Greeting, FYI, we noticed a 8.3% improvement of stress-ng.timerfd.ops_per_sec due to commit: commit: 96d5c61b1fff364edfae607e2bf2a66ee9616ff2 ("[PATCH v5 4/4] printk: use the lockless ringbuffer") url: https://github.com/0day-ci/linux/commits/John-Ogness/printk-replace-ringbuffer/20200709-212623 base: https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git 9ebcfadb0610322ac537dd7aa5d9cbc2b2894c68 in testcase: stress-ng on test machine: 96 threads Intel(R) Xeon(R) Gold 6252 CPU @ 2.10GHz with 256G memory with following parameters: nr_threads: 100% disk: 1HDD testtime: 30s class: interrupt cpufreq_governor: performance ucode: 0x5002f01 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: interrupt/gcc-9/performance/1HDD/x86_64-rhel-8.3/100%/debian-10.4-x86_64-20200603.cgz/lkp-csl-2sp6/stress-ng/30s/0x5002f01 commit: 72621a0b10 ("Revert "printk: lock/unlock console only for new logbuf entries"") 96d5c61b1f ("printk: use the lockless ringbuffer") 72621a0b1077a8ad 96d5c61b1fff364edfae607e2bf ---------------- --------------------------- %stddev %change %stddev \ | \ 2.274e+08 +18.6% 2.697e+08 stress-ng.sigq.ops 7580582 +18.6% 8991276 stress-ng.sigq.ops_per_sec 1.513e+08 ± 5% -8.3% 1.387e+08 ± 2% stress-ng.time.involuntary_context_switches 3.768e+08 ± 3% -5.9% 3.544e+08 ± 2% stress-ng.time.voluntary_context_switches 1.598e+09 ± 2% +8.3% 1.73e+09 stress-ng.timerfd.ops 53265971 ± 2% +8.3% 57674750 stress-ng.timerfd.ops_per_sec 3.716e+08 ± 2% +10.7% 4.115e+08 ± 3% cpuidle.C1.time 174505 ± 10% -14.5% 149157 ± 13% numa-meminfo.node0.AnonHugePages 32959 +2.1% 33668 proc-vmstat.nr_slab_reclaimable 90647 ± 43% -60.2% 36039 ±124% numa-vmstat.node0.numa_other 71315 ± 55% +76.4% 125804 ± 35% numa-vmstat.node1.numa_other 1075081 ± 3% -5.6% 1014755 vmstat.system.cs 3762322 +4.7% 3940838 vmstat.system.in 61530 ± 3% -12.1% 54104 ± 4% slabinfo.Acpi-State.active_objs 1209 ± 3% -11.9% 1065 ± 4% slabinfo.Acpi-State.active_slabs 61710 ± 3% -11.9% 54359 ± 4% slabinfo.Acpi-State.num_objs 1209 ± 3% -11.9% 1065 ± 4% slabinfo.Acpi-State.num_slabs 47136 ± 5% +6.0% 49962 ± 6% softirqs.CPU11.SCHED 45028 ± 2% +22.3% 55067 ± 10% softirqs.CPU16.SCHED 44744 ± 2% +22.1% 54634 ± 5% softirqs.CPU19.SCHED 45345 ± 2% +20.7% 54736 ± 8% softirqs.CPU23.SCHED 51163 ± 8% -10.2% 45932 softirqs.CPU30.SCHED 50701 ± 9% -10.2% 45552 softirqs.CPU36.SCHED 50848 ± 3% -11.0% 45253 softirqs.CPU41.SCHED 46949 ± 6% +17.2% 55030 ± 4% softirqs.CPU51.SCHED 45567 ± 2% +15.4% 52589 ± 11% softirqs.CPU55.SCHED 45734 +13.5% 51922 ± 9% softirqs.CPU64.SCHED 45342 +15.4% 52344 ± 5% softirqs.CPU67.SCHED 45901 +13.4% 52030 ± 9% softirqs.CPU68.SCHED 45578 +16.8% 53235 ± 7% softirqs.CPU69.SCHED 50784 ± 8% -9.3% 46080 softirqs.CPU77.SCHED 1187223 ± 26% -47.3% 626108 ± 43% sched_debug.cfs_rq:/.MIN_vruntime.avg 44095 ± 13% -37.3% 27628 ± 16% sched_debug.cfs_rq:/.load.avg 87004 ± 2% -24.3% 65828 ± 13% sched_debug.cfs_rq:/.load.stddev 1187223 ± 26% -47.3% 626108 ± 43% sched_debug.cfs_rq:/.max_vruntime.avg 87.24 ± 10% -17.7% 71.80 ± 7% sched_debug.cfs_rq:/.nr_spread_over.avg 10.92 ± 8% -25.6% 8.12 ± 10% sched_debug.cfs_rq:/.nr_spread_over.min 95.86 ± 12% -15.1% 81.42 ± 9% sched_debug.cfs_rq:/.nr_spread_over.stddev 133.70 ± 30% -81.5% 24.68 ±173% sched_debug.cfs_rq:/.removed.load_avg.max 58.28 ± 25% -80.1% 11.62 ±173% sched_debug.cfs_rq:/.removed.runnable_avg.max 