December 2021 - LKP - Ml01.01.Org

[sched/fair] 3b238896b2: stress-ng.sigsuspend.ops_per_sec -94.4% regression

by kernel test robot

Greeting, FYI, we noticed a -94.4% regression of stress-ng.sigsuspend.ops_per_sec due to commit: commit: 3b238896b2e9b768a7351537345c30897a00d545 ("sched/fair: Make place_entity() use wall-time") https://git.kernel.org/cgit/linux/kernel/git/peterz/queue.git sched/wip.migrate in testcase: stress-ng on test machine: 96 threads 2 sockets Intel(R) Xeon(R) Gold 6252 CPU @ 2.10GHz with 512G memory with following parameters: nr_threads: 100% disk: 1HDD testtime: 60s class: interrupt test: sigsuspend cpufreq_governor: performance ucode: 0x5003102 In addition to that, the commit also has significant impact on the following tests: +------------------+--------------------------------------------------------------------------------+ | testcase: change | stress-ng: stress-ng.sigq.ops_per_sec 32.7% improvement | | test machine | 96 threads 2 sockets Intel(R) Xeon(R) Gold 6252 CPU @ 2.10GHz with 512G memory | | test parameters | class=interrupt | | | cpufreq_governor=performance | | | disk=1HDD | | | nr_threads=100% | | | test=sigq | | | testtime=60s | | | ucode=0x5003102 | +------------------+--------------------------------------------------------------------------------+ If you fix the issue, kindly add following tag Reported-by: kernel test robot <oliver.sang(a)intel.com> Details are as below: --------------------------------------------------------------------------------------------------> To reproduce: git clone https://github.com/intel/lkp-tests.git cd lkp-tests sudo bin/lkp install job.yaml # job file is attached in this email bin/lkp split-job --compatible job.yaml # generate the yaml file for lkp run sudo bin/lkp run generated-yaml-file # if come across any failure that blocks the test, # please remove ~/.lkp and /lkp dir to run from a clean state. ========================================================================================= class/compiler/cpufreq_governor/disk/kconfig/nr_threads/rootfs/tbox_group/test/testcase/testtime/ucode: interrupt/gcc-9/performance/1HDD/x86_64-rhel-8.3/100%/debian-10.4-x86_64-20200603.cgz/lkp-csl-2sp7/sigsuspend/stress-ng/60s/0x5003102 commit: 72e0b13a60 ("sched/fair: Extract __sched_proportion()") 3b238896b2 ("sched/fair: Make place_entity() use wall-time") 72e0b13a60ca4641 3b238896b2e9b768a7351537345 ---------------- --------------------------- %stddev %change %stddev \ | \ 2.367e+08 ± 2% -94.4% 13332865 ± 31% stress-ng.sigsuspend.ops 3944390 ± 2% -94.4% 222205 ± 31% stress-ng.sigsuspend.ops_per_sec 4.74 -3.6 1.13 mpstat.cpu.all.usr% 446.04 -12.9% 388.45 pmeter.Average_Active_Power 86.74 +3.7% 89.91 iostat.cpu.system 4.63 -75.7% 1.13 iostat.cpu.user 35790 ± 21% -36.6% 22688 ± 16% numa-meminfo.node1.Active 32775 ± 6% -30.8% 22680 ± 16% numa-meminfo.node1.Active(anon) 8210 ± 5% -31.7% 5611 ± 17% numa-vmstat.node1.nr_active_anon 8210 ± 5% -31.7% 5611 ± 17% numa-vmstat.node1.nr_zone_active_anon 52868 ± 3% -19.6% 42530 ± 8% meminfo.Active 34766 ± 5% -29.8% 24409 ± 15% meminfo.Active(anon) 50993 +30.0% 66278 ± 8% meminfo.Mapped 14324592 +16.7% 16711317 ± 7% turbostat.IRQ 64.00 -4.9% 60.83 turbostat.PkgTmp 282.15 -15.2% 239.18 turbostat.PkgWatt 174.67 +133.8% 408.33 ± 2% vmstat.procs.r 10202745 -96.4% 367085 ± 31% vmstat.system.cs 218222 +16.9% 255013 ± 6% vmstat.system.in 8644 ± 6% -29.9% 6064 ± 15% proc-vmstat.nr_active_anon 70400 +1.5% 71423 proc-vmstat.nr_anon_pages 75563 +4.7% 79130 proc-vmstat.nr_inactive_anon 12754 ± 2% +30.6% 16658 ± 9% proc-vmstat.nr_mapped 8644 ± 6% -29.9% 6064 ± 15% proc-vmstat.nr_zone_active_anon 75563 +4.7% 79130 proc-vmstat.nr_zone_inactive_anon 17947 ± 3% +11.7% 20055 ± 2% proc-vmstat.pgreuse 7.04 ± 7% +55.2% 10.94 ± 10% perf-stat.i.MPKI 1.412e+10 -77.8% 3.134e+09 ± 4% perf-stat.i.branch-instructions 1.05 -0.2 0.80 ± 4% perf-stat.i.branch-miss-rate% 1.303e+08 -82.6% 22666821 ± 9% perf-stat.i.branch-misses 12.67 ± 5% +8.3 20.95 ± 14% perf-stat.i.cache-miss-rate% 63190625 -40.7% 37457750 perf-stat.i.cache-misses 5.063e+08 ± 7% -63.5% 1.849e+08 ± 14% perf-stat.i.cache-references 10634656 -96.4% 380197 ± 31% perf-stat.i.context-switches 3.48 +332.7% 15.05 ± 4% perf-stat.i.cpi 35031 ± 77% -75.9% 8439 ± 62% perf-stat.i.cpu-migrations 3959 +65.5% 6554 perf-stat.i.cycles-between-cache-misses 0.14 ± 2% -0.1 0.02 ± 8% perf-stat.i.dTLB-load-miss-rate% 28864098 ± 3% -96.9% 895165 ± 12% perf-stat.i.dTLB-load-misses 2.044e+10 -76.5% 4.8e+09 ± 4% perf-stat.i.dTLB-loads 0.08 ± 2% -0.1 0.01 ± 8% perf-stat.i.dTLB-store-miss-rate% 9936875 ± 2% -97.7% 224950 ± 12% perf-stat.i.dTLB-store-misses 1.245e+10 -76.9% 2.88e+09 ± 4% perf-stat.i.dTLB-stores 45.89 +25.7 71.62 ± 14% perf-stat.i.iTLB-load-miss-rate% 65254283 -82.2% 11601129 ± 31% perf-stat.i.iTLB-load-misses 76304341 -94.5% 4233425 ± 43% perf-stat.i.iTLB-loads 7.117e+10 -76.9% 1.646e+10 ± 4% perf-stat.i.instructions 0.30 -66.1% 0.10 ± 3% perf-stat.i.ipc 14.03 +12.0% 15.71 ± 3% perf-stat.i.major-faults 1140 -87.8% 138.82 ± 14% perf-stat.i.metric.K/sec 494.89 -76.9% 114.44 ± 4% perf-stat.i.metric.M/sec 3956 +3.8% 4106 perf-stat.i.minor-faults 86.26 +1.7 88.00 perf-stat.i.node-load-miss-rate% 3712220 ± 2% -15.2% 3149523 ± 2% perf-stat.i.node-load-misses 569634 ± 4% -29.0% 404349 ± 2% perf-stat.i.node-loads 6825744 -56.3% 2982359 perf-stat.i.node-store-misses 3970 +3.8% 4122 perf-stat.i.page-faults 7.12 ± 8% +56.7% 11.15 ± 10% perf-stat.overall.MPKI 0.92 -0.2 0.70 ± 6% perf-stat.overall.branch-miss-rate% 12.54 ± 6% +8.4 20.93 ± 15% perf-stat.overall.cache-miss-rate% 3.57 +333.7% 15.50 ± 4% perf-stat.overall.cpi 4022 +67.8% 6750 perf-stat.overall.cycles-between-cache-misses 0.14 -0.1 0.02 ± 9% perf-stat.overall.dTLB-load-miss-rate% 0.08 ± 2% -0.1 0.01 ± 9% perf-stat.overall.dTLB-store-miss-rate% 46.10 +26.9 73.01 ± 14% perf-stat.overall.iTLB-load-miss-rate% 0.28 -76.9% 0.06 ± 4% perf-stat.overall.ipc 86.61 +1.8 88.44 perf-stat.overall.node-load-miss-rate% 1.392e+10 -77.9% 3.079e+09 ± 4% perf-stat.ps.branch-instructions 1.282e+08 -83.1% 21686785 ± 10% perf-stat.ps.branch-misses 62297008 -40.5% 37066532 perf-stat.ps.cache-misses 4.989e+08 ± 7% -63.7% 1.812e+08 ± 14% perf-stat.ps.cache-references 10481921 -96.5% 367777 ± 32% perf-stat.ps.context-switches 34342 ± 79% -77.1% 7880 ± 61% perf-stat.ps.cpu-migrations 28488586 ± 3% -96.8% 916071 ± 13% perf-stat.ps.dTLB-load-misses 2.015e+10 -76.6% 4.724e+09 ± 4% perf-stat.ps.dTLB-loads 9798129 ± 2% -97.7% 221457 ± 12% perf-stat.ps.dTLB-store-misses 1.227e+10 -76.9% 2.838e+09 ± 3% perf-stat.ps.dTLB-stores 64325540 -82.3% 11412802 ± 31% perf-stat.ps.iTLB-load-misses 75210289 -94.5% 4140345 ± 43% perf-stat.ps.iTLB-loads 7.013e+10 -76.9% 1.618e+10 ± 4% perf-stat.ps.instructions 3656767 ± 2% -15.0% 3107908 perf-stat.ps.node-load-misses 565533 ± 4% -28.2% 406263 ± 2% perf-stat.ps.node-loads 6725699 -56.2% 2945119 perf-stat.ps.node-store-misses 4.44e+12 -77.0% 1.023e+12 ± 4% perf-stat.total.instructions 11468 ± 12% -38.8% 7014 ± 10% softirqs.CPU0.RCU 10882 ± 27% -49.7% 5471 ± 15% softirqs.CPU1.RCU 9406 ± 26% -52.9% 4428 ± 11% softirqs.CPU10.RCU 8925 ± 13% -45.4% 4872 ± 20% softirqs.CPU11.RCU 9296 ± 17% -51.1% 4548 ± 16% softirqs.CPU12.RCU 8862 ± 15% -50.2% 4411 ± 11% softirqs.CPU13.RCU 8675 ± 16% -44.3% 4834 ± 