb2268da0eb6b706fe582ef ---------------- --------------------------- %stddev %change %stddev \ | \ 98.50 +84.3% 181.50 ± 3% fsmark.files_per_sec 201.25 ± 24% +235.9% 676.00 ± 52% fsmark.time.involuntary_context_switches 67.00 ± 2% +310.4% 275.00 ± 3% fsmark.time.percent_of_cpu_this_job_got 92.12 ± 2% +311.2% 378.78 ± 3% fsmark.time.system_time 764632 ± 18% +669.6% 5884310 fsmark.time.voluntary_context_switches 0.98 ± 11% -5.7% 0.92 ± 10% boot-time.smp_boot 4639725 -54.5% 2110392 meminfo.Dirty 22793620 +16.9% 26639911 meminfo.Writeback 9.44 -7.4 2.01 ± 2% mpstat.cpu.all.iowait% 0.82 +2.3 3.17 ± 3% mpstat.cpu.all.sys% 89.45 +5.7% 94.51 iostat.cpu.idle 9.31 -78.8% 1.98 ± 2% iostat.cpu.iowait 0.95 ± 4% +239.5% 3.23 ± 3% iostat.cpu.system 2364563 ± 6% -58.4% 983026 ± 12% numa-meminfo.node0.Dirty 15165 ± 8% +15.6% 17534 ± 6% numa-meminfo.node0.Shmem 2279950 ± 5% -50.6% 1126676 ± 10% numa-meminfo.node1.Dirty 5408 ± 25% -47.0% 2869 ± 41% numa-meminfo.node1.Shmem 89.00 +5.6% 94.00 vmstat.cpu.id 9.00 -88.9% 1.00 vmstat.procs.b 1.00 +200.0% 3.00 vmstat.procs.r 14071 ± 14% +843.8% 132804 ± 2% vmstat.system.cs 7965182 ± 51% -65.6% 2737782 ±137% numa-numastat.node0.local_node 7993076 ± 51% -65.7% 2745575 ±137% numa-numastat.node0.numa_hit 1192997 ±173% +294.2% 4703020 ± 54% numa-numastat.node0.numa_miss 1220902 ±168% +285.8% 4710820 ± 54% numa-numastat.node0.other_node 1192997 ±173% +294.2% 4703020 ± 54% numa-numastat.node1.numa_foreign 29194348 ± 65% +156.8% 74982446 ± 3% cpuidle.C1.time 614163 ± 72% +548.6% 3983752 ± 8% cpuidle.C1.usage 3.703e+09 ± 51% +187.6% 1.065e+10 ± 22% cpuidle.C1E.time 15222120 ± 13% +63.5% 24881567 ± 14% cpuidle.C1E.usage 8.998e+09 ± 20% -79.9% 1.809e+09 ±134% cpuidle.C6.time 9904301 ± 10% +66.0% 16441007 ± 6% cpuidle.POLL.time 675155 ± 17% +392.9% 3327749 ± 6% cpuidle.POLL.usage 1591 ± 2% +16.6% 1855 ± 4% slabinfo.biovec-max.active_objs 1653 ± 2% +14.9% 1900 ± 4% slabinfo.biovec-max.num_objs 4963 ± 2% +16.3% 5770 ± 3% slabinfo.btrfs_delayed_node.active_objs 4987 ± 2% +16.1% 5791 ± 3% slabinfo.btrfs_delayed_node.num_objs 2834 ± 4% +13.8% 3224 ± 2% slabinfo.btrfs_ordered_extent.active_objs 2933 ± 3% +13.2% 3322 ± 2% slabinfo.btrfs_ordered_extent.num_objs 22120 ± 3% +9.4% 24207 ± 5% slabinfo.filp.num_objs 590993 ± 6% -58.5% 245356 ± 12% numa-vmstat.node0.nr_dirty 3791 ± 8% +15.6% 4383 ± 6% numa-vmstat.node0.nr_shmem 8101322 ± 48% -60.9% 3166607 ±115% numa-vmstat.node0.numa_hit 8074295 ± 48% -60.9% 3158895 ±115% numa-vmstat.node0.numa_local 1163378 ±173% +293.6% 4578545 ± 55% numa-vmstat.node0.numa_miss 1190408 ±168% +285.3% 4586258 ± 54% numa-vmstat.node0.numa_other 569934 ± 5% -50.7% 281036 ± 10% numa-vmstat.node1.nr_dirty 1350 ± 25% -46.9% 717.25 ± 41% numa-vmstat.node1.nr_shmem 1163392 ±173% +293.6% 4578595 ± 55% numa-vmstat.node1.numa_foreign 86.50 ± 7% +60.4% 138.75 ± 2% turbostat.Avg_MHz 5.62 ± 10% +0.9 6.56 ± 3% turbostat.Busy% 1549 ± 3% +37.2% 2125 ± 2% turbostat.Bzy_MHz 615790 ± 72% +547.0% 3984026 ± 8% turbostat.C1 0.22 ± 66% +0.3 0.56 ± 3% turbostat.C1% 15221796 ± 13% +63.5% 24881064 ± 14% turbostat.C1E 27.76 ± 51% +52.0 79.78 ± 22% turbostat.C1E% 67.49 ± 20% -54.0 13.51 ±134% turbostat.C6% 96.43 +6.6% 102.80 turbostat.PkgWatt 1160706 -54.6% 527074 proc-vmstat.nr_dirty 14826379 +2.1% 15135031 proc-vmstat.nr_file_pages 14543661 +2.1% 14852549 proc-vmstat.nr_inactive_file 1241 -2.7% 1207 proc-vmstat.nr_page_table_pages 5143 -0.8% 5100 proc-vmstat.nr_shmem 52491 +1.6% 53314 proc-vmstat.nr_slab_reclaimable 57094 +4.3% 59578 proc-vmstat.nr_slab_unreclaimable 5704228 +16.6% 6653630 proc-vmstat.nr_writeback 14543661 +2.1% 14852549 proc-vmstat.nr_zone_inactive_file 6865018 +4.6% 7180790 proc-vmstat.nr_zone_write_pending 4757461 ± 2% +34.0% 6373060 ± 2% proc-vmstat.numa_foreign 11471142 -14.1% 9856783 proc-vmstat.numa_hit 11439835 -14.1% 9825555 proc-vmstat.numa_local 4757461 ± 2% +34.0% 6373060 ± 2% proc-vmstat.numa_miss 4788768 ± 2% +33.7% 6404288 ± 2% proc-vmstat.numa_other 5368 ± 3% -7.9% 4943 proc-vmstat.pgactivate 763.18 ± 24% +277.2% 2878 ± 24% sched_debug.cfs_rq:/.exec_clock.avg 3908 ± 63% +150.5% 9793 ± 8% sched_debug.cfs_rq:/.exec_clock.max 1041 ± 36% +174.6% 2859 ± 3% sched_debug.cfs_rq:/.exec_clock.stddev 51.08 ± 12% -23.5% 39.10 ± 19% sched_debug.cfs_rq:/.load_avg.avg 28955 ± 21% +156.1% 74144 ± 22% sched_debug.cfs_rq:/.min_vruntime.avg 77632 ± 4% +163.1% 204261 ± 8% sched_debug.cfs_rq:/.min_vruntime.max 23904 ± 5% +160.8% 62349 ± 6% sched_debug.cfs_rq:/.min_vruntime.stddev -18011 -164.1% 11547 ±189% sched_debug.cfs_rq:/.spread0.avg 30657 ± 61% +362.1% 141676 ± 13% sched_debug.cfs_rq:/.spread0.max 23911 ± 5% +160.8% 62353 ± 6% sched_debug.cfs_rq:/.spread0.stddev 8971 ± 13% +1286.6% 124400 ± 2% sched_debug.cpu.nr_switches.avg 326674 ± 42% +188.8% 943564 ± 18% sched_debug.cpu.nr_switches.max 36613 ± 34% +365.8% 170553 ± 10% sched_debug.cpu.nr_switches.stddev 7385 ± 16% +1850.7% 144072 ± 2% sched_debug.cpu.sched_count.avg 323205 ± 43% +200.8% 972192 ± 18% sched_debug.cpu.sched_count.max 36207 ± 35% +412.3% 185505 ± 9% sched_debug.cpu.sched_count.stddev 3624 ± 16% +1592.5% 61342 ± 2% sched_debug.cpu.sched_goidle.avg 161191 ± 43% +191.6% 470040 ± 18% sched_debug.cpu.sched_goidle.max 18051 ± 35% +371.2% 85059 ± 10% sched_debug.cpu.sched_goidle.stddev 3672 ± 16% +2154.6% 82799 ± 3% sched_debug.cpu.ttwu_count.avg 180691 ± 42% +400.9% 905080 ± 2% sched_debug.cpu.ttwu_count.max 18925 ± 38% +722.1% 155592 ± 6% sched_debug.cpu.ttwu_count.stddev 662.08 -38.8% 404.94 ± 2% sched_debug.cpu.ttwu_local.avg 5.829e+08 ± 5% +46.2% 8.52e+08 ± 2% perf-stat.i.branch-instructions 4.91 ± 32% -3.2 1.75 perf-stat.i.branch-miss-rate% 10726947 ± 2% +9.3% 11729895 ± 8% perf-stat.i.cache-misses 14453 ± 14% +852.2% 137618 ± 2% perf-stat.i.context-switches 6.705e+09 ± 6% +77.1% 1.188e+10 ± 3% perf-stat.i.cpu-cycles 2.25 ± 29% +133.2% 5.25 ± 22% perf-stat.i.cpu-migrations 2108 ± 9% +76.5% 3721 ± 25% perf-stat.i.cycles-between-cache-misses 0.37 ± 22% -0.3 0.08 ±156% perf-stat.i.dTLB-load-miss-rate% 1231579 ± 20% -77.4% 278161 ±141% perf-stat.i.dTLB-load-misses 7.319e+08 ± 5% +40.1% 1.026e+09 ± 2% perf-stat.i.dTLB-loads 0.10 ± 21% -0.1 0.02 ±141% perf-stat.i.dTLB-store-miss-rate% 179997 ± 19% -74.9% 45267 ±129% perf-stat.i.dTLB-store-misses 3.336e+08 ± 5% +32.2% 4.41e+08 ± 2% perf-stat.i.dTLB-stores 1340141 ± 21% +46.2% 1959021 ± 4% perf-stat.i.iTLB-load-misses 1028018 ± 13% +63.2% 1677371 ± 2% perf-stat.i.iTLB-loads 2.893e+09 ± 5% +39.1% 4.026e+09 ± 2% perf-stat.i.instructions 76.46 ± 2% +4.8 81.30 ± 3% perf-stat.i.node-load-miss-rate% 616311 ± 4% +105.7% 1267509 ± 20% perf-stat.i.node-load-misses 53.09 ± 10% +25.4 78.49 ± 4% perf-stat.i.node-store-miss-rate% 248843 ± 26% +111.1% 525396 ± 17% perf-stat.i.node-store-misses 212587 ± 4% -39.3% 129033 ± 15% perf-stat.i.node-stores 4.15 ± 19% -2.0 2.13 perf-stat.overall.branch-miss-rate% 2.33 ± 9% +26.8% 2.95 ± 2% perf-stat.overall.cpi 625.64 ± 7% +62.9% 1018 ± 8% perf-stat.overall.cycles-between-cache-misses 0.17 ± 25% -0.1 0.03 ±141% perf-stat.overall.dTLB-load-miss-rate% 0.05 ± 24% -0.0 0.01 ±128% perf-stat.overall.dTLB-store-miss-rate% 0.43 ± 10% -21.8% 0.34 ± 2% perf-stat.overall.ipc 43.85 ± 2% +18.1 61.93 ± 7% perf-stat.overall.node-load-miss-rate% 52.98 ± 15% +27.0 79.93 ± 4% perf-stat.overall.node-store-miss-rate% 5.786e+08 ± 5% +46.1% 8.456e+08 ± 2% perf-stat.ps.branch-instructions 10655938 ± 2% +9.2% 11641373 ± 8% perf-stat.ps.cache-misses 14347 ± 14% +851.9% 136576 ± 2% perf-stat.ps.context-switches 6.657e+09 ± 6% +77.1% 1.179e+10 ± 3% perf-stat.ps.cpu-cycles 2.23 ± 29% +133.3% 5.21 ± 22% perf-stat.ps.cpu-migrations 1222682 ± 20% -77.4% 276165 ±141% perf-stat.ps.dTLB-load-misses 7.267e+08 ± 5% +40.1% 1.018e+09 ± 2% perf-stat.ps.dTLB-loads 178699 ± 19% -74.9% 44941 ±129% perf-stat.ps.dTLB-store-misses 3.312e+08 ± 4% +32.2% 4.378e+08 ± 2% perf-stat.ps.dTLB-stores 1330582 ± 21% +46.2% 1944678 ± 4% perf-stat.ps.iTLB-load-misses 1020385 ± 13% +63.2% 1664945 ± 2% perf-stat.ps.iTLB-loads 2.872e+09 ± 5% +39.1% 3.996e+09 ± 2% perf-stat.ps.instructions 611263 ± 4% +105.7% 1257464 ± 20% perf-stat.ps.node-load-misses 247453 ± 26% +111.0% 522107 ± 17% perf-stat.ps.node-store-misses 210950 ± 4% -39.3% 128103 ± 15% perf-stat.ps.node-stores 3.907e+11 ± 5% +39.3% 5.442e+11 ± 2% perf-stat.total.instructions 12342 ± 13% -13.4% 10692 ± 13% softirqs.CPU0.RCU 12466 ± 16% -13.6% 10765 ± 11% softirqs.CPU11.RCU 12356 ± 15% -14.6% 10554 ± 9% softirqs.CPU13.RCU 12632 ± 12% -16.6% 10537 ± 9% softirqs.CPU14.RCU 18944 ± 3% +17.8% 22313 ± 7% softirqs.CPU15.SCHED 65343 ± 13% -18.5% 53276 ± 8% softirqs.CPU2.TIMER 11755 ± 7% -21.1% 9278 ± 14% softirqs.CPU23.RCU 18741 ± 4% +13.1% 21196 softirqs.CPU24.SCHED 12699 ± 12% -17.8% 10445 ± 9% softirqs.CPU27.RCU 67824 ± 10% -24.7% 51099 ± 5% softirqs.CPU27.TIMER 18466 +14.4% 21133 ± 6% softirqs.CPU3.SCHED 12543 ± 11% -16.5% 10467 ± 8% softirqs.CPU31.RCU 13209 ± 16% -20.0% 10569 ± 9% softirqs.CPU32.RCU 13391 ± 13% -20.9% 10595 ± 9% softirqs.CPU34.RCU 12978 ± 14% -19.0% 10514 ± 9% softirqs.CPU35.RCU 12716 ± 12% -17.6% 10480 ± 8% softirqs.CPU37.RCU 13130 ± 17% -20.4% 10457 ± 8% softirqs.CPU41.RCU 12755 ± 11% -17.5% 10525 ± 9% softirqs.CPU43.RCU 13506 ± 13% -21.5% 10600 ± 9% softirqs.CPU44.RCU 13047 ± 14% -18.4% 10650 ± 7% softirqs.CPU45.RCU 13383 ± 14% -21.8% 10461 ± 8% softirqs.CPU46.RCU 13084 ± 14% -19.6% 10514 ± 8% softirqs.CPU47.RCU 13283 ± 11% -28.5% 9491 ± 31% softirqs.CPU50.RCU 13232 ± 12% -20.6% 10503 ± 5% softirqs.CPU51.RCU 12804 ± 8% -15.7% 10796 ± 10% softirqs.CPU53.RCU 12941 ± 12% -17.0% 10742 ± 10% softirqs.CPU54.RCU 12749 ± 11% -16.6% 10638 ± 10% softirqs.CPU56.RCU 13099 ± 14% -17.0% 10877 ± 9% softirqs.CPU58.RCU 13363 ± 9% -19.8% 10713 ± 10% softirqs.CPU6.RCU 12488 ± 13% -14.0% 10743 ± 10% softirqs.CPU60.RCU 12485 ± 13% -12.6% 10907 ± 9% softirqs.CPU61.RCU 12534 ± 14% -14.8% 10673 ± 10% softirqs.CPU7.RCU 11454 ± 7% -15.2% 9712 ± 9% softirqs.CPU72.RCU 13026 ± 28% -21.9% 10169 ± 7% softirqs.CPU76.RCU 12586 ± 13% -18.0% 10323 ± 10% softirqs.CPU8.RCU 12873 ± 17% -20.8% 10195 ± 9% softirqs.CPU80.RCU 12497 ± 14% -18.5% 10189 ± 9% softirqs.CPU81.RCU 12851 ± 15% -19.7% 10319 ± 9% softirqs.CPU82.RCU 12866 ± 15% -20.5% 10230 ± 8% softirqs.CPU83.RCU 12558 ± 12% -16.9% 10432 ± 7% softirqs.CPU85.RCU 12641 ± 16% -32.6% 8526 ± 37% softirqs.CPU86.RCU 12856 ± 16% -20.3% 10248 ± 8% softirqs.CPU88.RCU 13192 ± 19% -22.0% 10286 ± 7% softirqs.CPU89.RCU 11716 ± 8% -12.9% 10199 ± 9% softirqs.CPU90.RCU 12620 ± 12% -18.0% 10345 ± 7% softirqs.CPU91.RCU 12933 ± 16% -21.9% 10095 ± 8% softirqs.CPU92.RCU 13185 ± 16% -23.0% 10146 ± 9% softirqs.CPU93.RCU 13066 ± 16% -22.3% 10156 ± 8% softirqs.CPU94.RCU 12889 ± 16% -21.2% 10156 ± 8% softirqs.CPU95.RCU 5699200 ± 8% -13.7% 4919656 softirqs.TIMER 954.75 ± 39% +183.2% 2703 ± 54% interrupts.CPU0.RES:Rescheduling_interrupts 281.00 ± 21% -43.7% 158.25 ± 20% interrupts.CPU11.NMI:Non-maskable_interrupts 281.00 ± 21% -43.7% 158.25 ± 20% interrupts.CPU11.PMI:Performance_monitoring_interrupts 183.25 ±103% +4491.8% 8414 ± 66% interrupts.CPU15.RES:Rescheduling_interrupts 310.00 ± 55% -44.4% 172.25 ± 11% interrupts.CPU2.NMI:Non-maskable_interrupts 310.00 ± 55% -44.4% 172.25 ± 11% interrupts.CPU2.PMI:Performance_monitoring_interrupts 1.50 ±137% +24083.3% 362.75 ± 98% interrupts.CPU22.RES:Rescheduling_interrupts 248.25 ± 23% -36.3% 158.25 ± 17% interrupts.CPU24.NMI:Non-maskable_interrupts 248.25 ± 23% -36.3% 158.25 ± 17% interrupts.CPU24.PMI:Performance_monitoring_interrupts 7.25 ± 97% +21217.2% 1545 ± 96% interrupts.CPU24.RES:Rescheduling_interrupts 274.25 ± 16% -41.7% 160.00 ± 16% interrupts.CPU25.NMI:Non-maskable_interrupts 274.25 ± 16% -41.7% 160.00 ± 16% interrupts.CPU25.PMI:Performance_monitoring_interrupts 249.50 ± 25% -32.1% 169.50 ± 27% interrupts.CPU26.NMI:Non-maskable_interrupts 249.50 ± 25% -32.1% 169.50 ± 27% interrupts.CPU26.PMI:Performance_monitoring_interrupts 277.25 ± 26% -43.1% 157.75 ± 16% interrupts.CPU27.NMI:Non-maskable_interrupts 277.25 ± 26% -43.1% 157.75 ± 16% interrupts.CPU27.PMI:Performance_monitoring_interrupts 15.25 ±139% +73360.7% 11202 ±108% interrupts.CPU28.RES:Rescheduling_interrupts 258.75 ± 26% -40.9% 153.00 ± 30% interrupts.CPU29.NMI:Non-maskable_interrupts 258.75 ± 26% -40.9% 153.00 ± 30% interrupts.CPU29.PMI:Performance_monitoring_interrupts 9.25 ± 92% +89291.9% 8268 ±111% interrupts.CPU29.RES:Rescheduling_interrupts 9.00 ± 65% +1.6e+05% 14544 ± 72% interrupts.CPU3.RES:Rescheduling_interrupts 315.50 ± 12% -44.3% 175.75 ± 15% interrupts.CPU30.NMI:Non-maskable_interrupts 315.50 ± 12% -44.3% 175.75 ± 15% interrupts.CPU30.PMI:Performance_monitoring_interrupts 1.25 ± 87% +3.3e+05% 4066 ± 85% interrupts.CPU30.RES:Rescheduling_interrupts 528.50 ± 66% -70.1% 158.00 ± 11% interrupts.CPU31.NMI:Non-maskable_interrupts 528.50 ± 66% -70.1% 158.00 ± 11% interrupts.CPU31.PMI:Performance_monitoring_interrupts 1558 ±172% +216.0% 4923 ± 74% interrupts.CPU31.RES:Rescheduling_interrupts 581.75 ± 48% -63.3% 213.50 ± 44% interrupts.CPU32.NMI:Non-maskable_interrupts 581.75 ± 48% -63.3% 213.50 ± 44% interrupts.CPU32.PMI:Performance_monitoring_interrupts 295.25 ± 21% -27.9% 213.00 ± 34% interrupts.CPU33.NMI:Non-maskable_interrupts 295.25 ± 21% -27.9% 213.00 ± 34% interrupts.CPU33.PMI:Performance_monitoring_interrupts 