6.81 ± 25% -77.8% 1.51 ±173% sched_debug.cfs_rq:/.removed.runnable_avg.stddev 744305 ± 35% -57.0% 319901 ± 93% sched_debug.cfs_rq:/.spread0.avg 27562 ± 8% -48.5% 14191 ± 13% sched_debug.cpu.curr->pid.avg 35526 ± 5% -42.5% 20423 ± 11% sched_debug.cpu.curr->pid.max 14383 ± 47% -55.9% 6346 ± 36% sched_debug.cpu.curr->pid.min 39.65 ± 4% +16.5% 46.19 ± 7% sched_debug.cpu.nr_running.avg 1.17 ± 25% -76.2% 0.28 ±163% sched_debug.cpu.nr_uninterruptible.avg 3769782 ± 4% -8.4% 3451639 ± 3% sched_debug.cpu.sched_count.max 0.00 +2.2e+104% 216.75 ±138% interrupts.102:PCI-MSI.31981635-edge.i40e-eth0-TxRx-66 8246728 ± 4% +7.0% 8826785 interrupts.CAL:Function_call_interrupts 65853 ± 7% +35.4% 89155 ± 18% interrupts.CPU19.CAL:Function_call_interrupts 133669 ± 7% +79.6% 240043 ± 33% interrupts.CPU19.RES:Rescheduling_interrupts 85710 ± 6% +13.6% 97401 interrupts.CPU32.CAL:Function_call_interrupts 201257 ± 3% -12.8% 175586 ± 4% interrupts.CPU42.RES:Rescheduling_interrupts 7732 -38.0% 4798 ± 34% interrupts.CPU45.NMI:Non-maskable_interrupts 7732 -38.0% 4798 ± 34% interrupts.CPU45.PMI:Performance_monitoring_interrupts 197808 ± 4% -7.1% 183824 ± 6% interrupts.CPU46.RES:Rescheduling_interrupts 149600 ± 16% +70.4% 254923 ± 25% interrupts.CPU54.RES:Rescheduling_interrupts 150479 ± 16% +64.7% 247795 ± 37% interrupts.CPU57.RES:Rescheduling_interrupts 150695 ± 16% +48.9% 224356 ± 22% interrupts.CPU60.RES:Rescheduling_interrupts 60718 ± 6% +18.7% 72058 ± 3% interrupts.CPU62.CAL:Function_call_interrupts 68390 ± 4% +20.6% 82506 ± 10% interrupts.CPU63.CAL:Function_call_interrupts 0.00 +2.2e+104% 216.25 ±138% interrupts.CPU66.102:PCI-MSI.31981635-edge.i40e-eth0-TxRx-66 62888 ± 4% +22.3% 76902 ± 8% interrupts.CPU7.CAL:Function_call_interrupts 62071 ± 10% +29.5% 80355 ± 10% interrupts.CPU71.CAL:Function_call_interrupts 231484 ± 21% -25.0% 173696 ± 3% interrupts.CPU75.RES:Rescheduling_interrupts 234587 ± 12% -17.0% 194613 ± 13% interrupts.CPU77.RES:Rescheduling_interrupts 209574 ± 3% -15.0% 178038 ± 4% interrupts.CPU83.RES:Rescheduling_interrupts 87531 ± 4% +31.1% 114721 ± 7% interrupts.CPU88.CAL:Function_call_interrupts 7732 -37.8% 4806 ± 34% interrupts.CPU89.NMI:Non-maskable_interrupts 7732 -37.8% 4806 ± 34% interrupts.CPU89.PMI:Performance_monitoring_interrupts 94766 ± 7% +19.1% 112844 ± 10% interrupts.CPU91.CAL:Function_call_interrupts 91308 ± 6% +22.9% 112175 ± 8% interrupts.CPU92.CAL:Function_call_interrupts 87571 ± 11% +31.6% 115238 ± 14% interrupts.CPU94.CAL:Function_call_interrupts 7.54 +13.5% 8.56 ± 19% perf-stat.i.MPKI 1.312e+10 -2.8% 1.276e+10 perf-stat.i.branch-instructions 1.246e+08 -1.4% 1.228e+08 perf-stat.i.branch-misses 71092689 ± 3% -19.7% 57085156 ± 2% perf-stat.i.cache-misses 2.672e+08 -10.2% 2.4e+08 perf-stat.i.cache-references 100471 -4.4% 96054 perf-stat.i.cpu-clock 2.436e+11 -5.8% 2.295e+11 perf-stat.i.cpu-cycles 28918 ± 2% +8.8% 31448 ± 2% perf-stat.i.cycles-between-cache-misses 0.03 ± 5% +0.0 0.05 ± 68% perf-stat.i.dTLB-load-miss-rate% 3585193 ± 5% -17.4% 2960337 ± 3% perf-stat.i.dTLB-load-misses 0.06 +0.0 0.06 ± 11% perf-stat.i.dTLB-store-miss-rate% 6767973 -6.1% 6356168 ± 2% perf-stat.i.dTLB-store-misses 1.05e+10 -1.4% 1.036e+10 perf-stat.i.dTLB-stores 7143251 ± 4% -7.7% 6593711 ± 2% perf-stat.i.iTLB-loads 6.422e+10 -2.4% 6.265e+10 perf-stat.i.instructions 2.55 -2.7% 2.48 