15% softirqs.CPU14.RCU 8721 ± 14% -48.6% 4486 ± 14% softirqs.CPU15.RCU 10023 ± 18% -50.2% 4986 ± 20% softirqs.CPU16.RCU 9778 ± 17% -55.9% 4311 ± 13% softirqs.CPU17.RCU 9321 ± 19% -49.9% 4670 ± 7% softirqs.CPU18.RCU 9657 ± 17% -48.5% 4971 ± 19% softirqs.CPU19.RCU 9298 ± 12% -45.9% 5033 ± 10% softirqs.CPU2.RCU 9851 ± 13% -48.0% 5121 ± 17% softirqs.CPU20.RCU 9614 ± 14% -50.7% 4742 ± 16% softirqs.CPU21.RCU 9729 ± 21% -52.6% 4609 ± 15% softirqs.CPU22.RCU 9745 ± 19% -49.8% 4894 ± 14% softirqs.CPU23.RCU 9318 ± 22% -54.5% 4238 ± 12% softirqs.CPU24.RCU 9183 ± 22% -53.2% 4295 ± 7% softirqs.CPU25.RCU 9147 ± 21% -45.0% 5033 ± 44% softirqs.CPU26.RCU 9011 ± 20% -53.1% 4228 ± 7% softirqs.CPU27.RCU 9126 ± 16% -55.4% 4074 ± 10% softirqs.CPU28.RCU 9000 ± 19% -54.6% 4084 ± 10% softirqs.CPU29.RCU 9629 ± 4% -42.9% 5496 ± 21% softirqs.CPU3.RCU 9209 ± 15% -53.8% 4250 ± 10% softirqs.CPU30.RCU 8917 ± 18% -51.3% 4340 ± 12% softirqs.CPU31.RCU 8722 ± 19% -51.6% 4217 ± 7% softirqs.CPU32.RCU 1901 ± 24% +110.9% 4011 ± 69% softirqs.CPU32.SCHED 8769 ± 21% -52.7% 4148 ± 10% softirqs.CPU33.RCU 9004 ± 22% -55.5% 4004 ± 10% softirqs.CPU34.RCU 8837 ± 19% -54.1% 4052 ± 11% softirqs.CPU35.RCU 8794 ± 19% -52.1% 4210 ± 8% softirqs.CPU36.RCU 8877 ± 17% -55.2% 3974 ± 10% softirqs.CPU37.RCU 8710 ± 19% -53.3% 4070 ± 10% softirqs.CPU38.RCU 8777 ± 19% -53.7% 4060 ± 10% softirqs.CPU39.RCU 1988 ± 18% +124.9% 4471 ± 75% softirqs.CPU39.SCHED 8995 ± 16% -47.6% 4716 ± 13% softirqs.CPU4.RCU 8997 ± 21% -55.4% 4014 ± 9% softirqs.CPU40.RCU 8964 ± 19% -53.5% 4164 ± 12% softirqs.CPU41.RCU 8673 ± 19% -53.7% 4017 ± 11% softirqs.CPU42.RCU 8687 ± 19% -52.1% 4158 ± 13% softirqs.CPU43.RCU 8781 ± 19% -54.2% 4017 ± 12% softirqs.CPU44.RCU 8968 ± 22% -56.0% 3947 ± 13% softirqs.CPU45.RCU 9084 ± 16% -55.3% 4064 ± 11% softirqs.CPU46.RCU 9019 ± 25% -53.2% 4216 ± 10% softirqs.CPU47.RCU 8891 ± 19% -53.9% 4099 ± 8% softirqs.CPU48.RCU 8431 ± 15% -49.8% 4233 ± 11% softirqs.CPU49.RCU 8826 ± 12% -45.6% 4800 ± 11% softirqs.CPU5.RCU 8893 ± 15% -47.3% 4684 ± 17% softirqs.CPU50.RCU 9178 ± 14% -49.6% 4627 ± 14% softirqs.CPU51.RCU 9023 ± 16% -49.3% 4572 ± 19% softirqs.CPU52.RCU 8818 ± 18% -48.8% 4518 ± 19% softirqs.CPU53.RCU 9021 ± 21% -51.9% 4341 ± 14% softirqs.CPU54.RCU 8754 ± 18% -48.5% 4512 ± 14% softirqs.CPU55.RCU 8923 ± 14% -53.2% 4180 ± 11% softirqs.CPU56.RCU 8684 ± 23% -44.1% 4857 ± 21% softirqs.CPU57.RCU 8996 ± 20% -54.7% 4077 ± 12% softirqs.CPU58.RCU 9048 ± 16% -49.3% 4591 ± 11% softirqs.CPU59.RCU 8637 ± 13% -41.6% 5041 ± 19% softirqs.CPU6.RCU 8916 ± 21% -51.9% 4285 ± 8% softirqs.CPU60.RCU 9515 ± 16% -52.1% 4562 ± 9% softirqs.CPU61.RCU 9089 ± 21% -51.8% 4381 ± 12% softirqs.CPU62.RCU 9076 ± 16% -49.4% 4591 ± 14% softirqs.CPU63.RCU 9283 ± 20% -49.7% 4673 ± 12% softirqs.CPU64.RCU 9380 ± 19% -48.0% 4876 ± 18% softirqs.CPU65.RCU 9761 ± 20% -53.8% 4512 ± 16% softirqs.CPU66.RCU 9508 ± 20% -53.9% 4379 ± 13% softirqs.CPU67.RCU 9778 ± 16% -57.3% 4180 ± 13% softirqs.CPU68.RCU 9353 ± 15% -50.0% 4675 ± 21% softirqs.CPU69.RCU 8813 ± 16% -49.1% 4482 ± 14% softirqs.CPU7.RCU 10275 ± 23% -53.5% 4778 ± 18% softirqs.CPU70.RCU 9652 ± 13% -51.8% 4648 ± 7% softirqs.CPU71.RCU 8960 ± 19% -55.3% 4008 ± 9% softirqs.CPU72.RCU 8760 ± 19% -49.9% 4388 ± 14% softirqs.CPU73.RCU 8787 ± 19% -53.9% 4051 ± 11% softirqs.CPU74.RCU 9194 ± 18% -55.9% 4057 ± 8% softirqs.CPU75.RCU 8826 ± 18% -53.4% 4110 ± 9% softirqs.CPU76.RCU 8871 ± 18% -53.7% 4105 ± 6% softirqs.CPU77.RCU 9289 ± 15% -56.6% 4034 ± 8% softirqs.CPU78.RCU 8864 ± 18% -50.7% 4369 ± 11% softirqs.CPU79.RCU 8616 ± 18% -53.3% 4025 ± 11% softirqs.CPU80.RCU 8568 ± 20% -53.8% 3961 ± 7% softirqs.CPU81.RCU 8476 ± 24% -51.7% 4094 ± 7% softirqs.CPU82.RCU 8604 ± 20% -50.9% 4228 ± 14% softirqs.CPU83.RCU 8443 ± 20% -53.1% 3962 ± 7% softirqs.CPU84.RCU 8554 ± 19% -53.7% 3956 ± 9% softirqs.CPU85.RCU 8484 ± 20% -53.2% 3972 ± 10% softirqs.CPU86.RCU 8465 ± 20% -53.2% 3959 ± 8% softirqs.CPU87.RCU 8903 ± 23% -54.9% 4015 ± 11% softirqs.CPU88.RCU 8650 ± 21% -53.8% 3998 ± 9% softirqs.CPU89.RCU 8834 ± 20% -49.0% 4502 ± 7% softirqs.CPU9.RCU 8446 ± 19% -52.1% 4049 ± 15% softirqs.CPU90.RCU 8422 ± 19% -51.0% 4126 ± 12% softirqs.CPU91.RCU 8739 ± 23% -53.6% 4052 ± 14% softirqs.CPU92.RCU 8488 ± 20% -53.4% 3957 ± 12% softirqs.CPU93.RCU 8471 ± 20% -52.0% 4062 ± 13% softirqs.CPU94.RCU 8689 ± 20% -45.3% 4754 ± 15% softirqs.CPU95.RCU 868862 ± 17% -51.3% 423240 ± 9% softirqs.RCU 231896 ± 17% +39.8% 324268 ± 12% softirqs.SCHED 25.93 -21.6 4.29 ± 27% perf-profile.calltrace.cycles-pp.__sigsuspend 23.95 -19.8 4.18 ± 27% perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.__sigsuspend 23.88 -19.7 4.16 ± 27% perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.__sigsuspend 15.12 -11.4 3.76 ± 22% perf-profile.calltrace.cycles-pp.__send_signal.do_send_sig_info.kill_pid_info.kill_something_info.__x64_sys_kill 12.51 -10.8 1.70 ± 40% perf-profile.calltrace.cycles-pp.arch_do_signal_or_restart.exit_to_user_mode_prepare.syscall_exit_to_user_mode.do_syscall_64.entry_SYSCALL_64_after_hwframe 16.34 -10.2 6.18 ± 12% perf-profile.calltrace.cycles-pp.do_send_sig_info.kill_pid_info.kill_something_info.__x64_sys_kill.do_syscall_64 10.99 -9.6 1.41 ± 30% perf-profile.calltrace.cycles-pp.syscall_exit_to_user_mode.do_syscall_64.entry_SYSCALL_64_after_hwframe.__sigsuspend 10.90 -9.5 1.40 ± 29% perf-profile.calltrace.cycles-pp.exit_to_user_mode_prepare.syscall_exit_to_user_mode.do_syscall_64.entry_SYSCALL_64_after_hwframe.__sigsuspend 10.41 -7.9 2.48 ± 26% perf-profile.calltrace.cycles-pp.__x64_sys_rt_sigsuspend.do_syscall_64.entry_SYSCALL_64_after_hwframe.__sigsuspend 10.02 -7.6 2.46 ± 26% perf-profile.calltrace.cycles-pp.sigsuspend.__x64_sys_rt_sigsuspend.do_syscall_64.entry_SYSCALL_64_after_hwframe.__sigsuspend 9.87 -7.4 2.45 ± 26% perf-profile.calltrace.cycles-pp.schedule.sigsuspend.__x64_sys_rt_sigsuspend.do_syscall_64.entry_SYSCALL_64_after_hwframe 9.75 -7.3 2.42 ± 26% perf-profile.calltrace.cycles-pp.__schedule.schedule.sigsuspend.__x64_sys_rt_sigsuspend.do_syscall_64 9.68 -6.7 2.99 ± 24% perf-profile.calltrace.cycles-pp.signal_wake_up_state.__send_signal.do_send_sig_info.kill_pid_info.kill_something_info 7.10 ± 3% -6.0 1.08 ± 29% perf-profile.calltrace.cycles-pp.get_signal.arch_do_signal_or_restart.exit_to_user_mode_prepare.syscall_exit_to_user_mode.do_syscall_64 8.77 -5.9 2.90 ± 24% perf-profile.calltrace.cycles-pp.try_to_wake_up.signal_wake_up_state.__send_signal.do_send_sig_info.kill_pid_info 5.93 ± 3% -5.2 0.72 ± 49% perf-profile.calltrace.cycles-pp.dequeue_signal.get_signal.arch_do_signal_or_restart.exit_to_user_mode_prepare.syscall_exit_to_user_mode 5.21 -5.2 0.00 perf-profile.calltrace.cycles-pp.syscall_exit_to_user_mode.do_syscall_64.entry_SYSCALL_64_after_hwframe.kill 5.13 -5.1 0.00 perf-profile.calltrace.cycles-pp.exit_to_user_mode_prepare.syscall_exit_to_user_mode.do_syscall_64.entry_SYSCALL_64_after_hwframe.kill 4.98 ± 3% -5.0 0.00 perf-profile.calltrace.cycles-pp.__sigqueue_alloc.__send_signal.do_send_sig_info.kill_pid_info.kill_something_info 4.89 ± 3% -4.3 0.61 ± 49% perf-profile.calltrace.cycles-pp.__dequeue_signal.dequeue_signal.get_signal.arch_do_signal_or_restart.exit_to_user_mode_prepare 4.16 -3.7 0.45 ± 72% perf-profile.calltrace.cycles-pp.stress_usr1_handler 3.00 ± 3% -2.5 0.50 ± 71% perf-profile.calltrace.cycles-pp.dequeue_task_fair.