327.75 ± 25% -49.8% 164.50 ± 17% interrupts.CPU34.NMI:Non-maskable_interrupts 327.75 ± 25% -49.8% 164.50 ± 17% interrupts.CPU34.PMI:Performance_monitoring_interrupts 11.00 ± 61% +65011.4% 7162 ±137% interrupts.CPU34.RES:Rescheduling_interrupts 315.00 ± 24% -51.8% 151.75 ± 33% interrupts.CPU35.NMI:Non-maskable_interrupts 315.00 ± 24% -51.8% 151.75 ± 33% interrupts.CPU35.PMI:Performance_monitoring_interrupts 293.25 ± 22% -45.1% 161.00 ± 14% interrupts.CPU36.NMI:Non-maskable_interrupts 293.25 ± 22% -45.1% 161.00 ± 14% interrupts.CPU36.PMI:Performance_monitoring_interrupts 281.75 ± 29% -38.4% 173.50 ± 15% interrupts.CPU38.NMI:Non-maskable_interrupts 281.75 ± 29% -38.4% 173.50 ± 15% interrupts.CPU38.PMI:Performance_monitoring_interrupts 298.75 ± 20% -43.3% 169.50 ± 17% interrupts.CPU39.NMI:Non-maskable_interrupts 298.75 ± 20% -43.3% 169.50 ± 17% interrupts.CPU39.PMI:Performance_monitoring_interrupts 9.50 ± 86% +45005.3% 4285 ± 92% interrupts.CPU4.RES:Rescheduling_interrupts 297.50 ± 20% -42.4% 171.25 ± 13% interrupts.CPU40.NMI:Non-maskable_interrupts 297.50 ± 20% -42.4% 171.25 ± 13% interrupts.CPU40.PMI:Performance_monitoring_interrupts 298.00 ± 18% -42.2% 172.25 ± 14% interrupts.CPU41.NMI:Non-maskable_interrupts 298.00 ± 18% -42.2% 172.25 ± 14% interrupts.CPU41.PMI:Performance_monitoring_interrupts 379.50 ± 24% -50.0% 189.75 ± 23% interrupts.CPU42.NMI:Non-maskable_interrupts 379.50 ± 24% -50.0% 189.75 ± 23% interrupts.CPU42.PMI:Performance_monitoring_interrupts 325.75 ± 20% -48.9% 166.50 ± 18% interrupts.CPU44.NMI:Non-maskable_interrupts 325.75 ± 20% -48.9% 166.50 ± 18% interrupts.CPU44.PMI:Performance_monitoring_interrupts 1.50 ±100% +67400.0% 1012 ± 96% interrupts.CPU45.RES:Rescheduling_interrupts 314.25 ± 21% -46.3% 168.75 ± 12% interrupts.CPU46.NMI:Non-maskable_interrupts 314.25 ± 21% -46.3% 168.75 ± 12% interrupts.CPU46.PMI:Performance_monitoring_interrupts 261.00 ± 18% -42.6% 149.75 ± 34% interrupts.CPU49.NMI:Non-maskable_interrupts 261.00 ± 18% -42.6% 149.75 ± 34% interrupts.CPU49.PMI:Performance_monitoring_interrupts 342.75 ± 42% -56.8% 148.00 ± 32% interrupts.CPU50.NMI:Non-maskable_interrupts 342.75 ± 42% -56.8% 148.00 ± 32% interrupts.CPU50.PMI:Performance_monitoring_interrupts 2.25 ±110% +23233.3% 525.00 ±100% interrupts.CPU50.RES:Rescheduling_interrupts 270.50 ± 22% -37.3% 169.50 ± 14% interrupts.CPU51.NMI:Non-maskable_interrupts 270.50 ± 22% -37.3% 169.50 ± 14% interrupts.CPU51.PMI:Performance_monitoring_interrupts 3.00 ± 74% +12616.7% 381.50 ±104% interrupts.CPU51.RES:Rescheduling_interrupts 274.50 ± 25% -39.4% 166.25 ± 27% interrupts.CPU52.NMI:Non-maskable_interrupts 274.50 ± 25% -39.4% 166.25 ± 27% interrupts.CPU52.PMI:Performance_monitoring_interrupts 358.00 ± 37% -56.6% 155.25 ± 34% interrupts.CPU53.NMI:Non-maskable_interrupts 358.00 ± 37% -56.6% 155.25 ± 34% interrupts.CPU53.PMI:Performance_monitoring_interrupts 301.00 ± 29% -47.0% 159.50 ± 33% interrupts.CPU54.NMI:Non-maskable_interrupts 301.00 ± 29% -47.0% 159.50 ± 33% interrupts.CPU54.PMI:Performance_monitoring_interrupts 248.75 ± 26% -34.8% 162.25 ± 25% interrupts.CPU55.NMI:Non-maskable_interrupts 248.75 ± 26% -34.8% 162.25 ± 25% interrupts.CPU55.PMI:Performance_monitoring_interrupts 275.75 ± 26% -45.7% 149.75 ± 35% interrupts.CPU56.NMI:Non-maskable_interrupts 275.75 ± 26% -45.7% 149.75 ± 35% interrupts.CPU56.PMI:Performance_monitoring_interrupts 256.00 ± 15% -38.0% 158.75 ± 31% interrupts.CPU57.NMI:Non-maskable_interrupts 256.00 ± 15% -38.0% 158.75 ± 31% interrupts.CPU57.PMI:Performance_monitoring_interrupts 430.50 ± 59% -64.8% 151.50 ± 32% interrupts.CPU59.NMI:Non-maskable_interrupts 430.50 ± 59% -64.8% 151.50 ± 32% interrupts.CPU59.PMI:Performance_monitoring_interrupts 260.25 ± 16% -53.2% 121.75 ± 30% interrupts.CPU60.NMI:Non-maskable_interrupts 260.25 ± 16% -53.2% 121.75 ± 30% interrupts.CPU60.PMI:Performance_monitoring_interrupts 273.75 ± 17% -36.7% 173.25 ± 13% interrupts.CPU62.NMI:Non-maskable_interrupts 273.75 ± 17% -36.7% 173.25 ± 13% interrupts.CPU62.PMI:Performance_monitoring_interrupts 265.75 ± 27% -38.6% 163.25 ± 14% interrupts.CPU63.NMI:Non-maskable_interrupts 265.75 ± 27% -38.6% 163.25 ± 14% interrupts.CPU63.PMI:Performance_monitoring_interrupts 275.50 ± 24% -36.4% 175.25 ± 14% interrupts.CPU64.NMI:Non-maskable_interrupts 275.50 ± 24% -36.4% 175.25 ± 14% interrupts.CPU64.PMI:Performance_monitoring_interrupts 232.50 ± 15% -20.4% 185.00 ± 14% interrupts.CPU68.NMI:Non-maskable_interrupts 232.50 ± 15% -20.4% 185.00 ± 14% interrupts.CPU68.PMI:Performance_monitoring_interrupts 0.75 ±110% +9.8e+05% 7387 ±147% interrupts.CPU71.RES:Rescheduling_interrupts 276.00 ± 22% -34.0% 182.25 ± 17% interrupts.CPU78.NMI:Non-maskable_interrupts 276.00 ± 22% -34.0% 182.25 ± 17% interrupts.CPU78.PMI:Performance_monitoring_interrupts 2634 ± 43% -32.0% 1791 ± 8% interrupts.CPU79.CAL:Function_call_interrupts 399.50 ± 22% -50.8% 196.75 ± 27% interrupts.CPU80.NMI:Non-maskable_interrupts 399.50 ± 22% -50.8% 196.75 ± 27% interrupts.CPU80.PMI:Performance_monitoring_interrupts 257.25 ± 29% -28.6% 183.75 ± 23% interrupts.CPU81.NMI:Non-maskable_interrupts 257.25 ± 29% -28.6% 183.75 ± 23% interrupts.CPU81.PMI:Performance_monitoring_interrupts 0.00 +1.2e+105% 1217 ±173% interrupts.CPU83.TLB:TLB_shootdowns 1.25 ±173% +1.4e+05% 1787 ± 77% interrupts.CPU86.RES:Rescheduling_interrupts 256.00 ± 28% -36.0% 163.75 ± 21% interrupts.CPU87.NMI:Non-maskable_interrupts 256.00 ± 28% -36.0% 163.75 ± 21% interrupts.CPU87.PMI:Performance_monitoring_interrupts 9.25 ±138% +52624.3% 4877 ±155% interrupts.CPU87.RES:Rescheduling_interrupts 274.00 ± 31% -38.7% 168.00 ± 16% interrupts.CPU89.NMI:Non-maskable_interrupts 274.00 ± 31% -38.7% 168.00 ± 16% interrupts.CPU89.PMI:Performance_monitoring_interrupts 36.25 ±107% +3699.3% 1377 ±100% interrupts.CPU9.RES:Rescheduling_interrupts 376.50 ± 8% -48.1% 195.50 ± 22% interrupts.CPU90.NMI:Non-maskable_interrupts 376.50 ± 8% -48.1% 195.50 ± 22% interrupts.CPU90.PMI:Performance_monitoring_interrupts 300.75 ± 37% -44.1% 168.00 ± 16% interrupts.CPU92.NMI:Non-maskable_interrupts 300.75 ± 37% -44.1% 168.00 ± 16% interrupts.CPU92.PMI:Performance_monitoring_interrupts 26762 ± 15% -30.6% 18563 ± 12% interrupts.NMI:Non-maskable_interrupts 26762 ± 15% -30.6% 18563 ± 12% interrupts.PMI:Performance_monitoring_interrupts 35167 ± 4% +613.2% 250825 ± 10% interrupts.RES:Rescheduling_interrupts 54.58 ± 4% -12.9 41.68 ± 12% perf-profile.calltrace.cycles-pp.intel_idle.cpuidle_enter_state.cpuidle_enter.do_idle.cpu_startup_entry 84.09 -6.4 77.67 ± 3% perf-profile.calltrace.cycles-pp.cpuidle_enter_state.cpuidle_enter.do_idle.cpu_startup_entry.start_secondary 