perf-stat.i.metric.GHz 0.63 ± 3% +10.7% 0.70 ± 5% perf-stat.i.metric.K/sec 92744 -3.1% 89912 perf-stat.i.minor-faults 87.88 -1.4 86.43 perf-stat.i.node-load-miss-rate% 8868728 ± 13% -46.6% 4739379 ± 3% perf-stat.i.node-loads 94.74 -3.0 91.76 ± 2% perf-stat.i.node-store-miss-rate% 2508354 ± 11% -33.3% 1673742 perf-stat.i.node-stores 691526 -1.6% 680596 perf-stat.i.page-faults 99599 -3.6% 96043 perf-stat.i.task-clock 4.23 -4.5% 4.04 perf-stat.overall.MPKI 0.95 +0.0 0.96 perf-stat.overall.branch-miss-rate% 3.84 -2.4% 3.74 perf-stat.overall.cpi 0.02 ± 3% -0.0 0.02 ± 2% perf-stat.overall.dTLB-load-miss-rate% 0.06 -0.0 0.06 ± 2% perf-stat.overall.dTLB-store-miss-rate% 0.26 +2.5% 0.27 perf-stat.overall.ipc 47.96 +4.3 52.28 ± 3% perf-stat.overall.node-load-miss-rate% 70.13 +2.3 72.43 ± 2% perf-stat.overall.node-store-miss-rate% 1.232e+10 +2.0% 1.257e+10 perf-stat.ps.branch-instructions 1.166e+08 +3.3% 1.205e+08 perf-stat.ps.branch-misses 67786783 -5.2% 64234227 ± 4% perf-stat.ps.cache-misses 1078561 ± 3% -5.5% 1019000 perf-stat.ps.context-switches 1.714e+10 +2.3% 1.753e+10 perf-stat.ps.dTLB-loads 9.794e+09 +2.6% 1.005e+10 perf-stat.ps.dTLB-stores 87676758 +4.4% 91553262 perf-stat.ps.iTLB-load-misses 6.02e+10 +2.2% 6.15e+10 perf-stat.ps.instructions 9026151 -12.8% 7873090 ± 10% perf-stat.ps.node-loads 2511686 -9.8% 2265767 ± 6% perf-stat.ps.node-stores 642630 +1.6% 652856 perf-stat.ps.page-faults 3.27e+13 +2.2% 3.341e+13 perf-stat.total.instructions 26.27 ± 2% -2.7 23.56 ± 2% perf-profile.calltrace.cycles-pp.security_task_kill.group_send_sig_info.kill_pid_info.do_rt_sigqueueinfo.__x64_sys_rt_sigqueueinfo 26.23 ± 2% -2.7 23.52 ± 2% perf-profile.calltrace.cycles-pp.apparmor_task_kill.security_task_kill.group_send_sig_info.kill_pid_info.do_rt_sigqueueinfo 26.45 ± 2% -2.7 23.74 ± 2% perf-profile.calltrace.cycles-pp.group_send_sig_info.kill_pid_info.do_rt_sigqueueinfo.__x64_sys_rt_sigqueueinfo.do_syscall_64 13.52 ± 2% -2.4 11.11 ± 2% perf-profile.calltrace.cycles-pp.aa_get_task_label.apparmor_task_kill.security_task_kill.group_send_sig_info.kill_pid_info 47.08 -2.4 44.67 perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe 47.16 -2.4 44.76 perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe 46.12 -2.3 43.82 perf-profile.calltrace.cycles-pp.kill_pid_info.do_rt_sigqueueinfo.__x64_sys_rt_sigqueueinfo.do_syscall_64.entry_SYSCALL_64_after_hwframe 46.36 -2.3 44.07 perf-profile.calltrace.cycles-pp.do_rt_sigqueueinfo.__x64_sys_rt_sigqueueinfo.do_syscall_64.entry_SYSCALL_64_after_hwframe 46.71 -2.3 44.43 perf-profile.calltrace.cycles-pp.__x64_sys_rt_sigqueueinfo.do_syscall_64.entry_SYSCALL_64_after_hwframe 2.99 ± 14% -1.0 1.98 ± 14% perf-profile.calltrace.cycles-pp.__lll_unlock_wake 2.83 ± 14% -1.0 1.83 ± 15% perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.__lll_unlock_wake 2.80 ± 14% -1.0 1.81 ± 15% perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.__lll_unlock_wake 2.67 ± 14% -0.9 1.73 ± 15% perf-profile.calltrace.cycles-pp.__x64_sys_futex.do_syscall_64.entry_SYSCALL_64_after_hwframe.__lll_unlock_wake 2.63 ± 14% -0.9 1.70 ± 15% perf-profile.calltrace.cycles-pp.do_futex.__x64_sys_futex.do_syscall_64.entry_SYSCALL_64_after_hwframe.__lll_unlock_wake 7.36 ± 3% -0.7 6.70 ± 2% perf-profile.calltrace.cycles-pp.__lll_lock_wait 6.73 ± 3% -0.6 6.14 ± 2% perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.