__schedule.schedule.sigsuspend.__x64_sys_rt_sigsuspend 3.22 ± 3% -2.4 0.86 ± 46% perf-profile.calltrace.cycles-pp.ttwu_do_activate.try_to_wake_up.signal_wake_up_state.__send_signal.do_send_sig_info 3.15 ± 2% -2.3 0.84 ± 46% perf-profile.calltrace.cycles-pp.enqueue_task_fair.ttwu_do_activate.try_to_wake_up.signal_wake_up_state.__send_signal 2.44 ± 2% -2.2 0.28 ±100% perf-profile.calltrace.cycles-pp.switch_mm_irqs_off.__schedule.schedule.sigsuspend.__x64_sys_rt_sigsuspend 1.94 -1.6 0.31 ±100% perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.stress_usr1_handler 1.75 -1.4 0.30 ±100% perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.stress_usr1_handler 1.74 -1.4 0.30 ±100% perf-profile.calltrace.cycles-pp.syscall_exit_to_user_mode.do_syscall_64.entry_SYSCALL_64_after_hwframe.stress_usr1_handler 1.74 ± 2% -1.4 0.30 ±100% perf-profile.calltrace.cycles-pp.exit_to_user_mode_prepare.syscall_exit_to_user_mode.do_syscall_64.entry_SYSCALL_64_after_hwframe.stress_usr1_handler 1.53 ± 3% -0.9 0.62 ± 46% perf-profile.calltrace.cycles-pp.enqueue_entity.enqueue_task_fair.ttwu_do_activate.try_to_wake_up.signal_wake_up_state 0.87 ± 2% +1.2 2.03 ± 5% perf-profile.calltrace.cycles-pp._raw_spin_lock_irqsave.__lock_task_sighand.do_send_sig_info.kill_pid_info.kill_something_info 0.89 ± 2% +1.2 2.06 ± 5% perf-profile.calltrace.cycles-pp.__lock_task_sighand.do_send_sig_info.kill_pid_info.kill_something_info.__x64_sys_kill 1.16 ± 2% +2.0 3.15 ± 3% perf-profile.calltrace.cycles-pp.aa_may_signal.apparmor_task_kill.security_task_kill.group_send_sig_info.kill_pid_info 21.36 +19.5 40.83 ± 2% perf-profile.calltrace.cycles-pp.aa_get_task_label.apparmor_task_kill.security_task_kill.group_send_sig_info.kill_pid_info 67.71 +26.2 93.92 perf-profile.calltrace.cycles-pp.kill 66.30 +27.0 93.27 perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.kill 66.07 +27.1 93.14 perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.kill 60.72 +32.1 92.80 perf-profile.calltrace.cycles-pp.__x64_sys_kill.do_syscall_64.entry_SYSCALL_64_after_hwframe.kill 59.96 +32.1 92.04 perf-profile.calltrace.cycles-pp.kill_pid_info.kill_something_info.__x64_sys_kill.do_syscall_64.entry_SYSCALL_64_after_hwframe 60.36 +32.1 92.44 perf-profile.calltrace.cycles-pp.kill_something_info.__x64_sys_kill.do_syscall_64.entry_SYSCALL_64_after_hwframe.kill 43.27 +42.0 85.30 ± 2% perf-profile.calltrace.cycles-pp.apparmor_task_kill.security_task_kill.group_send_sig_info.kill_pid_info.kill_something_info 43.35 +42.1 85.46 ± 2% perf-profile.calltrace.cycles-pp.security_task_kill.group_send_sig_info.kill_pid_info.kill_something_info.__x64_sys_kill 43.54 +42.2 85.76 ± 2% perf-profile.calltrace.cycles-pp.group_send_sig_info.kill_pid_info.kill_something_info.__x64_sys_kill.do_syscall_64 26.21 -21.9 4.30 ± 27% perf-profile.children.cycles-pp.__sigsuspend 17.98 -15.8 2.14 ± 26% perf-profile.children.cycles-pp.syscall_exit_to_user_mode 17.79 -15.7 2.04 ± 27% perf-profile.children.cycles-pp.exit_to_user_mode_prepare 14.05 -11.5 2.51 ± 25% perf-profile.children.cycles-pp.schedule 15.15 -11.4 3.77 ± 22% perf-profile.children.cycles-pp.__send_signal 13.88 -11.3 2.59 ± 26% perf-profile.children.cycles-pp.__schedule 12.52 -10.6 1.87 ± 30% perf-profile.children.cycles-pp.arch_do_signal_or_restart 16.34 -10.2 6.19 ± 12% perf-profile.children.cycles-pp.do_send_sig_info 10.42 -7.9 2.48 ± 26% perf-profile.children.cycles-pp.__x64_sys_rt_sigsuspend 10.02 -7.6 2.46 ± 26% perf-profile.children.cycles-pp.sigsuspend 9.69 -6.7 2.99 ± 24% perf-profile.children.cycles-pp.signal_wake_up_state 7.14 ± 3% -6.1 1.08 ± 29% perf-profile.children.cycles-pp.get_signal 8.79 -5.9 2.90 ± 24% perf-profile.children.cycles-pp.try_to_wake_up 5.95 ± 3% -5.2 0.78 ± 29% perf-profile.children.cycles-pp.dequeue_signal 4.98 ± 3% -4.7 0.30 ± 22% perf-profile.children.cycles-pp.__sigqueue_alloc 4.90 ± 3% -4.2 0.66 ± 29% perf-profile.children.cycles-pp.__dequeue_signal 4.30 ± 4% -4.1 0.18 ± 21% perf-profile.children.cycles-pp.inc_rlimit_get_ucounts 4.27 ± 3% -4.0 0.28 ± 26% perf-profile.children.cycles-pp.__sigqueue_free 4.21 ± 3% -3.9 0.27 ± 26% perf-profile.children.cycles-pp.do_dec_rlimit_put_ucounts 3.78 ± 2% -3.3 0.48 ± 30% perf-profile.children.cycles-pp.switch_mm_irqs_off 3.83 -3.3 0.52 ± 31% perf-profile.children.cycles-pp.__x64_sys_rt_sigreturn 3.55 -3.3 0.28 ± 31% perf-profile.children.cycles-pp.__setup_rt_frame 3.49 -2.9 0.57 ± 31% perf-profile.children.cycles-pp.stress_usr1_handler 3.06 -2.8 0.25 ± 31% perf-profile.children.cycles-pp.copy_fpstate_to_sigframe 3.01 ± 3% -2.4 0.62 ± 29% perf-profile.children.cycles-pp.dequeue_task_fair 3.22 ± 2% -2.3 0.95 ± 26% perf-profile.children.cycles-pp.ttwu_do_activate 3.16 ± 2% -2.2 0.93 ± 26% perf-profile.children.cycles-pp.enqueue_task_fair 2.32 -2.1 0.26 ± 30% perf-profile.children.cycles-pp.restore_sigcontext 2.44 -2.0 0.40 ± 23% perf-profile.children.cycles-pp.select_task_rq_fair 2.23 -2.0 0.24 ± 17% perf-profile.children.cycles-pp.pick_next_task_fair 2.21 -2.0 0.22 ± 18% perf-profile.children.cycles-pp.select_idle_sibling 2.51 -1.9 0.65 ± 24% perf-profile.children.cycles-pp.update_curr 1.93 -1.7 0.23 ± 30% perf-profile.children.cycles-pp.fpu__restore_sig 1.90 -1.7 0.22 ± 31% perf-profile.children.cycles-pp.__fpu_restore_sig 1.72 -1.6 0.13 ± 15% perf-profile.children.cycles-pp.select_idle_cpu 2.00 ± 2% -1.6 0.43 ± 25% perf-profile.children.cycles-pp.update_load_avg 1.43 -1.2 0.20 ± 30% perf-profile.children.cycles-pp.restore_fpregs_from_user 1.24 ± 2% -1.2 0.04 ± 71% perf-profile.children.cycles-pp.load_new_mm_cr3 1.50 ± 4% -1.2 0.32 ± 30% perf-profile.children.cycles-pp.recalc_sigpending 1.28 ± 2% -1.1 0.16 ± 29% perf-profile.children.cycles-pp.reweight_entity 1.40 ± 2% -1.1 0.34 ± 30% perf-profile.children.cycles-pp.dequeue_entity 1.58 ± 3% -1.1 0.53 ± 30% perf-profile.children.cycles-pp._raw_spin_lock_irq 1.52 ± 3% -1.0 0.56 ± 32% perf-profile.children.cycles-pp.__set_current_blocked 1.01 -0.9 0.08 ± 21% perf-profile.children.cycles-pp.native_irq_return_iret 1.57 ± 2% -0.9 0.68 ± 26% perf-profile.children.cycles-pp.enqueue_entity 0.97 ± 3% -0.9 0.10 ± 22% perf-profile.children.cycles-pp.__calc_delta 0.97 -0.8 0.14 ± 22% perf-profile.children.cycles-pp.__switch_to 0.89 -0.8 0.07 ± 47% perf-profile.children.cycles-pp.set_next_entity 0.95 -0.8 0.14 ± 19% perf-profile.children.cycles-pp.ttwu_do_wakeup 0.83 -0.8 0.02 ± 99% perf-profile.children.cycles-pp.__switch_to_asm 0.91 -0.8 0.13 ± 21% perf-profile.children.cycles-pp.check_preempt_curr 0.88 -0.8 0.12 ± 34% perf-profile.children.cycles-pp.fpu__clear_user_states 0.80 -0.8 0.04 ± 72% perf-profile.children.cycles-pp._copy_from_user 0.97 ± 2% -0.7 0.25 ± 30% perf-profile.children.cycles-pp.fpregs_mark_activate 0.77 ± 2% -0.7 0.08 ± 17% perf-profile.children.cycles-pp.check_preempt_wakeup 0.74 -0.7 0.06 ± 48% perf-profile.children.cycles-pp.available_idle_cpu 0.86 ± 3% -0.7 0.20 ± 6% perf-profile.children.cycles-pp.stress_sigsuspend 0.67 -0.6 0.04 ± 71% perf-profile.children.cycles-pp.___perf_sw_event 0.67 ± 2% -0.5 0.15 ± 23% perf-profile.children.cycles-pp.__update_load_avg_se 0.52 ± 15% -0.5 0.04 ±101% perf-profile.children.cycles-pp.update_cfs_group 0.49 ± 2% -0.5 0.03 ±100% perf-profile.children.cycles-pp.__might_fault 0.57 ± 2% -0.5 0.12 ± 26% perf-profile.children.cycles-pp.kmem_cache_alloc 0.50 -0.4 0.09 ± 22% perf-profile.children.cycles-pp.