84.87 -5.9 78.93 ± 3% perf-profile.calltrace.cycles-pp.cpuidle_enter.do_idle.cpu_startup_entry.start_secondary.secondary_startup_64 97.14 -1.9 95.20 perf-profile.calltrace.cycles-pp.cpu_startup_entry.start_secondary.secondary_startup_64 97.14 -1.9 95.20 perf-profile.calltrace.cycles-pp.start_secondary.secondary_startup_64 97.06 -1.9 95.12 perf-profile.calltrace.cycles-pp.do_idle.cpu_startup_entry.start_secondary.secondary_startup_64 97.91 -0.8 97.10 perf-profile.calltrace.cycles-pp.secondary_startup_64 0.92 ± 14% +0.2 1.17 ± 11% perf-profile.calltrace.cycles-pp.ktime_get.tick_irq_enter.irq_enter.smp_apic_timer_interrupt.apic_timer_interrupt 1.11 ± 4% +0.3 1.44 ± 13% perf-profile.calltrace.cycles-pp.native_write_msr.lapic_next_deadline.clockevents_program_event.hrtimer_interrupt.smp_apic_timer_interrupt 1.35 ± 2% +0.3 1.68 ± 12% perf-profile.calltrace.cycles-pp.lapic_next_deadline.clockevents_program_event.hrtimer_interrupt.smp_apic_timer_interrupt.apic_timer_interrupt 0.15 ±173% +0.5 0.66 ± 17% perf-profile.calltrace.cycles-pp.ktime_get.tick_sched_timer.__hrtimer_run_queues.hrtimer_interrupt.smp_apic_timer_interrupt 0.56 ± 61% +0.5 1.09 ± 20% perf-profile.calltrace.cycles-pp.ktime_get_update_offsets_now.hrtimer_interrupt.smp_apic_timer_interrupt.apic_timer_interrupt.cpuidle_enter_state 0.16 ±173% +0.6 0.71 ± 12% perf-profile.calltrace.cycles-pp.calc_global_load_tick.scheduler_tick.update_process_times.tick_sched_handle.tick_sched_timer 0.18 ±173% +0.7 0.92 ± 19% perf-profile.calltrace.cycles-pp.run_local_timers.update_process_times.tick_sched_handle.tick_sched_timer.__hrtimer_run_queues 3.78 ± 8% +1.4 5.15 ± 12% perf-profile.calltrace.cycles-pp.tick_sched_timer.__hrtimer_run_queues.hrtimer_interrupt.smp_apic_timer_interrupt.apic_timer_interrupt 0.75 ± 93% +1.5 2.21 ± 14% perf-profile.calltrace.cycles-pp.ktime_get.tick_nohz_irq_exit.irq_exit.smp_apic_timer_interrupt.apic_timer_interrupt 0.42 ±173% +1.5 1.89 ± 7% perf-profile.calltrace.cycles-pp.timekeeping_max_deferment.tick_nohz_next_event.tick_nohz_get_sleep_length.menu_select.do_idle 0.77 ± 91% +1.5 2.25 ± 14% perf-profile.calltrace.cycles-pp.tick_nohz_irq_exit.irq_exit.smp_apic_timer_interrupt.apic_timer_interrupt.cpuidle_enter_state 3.93 ± 19% +1.9 5.85 ± 2% perf-profile.calltrace.cycles-pp.tick_nohz_next_event.tick_nohz_get_sleep_length.menu_select.do_idle.cpu_startup_entry 4.89 ± 14% +2.0 6.90 ± 2% perf-profile.calltrace.cycles-pp.tick_nohz_get_sleep_length.menu_select.do_idle.cpu_startup_entry.start_secondary 4.40 ± 13% +2.0 6.45 ± 11% perf-profile.calltrace.cycles-pp.irq_exit.smp_apic_timer_interrupt.apic_timer_interrupt.cpuidle_enter_state.cpuidle_enter 1.85 ± 74% +2.8 4.66 ± 15% perf-profile.calltrace.cycles-pp.ktime_get.clockevents_program_event.hrtimer_interrupt.smp_apic_timer_interrupt.apic_timer_interrupt 3.33 ± 40% +3.2 6.51 ± 14% perf-profile.calltrace.cycles-pp.clockevents_program_event.hrtimer_interrupt.smp_apic_timer_interrupt.apic_timer_interrupt.cpuidle_enter_state 9.27 ± 5% +4.0 13.26 ± 14% perf-profile.calltrace.cycles-pp.menu_select.do_idle.cpu_startup_entry.start_secondary.secondary_startup_64 12.25 ± 11% +4.3 16.56 ± 12% perf-profile.calltrace.cycles-pp.hrtimer_interrupt.smp_apic_timer_interrupt.apic_timer_interrupt.cpuidle_enter_state.cpuidle_enter 19.44 ± 7% +5.9 25.33 ± 11% perf-profile.calltrace.cycles-pp.smp_apic_timer_interrupt.apic_timer_interrupt.cpuidle_enter_state.cpuidle_enter.do_idle 23.39 ± 7% +7.8 31.24 ± 10% perf-profile.calltrace.cycles-pp.apic_timer_interrupt.cpuidle_enter_state.cpuidle_enter.do_idle.cpu_startup_entry 54.85 ± 4% -12.9 41.90 ± 12% perf-profile.children.cycles-pp.intel_idle 85.51 -4.9 80.64 ± 2% perf-profile.children.cycles-pp.cpuidle_enter_state 85.56 -4.8 80.71 ± 2% perf-profile.children.cycles-pp.cpuidle_enter 97.14 -1.9 95.20 perf-profile.children.cycles-pp.start_secondary 97.91 -0.8 97.10 perf-profile.children.cycles-pp.secondary_startup_64 97.91 -0.8 97.10 perf-profile.children.cycles-pp.cpu_startup_entry 97.99 -0.8 97.22 perf-profile.children.cycles-pp.do_idle 0.55 ± 22% -0.3 0.27 ± 13% perf-profile.children.cycles-pp.__remove_hrtimer 0.68 ± 18% -0.2 0.46 ± 12% perf-profile.children.cycles-pp.irq_work_interrupt 0.68 ± 18% -0.2 0.46 ± 12% perf-profile.children.cycles-pp.smp_irq_work_interrupt 0.68 ± 18% -0.2 0.46 ± 12% perf-profile.children.cycles-pp.irq_work_run 0.68 ± 18% -0.2 0.46 ± 12% perf-profile.children.cycles-pp.printk 0.68 ± 18% -0.2 0.46 ± 12% perf-profile.children.cycles-pp.vprintk_emit 0.43 ± 22% -0.2 0.23 ± 3% perf-profile.children.cycles-pp.timerqueue_del 0.67 ± 11% -0.2 0.49 ± 21% perf-profile.children.cycles-pp.serial8250_console_putchar 0.69 ± 12% -0.2 0.51 ± 20% perf-profile.children.cycles-pp.uart_console_write 0.68 ± 11% -0.2 0.51 ± 20% perf-profile.children.cycles-pp.wait_for_xmitr 0.27 ± 22% -0.1 0.15 ± 8% perf-profile.children.cycles-pp.rb_next 0.30 ± 19% -0.1 0.19 ± 13% perf-profile.children.cycles-pp.__hrtimer_get_next_event 0.51 ± 6% -0.1 0.39 ± 15% perf-profile.children.cycles-pp.io_serial_in 0.16 ± 30% -0.1 0.06 ± 6% perf-profile.children.cycles-pp.run_posix_cpu_timers 0.17 ± 23% -0.1 0.10 ± 10% perf-profile.children.cycles-pp.account_process_tick 0.14 ± 6% -0.1 0.08 ± 17% perf-profile.children.cycles-pp.rb_erase 0.11 ± 24% +0.0 0.14 ± 18% perf-profile.children.cycles-pp.__x86_indirect_thunk_rax 0.11 ± 7% +0.0 0.15 ± 7% perf-profile.children.cycles-pp.raise_softirq 0.08 ± 17% +0.0 0.12 ± 18% perf-profile.children.cycles-pp.smp_call_function_single 0.01 ±173% +0.0 0.06 ± 9% perf-profile.children.cycles-pp.search_binary_handler 0.01 ±173% +0.0 0.06 ± 9% perf-profile.children.cycles-pp.load_elf_binary 0.07 ± 11% +0.0 0.12 ± 5% perf-profile.children.cycles-pp.__handle_mm_fault 0.07 ± 14% +0.0 0.12 ± 8% perf-profile.children.cycles-pp.handle_mm_fault 0.09 ± 16% +0.1 0.14 ± 3% perf-profile.children.cycles-pp.__do_page_fault 0.10 ± 22% +0.1 0.15 ± 4% perf-profile.children.cycles-pp.page_fault 0.10 ± 7% +0.1 0.15 ± 18% perf-profile.children.cycles-pp.find_next_and_bit 0.09 ± 16% +0.1 0.14 ± 5% perf-profile.children.cycles-pp.do_page_fault 0.01 ±173% +0.1 0.07 ± 31% perf-profile.children.cycles-pp.mmput 0.01 ±173% +0.1 0.07 ± 31% perf-profile.children.cycles-pp.exit_mmap 0.01 ±173% +0.1 0.08 ± 27% perf-profile.children.cycles-pp.__libc_fork 0.00 +0.1 0.07 ± 28% perf-profile.children.cycles-pp.