__lll_lock_wait 6.71 ± 3% -0.6 6.13 ± 2% perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.__lll_lock_wait 4.23 ± 4% -0.5 3.77 ± 3% perf-profile.calltrace.cycles-pp.__x64_sys_futex.do_syscall_64.entry_SYSCALL_64_after_hwframe.__lll_lock_wait 4.19 ± 4% -0.5 3.74 ± 3% perf-profile.calltrace.cycles-pp.do_futex.__x64_sys_futex.do_syscall_64.entry_SYSCALL_64_after_hwframe.__lll_lock_wait 5.59 ± 2% -0.4 5.22 ± 2% perf-profile.calltrace.cycles-pp.futex_wait.do_futex.__x64_sys_futex.do_syscall_64.entry_SYSCALL_64_after_hwframe 4.78 ± 2% -0.3 4.47 ± 2% perf-profile.calltrace.cycles-pp.futex_wait_queue_me.futex_wait.do_futex.__x64_sys_futex.do_syscall_64 0.52 ± 2% -0.3 0.25 ±100% perf-profile.calltrace.cycles-pp.__lock_task_sighand.do_send_sig_info.kill_pid_info.do_rt_sigqueueinfo.__x64_sys_rt_sigqueueinfo 4.12 ± 2% -0.2 3.88 ± 2% perf-profile.calltrace.cycles-pp.schedule.futex_wait_queue_me.futex_wait.do_futex.__x64_sys_futex 4.06 ± 2% -0.2 3.81 ± 2% perf-profile.calltrace.cycles-pp.__sched_text_start.schedule.futex_wait_queue_me.futex_wait.do_futex 0.76 ± 4% -0.1 0.62 ± 6% perf-profile.calltrace.cycles-pp._raw_spin_lock.__sched_text_start.schedule.futex_wait_queue_me.futex_wait 0.69 ± 4% -0.1 0.56 ± 6% perf-profile.calltrace.cycles-pp.native_queued_spin_lock_slowpath._raw_spin_lock.__sched_text_start.schedule.futex_wait_queue_me 1.08 ± 3% -0.1 0.99 perf-profile.calltrace.cycles-pp.get_signal.do_signal.__prepare_exit_to_usermode.do_syscall_64.entry_SYSCALL_64_after_hwframe 1.32 ± 2% -0.1 1.24 perf-profile.calltrace.cycles-pp.stack_trace_save_tsk.__account_scheduler_latency.update_stats_enqueue_sleeper.enqueue_entity.enqueue_task_fair 0.75 ± 4% -0.1 0.68 ± 3% perf-profile.calltrace.cycles-pp.dequeue_signal.get_signal.do_signal.__prepare_exit_to_usermode.do_syscall_64 0.96 ± 3% -0.1 0.90 perf-profile.calltrace.cycles-pp.generic_file_buffered_read.new_sync_read.vfs_read.ksys_pread64.do_syscall_64 1.08 ± 3% -0.1 1.02 perf-profile.calltrace.cycles-pp.new_sync_read.vfs_read.ksys_pread64.do_syscall_64.entry_SYSCALL_64_after_hwframe 0.77 -0.1 0.71 perf-profile.calltrace.cycles-pp.__pthread_mutex_lock 0.73 ± 2% -0.0 0.68 ± 3% perf-profile.calltrace.cycles-pp.dequeue_task_fair.__sched_text_start.schedule.futex_wait_queue_me.futex_wait 0.55 +0.0 0.56 perf-profile.calltrace.cycles-pp.select_idle_sibling.select_task_rq_fair.try_to_wake_up.signal_wake_up_state.__send_signal 0.64 ± 2% +0.1 0.70 ± 2% perf-profile.calltrace.cycles-pp.aa_may_signal.apparmor_task_kill.security_task_kill.group_send_sig_info.kill_pid_info 1.47 +0.1 1.55 perf-profile.calltrace.cycles-pp.__x64_sys_futex.do_syscall_64.entry_SYSCALL_64_after_hwframe.pthread_cond_timedwait@@GLIBC_2.3.2 1.43 +0.1 1.51 perf-profile.calltrace.cycles-pp.do_futex.__x64_sys_futex.do_syscall_64.entry_SYSCALL_64_after_hwframe.pthread_cond_timedwait@@GLIBC_2.3.2 1.56 +0.1 1.65 perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.pthread_cond_timedwait@@GLIBC_2.3.2 1.58 +0.1 1.67 perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.pthread_cond_timedwait@@GLIBC_2.3.2 1.79 +0.1 1.88 perf-profile.calltrace.cycles-pp.pthread_cond_timedwait@@GLIBC_2.3.2 0.74 ± 9% +0.2 0.98 ± 4% perf-profile.calltrace.cycles-pp.enqueue_entity.enqueue_task_fair.activate_task.ttwu_do_activate.sched_ttwu_pending 0.76 ± 8% +0.2 1.00 ± 4% perf-profile.calltrace.cycles-pp.ttwu_do_activate.sched_ttwu_pending.