__update_load_avg_cfs_rq 0.76 ± 4% -0.4 0.35 ± 31% perf-profile.children.cycles-pp.signal_setup_done 0.41 ± 2% -0.4 0.02 ± 99% perf-profile.children.cycles-pp.copy_user_enhanced_fast_string 0.43 -0.4 0.05 ± 46% perf-profile.children.cycles-pp.perf_trace_sched_wakeup_template 0.55 ± 5% -0.3 0.22 ± 33% perf-profile.children.cycles-pp.__set_task_blocked 0.39 ± 2% -0.3 0.10 ± 27% perf-profile.children.cycles-pp.kmem_cache_free 0.29 ± 8% -0.2 0.05 ± 73% perf-profile.children.cycles-pp.finish_task_switch 0.46 -0.2 0.22 ± 24% perf-profile.children.cycles-pp.update_rq_clock 0.27 ± 7% -0.2 0.04 ± 71% perf-profile.children.cycles-pp.set_next_buddy 0.24 ± 2% -0.2 0.02 ± 99% perf-profile.children.cycles-pp.perf_tp_event 0.26 ± 6% -0.2 0.10 ± 19% perf-profile.children.cycles-pp.cpuacct_charge 0.52 ± 2% -0.1 0.38 ± 2% perf-profile.children.cycles-pp.__entry_text_start 0.47 -0.1 0.36 ± 2% perf-profile.children.cycles-pp.syscall_return_via_sysret 0.14 ± 5% -0.1 0.06 ± 47% perf-profile.children.cycles-pp.complete_signal 0.10 ± 7% -0.1 0.03 ±100% perf-profile.children.cycles-pp.recalc_sigpending_tsk 0.11 ± 5% -0.1 0.05 ± 45% perf-profile.children.cycles-pp.__enqueue_entity 0.08 ± 4% -0.1 0.02 ± 99% perf-profile.children.cycles-pp.ktime_get 0.15 ± 5% -0.1 0.10 ± 47% perf-profile.children.cycles-pp.update_min_vruntime 0.43 ± 3% -0.0 0.38 ± 4% perf-profile.children.cycles-pp.sysvec_apic_timer_interrupt 0.38 ± 2% -0.0 0.34 ± 4% perf-profile.children.cycles-pp.__sysvec_apic_timer_interrupt 0.12 ± 4% -0.0 0.09 ± 16% perf-profile.children.cycles-pp._raw_spin_unlock_irqrestore 0.10 ± 3% -0.0 0.06 ± 7% perf-profile.children.cycles-pp.syscall_exit_to_user_mode_prepare 0.10 ± 3% -0.0 0.06 ± 7% perf-profile.children.cycles-pp.clockevents_program_event 0.37 ± 2% -0.0 0.34 ± 4% perf-profile.children.cycles-pp.hrtimer_interrupt 0.08 ± 5% -0.0 0.06 ± 8% perf-profile.children.cycles-pp.entry_SYSCALL_64_safe_stack 0.08 ± 4% -0.0 0.06 ± 9% perf-profile.children.cycles-pp.syscall_enter_from_user_mode 0.18 ± 4% -0.0 0.16 ± 2% perf-profile.children.cycles-pp.tick_sched_timer 0.02 ± 99% +0.0 0.07 ± 11% perf-profile.children.cycles-pp.from_kuid_munged 0.00 +0.1 0.06 ± 8% perf-profile.children.cycles-pp.map_id_up 0.16 ± 4% +0.1 0.22 ± 3% perf-profile.children.cycles-pp.send_signal 0.00 +0.1 0.06 ± 7% perf-profile.children.cycles-pp.audit_signal_info 0.16 ± 3% +0.1 0.25 ± 2% perf-profile.children.cycles-pp.check_kill_permission 0.14 ± 3% +0.1 0.24 ± 5% perf-profile.children.cycles-pp.prepare_signal 0.00 +0.1 0.13 ± 30% perf-profile.children.cycles-pp.__sched_proportion 0.51 ± 2% +0.2 0.68 ± 3% perf-profile.children.cycles-pp.asm_sysvec_apic_timer_interrupt 0.01 ±223% +0.2 0.18 ± 35% perf-profile.children.cycles-pp.__slab_free 0.00 +0.2 0.23 ± 25% perf-profile.children.cycles-pp.__task_rq_lock 1.38 +0.8 2.22 ± 3% perf-profile.children.cycles-pp._raw_spin_lock_irqsave 0.89 ± 2% +1.2 2.07 ± 5% perf-profile.children.cycles-pp.__lock_task_sighand 0.04 ±146% +1.3 1.34 ± 22% perf-profile.children.cycles-pp.native_queued_spin_lock_slowpath 1.17 ± 2% +2.0 3.17 ± 3% perf-profile.children.cycles-pp.aa_may_signal 93.84 +4.6 98.42 perf-profile.children.cycles-pp.entry_SYSCALL_64_after_hwframe 93.32 +5.0 98.28 perf-profile.children.cycles-pp.do_syscall_64 21.39 +19.6 40.98 ± 2% perf-profile.children.cycles-pp.aa_get_task_label 67.91 +26.2 94.14 perf-profile.children.cycles-pp.kill 59.97 +32.1 92.05 perf-profile.children.cycles-pp.kill_pid_info 60.73 +32.1 92.81 perf-profile.children.cycles-pp.__x64_sys_kill 60.37 +32.1 92.46 perf-profile.children.cycles-pp.kill_something_info 43.35 +42.1 85.46 ± 2% perf-profile.children.cycles-pp.security_task_kill 43.30 +42.1 85.42 ± 2% perf-profile.children.cycles-pp.apparmor_task_kill 43.54 +42.2 85.76 ± 2% perf-profile.children.cycles-pp.group_send_sig_info 4.30 ± 4% -4.1 0.18 ± 21% perf-profile.self.cycles-pp.inc_rlimit_get_ucounts 4.20 ± 3% -3.9 0.27 ± 26% perf-profile.self.cycles-pp.do_dec_rlimit_put_ucounts 2.52 ± 3% -2.1 0.41 ± 31% perf-profile.self.cycles-pp.switch_mm_irqs_off 1.78 ± 2% -1.5 0.30 ± 24% perf-profile.self.cycles-pp.__schedule 1.60 ± 2% -1.4 0.15 ± 30% perf-profile.self.cycles-pp.copy_fpstate_to_sigframe 1.78 ± 2% -1.4 0.35 ± 28% perf-profile.self.cycles-pp._raw_spin_lock 1.24 ± 2% -1.2 0.04 ± 71% perf-profile.self.cycles-pp.load_new_mm_cr3 1.57 ± 3% -1.1 0.44 ± 32% perf-profile.self.cycles-pp._raw_spin_lock_irq 1.40 ± 4% -1.1 0.28 ± 30% perf-profile.self.cycles-pp.recalc_sigpending 1.00 -0.9 0.08 ± 21% perf-profile.self.cycles-pp.native_irq_return_iret 0.96 ± 3% -0.9 0.10 ± 26% perf-profile.self.cycles-pp.__calc_delta 0.90 ± 7% -0.8 0.08 ± 47% perf-profile.self.cycles-pp.signal_wake_up_state 0.95 -0.8 0.14 ± 22% perf-profile.self.cycles-pp.__switch_to 0.82 -0.8 0.03 ±100% perf-profile.self.cycles-pp.restore_fpregs_from_user 0.79 -0.8 0.02 ± 99% perf-profile.self.cycles-pp.__switch_to_asm 0.93 ± 2% -0.7 0.24 ± 30% perf-profile.self.cycles-pp.fpregs_mark_activate 0.72 -0.7 0.06 ± 48% perf-profile.self.cycles-pp.available_idle_cpu 0.81 ± 6% -0.6 0.18 ± 27% perf-profile.self.cycles-pp.update_load_avg 0.66 ± 2% -0.6 0.06 ± 7% perf-profile.self.cycles-pp.select_idle_cpu 0.90 ± 4% -0.5 0.35 ± 25% perf-profile.self.cycles-pp.update_curr 0.65 -0.5 0.14 ± 25% perf-profile.self.cycles-pp.__update_load_avg_se 0.65 ± 3% -0.5 0.18 ± 5% perf-profile.self.cycles-pp.stress_sigsuspend 0.51 ± 16% -0.5 0.04 ±101% perf-profile.self.cycles-pp.update_cfs_group 0.47 ± 5% -0.4 0.06 ± 46% perf-profile.self.cycles-pp.pick_next_task_fair 0.48 -0.4 0.08 ± 46% perf-profile.self.cycles-pp.__update_load_avg_cfs_rq 0.40 ± 2% -0.4 0.02 ± 99% perf-profile.self.cycles-pp.copy_user_enhanced_fast_string 0.51 ± 2% -0.4 0.14 ± 3% perf-profile.self.cycles-pp.entry_SYSCALL_64_after_hwframe 0.38 ± 4% -0.4 0.04 ± 71% perf-profile.self.cycles-pp.enqueue_task_fair 0.38 ± 5% -0.3 0.10 ± 25% perf-profile.self.cycles-pp.enqueue_entity 0.32 ± 2% -0.2 0.08 ± 46% perf-profile.self.cycles-pp.get_signal 0.30 ± 2% -0.2 0.05 ± 45% perf-profile.self.cycles-pp.check_preempt_wakeup 0.30 ± 7% -0.2 0.07 ± 51% perf-profile.self.cycles-pp.dequeue_task_fair 0.28 ± 3% -0.2 0.07 ± 46% perf-profile.self.cycles-pp.select_idle_sibling 0.28 ± 4% -0.2 0.07 ± 47% perf-profile.self.cycles-pp.kmem_cache_alloc 0.24 ± 7% -0.2 0.04 ± 71% perf-profile.self.cycles-pp.set_next_buddy 0.27 ± 2% -0.2 0.08 ± 4% perf-profile.self.cycles-pp.exit_to_user_mode_prepare 0.25 ± 3% -0.2 0.08 ± 8% perf-profile.self.cycles-pp.do_syscall_64 0.22 ± 3% -0.2 0.06 ± 47% perf-profile.self.cycles-pp.select_task_rq_fair 0.26 ± 6% -0.2 0.10 ± 19% perf-profile.self.cycles-pp.cpuacct_charge 0.18 ± 2% -0.1 0.04 ± 71% perf-profile.self.cycles-pp.arch_do_signal_or_restart 0.17 ± 4% -0.1 0.06 ± 49% perf-profile.self.cycles-pp.kmem_cache_free 0.14 ± 4% -0.1 0.04 ± 71% perf-profile.self.cycles-pp.check_preempt_curr 0.46 -0.1 0.36 ± 2% perf-profile.self.cycles-pp.syscall_return_via_sysret 0.18 ± 4% -0.1 0.08 ± 26% perf-profile.self.cycles-pp.__dequeue_signal 0.26 ± 2% -0.1 0.17 ± 4% perf-profile.self.cycles-pp.__entry_text_start 0.10 ± 4% -0.1 0.03 ±100% perf-profile.self.cycles-pp.recalc_sigpending_tsk 0.15 ± 7% -0.0 0.10 ± 47% perf-profile.self.cycles-pp.update_min_vruntime 0.10 ± 4% -0.0 0.05 ± 45% perf-profile.self.cycles-pp.