__x64_sys_clone 0.00 +0.1 0.07 ± 28% perf-profile.children.cycles-pp._do_fork 0.00 +0.1 0.08 perf-profile.children.cycles-pp.read 0.07 ± 20% +0.1 0.15 ± 14% perf-profile.children.cycles-pp.tick_check_broadcast_expired 0.17 ± 15% +0.1 0.26 ± 7% perf-profile.children.cycles-pp.ksys_read 0.17 ± 15% +0.1 0.26 ± 7% perf-profile.children.cycles-pp.vfs_read 0.01 ±173% +0.1 0.10 ± 19% perf-profile.children.cycles-pp.timekeeping_advance 0.03 ±100% +0.1 0.14 ± 16% perf-profile.children.cycles-pp.tick_sched_do_timer 0.46 ± 8% +0.1 0.57 ± 8% perf-profile.children.cycles-pp.update_sd_lb_stats 0.19 ± 23% +0.1 0.30 ± 8% perf-profile.children.cycles-pp.call_cpuidle 0.36 ± 23% +0.1 0.48 ± 10% perf-profile.children.cycles-pp.__intel_pmu_enable_all 0.18 ± 27% +0.1 0.31 ± 7% perf-profile.children.cycles-pp.trigger_load_balance 0.41 ± 14% +0.1 0.55 ± 6% perf-profile.children.cycles-pp.rcu_idle_exit 0.09 ± 19% +0.2 0.33 ± 17% perf-profile.children.cycles-pp.hrtimer_forward 1.39 ± 2% +0.3 1.71 ± 12% perf-profile.children.cycles-pp.lapic_next_deadline 0.30 ± 48% +0.3 0.63 ± 22% perf-profile.children.cycles-pp._raw_spin_trylock 0.93 ± 18% +0.4 1.30 ± 9% perf-profile.children.cycles-pp._raw_spin_lock_irqsave 0.74 ± 5% +0.4 1.13 ± 31% perf-profile.children.cycles-pp._raw_spin_unlock_irqrestore 1.23 ± 20% +0.4 1.63 ± 12% perf-profile.children.cycles-pp.do_syscall_64 0.70 ± 23% +0.4 1.10 ± 21% perf-profile.children.cycles-pp.ktime_get_update_offsets_now 0.32 ± 63% +0.4 0.73 ± 12% perf-profile.children.cycles-pp.calc_global_load_tick 1.23 ± 20% +0.4 1.63 ± 11% perf-profile.children.cycles-pp.entry_SYSCALL_64_after_hwframe 1.55 ± 6% +0.5 2.02 ± 12% perf-profile.children.cycles-pp.native_write_msr 0.44 ± 37% +0.5 0.94 ± 19% perf-profile.children.cycles-pp.run_local_timers 1.20 ± 11% +0.6 1.76 ± 13% perf-profile.children.cycles-pp.native_irq_return_iret 0.57 ±113% +1.3 1.91 ± 7% perf-profile.children.cycles-pp.timekeeping_max_deferment 0.93 ± 63% +1.4 2.28 ± 14% perf-profile.children.cycles-pp.tick_nohz_irq_exit 3.83 ± 8% +1.4 5.21 ± 12% perf-profile.children.cycles-pp.tick_sched_timer 4.01 ± 18% +1.9 5.94 ± 2% perf-profile.children.cycles-pp.tick_nohz_next_event 4.96 ± 14% +2.0 6.98 ± 2% perf-profile.children.cycles-pp.tick_nohz_get_sleep_length 6.77 ± 12% +2.7 9.46 ± 12% perf-profile.children.cycles-pp.irq_exit 3.39 ± 39% +3.2 6.59 ± 14% perf-profile.children.cycles-pp.clockevents_program_event 9.43 ± 5% +4.0 13.42 ± 14% perf-profile.children.cycles-pp.menu_select 12.45 ± 11% +4.3 16.79 ± 12% perf-profile.children.cycles-pp.hrtimer_interrupt 4.44 ± 45% +4.8 9.22 ± 11% perf-profile.children.cycles-pp.ktime_get 19.69 ± 7% +6.0 25.66 ± 11% perf-profile.children.cycles-pp.smp_apic_timer_interrupt 21.81 ± 7% +7.0 28.80 ± 10% perf-profile.children.cycles-pp.apic_timer_interrupt 54.70 ± 4% -12.8 41.87 ± 12% perf-profile.self.cycles-pp.intel_idle 0.51 ± 6% -0.1 0.39 ± 15% perf-profile.self.cycles-pp.io_serial_in 0.16 ± 30% -0.1 0.06 ± 6% perf-profile.self.cycles-pp.run_posix_cpu_timers 0.17 ± 23% -0.1 0.10 ± 12% perf-profile.self.cycles-pp.account_process_tick 0.12 ± 7% -0.0 0.07 ± 22% perf-profile.self.cycles-pp.rb_erase 0.10 ± 8% +0.0 0.14 ± 6% perf-profile.self.cycles-pp.raise_softirq 0.05 ± 8% +0.0 0.09 ± 19% perf-profile.self.cycles-pp.stack_trace_save_tsk 0.04 ± 58% +0.0 0.08 ± 19% perf-profile.self.cycles-pp.end_page_writeback 0.10 ± 11% +0.1 0.15 ± 19% perf-profile.self.cycles-pp.find_next_and_bit 0.05 ± 62% +0.1 0.14 ± 15% perf-profile.self.cycles-pp.tick_check_broadcast_expired 0.23 ± 17% +0.1 0.34 ± 4% perf-profile.self.cycles-pp.rcu_idle_exit 0.18 ± 23% +0.1 0.30 ± 6% perf-profile.self.cycles-pp.call_cpuidle 0.15 ± 32% +0.1 0.28 ± 6% perf-profile.self.cycles-pp.trigger_load_balance 0.69 ± 8% +0.2 0.92 ± 14% perf-profile.self.cycles-pp._raw_spin_unlock_irqrestore 0.08 ± 17% +0.2 0.32 ± 15% perf-profile.self.cycles-pp.hrtimer_forward 0.86 ± 17% +0.2 1.11 ± 2% perf-profile.self.cycles-pp._raw_spin_lock_irqsave 0.33 ± 19% +0.3 0.59 ± 7% perf-profile.self.cycles-pp.__softirqentry_text_start 0.23 ± 56% +0.3 0.52 ± 12% perf-profile.self.cycles-pp.tick_sched_timer 0.51 ± 25% +0.3 0.81 ± 6% perf-profile.self.cycles-pp.tick_nohz_next_event 0.30 ± 48% +0.3 0.63 ± 22% perf-profile.self.cycles-pp._raw_spin_trylock 0.54 ± 28% +0.4 0.93 ± 20% perf-profile.self.cycles-pp.ktime_get_update_offsets_now 0.31 ± 69% +0.4 0.71 ± 13% perf-profile.self.cycles-pp.calc_global_load_tick 1.54 ± 6% +0.5 2.01 ± 12% perf-profile.self.cycles-pp.native_write_msr 0.42 ± 40% +0.5 0.91 ± 18% perf-profile.self.cycles-pp.run_local_timers 1.20 ± 11% +0.6 1.75 ± 13% perf-profile.self.cycles-pp.native_irq_return_iret 0.56 ±119% +1.3 1.90 ± 7% perf-profile.self.cycles-pp.timekeeping_max_deferment 2.71 ± 2% +1.5 4.19 ± 31% perf-profile.self.cycles-pp.cpuidle_enter_state 3.75 ± 5% +2.0 5.80 ± 31% perf-profile.self.cycles-pp.menu_select 3.47 ± 56% +4.6 8.04 ± 11% perf-profile.self.cycles-pp.ktime_get *************************************************************************************************** lkp-csl-2sp7: 96 threads Intel(R) Xeon(R) Gold 6252 CPU @ 2.10GHz with 256G memory ========================================================================================= compiler/cpufreq_governor/disk/filesize/fs/iterations/kconfig/nr_directories/nr_files_per_directory/nr_threads/rootfs/sync_method/tbox_group/test_size/testcase/ucode: gcc-7/performance/1SSD/16MB/f2fs/1x/x86_64-rhel-7.6/16d/256fpd/32t/debian-x86_64-2019-09-23.cgz/NoSync/lkp-csl-2sp7/60G/fsmark/0x500002b commit: eb094f0696 ("Merge branch 'x86-pti-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip") e4f9eb2268 ("writeback: add elastic bdi in cgwb bdp") eb094f06963bb0fd e4f9eb2268da0eb6b706fe582ef ---------------- --------------------------- %stddev %change %stddev \ | \ 181861 ± 2% -15.6% 153543 fsmark.app_overhead 85.92 +39.4% 119.80 fsmark.files_per_sec 198.50 ± 2% +28.3% 254.75 ± 3% fsmark.time.percent_of_cpu_this_job_got 286.52 ± 2% +29.5% 370.98 ± 3% fsmark.time.system_time 102252 -19.7% 82096 ± 2% fsmark.time.voluntary_context_switches 41480 ± 17% -10.7% 37022 ± 15% numa-meminfo.node0.Writeback 6836583 ± 35% -38.8% 4184696 ± 55% numa-numastat.node0.local_node 6852179 ± 35% -38.7% 4197165 ± 55% numa-numastat.node0.numa_hit 6824137 ± 35% -34.6% 4465626 ± 52% numa-vmstat.node0.numa_hit 6808740 ± 35% -34.6% 4453309 ± 52% numa-vmstat.node0.numa_local 89.04 +7.9% 96.06 iostat.cpu.idle 8.47 ± 3% -90.8% 0.78 iostat.cpu.iowait 2.25 ± 2% +29.7% 2.92 ± 3% iostat.cpu.system 8.58 ± 3% -7.8 0.78 mpstat.cpu.all.iowait% 0.10 ± 30% -0.0 0.05 ± 19% mpstat.cpu.all.soft% 2.18 ± 2% +0.7 2.90 ± 3% mpstat.cpu.all.sys% 26823 +11.0% 29767 ± 5% slabinfo.nat_entry.active_objs 27331 +10.9% 30313 ± 5% slabinfo.nat_entry.num_objs 1235 ± 7% +13.8% 1405 ± 7% slabinfo.task_group.active_objs 1235 ± 7% +13.8% 1405 ± 7% slabinfo.task_group.num_objs 15229559 ± 