__sysvec_call_function_single.asm_call_on_stack.sysvec_call_function_single 0.76 ± 8% +0.2 1.00 ± 4% perf-profile.calltrace.cycles-pp.activate_task.ttwu_do_activate.sched_ttwu_pending.__sysvec_call_function_single.asm_call_on_stack 0.76 ± 8% +0.2 1.00 ± 4% perf-profile.calltrace.cycles-pp.enqueue_task_fair.activate_task.ttwu_do_activate.sched_ttwu_pending.__sysvec_call_function_single 0.81 ± 8% +0.3 1.07 ± 4% perf-profile.calltrace.cycles-pp.sched_ttwu_pending.__sysvec_call_function_single.asm_call_on_stack.sysvec_call_function_single.asm_sysvec_call_function_single 0.84 ± 8% +0.3 1.09 ± 4% perf-profile.calltrace.cycles-pp.asm_call_on_stack.sysvec_call_function_single.asm_sysvec_call_function_single.finish_task_switch.__sched_text_start 0.85 ± 7% +0.3 1.11 ± 4% perf-profile.calltrace.cycles-pp.sysvec_call_function_single.asm_sysvec_call_function_single.finish_task_switch.__sched_text_start.schedule_idle 0.83 ± 8% +0.3 1.09 ± 4% perf-profile.calltrace.cycles-pp.__sysvec_call_function_single.asm_call_on_stack.sysvec_call_function_single.asm_sysvec_call_function_single.finish_task_switch 0.91 ± 7% +0.3 1.18 ± 4% perf-profile.calltrace.cycles-pp.finish_task_switch.__sched_text_start.schedule_idle.do_idle.cpu_startup_entry 0.88 ± 7% +0.3 1.15 ± 4% perf-profile.calltrace.cycles-pp.asm_sysvec_call_function_single.finish_task_switch.__sched_text_start.schedule_idle.do_idle 1.57 ± 10% +0.4 1.95 ± 5% perf-profile.calltrace.cycles-pp.native_queued_spin_lock_slowpath._raw_spin_lock.try_to_wake_up.wake_up_q.futex_wake 1.60 ± 10% +0.4 1.98 ± 5% perf-profile.calltrace.cycles-pp._raw_spin_lock.try_to_wake_up.wake_up_q.futex_wake.do_futex 4.32 ± 7% +0.7 5.00 ± 3% perf-profile.calltrace.cycles-pp.native_queued_spin_lock_slowpath._raw_spin_lock.__sched_text_start.schedule_idle.do_idle 4.38 ± 6% +0.7 5.06 ± 3% perf-profile.calltrace.cycles-pp._raw_spin_lock.__sched_text_start.schedule_idle.do_idle.cpu_startup_entry 6.08 ± 6% +1.0 7.08 ± 3% perf-profile.calltrace.cycles-pp.__sched_text_start.schedule_idle.do_idle.cpu_startup_entry.start_secondary 6.10 ± 6% +1.0 7.10 ± 3% perf-profile.calltrace.cycles-pp.schedule_idle.do_idle.cpu_startup_entry.start_secondary.secondary_startup_64 5.92 ± 6% +1.1 7.03 ± 3% perf-profile.calltrace.cycles-pp.do_futex.__x64_sys_futex.do_syscall_64.entry_SYSCALL_64_after_hwframe.pthread_cond_signal@@GLIBC_2.3.2 5.94 ± 6% +1.1 7.05 ± 3% perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.pthread_cond_signal@@GLIBC_2.3.2 5.95 ± 6% +1.1 7.07 ± 3% perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.pthread_cond_signal@@GLIBC_2.3.2 5.93 ± 6% +1.1 7.04 ± 3% perf-profile.calltrace.cycles-pp.__x64_sys_futex.do_syscall_64.entry_SYSCALL_64_after_hwframe.pthread_cond_signal@@GLIBC_2.3.2 6.08 ± 6% +1.1 7.20 ± 3% perf-profile.calltrace.cycles-pp.pthread_cond_signal@@GLIBC_2.3.2 9.26 ± 7% +1.8 11.02 ± 3% perf-profile.calltrace.cycles-pp.intel_idle.cpuidle_enter_state.cpuidle_enter.do_idle.cpu_startup_entry 9.55 ± 7% +1.8 11.38 ± 3% perf-profile.calltrace.cycles-pp.cpuidle_enter_state.cpuidle_enter.do_idle.cpu_startup_entry.start_secondary 9.56 ± 7% +1.8 11.40 ± 3% perf-profile.calltrace.cycles-pp.cpuidle_enter.do_idle.cpu_startup_entry.start_secondary.secondary_startup_64 16.74 ± 6% +3.0 19.71 ± 