__enqueue_entity 0.09 ± 4% -0.0 0.06 perf-profile.self.cycles-pp.syscall_exit_to_user_mode_prepare 0.08 ± 5% -0.0 0.05 ± 7% perf-profile.self.cycles-pp.entry_SYSCALL_64_safe_stack 0.05 +0.0 0.07 ± 12% perf-profile.self.cycles-pp.kill_pid_info 0.06 ± 6% +0.0 0.09 ± 5% perf-profile.self.cycles-pp.kill_something_info 0.06 ± 7% +0.0 0.10 ± 3% perf-profile.self.cycles-pp.send_signal 0.00 +0.1 0.05 ± 8% perf-profile.self.cycles-pp.audit_signal_info 0.00 +0.1 0.06 ± 9% perf-profile.self.cycles-pp.map_id_up 0.01 ±223% +0.1 0.06 ± 11% perf-profile.self.cycles-pp.do_send_sig_info 0.00 +0.1 0.08 ± 4% perf-profile.self.cycles-pp.check_kill_permission 0.13 ± 2% +0.1 0.23 ± 5% perf-profile.self.cycles-pp.prepare_signal 0.01 ±223% +0.2 0.18 ± 35% perf-profile.self.cycles-pp.__slab_free 1.38 ± 2% +0.8 2.15 ± 4% perf-profile.self.cycles-pp._raw_spin_lock_irqsave 0.04 ±146% +1.3 1.34 ± 22% perf-profile.self.cycles-pp.native_queued_spin_lock_slowpath 1.16 ± 2% +2.0 3.16 ± 3% perf-profile.self.cycles-pp.aa_may_signal 21.28 +19.5 40.80 ± 2% perf-profile.self.cycles-pp.aa_get_task_label 20.65 +20.4 41.10 ± 3% perf-profile.self.cycles-pp.apparmor_task_kill *************************************************************************************************** lkp-csl-2sp7: 96 threads 2 sockets Intel(R) Xeon(R) Gold 6252 CPU @ 2.10GHz with 512G memory ========================================================================================= class/compiler/cpufreq_governor/disk/kconfig/nr_threads/rootfs/tbox_group/test/testcase/testtime/ucode: interrupt/gcc-9/performance/1HDD/x86_64-rhel-8.3/100%/debian-10.4-x86_64-20200603.cgz/lkp-csl-2sp7/sigq/stress-ng/60s/0x5003102 commit: 72e0b13a60 ("sched/fair: Extract __sched_proportion()") 3b238896b2 ("sched/fair: Make place_entity() use wall-time") 72e0b13a60ca4641 3b238896b2e9b768a7351537345 ---------------- --------------------------- %stddev %change %stddev \ | \ 5.846e+08 +32.7% 7.757e+08 stress-ng.sigq.ops 9743950 +32.7% 12928730 stress-ng.sigq.ops_per_sec 31588 ± 2% -12.1% 27768 ± 8% numa-meminfo.node1.Active 447.77 -10.3% 401.63 pmeter.Average_Active_Power 87.16 +1.4% 88.35 iostat.cpu.system 5.16 ± 2% -31.7% 3.53 ± 8% iostat.cpu.user 27354112 ± 21% +22.4% 33484800 ± 3% meminfo.DirectMap2M 48605 ± 3% +9.4% 53170 ± 5% meminfo.Mapped 0.85 ± 2% -0.1 0.75 mpstat.cpu.all.irq% 5.29 ± 2% -1.7 3.61 ± 9% mpstat.cpu.all.usr% 16982026 ± 8% -17.9% 13934268 turbostat.IRQ 64.67 -5.9% 60.83 turbostat.PkgTmp 282.07 -12.0% 248.25 turbostat.PkgWatt 126.17 +40.0% 176.67 vmstat.procs.r 10943409 ± 4% -99.6% 43112 ± 22% vmstat.system.cs 261118 ± 8% -18.1% 213884 vmstat.system.in 8172 ± 3% -12.6% 7145 ± 9% proc-vmstat.nr_active_anon 73157 +1.3% 74140 proc-vmstat.nr_inactive_anon 12085 ± 2% +10.3% 13330 ± 5% proc-vmstat.nr_mapped 8172 ± 3% -12.6% 7145 ± 9% proc-vmstat.nr_zone_active_anon 73157 +1.3% 74140 proc-vmstat.nr_zone_inactive_anon 17619 ± 3% +6.7% 18807 proc-vmstat.pgreuse 9252 ± 10% -28.6% 6603 ± 6% softirqs.CPU0.RCU 5513 ± 74% -57.8% 2325 softirqs.CPU39.SCHED 7004 ± 21% -36.3% 4460 ± 7% softirqs.CPU5.RCU 7001 ± 26% -40.9% 4136 ± 7% softirqs.CPU77.RCU 6640 ± 24% -43.4% 3758 ± 6% softirqs.CPU80.RCU 609663 ± 5% -35.1% 395530 ± 5% softirqs.RCU 5.88 ± 6% -31.2% 4.04 ± 4% perf-stat.i.MPKI 1.573e+10 ± 2% -61.1% 6.113e+09 perf-stat.i.branch-instructions 1.15 -0.2 0.94 perf-stat.i.branch-miss-rate% 1.64e+08 ± 2% -68.6% 51465290 perf-stat.i.branch-misses 13.81 ± 4% +16.9 30.75 perf-stat.i.cache-miss-rate% 63768243 ± 2% -38.1% 39460848 ± 2% perf-stat.i.cache-misses 4.634e+08 ± 3% -72.7% 1.265e+08 ± 2% perf-stat.i.cache-references 11312988 ± 4% -99.7% 39559 ± 23% perf-stat.i.context-switches 3.18 ± 2% +145.0% 7.79 perf-stat.i.cpi 12225 ± 48% -97.9% 257.47 ± 11% perf-stat.i.cpu-migrations 3939 +60.4% 6319 ± 2% perf-stat.i.cycles-between-cache-misses 640967 ± 17% -34.2% 421541 ± 27% perf-stat.i.dTLB-load-misses 2.212e+10 ± 2% -58.9% 9.085e+09 perf-stat.i.dTLB-loads 1.4e+10 ± 2% -55.3% 6.259e+09 perf-stat.i.dTLB-stores 63.59 +33.4 97.03 perf-stat.i.iTLB-load-miss-rate% 82891230 ± 3% -43.3% 47035876 ± 11% perf-stat.i.iTLB-load-misses 46012758 ± 6% -99.1% 423144 ± 12% perf-stat.i.iTLB-loads 7.858e+10 ± 2% -59.4% 3.19e+10 perf-stat.i.instructions 1177 -18.5% 959.77 ± 7% perf-stat.i.instructions-per-iTLB-miss 0.33 ± 2% -54.0% 0.15 perf-stat.i.ipc 717.60 ± 4% -87.7% 88.11 ± 3% perf-stat.i.metric.K/sec 544.80 ± 2% -58.7% 224.75 perf-stat.i.metric.M/sec 3522470 -20.3% 2806803 perf-stat.i.node-load-misses 542899 -24.9% 407696 ± 3% perf-stat.i.node-loads 6453797 -55.3% 2885454 ± 2% perf-stat.i.node-store-misses 5.91 ± 6% -32.8% 3.97 ± 3% perf-stat.overall.MPKI 1.04 -0.2 0.84 perf-stat.overall.branch-miss-rate% 13.78 ± 3% +17.4 31.21 perf-stat.overall.cache-miss-rate% 3.25 ± 2% +146.4% 8.00 perf-stat.overall.cpi 3996 ± 2% +61.7% 6461 ± 2% perf-stat.overall.cycles-between-cache-misses 0.00 ± 11% +0.0 0.00 ± 20% perf-stat.overall.dTLB-load-miss-rate% 0.00 ± 8% +0.0 0.00 ± 14% perf-stat.overall.dTLB-store-miss-rate% 64.33 +34.8 99.10 perf-stat.overall.iTLB-load-miss-rate% 948.15 -27.6% 686.11 ± 10% perf-stat.overall.instructions-per-iTLB-miss 0.31 ± 2% -59.4% 0.13 perf-stat.overall.ipc 1.55e+10 ± 2% -61.2% 6.021e+09 perf-stat.ps.branch-instructions 1.615e+08 ± 2% -68.7% 50558947 perf-stat.ps.branch-misses 62874752 ± 2% -38.1% 38901762 ± 2% perf-stat.ps.cache-misses 4.568e+08 ± 3% -72.7% 1.247e+08 ± 2% perf-stat.ps.cache-references 11155284 ± 4% -99.7% 38803 ± 23% perf-stat.ps.context-switches 11883 ± 49% -97.9% 252.76 ± 11% perf-stat.ps.cpu-migrations 648187 ± 13% -32.2% 439410 ± 20% perf-stat.ps.dTLB-load-misses 2.18e+10 ± 2% -59.0% 8.95e+09 perf-stat.ps.dTLB-loads 1.38e+10 ± 2% -55.3% 6.167e+09 perf-stat.ps.dTLB-stores 81714320 ± 3% -43.3% 46365608 ± 11% perf-stat.ps.iTLB-load-misses 45364914 ± 5% -99.1% 412946 ± 12% perf-stat.ps.iTLB-loads 7.745e+10 ± 2% -59.4% 3.143e+10 perf-stat.ps.instructions 3470769 -20.3% 2765263 perf-stat.ps.node-load-misses 537686 -24.7% 405062 ± 3% perf-stat.ps.node-loads 6359566 -55.3% 2843111 perf-stat.ps.node-store-misses 4.892e+12 ± 2% -59.6% 1.979e+12 perf-stat.total.instructions 17.99 ± 2% -18.0 0.00 perf-profile.calltrace.cycles-pp.__sigtimedwait 16.51 ± 2% -16.5 0.00 perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.__sigtimedwait 16.30 ± 2% -16.3 0.00 perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.__sigtimedwait 15.33 ± 2% -15.3 0.00 perf-profile.calltrace.cycles-pp.__x64_sys_rt_sigtimedwait.do_syscall_64.entry_SYSCALL_64_after_hwframe.__sigtimedwait 14.18 ± 2% -14.2 0.00 perf-profile.calltrace.cycles-pp.do_sigtimedwait.__x64_sys_rt_sigtimedwait.do_syscall_64.entry_SYSCALL_64_after_hwframe.__sigtimedwait 12.68 -12.7 0.00 perf-profile.calltrace.cycles-pp.__send_signal.do_send_sig_info.kill_pid_info.do_rt_sigqueueinfo.__x64_sys_rt_sigqueueinfo 14.13 -11.5 2.67 ± 2% perf-profile.calltrace.cycles-pp.do_send_sig_info.kill_pid_info.do_rt_sigqueueinfo.__x64_sys_rt_sigqueueinfo.do_syscall_64 8.78 -8.8 0.00 perf-profile.calltrace.cycles-pp.signal_wake_up_state.__send_signal.do_send_sig_info.kill_pid_info.do_rt_sigqueueinfo 8.55 -8.6 0.00 perf-profile.calltrace.cycles-pp.schedule_hrtimeout_range_clock.do_sigtimedwait.__x64_sys_rt_sigtimedwait.do_syscall_64.entry_SYSCALL_64_after_hwframe 8.16 -8.2 0.00 perf-profile.calltrace.cycles-pp.try_to_wake_up.signal_wake_up_state.