58% +67.5% 25512150 ± 9% turbostat.C1E 40.66 ± 77% +50.7 91.40 ± 2% turbostat.C1E% 9576498 ± 46% -98.0% 190269 ± 40% turbostat.C6 52.09 ± 55% -49.8 2.30 ± 19% turbostat.C6% 88.75 +8.2% 96.00 vmstat.cpu.id 8.00 -100.0% 0.00 vmstat.procs.b 2.00 +50.0% 3.00 vmstat.procs.r 3502 -7.3% 3246 vmstat.system.cs 5.72e+09 ± 77% +125.2% 1.288e+10 cpuidle.C1E.time 15230307 ± 58% +67.5% 25512110 ± 9% cpuidle.C1E.usage 7.309e+09 ± 55% -95.5% 3.319e+08 ± 19% cpuidle.C6.time 9587605 ± 46% -97.9% 202885 ± 37% cpuidle.C6.usage 1.79e+08 ±170% -98.7% 2281628 ± 26% cpuidle.POLL.time 204680 ± 6% +25.6% 257009 ± 6% sched_debug.cfs_rq:/.min_vruntime.max 2844 -9.2% 2582 sched_debug.cpu.sched_count.avg 1375 ± 2% -9.8% 1240 sched_debug.cpu.sched_goidle.avg 1436 -9.1% 1306 sched_debug.cpu.ttwu_count.avg 662.09 ± 2% -40.9% 391.06 ± 2% sched_debug.cpu.ttwu_local.avg 27940 +2.1% 28536 proc-vmstat.nr_active_file 6852781 +5.6% 7234155 proc-vmstat.nr_dirty 14437609 +2.5% 14803468 proc-vmstat.nr_file_pages 14134934 +2.6% 14500568 proc-vmstat.nr_inactive_file 6784 -0.7% 6738 proc-vmstat.nr_mapped 52131 +1.6% 52983 proc-vmstat.nr_slab_reclaimable 27940 +2.1% 28536 proc-vmstat.nr_zone_active_file 14134934 +2.6% 14500568 proc-vmstat.nr_zone_inactive_file 6873487 +5.5% 7254778 proc-vmstat.nr_zone_write_pending 3081233 ± 6% +57.1% 4839628 ± 5% proc-vmstat.numa_foreign 13183834 -13.4% 11419080 ± 2% proc-vmstat.numa_hit 13152450 -13.4% 11387779 ± 2% proc-vmstat.numa_local 3081233 ± 6% +57.1% 4839628 ± 5% proc-vmstat.numa_miss 3112617 ± 5% +56.5% 4870930 ± 5% proc-vmstat.numa_other 197.50 ± 25% -41.8% 115.00 ± 25% interrupts.CPU11.NMI:Non-maskable_interrupts 197.50 ± 25% -41.8% 115.00 ± 25% interrupts.CPU11.PMI:Performance_monitoring_interrupts 191.25 ± 23% -42.6% 109.75 ± 26% interrupts.CPU12.NMI:Non-maskable_interrupts 191.25 ± 23% -42.6% 109.75 ± 26% interrupts.CPU12.PMI:Performance_monitoring_interrupts 173.50 ± 18% -31.7% 118.50 ± 23% interrupts.CPU13.NMI:Non-maskable_interrupts 173.50 ± 18% -31.7% 118.50 ± 23% interrupts.CPU13.PMI:Performance_monitoring_interrupts 191.50 ± 22% -34.5% 125.50 ± 26% interrupts.CPU15.NMI:Non-maskable_interrupts 191.50 ± 22% -34.5% 125.50 ± 26% interrupts.CPU15.PMI:Performance_monitoring_interrupts 202.50 ± 26% -37.9% 125.75 ± 25% interrupts.CPU17.NMI:Non-maskable_interrupts 202.50 ± 26% -37.9% 125.75 ± 25% interrupts.CPU17.PMI:Performance_monitoring_interrupts 2753 ±100% -99.9% 4.00 ± 39% interrupts.CPU20.RES:Rescheduling_interrupts 9094 ±117% -78.7% 1940 ± 16% interrupts.CPU33.CAL:Function_call_interrupts 2836 ± 35% -31.5% 1943 ± 16% interrupts.CPU38.CAL:Function_call_interrupts 6869 ±138% -99.9% 5.75 ± 85% interrupts.CPU38.RES:Rescheduling_interrupts 2347 ± 14% -17.2% 1943 ± 16% interrupts.CPU39.CAL:Function_call_interrupts 3990 ± 75% -51.4% 1941 ± 16% interrupts.CPU41.CAL:Function_call_interrupts 2353 ± 14% -17.6% 1940 ± 16% interrupts.CPU45.CAL:Function_call_interrupts 2325 ± 14% -16.6% 1938 ± 16% interrupts.CPU49.CAL:Function_call_interrupts 955.00 ± 44% -90.3% 93.00 ±149% interrupts.CPU5.RES:Rescheduling_interrupts 29.75 ± 99% +1516.0% 480.75 ± 94% interrupts.CPU6.RES:Rescheduling_interrupts 159.50 ± 15% -33.5% 106.00 ± 25% interrupts.CPU63.NMI:Non-maskable_interrupts 159.50 ± 15% -33.5% 106.00 ± 25% interrupts.CPU63.PMI:Performance_monitoring_interrupts 2322 ± 14% -17.1% 1924 ± 17% interrupts.CPU65.CAL:Function_call_interrupts 281.50 ± 50% -53.5% 131.00 ± 12% interrupts.CPU7.NMI:Non-maskable_interrupts 281.50 ± 50% -53.5% 131.00 ± 12% interrupts.CPU7.PMI:Performance_monitoring_interrupts 2.50 ± 91% +5730.0% 145.75 ±158% interrupts.CPU73.RES:Rescheduling_interrupts 159.75 ± 84% +145.4% 392.00 ± 36% interrupts.TLB:TLB_shootdowns 2.38 ± 42% -0.9 1.53 perf-stat.i.branch-miss-rate% 3487 -7.4% 3229 perf-stat.i.context-switches 1.98 ± 10% -22.6% 1.53 ± 16% perf-stat.i.cpu-migrations 0.14 ± 52% -0.1 0.01 ± 18% perf-stat.i.dTLB-load-miss-rate% 659751 ± 52% -92.7% 48076 ± 8% perf-stat.i.dTLB-load-misses 0.04 ± 55% -0.0 0.00 ± 12% perf-stat.i.dTLB-store-miss-rate% 94475 ± 55% -90.7% 8798 ± 11% perf-stat.i.dTLB-store-misses 55.83 ± 4% -4.9 50.93 perf-stat.i.iTLB-load-miss-rate% 2649 -2.3% 2589 perf-stat.i.minor-faults 81.20 ± 2% +5.5 86.71 perf-stat.i.node-load-miss-rate% 484257 ± 7% +29.8% 628546 ± 7% perf-stat.i.node-load-misses 62.30 ± 17% +20.4 82.69 ± 4% perf-stat.i.node-store-miss-rate% 514471 ± 3% +31.6% 677042 ± 3% perf-stat.i.node-store-misses 358788 ± 4% -18.9% 290959 ± 4% perf-stat.i.node-stores 2648 -2.2% 2589 perf-stat.i.page-faults 0.08 ± 58% -0.1 0.01 ± 8% perf-stat.overall.dTLB-load-miss-rate% 0.03 ± 55% -0.0 0.00 ± 11% perf-stat.overall.dTLB-store-miss-rate% 57.62 ± 3% -4.4 53.26 perf-stat.overall.iTLB-load-miss-rate% 84.13 +3.6 87.71 perf-stat.overall.node-load-miss-rate% 58.90 ± 2% +11.0 69.93 perf-stat.overall.node-store-miss-rate% 3462 -7.4% 3206 perf-stat.ps.context-switches 1.96 ± 10% -22.6% 1.52 ± 16% perf-stat.ps.cpu-migrations 655168 ± 52% -92.7% 47743 ± 8% perf-stat.ps.dTLB-load-misses 93819 ± 55% -90.7% 8737 ± 11% perf-stat.ps.dTLB-store-misses 2630 -2.3% 2571 perf-stat.ps.minor-faults 480779 ± 7% +29.8% 624079 ± 7% perf-stat.ps.node-load-misses 510737 ± 3% +31.6% 672190 ± 3% perf-stat.ps.node-store-misses 356350 ± 4% -18.9% 289023 ± 4% perf-stat.ps.node-stores 2630 -2.2% 2571 perf-stat.ps.page-faults 14573 ± 8% -23.4% 11161 ± 2% softirqs.CPU0.RCU 14485 ± 13% -24.9% 10882 ± 4% softirqs.CPU1.RCU 14537 ± 10% -26.0% 10762 ± 4% softirqs.CPU10.RCU 14502 ± 10% -26.1% 10723 ± 4% softirqs.CPU11.RCU 14234 ± 9% -19.1% 11517 softirqs.CPU12.RCU 14620 ± 12% -25.2% 10942 softirqs.CPU13.RCU 16181 ± 9% -39.4% 9804 ± 26% softirqs.CPU14.RCU 14249 ± 9% -23.1% 10962 ± 7% softirqs.CPU15.RCU 16345 ± 36% -36.0% 10457 ± 7% softirqs.CPU16.RCU 13746 ± 6% -18.0% 11276 ± 9% softirqs.CPU17.RCU 12917 ± 5% -14.1% 11093 ± 6% softirqs.CPU18.RCU 13142 ± 10% -17.3% 10874 ± 2% softirqs.CPU19.RCU 14030 ± 7% -21.7% 10991 softirqs.CPU2.RCU 14155 ± 4% -16.0% 11894 ± 8% softirqs.CPU20.RCU 20588 ± 5% -6.6% 19220 softirqs.CPU20.SCHED 13883 ± 9% -21.9% 10842 ± 3% softirqs.CPU21.RCU 13766 ± 6% -17.9% 11298 ± 5% softirqs.CPU22.RCU 13611 ± 4% -19.3% 10988 ± 5% softirqs.CPU23.RCU 15069 ± 9% -16.9% 12527 ± 12% softirqs.CPU24.RCU 13603 ± 5% -19.0% 11015 ± 5% softirqs.CPU25.RCU 13213 ± 3% -19.3% 10659 ± 5% softirqs.CPU26.RCU 13608 ± 3% -21.2% 10719 ± 5% softirqs.CPU27.RCU 13584 ± 3% -20.6% 10783 ± 5% softirqs.CPU28.RCU 13707 -19.4% 11043 ± 9% softirqs.CPU29.RCU 13609 ± 2% -19.5% 10949 ± 5% softirqs.CPU30.RCU 13826 ± 6% -19.4% 11137 ± 7% softirqs.CPU31.RCU 14447 ± 4% -23.4% 11060 ± 6% softirqs.CPU32.RCU 14353 ± 3% -21.3% 11291 ± 8% softirqs.CPU33.RCU 14954 ± 5% -24.1% 11357 ± 8% softirqs.CPU34.RCU 14775 ± 6% -24.9% 11102 ± 5% softirqs.CPU35.RCU 14473 ± 6% -23.1% 11125 ± 5% softirqs.CPU36.RCU 14422 ± 4% -23.7% 10997 ± 6% softirqs.CPU37.RCU 14698 ± 6% -23.2% 11293 ± 9% softirqs.CPU38.RCU 14324 ± 8% -19.5% 11537 ± 9% softirqs.CPU39.RCU 14767 ± 9% -21.6% 11582 ± 9% softirqs.CPU4.RCU 14756 ± 6% -24.7% 11116 ± 6% softirqs.CPU41.RCU 14452 ± 7% -22.9% 11143 ± 8% softirqs.CPU42.RCU 14440 ± 4% -22.3% 11220 ± 6% softirqs.CPU43.RCU 14323 ± 10% -22.6% 11081 ± 6% softirqs.CPU44.RCU 15165 ± 7% -26.9% 11090 ± 6% softirqs.CPU45.RCU 15026 ± 8% -26.1% 11108 ± 6% softirqs.CPU46.RCU 14623 ± 6% -21.2% 11521 ± 11% softirqs.CPU47.RCU 14161 ± 7% -23.3% 10861 ± 5% softirqs.CPU48.RCU 14237 ± 12% -21.1% 11227 ± 6% softirqs.CPU49.RCU 14550 ± 9% -23.8% 11082 ± 2% softirqs.CPU5.RCU 16170 ± 7% -27.9% 11654 ± 11% softirqs.CPU51.RCU 67978 ± 12% -21.4% 53439 ± 13% softirqs.CPU51.TIMER 15390 ± 17% -29.1% 10912 ± 5% softirqs.CPU52.RCU 14734 ± 9% -24.5% 11122 ± 2% softirqs.CPU53.RCU 14260 ± 9% -26.3% 10511 ± 6% softirqs.CPU54.RCU 14341 ± 10% -24.2% 10863 ± 5% softirqs.CPU56.RCU 14111 ± 9% -23.5% 10794 ± 5% softirqs.CPU57.RCU 14339 ± 9% -24.8% 10778 ± 6% softirqs.CPU58.RCU 14423 ± 10% -25.2% 10785 ± 5% softirqs.CPU59.RCU 14253 ± 8% -19.3% 11501 ± 18% softirqs.CPU6.RCU 14423 ± 10% -25.1% 10798 ± 4% softirqs.CPU60.RCU 14437 ± 10% -22.5% 11189 ± 7% softirqs.CPU61.RCU 14208 ± 11% -29.0% 10084 ± 12% softirqs.CPU62.RCU 13388 ± 7% -19.9% 10717 ± 2% softirqs.CPU64.RCU 13585 ± 7% -22.9% 10473 ± 4% softirqs.CPU65.RCU 12562 ± 6% -14.6% 10731 ± 11% softirqs.CPU66.RCU 12721 ± 6% -18.9% 10320 ± 5% softirqs.CPU67.RCU 13154 ± 5% -20.2% 10499 ± 3% softirqs.CPU68.RCU 13112 ± 6% -19.9% 10503 ± 4% softirqs.CPU69.RCU 14259 ± 8% -27.6% 10321 ± 9% softirqs.CPU7.RCU 13513 ± 6% -22.1% 10525 ± 3% softirqs.CPU70.RCU 13559 ± 6% -20.5% 10783 ± 3% softirqs.CPU71.RCU 13422 ± 5% -22.9% 10352 ± 3% softirqs.CPU72.RCU 13196 ± 4% -22.1% 10274 ± 5% softirqs.CPU74.RCU 13132 ± 4% -20.6% 10427 ± 4% softirqs.CPU75.RCU 13502 ± 2% -23.3% 10359 ± 6% softirqs.CPU77.RCU 13393 ± 4% -22.2% 10414 ± 5% softirqs.CPU78.RCU 13119 ± 3% -22.6% 10158 ± 6% softirqs.CPU79.RCU 14239 ± 10% -25.4% 10625 ± 5% softirqs.CPU8.RCU 14006 ± 5% -21.6% 10983 ± 8% softirqs.CPU80.RCU 13848 ± 5% -20.5% 11012 ± 8% softirqs.CPU81.RCU 14386 ± 4% -22.4% 11169 ± 6% softirqs.CPU82.RCU 14429 ± 10% -24.4% 10902 ± 6% softirqs.CPU83.RCU 14024 ± 6% -20.2% 11198 ± 11% softirqs.CPU84.RCU 14124 ± 5% -21.4% 11100 ± 8% softirqs.CPU85.RCU 14448 ± 6% -25.5% 10769 ± 7% softirqs.CPU86.RCU 13965 ± 7% -23.5% 10681 ± 6% softirqs.CPU87.RCU 13792 ± 8% -21.7% 10802 ± 5% softirqs.CPU88.RCU 14454 ± 6% -23.8% 11021 ± 8% softirqs.CPU89.RCU 14117 ± 8% -22.7% 10910 ± 4% softirqs.CPU9.RCU 13597 ± 6% -21.3% 10696 ± 8% softirqs.CPU90.RCU 13972 ± 6% -23.5% 10693 ± 5% softirqs.CPU91.RCU 13956 ± 12% -23.2% 10713 ± 7% softirqs.CPU92.RCU 66146 ± 12% -18.1% 54161 ± 5% softirqs.CPU92.TIMER 14347 ± 7% -25.6% 10668 ± 7% softirqs.CPU93.RCU 14787 ± 7% -26.9% 10810 ± 6% softirqs.CPU94.RCU 14463 ± 5% -25.1% 10838 ± 8% softirqs.CPU95.RCU 1353112 ± 5% -22.3% 1050993 ± 4% softirqs.RCU 47.02 ± 9% -9.1 37.95 perf-profile.calltrace.cycles-pp.intel_idle.cpuidle_enter_state.cpuidle_enter.do_idle.cpu_startup_entry 79.13 ± 3% -5.9 73.22 perf-profile.calltrace.cycles-pp.cpuidle_enter_state.cpuidle_enter.do_idle.cpu_startup_entry.start_secondary 80.01 ± 2% -5.6 74.36 perf-profile.calltrace.cycles-pp.cpuidle_enter.do_idle.cpu_startup_entry.start_secondary.secondary_startup_64 1.11 ± 18% +0.4 1.47 ± 8% perf-profile.calltrace.cycles-pp.scheduler_tick.update_process_times.tick_sched_handle.tick_sched_timer.__hrtimer_run_queues 1.27 ± 20% +0.4 1.69 ± 5% perf-profile.calltrace.cycles-pp.native_write_msr.lapic_next_deadline.clockevents_program_event.hrtimer_interrupt.smp_apic_timer_interrupt 0.32 ±101% +0.4 0.76 ± 11% perf-profile.calltrace.cycles-pp.calc_global_load_tick.scheduler_tick.update_process_times.tick_sched_handle.tick_sched_timer 0.51 ± 63% +0.5 0.99 ± 17% perf-profile.calltrace.cycles-pp.ktime_get.tick_irq_enter.irq_enter.smp_apic_timer_interrupt.apic_timer_interrupt 0.14 ±173% +0.5 0.64 ± 11% perf-profile.calltrace.cycles-pp._raw_spin_trylock.rebalance_domains.__softirqentry_text_start.irq_exit.smp_apic_timer_interrupt 1.52 ± 20% +0.5 2.03 ± 5% perf-profile.calltrace.cycles-pp.lapic_next_deadline.clockevents_program_event.hrtimer_interrupt.smp_apic_timer_interrupt.apic_timer_interrupt 0.52 ± 62% +0.5 1.04 ± 16% perf-profile.calltrace.cycles-pp.ktime_get_update_offsets_now.hrtimer_interrupt.smp_apic_timer_interrupt.apic_timer_interrupt.cpuidle_enter_state 3.18 ± 8% +0.6 3.74 ± 8% perf-profile.calltrace.cycles-pp.tick_sched_handle.tick_sched_timer.__hrtimer_run_queues.hrtimer_interrupt.smp_apic_timer_interrupt 2.97 ± 10% +0.6 3.61 ± 8% perf-profile.calltrace.cycles-pp.update_process_times.tick_sched_handle.tick_sched_timer.__hrtimer_run_queues.hrtimer_interrupt 0.00 +0.7 0.66 ± 14% perf-profile.calltrace.cycles-pp.ktime_get.tick_sched_timer.__hrtimer_run_queues.hrtimer_interrupt.smp_apic_timer_interrupt 0.97 ± 74% +1.3 2.22 ± 22% perf-profile.calltrace.cycles-pp.ktime_get.tick_nohz_irq_exit.irq_exit.smp_apic_timer_interrupt.apic_timer_interrupt 1.01 ± 72% +1.3 2.27 ± 22% perf-profile.calltrace.cycles-pp.tick_nohz_irq_exit.irq_exit.smp_apic_timer_interrupt.apic_timer_interrupt.cpuidle_enter_state 7.13 ± 8% +1.4 8.48 ± 4% perf-profile.calltrace.cycles-pp.__hrtimer_run_queues.hrtimer_interrupt.smp_apic_timer_interrupt.apic_timer_interrupt.cpuidle_enter_state 4.00 ± 8% +1.4 5.42 ± 7% perf-profile.calltrace.cycles-pp.tick_sched_timer.