3% perf-profile.calltrace.cycles-pp.do_idle.cpu_startup_entry.start_secondary.secondary_startup_64 16.75 ± 6% +3.0 19.73 ± 3% perf-profile.calltrace.cycles-pp.cpu_startup_entry.start_secondary.secondary_startup_64 16.75 ± 6% +3.0 19.73 ± 3% perf-profile.calltrace.cycles-pp.start_secondary.secondary_startup_64 16.90 ± 6% +3.0 19.93 ± 3% perf-profile.calltrace.cycles-pp.secondary_startup_64 76.06 -2.9 73.12 perf-profile.children.cycles-pp.do_syscall_64 76.41 -2.9 73.48 perf-profile.children.cycles-pp.entry_SYSCALL_64_after_hwframe 26.27 ± 2% -2.7 23.56 ± 2% perf-profile.children.cycles-pp.security_task_kill 26.25 ± 2% -2.7 23.54 ± 2% perf-profile.children.cycles-pp.apparmor_task_kill 26.45 ± 2% -2.7 23.75 ± 2% perf-profile.children.cycles-pp.group_send_sig_info 13.53 ± 2% -2.4 11.12 ± 2% perf-profile.children.cycles-pp.aa_get_task_label 46.12 -2.3 43.83 perf-profile.children.cycles-pp.kill_pid_info 46.36 -2.3 44.07 perf-profile.children.cycles-pp.do_rt_sigqueueinfo 46.72 -2.3 44.44 perf-profile.children.cycles-pp.__x64_sys_rt_sigqueueinfo 3.02 ± 14% -1.0 2.01 ± 14% perf-profile.children.cycles-pp.__lll_unlock_wake 7.39 ± 3% -0.7 6.73 ± 2% perf-profile.children.cycles-pp.__lll_lock_wait 5.47 ± 3% -0.4 5.04 ± 3% perf-profile.children.cycles-pp.schedule 5.59 ± 2% -0.4 5.22 ± 2% perf-profile.children.cycles-pp.futex_wait 4.30 ± 5% -0.4 3.94 ± 2% perf-profile.children.cycles-pp.__prepare_exit_to_usermode 4.79 ± 2% -0.3 4.48 ± 2% perf-profile.children.cycles-pp.futex_wait_queue_me 1.53 ± 3% -0.1 1.41 perf-profile.children.cycles-pp.get_signal 0.66 ± 5% -0.1 0.56 ± 3% perf-profile.children.cycles-pp.switch_mm_irqs_off 1.09 ± 3% -0.1 0.99 ± 2% perf-profile.children.cycles-pp.dequeue_signal 0.62 ± 4% -0.1 0.54 ± 4% perf-profile.children.cycles-pp.__task_rq_lock 0.89 ± 4% -0.1 0.80 ± 2% perf-profile.children.cycles-pp.__set_current_blocked 0.53 ± 5% -0.1 0.45 ± 3% perf-profile.children.cycles-pp.recalc_sigpending 0.67 ± 5% -0.1 0.60 ± 3% perf-profile.children.cycles-pp.__switch_to 0.52 ± 4% -0.1 0.45 ± 5% perf-profile.children.cycles-pp.futex_wait_setup 1.09 ± 2% -0.1 1.03 perf-profile.children.cycles-pp.new_sync_read 0.97 ± 3% -0.1 0.91 perf-profile.children.cycles-pp.generic_file_buffered_read 0.65 ± 4% -0.1 0.59 ± 2% perf-profile.children.cycles-pp._raw_spin_lock_irq 0.20 ± 5% -0.0 0.15 ± 3% perf-profile.children.cycles-pp.put_task_stack 0.51 ± 3% -0.0 0.46 ± 2% perf-profile.children.cycles-pp.__sigqueue_free 0.77 -0.0 0.72 perf-profile.children.cycles-pp.__pthread_mutex_lock 0.41 ± 4% -0.0 0.36 ± 2% perf-profile.children.cycles-pp.__set_task_blocked 0.64 ± 2% -0.0 0.60 perf-profile.children.cycles-pp.pagecache_get_page 0.30 ± 5% -0.0 0.26 ± 4% perf-profile.children.cycles-pp.fpregs_mark_activate 0.13 ± 9% -0.0 0.10 ± 7% perf-profile.children.cycles-pp.switch_fpu_return 0.24 ± 4% -0.0 0.21 ± 3% perf-profile.children.cycles-pp.kmem_cache_free 0.52 ± 2% -0.0 0.49 ± 2% perf-profile.children.cycles-pp.__lock_task_sighand 0.46 ± 2% -0.0 0.44 ± 2% perf-profile.children.cycles-pp.signal_setup_done 0.26 -0.0 0.23 ± 2% perf-profile.children.cycles-pp.mark_wake_futex 0.20 ± 2% -0.0 0.18 ± 2% perf-profile.children.cycles-pp.file_remove_privs 0.15 -0.0 0.13 ± 3% perf-profile.children.cycles-pp.dentry_needs_remove_privs 0.14 ± 3% -0.0 0.12 perf-profile.children.cycles-pp.