__send_signal.do_send_sig_info.kill_pid_info 7.42 -7.4 0.00 perf-profile.calltrace.cycles-pp.schedule.schedule_hrtimeout_range_clock.do_sigtimedwait.__x64_sys_rt_sigtimedwait.do_syscall_64 7.23 -7.2 0.00 perf-profile.calltrace.cycles-pp.__schedule.schedule.schedule_hrtimeout_range_clock.do_sigtimedwait.__x64_sys_rt_sigtimedwait 5.99 ± 4% -6.0 0.00 perf-profile.calltrace.cycles-pp.syscall_exit_to_user_mode.do_syscall_64.entry_SYSCALL_64_after_hwframe.sigqueue 5.88 ± 4% -5.9 0.00 perf-profile.calltrace.cycles-pp.exit_to_user_mode_prepare.syscall_exit_to_user_mode.do_syscall_64.entry_SYSCALL_64_after_hwframe.sigqueue 0.94 +0.2 1.18 perf-profile.calltrace.cycles-pp.__copy_siginfo_from_user.__x64_sys_rt_sigqueueinfo.do_syscall_64.entry_SYSCALL_64_after_hwframe.syscall 0.65 ± 2% +0.3 0.90 perf-profile.calltrace.cycles-pp.__entry_text_start.syscall 1.58 +0.3 1.85 perf-profile.calltrace.cycles-pp.__x64_sys_rt_sigqueueinfo.do_syscall_64.entry_SYSCALL_64_after_hwframe.syscall 1.12 ± 2% +0.4 1.49 perf-profile.calltrace.cycles-pp.getuid 1.12 +0.4 1.50 perf-profile.calltrace.cycles-pp.__getpid 1.96 +0.4 2.38 perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.syscall 0.79 +0.5 1.27 ± 20% perf-profile.calltrace.cycles-pp._copy_from_user.__copy_siginfo_from_user.__x64_sys_rt_sigqueueinfo.do_syscall_64.entry_SYSCALL_64_after_hwframe 2.16 ± 2% +0.5 2.67 perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.syscall 0.08 ±223% +0.5 0.63 perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.getuid 0.00 +0.6 0.59 perf-profile.calltrace.cycles-pp.__copy_siginfo_from_user.__x64_sys_rt_sigqueueinfo.do_syscall_64.entry_SYSCALL_64_after_hwframe.sigqueue 0.00 +0.6 0.63 perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.__getpid 1.07 ± 5% +0.9 1.98 ± 2% perf-profile.calltrace.cycles-pp._raw_spin_lock_irqsave.__lock_task_sighand.do_send_sig_info.kill_pid_info.do_rt_sigqueueinfo 1.10 ± 5% +0.9 2.02 ± 2% perf-profile.calltrace.cycles-pp.__lock_task_sighand.do_send_sig_info.kill_pid_info.do_rt_sigqueueinfo.__x64_sys_rt_sigqueueinfo 3.54 ± 2% +0.9 4.47 perf-profile.calltrace.cycles-pp.syscall 1.47 ± 2% +1.2 2.63 ± 4% perf-profile.calltrace.cycles-pp.aa_may_signal.apparmor_task_kill.security_task_kill.group_send_sig_info.kill_pid_info 23.78 +14.8 38.63 perf-profile.calltrace.cycles-pp.aa_get_task_label.apparmor_task_kill.security_task_kill.group_send_sig_info.kill_pid_info 75.14 +16.6 91.72 perf-profile.calltrace.cycles-pp.sigqueue 73.04 +17.4 90.39 perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.sigqueue 72.80 +17.4 90.23 perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.sigqueue 65.69 +23.0 88.73 perf-profile.calltrace.cycles-pp.kill_pid_info.do_rt_sigqueueinfo.__x64_sys_rt_sigqueueinfo.do_syscall_64.entry_SYSCALL_64_after_hwframe 66.12 +23.1 89.19 perf-profile.calltrace.cycles-pp.do_rt_sigqueueinfo.__x64_sys_rt_sigqueueinfo.do_syscall_64.entry_SYSCALL_64_after_hwframe.sigqueue 66.65 +23.3 89.92 perf-profile.calltrace.cycles-pp.__x64_sys_rt_sigqueueinfo.do_syscall_64.entry_SYSCALL_64_after_hwframe.sigqueue 51.18 +34.3 85.51 perf-profile.calltrace.cycles-pp.apparmor_task_kill.security_task_kill.group_send_sig_info.kill_pid_info.do_rt_sigqueueinfo 51.27 +34.4 85.69 perf-profile.calltrace.cycles-pp.security_task_kill.group_send_sig_info.kill_pid_info.do_rt_sigqueueinfo.__x64_sys_rt_sigqueueinfo 51.47 +34.5 85.96 perf-profile.calltrace.cycles-pp.group_send_sig_info.kill_pid_info.do_rt_sigqueueinfo.__x64_sys_rt_sigqueueinfo.do_syscall_64 18.11 ± 2% -18.0 0.09 ± 32% perf-profile.children.cycles-pp.__sigtimedwait 15.35 ± 2% -15.3 0.08 ± 34% perf-profile.children.cycles-pp.__x64_sys_rt_sigtimedwait 14.20 ± 2% -14.1 0.07 ± 34% perf-profile.children.cycles-pp.do_sigtimedwait 12.71 -12.4 0.32 ± 6% perf-profile.children.cycles-pp.__send_signal 12.39 -12.4 0.04 ± 72% perf-profile.children.cycles-pp.schedule 12.11 -12.1 0.04 ± 73% perf-profile.children.cycles-pp.__schedule 14.14 -11.5 2.69 ± 2% perf-profile.children.cycles-pp.do_send_sig_info 8.79 -8.8 0.03 ±102% perf-profile.children.cycles-pp.signal_wake_up_state 8.57 -8.6 0.02 ±144% perf-profile.children.cycles-pp.schedule_hrtimeout_range_clock 8.18 -8.2 0.02 ±144% perf-profile.children.cycles-pp.try_to_wake_up 6.93 ± 3% -6.4 0.49 ± 2% perf-profile.children.cycles-pp.exit_to_user_mode_prepare 7.30 ± 3% -6.4 0.92 ± 2% perf-profile.children.cycles-pp.syscall_exit_to_user_mode 0.60 ± 2% -0.3 0.32 ± 6% perf-profile.children.cycles-pp.stress_sigq 0.70 ± 2% -0.2 0.49 ± 2% perf-profile.children.cycles-pp.__might_fault 0.44 -0.2 0.27 ± 3% perf-profile.children.cycles-pp.__might_resched 0.20 ± 4% -0.2 0.04 ± 45% perf-profile.children.cycles-pp.ktime_get 0.16 ± 3% -0.1 0.08 ± 6% perf-profile.children.cycles-pp._raw_spin_unlock_irqrestore 0.44 ± 5% -0.1 0.37 perf-profile.children.cycles-pp.sysvec_apic_timer_interrupt 0.40 ± 5% -0.1 0.33 ± 2% perf-profile.children.cycles-pp.__sysvec_apic_timer_interrupt 0.40 ± 4% -0.1 0.33 ± 2% perf-profile.children.cycles-pp.hrtimer_interrupt 0.68 ± 2% -0.1 0.63 perf-profile.children.cycles-pp.copy_user_generic_unrolled 0.24 ± 5% -0.0 0.20 ± 2% perf-profile.children.cycles-pp.__hrtimer_run_queues 0.10 ± 7% -0.0 0.06 ± 7% perf-profile.children.cycles-pp.clockevents_program_event 0.20 ± 8% -0.0 0.16 ± 3% perf-profile.children.cycles-pp.tick_sched_timer 0.16 ± 4% -0.0 0.12 perf-profile.children.cycles-pp.__might_sleep 0.18 ± 8% -0.0 0.14 ± 3% perf-profile.children.cycles-pp.tick_sched_handle 0.14 ± 9% -0.0 0.11 ± 3% perf-profile.children.cycles-pp.scheduler_tick 0.10 ± 11% -0.0 0.08 perf-profile.children.cycles-pp.task_tick_fair 0.35 -0.0 0.33 ± 2% perf-profile.children.cycles-pp.copy_user_enhanced_fast_string 0.05 ± 8% +0.0 0.06 ± 7% perf-profile.children.cycles-pp.find_vpid 0.05 +0.0 0.06 ± 7% perf-profile.children.cycles-pp.known_siginfo_layout 0.20 ± 4% +0.0 0.22 ± 3% perf-profile.children.cycles-pp.syscall_enter_from_user_mode 0.05 ± 8% +0.0 0.08 perf-profile.children.cycles-pp.map_id_up 0.22 ± 2% +0.0 0.25 ± 2% perf-profile.children.cycles-pp.__x64_sys_getpid 0.06 ± 7% +0.0 0.09 ± 4% perf-profile.children.cycles-pp.from_kuid_munged 0.22 ± 3% +0.0 0.26 ± 2% perf-profile.children.cycles-pp.entry_SYSCALL_64_safe_stack 0.18 ± 2% +0.1 0.23 ± 3% perf-profile.children.cycles-pp.send_signal 0.01 ±223% +0.1 0.06 ± 11% perf-profile.children.cycles-pp.audit_signal_info 0.52 ± 3% +0.1 0.58 ± 2% perf-profile.children.cycles-pp.__task_pid_nr_ns 0.17 ± 5% +0.1 0.23 ± 3% perf-profile.children.cycles-pp.check_kill_permission 0.18 ± 2% +0.1 0.25 ± 3% perf-profile.children.cycles-pp.syscall_exit_to_user_mode_prepare 0.54 ± 4% +0.1 0.60 ± 3% perf-profile.children.cycles-pp.asm_sysvec_apic_timer_interrupt 1.59 ± 2% +0.3 1.84 perf-profile.children.cycles-pp.syscall_return_via_sysret 1.85 ± 2% +0.4 2.24 perf-profile.children.cycles-pp.__entry_text_start 1.41 +0.4 1.82 perf-profile.children.cycles-pp.__copy_siginfo_from_user 1.34 ± 2% +0.4 1.78 perf-profile.children.cycles-pp.getuid 1.34 ± 2% +0.5 1.79 perf-profile.children.cycles-pp.__getpid 1.10 ± 5% +0.9 2.02 ± 2% perf-profile.children.cycles-pp.