__hrtimer_run_queues.hrtimer_interrupt.smp_apic_timer_interrupt.apic_timer_interrupt 5.37 ± 11% +1.6 6.94 ± 8% perf-profile.calltrace.cycles-pp.irq_exit.smp_apic_timer_interrupt.apic_timer_interrupt.cpuidle_enter_state.cpuidle_enter 5.57 ± 17% +1.6 7.18 ± 8% perf-profile.calltrace.cycles-pp.tick_nohz_get_sleep_length.menu_select.do_idle.cpu_startup_entry.start_secondary 4.38 ± 19% +1.6 5.99 ± 11% perf-profile.calltrace.cycles-pp.tick_nohz_next_event.tick_nohz_get_sleep_length.menu_select.do_idle.cpu_startup_entry 9.86 ± 16% +3.1 12.96 ± 2% perf-profile.calltrace.cycles-pp.menu_select.do_idle.cpu_startup_entry.start_secondary.secondary_startup_64 13.67 ± 19% +4.5 18.16 ± 2% perf-profile.calltrace.cycles-pp.hrtimer_interrupt.smp_apic_timer_interrupt.apic_timer_interrupt.cpuidle_enter_state.cpuidle_enter 21.15 ± 12% +6.4 27.60 perf-profile.calltrace.cycles-pp.smp_apic_timer_interrupt.apic_timer_interrupt.cpuidle_enter_state.cpuidle_enter.do_idle 26.11 ± 15% +7.8 33.89 perf-profile.calltrace.cycles-pp.apic_timer_interrupt.cpuidle_enter_state.cpuidle_enter.do_idle.cpu_startup_entry 47.35 ± 9% -9.0 38.31 perf-profile.children.cycles-pp.intel_idle 80.89 ± 3% -5.7 75.19 perf-profile.children.cycles-pp.cpuidle_enter 80.81 ± 3% -5.7 75.12 perf-profile.children.cycles-pp.cpuidle_enter_state 0.49 ± 45% -0.2 0.30 ± 12% perf-profile.children.cycles-pp.timerqueue_add 0.22 ± 32% -0.1 0.13 ± 15% perf-profile.children.cycles-pp.rb_insert_color 0.18 ± 12% -0.1 0.11 ± 29% perf-profile.children.cycles-pp.account_process_tick 0.17 ± 25% -0.1 0.11 ± 13% perf-profile.children.cycles-pp.run_posix_cpu_timers 0.20 ± 14% -0.1 0.14 ± 11% perf-profile.children.cycles-pp.drm_fb_helper_dirty_work 0.15 ± 18% -0.0 0.10 ± 18% perf-profile.children.cycles-pp.rb_erase 0.06 ± 15% +0.0 0.07 ± 14% perf-profile.children.cycles-pp.schedule 0.04 ± 60% +0.0 0.08 ± 23% perf-profile.children.cycles-pp._raw_write_lock 0.07 ± 13% +0.0 0.10 ± 28% perf-profile.children.cycles-pp.execve 0.07 ± 17% +0.0 0.11 ± 18% perf-profile.children.cycles-pp.tick_check_broadcast_expired 0.03 ±100% +0.0 0.07 ± 17% perf-profile.children.cycles-pp.__fprop_inc_percpu_max 0.10 ± 12% +0.0 0.15 ± 5% perf-profile.children.cycles-pp.__might_sleep 0.03 ±100% +0.1 0.08 ± 23% perf-profile.children.cycles-pp.__libc_fork 0.10 ± 36% +0.1 0.16 ± 17% perf-profile.children.cycles-pp.up_read 0.22 ± 14% +0.1 0.28 ± 9% perf-profile.children.cycles-pp.idle_cpu 0.12 ± 21% +0.1 0.20 ± 14% perf-profile.children.cycles-pp.raise_softirq 0.16 ± 15% +0.1 0.23 ± 16% perf-profile.children.cycles-pp.down_read 0.01 ±173% +0.1 0.09 ± 45% perf-profile.children.cycles-pp.timekeeping_advance 0.22 ± 17% +0.1 0.30 ± 7% perf-profile.children.cycles-pp.menu_reflect 0.06 ± 11% +0.1 0.16 ± 77% perf-profile.children.cycles-pp.mmput 0.15 ± 36% +0.1 0.26 ± 15% perf-profile.children.cycles-pp.read_node_page 0.19 ± 33% +0.1 0.29 ± 18% perf-profile.children.cycles-pp.___might_sleep 0.36 ± 20% +0.1 0.46 ± 6% perf-profile.children.cycles-pp.rcu_core 0.19 ± 23% +0.1 0.29 ± 7% perf-profile.children.cycles-pp.trigger_load_balance 0.43 ± 18% +0.1 0.54 ± 6% perf-profile.children.cycles-pp.__intel_pmu_enable_all 0.02 ±173% +0.1 0.13 ± 28% perf-profile.children.cycles-pp.tick_sched_do_timer 0.37 ± 25% +0.1 0.48 ± 15% perf-profile.children.cycles-pp.clear_page_dirty_for_io 0.16 ± 18% +0.1 0.28 ± 10% perf-profile.children.cycles-pp.mutex_lock 0.09 ±108% +0.1 0.23 ± 26% perf-profile.children.cycles-pp.wake_up_klogd_work_func 0.37 ± 20% +0.2 0.56 ± 11% perf-profile.children.cycles-pp.f2fs_submit_page_write 0.43 ± 31% +0.3 0.71 ± 9% perf-profile.children.cycles-pp._raw_spin_trylock 0.11 ± 23% +0.3 0.40 ± 32% perf-profile.children.cycles-pp.hrtimer_forward 0.90 ± 18% +0.3 1.21 ± 9% perf-profile.children.cycles-pp._raw_spin_lock_irqsave 1.15 ± 18% +0.4 1.52 ± 8% perf-profile.children.cycles-pp.scheduler_tick 0.40 ± 58% +0.4 0.77 ± 12% perf-profile.children.cycles-pp.calc_global_load_tick 0.62 ± 29% +0.4 1.05 ± 16% perf-profile.children.cycles-pp.ktime_get_update_offsets_now 1.18 ± 17% +0.4 1.61 ± 8% perf-profile.children.cycles-pp.read_tsc 1.56 ± 18% +0.5 2.07 ± 6% perf-profile.children.cycles-pp.lapic_next_deadline 1.75 ± 19% +0.5 2.29 ± 5% perf-profile.children.cycles-pp.native_write_msr 3.23 ± 8% +0.6 3.88 ± 7% perf-profile.children.cycles-pp.tick_sched_handle 3.04 ± 10% +0.7 3.76 ± 7% perf-profile.children.cycles-pp.update_process_times 1.15 ± 49% +1.2 2.31 ± 21% perf-profile.children.cycles-pp.tick_nohz_irq_exit 7.28 ± 8% +1.4 8.72 ± 4% perf-profile.children.cycles-pp.__hrtimer_run_queues 4.07 ± 8% +1.5 5.59 ± 6% perf-profile.children.cycles-pp.tick_sched_timer 5.64 ± 17% +1.6 7.29 ± 8% perf-profile.children.cycles-pp.tick_nohz_get_sleep_length 4.46 ± 19% +1.6 6.10 ± 10% perf-profile.children.cycles-pp.tick_nohz_next_event 6.47 ± 16% +1.8 8.28 ± 7% perf-profile.children.cycles-pp.irq_exit 10.02 ± 16% +3.2 13.17 ± 2% perf-profile.children.cycles-pp.menu_select 5.46 ± 48% +3.9 9.37 ± 5% perf-profile.children.cycles-pp.ktime_get 13.91 ± 18% +4.6 18.54 ± 2% perf-profile.children.cycles-pp.hrtimer_interrupt 21.48 ± 12% +6.5 27.95 perf-profile.children.cycles-pp.smp_apic_timer_interrupt 24.16 ± 13% +7.2 31.34 perf-profile.children.cycles-pp.apic_timer_interrupt 47.25 ± 9% -9.0 38.30 perf-profile.self.cycles-pp.intel_idle 0.19 ± 36% -0.1 0.11 ± 25% perf-profile.self.cycles-pp.rb_insert_color 0.24 ± 36% -0.1 0.15 ± 14% perf-profile.self.cycles-pp.rb_next 0.18 ± 11% -0.1 0.11 ± 29% perf-profile.self.cycles-pp.account_process_tick 0.14 ± 23% -0.1 0.08 ± 21% perf-profile.self.cycles-pp.rb_erase 0.08 ± 20% -0.0 0.03 ±100% perf-profile.self.cycles-pp.cpuidle_reflect 0.04 ± 60% +0.0 0.08 ± 23% perf-profile.self.cycles-pp._raw_write_lock 0.10 ± 22% +0.0 0.14 ± 11% perf-profile.self.cycles-pp.cpuidle_governor_latency_req 0.10 ± 15% +0.0 0.14 ± 7% perf-profile.self.cycles-pp.__might_sleep 0.06 ± 11% +0.0 0.11 ± 16% perf-profile.self.cycles-pp.tick_check_broadcast_expired 0.10 ± 36% +0.1 0.16 ± 14% perf-profile.self.cycles-pp.up_read 0.15 ± 23% +0.1 0.22 ± 10% perf-profile.self.cycles-pp.menu_reflect 0.08 ± 15% +0.1 0.15 ± 14% perf-profile.self.cycles-pp.mutex_lock 0.12 ± 22% +0.1 0.19 ± 19% perf-profile.self.cycles-pp.raise_softirq 0.15 ± 36% +0.1 0.25 ± 13% perf-profile.self.cycles-pp.trigger_load_balance 0.17 ± 31% +0.1 0.27 ± 19% perf-profile.self.cycles-pp.f2fs_do_write_data_page 0.11 ± 36% +0.1 0.21 ± 18% perf-profile.self.cycles-pp.read_node_page 0.10 ± 15% +0.1 0.21 ± 18% perf-profile.self.cycles-pp.pagecache_get_page 0.19 ± 32% +0.1 0.29 ± 16% perf-profile.self.cycles-pp.___might_sleep 0.33 ± 20% +0.1 0.44 ± 8% perf-profile.self.cycles-pp.hrtimer_interrupt 0.33 ± 24% +0.2 0.54 ± 16% perf-profile.self.cycles-pp.tick_sched_timer 0.92 ± 22% +0.2 1.17 ± 4% perf-profile.self.cycles-pp._raw_spin_unlock_irqrestore 0.38 ± 8% +0.3 0.64 ± 17% perf-profile.self.cycles-pp.__softirqentry_text_start 0.11 ± 23% +0.3 0.39 ± 32% perf-profile.self.cycles-pp.hrtimer_forward 0.43 ± 31% +0.3 0.71 ± 9% perf-profile.self.cycles-pp._raw_spin_trylock 0.55 ± 10% +0.3 0.84 ± 21% perf-profile.self.cycles-pp.tick_nohz_next_event 0.45 ± 25% +0.3 0.79 ± 22% perf-profile.self.cycles-pp.ktime_get_update_offsets_now 0.40 ± 61% +0.3 0.74 ± 12% perf-profile.self.cycles-pp.calc_global_load_tick 1.14 ± 17% +0.4 1.57 ± 7% perf-profile.self.cycles-pp.read_tsc 1.75 ± 19% +0.5 2.28 ± 5% perf-profile.self.cycles-pp.native_write_msr 3.62 ± 23% +1.6 5.21 ± 4% perf-profile.self.cycles-pp.menu_select 4.41 ± 58% +3.6 7.99 ± 7% perf-profile.self.cycles-pp.ktime_get 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