__unwind_start 0.07 ± 5% -0.0 0.06 ± 7% perf-profile.children.cycles-pp.clockevents_program_event 0.12 ± 4% -0.0 0.11 perf-profile.children.cycles-pp.security_inode_need_killpriv 0.07 ± 7% -0.0 0.05 perf-profile.children.cycles-pp.__vfs_getxattr 0.18 ± 2% -0.0 0.17 ± 4% perf-profile.children.cycles-pp.__orc_find 0.08 +0.0 0.09 perf-profile.children.cycles-pp.task_curr 0.10 ± 4% +0.0 0.11 perf-profile.children.cycles-pp.hrtimer_cancel 0.15 +0.0 0.16 ± 2% perf-profile.children.cycles-pp.check_kill_permission 0.06 ± 7% +0.0 0.07 perf-profile.children.cycles-pp.set_next_task_idle 0.15 ± 4% +0.0 0.17 ± 3% perf-profile.children.cycles-pp.__might_sleep 0.08 ± 5% +0.0 0.10 ± 4% perf-profile.children.cycles-pp.__next_timer_interrupt 0.13 ± 3% +0.0 0.15 ± 2% perf-profile.children.cycles-pp._find_next_bit 0.81 +0.0 0.82 perf-profile.children.cycles-pp.select_idle_sibling 0.28 +0.0 0.30 perf-profile.children.cycles-pp.__copy_siginfo_from_user 0.73 +0.0 0.75 perf-profile.children.cycles-pp.getuid 0.41 +0.0 0.43 perf-profile.children.cycles-pp.available_idle_cpu 0.43 ± 2% +0.0 0.46 perf-profile.children.cycles-pp._copy_from_user 0.93 +0.0 0.97 perf-profile.children.cycles-pp.dequeue_entity 0.42 +0.0 0.46 perf-profile.children.cycles-pp.menu_select 0.11 ± 6% +0.0 0.16 ± 5% perf-profile.children.cycles-pp.flush_smp_call_function_from_idle 0.64 ± 2% +0.1 0.70 ± 2% perf-profile.children.cycles-pp.aa_may_signal 1.79 +0.1 1.89 perf-profile.children.cycles-pp.pthread_cond_timedwait@@GLIBC_2.3.2 1.83 ± 3% +0.3 2.11 perf-profile.children.cycles-pp.finish_task_switch 2.64 ± 3% +0.3 2.98 ± 2% perf-profile.children.cycles-pp.asm_call_on_stack 2.03 ± 4% +0.4 2.39 ± 2% perf-profile.children.cycles-pp.sysvec_call_function_single 1.99 ± 4% +0.4 2.35 ± 2% perf-profile.children.cycles-pp.__sysvec_call_function_single 2.09 ± 4% +0.4 2.46 ± 2% perf-profile.children.cycles-pp.asm_sysvec_call_function_single 2.04 ± 4% +0.4 2.45 ± 2% perf-profile.children.cycles-pp.sched_ttwu_pending 11.57 +0.6 12.15 perf-profile.children.cycles-pp.__sched_text_start 17.81 +0.6 18.45 perf-profile.children.cycles-pp.enqueue_task_fair 17.83 +0.6 18.47 perf-profile.children.cycles-pp.activate_task 17.83 +0.6 18.48 perf-profile.children.cycles-pp.ttwu_do_activate 16.12 +0.6 16.77 perf-profile.children.cycles-pp.update_stats_enqueue_sleeper 16.08 +0.6 16.72 perf-profile.children.cycles-pp.__account_scheduler_latency 17.16 +0.7 17.84 perf-profile.children.cycles-pp.enqueue_entity 25.29 +0.7 26.00 perf-profile.children.cycles-pp.try_to_wake_up 14.49 +0.7 15.20 perf-profile.children.cycles-pp._raw_spin_lock_irqsave 13.01 ± 4% +0.9 13.90 perf-profile.children.cycles-pp._raw_spin_lock 6.16 ± 6% +1.0 7.18 ± 3% perf-profile.children.cycles-pp.schedule_idle 6.09 ± 6% +1.1 7.20 ± 3% perf-profile.children.cycles-pp.pthread_cond_signal@@GLIBC_2.3.2 25.45 ± 3% +1.7 27.18 perf-profile.children.cycles-pp.native_queued_spin_lock_slowpath 9.33 ± 7% +1.8 11.12 ± 3% perf-profile.children.cycles-pp.intel_idle 9.64 ± 7% +1.9 11.50 ± 3% perf-profile.children.cycles-pp.cpuidle_enter_state 9.64 ± 7% +1.9 11.50 ± 3% perf-profile.children.cycles-pp.cpuidle_enter 16.75 ± 6% +3.0 19.73 ± 3% perf-profile.children.cycles-pp.start_secondary 16.90 ± 6% +3.0 19.93 ± 3% perf-profile.children.cycles-pp.secondary_startup_64 16.90 ± 6% +3.0 19.93 ± 3% perf-profile.children.cycles-pp.cpu_startup_entry 16.89 ± 6% +3.0 19.91 ± 3% perf-profile.children.cycles-pp.do_idle 13.42 ± 2% -2.4 11.04 ± 2% perf-profile.self.cycles-pp.aa_get_task_label 0.88 ± 4% -0.1 0.77 perf-profile.self.cycles-pp._raw_spin_lock 0.51 ± 5% -0.1 0.41 ± 3% perf-profile.self.cycles-pp.switch_mm_irqs_off 0.43 ± 5% -0.1 0.35 ± 4% perf-profile.self.cycles-pp.futex_wait_queue_me 0.44 ± 6% -0.1 0.37 ± 3% perf-profile.self.cycles-pp.recalc_sigpending 0.63 ± 5% -0.1 0.56 ± 3% perf-profile.self.cycles-pp.