__lock_task_sighand 3.90 ± 2% +1.1 4.96 perf-profile.children.cycles-pp.syscall 1.48 ± 2% +1.2 2.64 ± 4% perf-profile.children.cycles-pp.aa_may_signal 92.77 +1.8 94.55 perf-profile.children.cycles-pp.entry_SYSCALL_64_after_hwframe 91.95 +1.9 93.88 perf-profile.children.cycles-pp.do_syscall_64 23.82 +14.9 38.74 perf-profile.children.cycles-pp.aa_get_task_label 75.32 +16.7 91.97 perf-profile.children.cycles-pp.sigqueue 65.70 +23.0 88.74 perf-profile.children.cycles-pp.kill_pid_info 66.55 +23.1 89.64 perf-profile.children.cycles-pp.do_rt_sigqueueinfo 68.28 +23.5 91.82 perf-profile.children.cycles-pp.__x64_sys_rt_sigqueueinfo 51.22 +34.4 85.63 perf-profile.children.cycles-pp.apparmor_task_kill 51.28 +34.4 85.69 perf-profile.children.cycles-pp.security_task_kill 51.48 +34.5 85.96 perf-profile.children.cycles-pp.group_send_sig_info 0.60 ± 2% -0.3 0.31 ± 5% perf-profile.self.cycles-pp.stress_sigq 0.43 -0.2 0.27 ± 2% perf-profile.self.cycles-pp.__might_resched 0.82 ± 2% -0.1 0.68 perf-profile.self.cycles-pp.entry_SYSCALL_64_after_hwframe 0.24 ± 2% -0.1 0.14 ± 2% perf-profile.self.cycles-pp.__send_signal 0.19 ± 5% -0.1 0.10 ± 6% perf-profile.self.cycles-pp.__might_fault 0.37 ± 4% -0.1 0.30 ± 2% perf-profile.self.cycles-pp.do_syscall_64 0.65 ± 3% -0.0 0.60 perf-profile.self.cycles-pp.copy_user_generic_unrolled 0.14 ± 3% -0.0 0.10 ± 3% perf-profile.self.cycles-pp.__might_sleep 0.14 ± 5% -0.0 0.11 ± 4% perf-profile.self.cycles-pp.__x64_sys_getuid 0.32 ± 2% -0.0 0.29 ± 2% perf-profile.self.cycles-pp.copy_user_enhanced_fast_string 0.08 ± 4% -0.0 0.06 ± 6% perf-profile.self.cycles-pp._raw_spin_unlock_irqrestore 0.05 +0.0 0.06 ± 6% perf-profile.self.cycles-pp.do_send_sig_info 0.05 ± 8% +0.0 0.07 ± 5% perf-profile.self.cycles-pp.security_task_kill 0.17 ± 4% +0.0 0.18 ± 2% perf-profile.self.cycles-pp.__copy_siginfo_from_user 0.18 ± 4% +0.0 0.20 perf-profile.self.cycles-pp.syscall_enter_from_user_mode 0.06 ± 8% +0.0 0.08 ± 5% perf-profile.self.cycles-pp.check_kill_permission 0.05 +0.0 0.08 ± 6% perf-profile.self.cycles-pp.kill_pid_info 0.21 ± 2% +0.0 0.25 ± 3% perf-profile.self.cycles-pp.entry_SYSCALL_64_safe_stack 0.13 ± 3% +0.0 0.18 ± 4% perf-profile.self.cycles-pp.do_rt_sigqueueinfo 0.08 ± 5% +0.0 0.13 ± 5% perf-profile.self.cycles-pp.send_signal 0.03 ± 70% +0.0 0.08 ± 4% perf-profile.self.cycles-pp.map_id_up 0.16 ± 3% +0.0 0.21 ± 3% perf-profile.self.cycles-pp.syscall_exit_to_user_mode_prepare 0.01 ±223% +0.0 0.06 ± 6% perf-profile.self.cycles-pp.audit_signal_info 0.00 +0.1 0.05 perf-profile.self.cycles-pp.known_siginfo_layout 0.51 ± 2% +0.1 0.56 ± 2% perf-profile.self.cycles-pp.__task_pid_nr_ns 0.22 ± 4% +0.1 0.29 ± 3% perf-profile.self.cycles-pp.getuid 0.22 ± 3% +0.1 0.30 ± 3% perf-profile.self.cycles-pp.__getpid 0.46 ± 3% +0.1 0.59 perf-profile.self.cycles-pp.sigqueue 1.88 +0.1 2.01 ± 2% perf-profile.self.cycles-pp._raw_spin_lock_irqsave 0.58 +0.2 0.76 ± 6% perf-profile.self.cycles-pp.syscall 0.84 ± 2% +0.2 1.03 perf-profile.self.cycles-pp.__entry_text_start 1.57 ± 2% +0.3 1.83 perf-profile.self.cycles-pp.syscall_return_via_sysret 1.46 ± 2% +1.2 2.63 ± 4% perf-profile.self.cycles-pp.aa_may_signal 23.69 ± 2% +14.9 38.57 perf-profile.self.cycles-pp.aa_get_task_label 25.80 +18.3 44.06 perf-profile.self.cycles-pp.apparmor_task_kill 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. --- 0DAY/LKP+ Test Infrastructure Open Source Technology Center https://lists.01.org/hyperkitty/list/[email protected] Intel Corporation Thanks, Oliver Sang

7 months, 2 weeks

1
0
0 / 0

[sched/fair] b08e888d97: hackbench.throughput 46.6% improvement

by kernel test robot

Greeting, FYI, we noticed a 46.6% improvement of hackbench.throughput due to commit: commit: b08e888d9715f01546da7a40ca3ff72b9d1a78cc ("sched/fair: Force progress on min_vruntime") https://git.kernel.org/cgit/linux/kernel/git/peterz/queue.git sched/wip.migrate in testcase: hackbench on test machine: 128 threads 2 sockets Intel(R) Xeon(R) Gold 6338 CPU @ 2.00GHz with 256G memory with following parameters: nr_threads: 100% iterations: 4 mode: threads ipc: pipe cpufreq_governor: performance ucode: 0xd000280 test-description: Hackbench is both a benchmark and a stress test for the Linux kernel scheduler. test-url: https://github.com/linux-test-project/ltp/blob/master/testcases/kernel/sc... In addition to that, the commit also has significant impact on the following tests: +------------------+------------------------------------------------------------------------------------------------------------+ | testcase: change | phoronix-test-suite: phoronix-test-suite.schbench.32.32.usec,_99.9th_latency_percentile -60.6% improvement | | test machine | 96 threads 2 sockets Intel(R) Xeon(R) Gold 6252 CPU @ 2.10GHz with 128G memory | | test parameters | cpufreq_governor=performance | | | option_a=32 | | | option_b=32 | | | test=schbench-1.0.0 | | | ucode=0x5003006 | +------------------+------------------------------------------------------------------------------------------------------------+ | testcase: change | hackbench: hackbench.throughput 55.5% improvement | | test machine | 104 threads 2 sockets Skylake with 192G memory | | test parameters | cpufreq_governor=performance | | | ipc=pipe | | | iterations=4 | | | mode=threads | | | nr_threads=100% | | | ucode=0x2006a0a | +------------------+------------------------------------------------------------------------------------------------------------+ Details are as below: --------------------------------------------------------------------------------------------------> To reproduce: git clone https://github.com/intel/lkp-tests.git cd lkp-tests sudo bin/lkp install job.yaml # job file is attached in this email bin/lkp split-job --compatible job.yaml # generate the yaml file for lkp run sudo bin/lkp run generated-yaml-file # if come across any failure that blocks the test, # please remove ~/.lkp and /lkp dir to run from a clean state. ========================================================================================= compiler/cpufreq_governor/ipc/iterations/kconfig/mode/nr_threads/rootfs/tbox_group/testcase/ucode: gcc-9/performance/pipe/4/x86_64-rhel-8.3/threads/100%/debian-10.4-x86_64-20200603.cgz/lkp-icl-2sp2/hackbench/0xd000280 commit: v5.16-rc6 b08e888d97 ("sched/fair: Force progress on min_vruntime") v5.16-rc6 b08e888d9715f01546da7a40ca3 ---------------- --------------------------- %stddev %change %stddev \ | \ 653575 +46.6% 958089 hackbench.throughput 17908198 ± 5% -36.4% 11391663 ± 5% cpuidle..usage 155.26 -24.8% 116.73 ± 3% uptime.boot 0.03 ± 3% -0.0 0.03 ± 6% mpstat.cpu.all.soft% 9.86 +3.3 13.20 mpstat.cpu.all.usr% 2052 ± 20% -35.2% 1329 ± 23% numa-meminfo.node0.Active 2052 ± 20% -35.2% 1329 ± 23% numa-meminfo.node0.Active(anon) 3312 -16.9% 2753 ± 2% meminfo.Active 3312 -16.9% 2753 ± 2% meminfo.Active(anon) 128712 ± 2% -24.9% 96605 meminfo.AnonHugePages 2554 +1.2% 2584 turbostat.Bzy_MHz 17637175 ± 5% -35.5% 11382497 ± 5% turbostat.C1 1.321e+08 ± 4% -77.7% 29492706 ± 3% turbostat.IRQ 1213 +108.1% 2525 ± 3% vmstat.procs.r 23544038 -94.2% 1373085 ± 4% vmstat.system.cs 1267010 ± 3% -65.1% 441932 ± 2% vmstat.system.in 28404703 ± 7% +154.1% 72168987 ± 4% numa-numastat.node0.local_node 28445356 ± 7% +154.0% 72237824 ± 4% numa-numastat.node0.numa_hit 25297912 ± 6% +186.2% 72404938 ± 4% numa-numastat.node1.local_node 25371744 ± 6% +185.5% 72437776 ± 4% numa-numastat.node1.numa_hit 513.50 ± 21% -35.8% 329.67 ± 24% numa-vmstat.node0.nr_active_anon 513.50 ± 21% -35.8% 329.67 ± 24% numa-vmstat.node0.nr_zone_active_anon 16630487 ± 8% +129.4% 38157859 ± 4% numa-vmstat.node0.numa_hit 16587877 ± 8% +129.6% 38086060 ± 4% numa-vmstat.node0.numa_local 14598373 ± 8% +159.4% 37867111 ± 6% numa-vmstat.node1.numa_hit 14483676 ± 8% +160.9% 37790942 ± 6% numa-vmstat.node1.numa_local 6.63 ± 64% -6.0 0.62 ±223% perf-profile.calltrace.cycles-pp.do_filp_open.do_sys_openat2.do_sys_open.do_syscall_64.entry_SYSCALL_64_after_hwframe 6.63 ± 64% -6.0 0.62 ±223% perf-profile.calltrace.cycles-pp.path_openat.do_filp_open.do_sys_openat2.do_sys_open.do_syscall_64 3.75 ± 72% -3.7 0.00 perf-profile.calltrace.cycles-pp.open64 5.44 ± 51% -2.9 2.52 ±163% perf-profile.calltrace.cycles-pp.copy_page_from_iter_atomic.generic_perform_write.