__switch_to 0.52 ± 4% -0.1 0.45 ± 2% perf-profile.self.cycles-pp._raw_spin_lock_irq 0.73 -0.1 0.67 perf-profile.self.cycles-pp.__pthread_mutex_lock 0.20 ± 5% -0.0 0.15 ± 3% perf-profile.self.cycles-pp.put_task_stack 0.51 ± 3% -0.0 0.46 ± 2% perf-profile.self.cycles-pp.__sigqueue_free 0.30 ± 3% -0.0 0.26 ± 9% perf-profile.self.cycles-pp.futex_wait_setup 0.21 ± 3% -0.0 0.17 ± 4% perf-profile.self.cycles-pp.pagecache_get_page 0.29 ± 4% -0.0 0.25 ± 4% perf-profile.self.cycles-pp.__lll_lock_wait 0.29 ± 5% -0.0 0.25 ± 4% perf-profile.self.cycles-pp.fpregs_mark_activate 0.35 ± 3% -0.0 0.32 perf-profile.self.cycles-pp.generic_file_buffered_read 0.13 ± 8% -0.0 0.10 ± 8% perf-profile.self.cycles-pp.switch_fpu_return 0.18 -0.0 0.16 ± 4% perf-profile.self.cycles-pp.simple_write_end 0.12 ± 3% -0.0 0.10 ± 8% perf-profile.self.cycles-pp.ktime_get 0.10 ± 10% -0.0 0.08 ± 5% perf-profile.self.cycles-pp.wake_up_q 0.15 ± 3% -0.0 0.13 perf-profile.self.cycles-pp.select_task_rq_fair 0.08 -0.0 0.07 ± 7% perf-profile.self.cycles-pp.generic_file_write_iter 0.18 ± 2% -0.0 0.17 ± 4% perf-profile.self.cycles-pp.__orc_find 0.11 ± 3% -0.0 0.10 perf-profile.self.cycles-pp.__unqueue_futex 0.08 -0.0 0.07 perf-profile.self.cycles-pp.arch_stack_walk 0.08 +0.0 0.09 perf-profile.self.cycles-pp.task_curr 0.19 ± 2% +0.0 0.21 ± 2% perf-profile.self.cycles-pp.prepare_signal 0.13 ± 3% +0.0 0.15 ± 3% perf-profile.self.cycles-pp.__dequeue_signal 0.13 ± 3% +0.0 0.14 ± 3% perf-profile.self.cycles-pp._find_next_bit 0.09 ± 4% +0.0 0.11 perf-profile.self.cycles-pp.menu_select 0.41 +0.0 0.42 ± 2% perf-profile.self.cycles-pp.available_idle_cpu 0.63 ± 3% +0.1 0.70 ± 2% perf-profile.self.cycles-pp.aa_may_signal 25.44 ± 3% +1.7 27.17 perf-profile.self.cycles-pp.native_queued_spin_lock_slowpath 9.33 ± 7% +1.8 11.12 ± 3% perf-profile.self.cycles-pp.intel_idle stress-ng.sigq.ops 3e+08 +-----------------------------------------------------------------+ | O O O O O O O O O O O O O O O O O O O O O O O | 2.5e+08 |-+ O | |..+.+..+.+..+.+.. .+.. .+..+.+..+.+..+ | | + +.+..+.+. | 2e+08 |-+ | | | 1.5e+08 |-+ | | | 1e+08 |-+ | | | | | 5e+07 |-+ | | | 0 +-----------------------------------------------------------------+ stress-ng.sigq.ops_per_sec 1e+07 +-------------------------------------------------------------------+ 9e+06 |-+O O O O O O O O O O O O O O O O O O O O O O O | | O | 8e+06 |..+.+..+.+..+..+. .+.. .+..+.+..+.+..+ | 7e+06 |-+ +. +.+..+.+. | | | 6e+06 |-+ | 5e+06 |-+ | 4e+06 |-+ | | | 3e+06 |-+ | 2e+06 |-+ | | | 1e+06 |-+ | 0 +-------------------------------------------------------------------+ [*] bisect-good sample [O] bisect-bad sample Disclaimer: Results have been estimated based on internal Intel analysis and are provided for informational purposes only. Any difference in system hardware or software design or configuration may affect actual performance. Thanks, Rong Chen