__generic_file_write_iter.generic_file_write_iter.new_sync_write 4.48 ± 57% -2.7 1.76 ±141% perf-profile.calltrace.cycles-pp.number.vsnprintf.seq_vprintf.seq_printf.show_interrupts 3.65 ± 77% -1.0 2.67 ±223% perf-profile.calltrace.cycles-pp.proc_pid_status.proc_single_show.seq_read_iter.seq_read.vfs_read 6.63 ± 64% -6.0 0.62 ±223% perf-profile.children.cycles-pp.do_sys_open 6.63 ± 64% -6.0 0.62 ±223% perf-profile.children.cycles-pp.do_sys_openat2 6.63 ± 64% -6.0 0.62 ±223% perf-profile.children.cycles-pp.do_filp_open 6.63 ± 64% -6.0 0.62 ±223% perf-profile.children.cycles-pp.path_openat 5.04 ± 64% -3.3 1.76 ±141% perf-profile.children.cycles-pp.number 5.44 ± 51% -2.9 2.52 ±163% perf-profile.children.cycles-pp.copy_page_from_iter_atomic 5.04 ± 64% -3.3 1.76 ±141% perf-profile.self.cycles-pp.number 826.83 -16.8% 688.33 ± 2% proc-vmstat.nr_active_anon 79216 -1.6% 77968 proc-vmstat.nr_anon_pages 84555 ± 2% -2.6% 82387 proc-vmstat.nr_inactive_anon 92536 -4.6% 88260 proc-vmstat.nr_kernel_stack 6216 ± 31% -16.0% 5220 proc-vmstat.nr_shmem 826.83 -16.8% 688.33 ± 2% proc-vmstat.nr_zone_active_anon 84555 ± 2% -2.6% 82387 proc-vmstat.nr_zone_inactive_anon 40595 ± 24% -85.3% 5957 ± 89% proc-vmstat.numa_hint_faults 20890 ± 41% -87.4% 2629 ±105% proc-vmstat.numa_hint_faults_local 53819891 +168.8% 1.447e+08 proc-vmstat.numa_hit 53705406 +169.2% 1.446e+08 proc-vmstat.numa_local 20887 ± 27% -84.1% 3328 ±100% proc-vmstat.numa_pages_migrated 72657 ± 30% -55.8% 32092 ± 61% proc-vmstat.numa_pte_updates 53822302 +168.7% 1.446e+08 proc-vmstat.pgalloc_normal 449333 ± 13% -33.5% 298589 ± 3% proc-vmstat.pgfault 53610460 +169.4% 1.444e+08 proc-vmstat.pgfree 20887 ± 27% -84.1% 3328 ±100% proc-vmstat.pgmigrate_success 20678 ± 2% -32.9% 13880 ± 4% proc-vmstat.pgreuse 7.20 ± 2% -56.8% 3.11 ± 2% perf-stat.i.MPKI 5.303e+10 -4.0% 5.092e+10 perf-stat.i.branch-instructions 0.63 -0.5 0.16 perf-stat.i.branch-miss-rate% 3.195e+08 -77.6% 71713145 perf-stat.i.branch-misses 7.04 ± 4% +18.3 25.32 ± 3% perf-stat.i.cache-miss-rate% 1.199e+08 ± 3% +41.4% 1.695e+08 ± 2% perf-stat.i.cache-misses 1.824e+09 -59.2% 7.436e+08 ± 2% perf-stat.i.cache-references 24276211 -94.4% 1358591 ± 4% perf-stat.i.context-switches 1521377 ± 3% -87.5% 190633 ± 7% perf-stat.i.cpu-migrations 3127 ± 5% -39.4% 1893 ± 2% perf-stat.i.cycles-between-cache-misses 0.00 ± 6% -0.0 0.00 ± 9% perf-stat.i.dTLB-load-miss-rate% 1804532 ± 5% -23.3% 1383626 ± 10% perf-stat.i.dTLB-load-misses 0.00 ± 8% -0.0 0.00 ± 4% perf-stat.i.dTLB-store-miss-rate% 343753 ± 3% -23.8% 261974 ± 4% perf-stat.i.dTLB-store-misses 4.648e+10 -3.9% 4.464e+10 perf-stat.i.dTLB-stores 2.617e+11 -3.4% 2.528e+11 perf-stat.i.instructions 0.82 -3.5% 0.79 perf-stat.i.ipc 517.04 ± 2% -9.8% 466.28 perf-stat.i.metric.K/sec 1407 -3.3% 1361 perf-stat.i.metric.M/sec 87.20 -17.6 69.59 perf-stat.i.node-load-miss-rate% 2795035 ± 6% +214.8% 8799183 ± 5% perf-stat.i.node-loads 59.48 +3.0 62.46 perf-stat.i.node-store-miss-rate% 11371827 ± 4% +62.7% 18504651 ± 2% perf-stat.i.node-store-misses 7495979 ± 3% +48.1% 11099696 perf-stat.i.node-stores 6.92 ± 2% -57.8% 2.92 ± 2% perf-stat.overall.MPKI 0.60 -0.5 0.14 perf-stat.overall.branch-miss-rate% 6.62 ± 4% +16.3 22.96 ± 4% perf-stat.overall.cache-miss-rate% 1.20 +4.7% 1.26 perf-stat.overall.cpi 2621 ± 3% -28.5% 1873 ± 2% perf-stat.overall.cycles-between-cache-misses 0.00 ± 5% -0.0 0.00 ± 11% perf-stat.overall.dTLB-load-miss-rate% 0.00 ± 2% -0.0 0.00 ± 4% perf-stat.overall.dTLB-store-miss-rate% 0.83 -4.5% 0.80 perf-stat.overall.ipc 86.77 -17.9 68.83 perf-stat.overall.node-load-miss-rate% 60.35 +2.2 62.51 perf-stat.overall.node-store-miss-rate% 5.269e+10 -4.6% 5.025e+10 perf-stat.ps.branch-instructions 3.154e+08 -77.7% 70229688 perf-stat.ps.branch-misses 1.191e+08 ± 3% +40.4% 1.673e+08 ± 2% perf-stat.ps.cache-misses 1.8e+09 ± 2% -59.5% 7.291e+08 ± 2% perf-stat.ps.cache-references 24036022 -94.5% 1320301 ± 4% perf-stat.ps.context-switches 1470959 ± 3% -87.6% 182972 ± 7% perf-stat.ps.cpu-migrations 1759980 ± 5% -23.8% 1341985 ± 11% perf-stat.ps.dTLB-load-misses 335955 ± 2% -24.1% 255091 ± 4% perf-stat.ps.dTLB-store-misses 4.618e+10 -4.6% 4.406e+10 perf-stat.ps.dTLB-stores 2.6e+11 -4.1% 2.495e+11 perf-stat.ps.instructions 2784328 ± 5% +212.5% 8701815 ± 5% perf-stat.ps.node-loads 11244792 ± 4% +62.0% 18220133 ± 2% perf-stat.ps.node-store-misses 7386068 ± 3% +47.9% 10923448 perf-stat.ps.node-stores 2.568e+13 -37.0% 1.619e+13 perf-stat.total.instructions 18746 ± 12% -39.3% 11371 ± 9% softirqs.CPU0.RCU 19003 ± 13% -37.5% 11885 ± 16% softirqs.CPU1.RCU 19070 ± 12% -42.2% 11015 ± 9% softirqs.CPU10.RCU 19263 ± 6% -38.0% 11951 ± 6% softirqs.CPU100.RCU 19660 ± 7% -39.6% 11878 ± 5% softirqs.CPU101.RCU 19396 ± 6% -38.4% 11942 ± 5% softirqs.CPU102.RCU 19208 ± 6% -38.0% 11912 ± 5% softirqs.CPU103.RCU 19759 ± 7% -40.1% 11826 ± 5% softirqs.CPU104.RCU 19676 ± 6% -40.1% 11787 ± 5% softirqs.CPU105.RCU 19141 ± 6% -38.1% 11849 ± 6% softirqs.CPU106.RCU 19236 ± 6% -38.2% 11883 ± 6% softirqs.CPU107.RCU 19948 ± 5% -39.7% 12033 ± 5% softirqs.CPU108.RCU 19426 ± 6% -39.1% 11832 ± 6% softirqs.CPU109.RCU 18843 ± 11% -36.0% 12060 ± 21% softirqs.CPU11.RCU 19548 ± 6% -39.8% 11765 ± 6% softirqs.CPU110.RCU 19460 ± 6% -38.7% 11920 ± 5% softirqs.CPU111.RCU 17625 ± 6% -39.9% 10596 ± 4% softirqs.CPU112.RCU 17477 ± 6% -40.1% 10472 ± 5% softirqs.CPU113.RCU 17702 ± 8% -40.6% 10506 ± 5% softirqs.CPU114.RCU 17433 ± 7% -39.6% 10530 ± 4% softirqs.CPU115.RCU 17184 ± 9% -38.5% 10572 ± 5% softirqs.CPU116.RCU 17123 ± 6% -38.5% 10534 ± 8% softirqs.CPU117.RCU 17453 ± 6% -39.9% 10497 ± 5% softirqs.CPU118.RCU 17449 ± 7% -40.4% 10395 ± 5% softirqs.CPU119.RCU 18501 ± 12% -39.6% 11180 ± 10% softirqs.CPU12.RCU 17417 ± 6% -39.1% 10600 ± 5% softirqs.CPU120.RCU 17554 ± 6% -40.2% 10501 ± 6% softirqs.CPU121.RCU 18068 ± 12% -39.4% 10945 ± 7% softirqs.CPU122.RCU 17356 ± 5% -39.1% 10574 ± 5% softirqs.CPU123.RCU 17411 ± 6% -38.5% 10715 ± 5% softirqs.CPU124.RCU 17615 ± 6% -39.2% 10702 ± 6% softirqs.CPU125.RCU 17569 ± 6% -39.5% 10631 ± 5% softirqs.CPU126.RCU 17797 ± 6% -40.2% 10635 ± 5% softirqs.CPU127.RCU 19570 ± 13% -38.9% 11967 ± 21% softirqs.CPU13.RCU 18846 ± 11% -38.5% 11586 ± 13% softirqs.CPU14.RCU 18642 ± 13% -39.6% 11255 ± 10% softirqs.CPU15.RCU 18684 ± 12% -41.8% 10869 ± 10% softirqs.CPU16.RCU 18890 ± 14% -42.9% 10790 ± 11% softirqs.CPU17.RCU 18794 ± 13% -40.0% 11278 ± 6% softirqs.CPU18.RCU 18930 ± 13% -41.4% 11096 ± 11% softirqs.CPU19.RCU 18567 ± 13% -40.6% 11028 ± 9% softirqs.CPU2.RCU 18769 ± 12% -41.4% 11006 ± 9% softirqs.CPU20.RCU 18500 ± 12% -40.3% 11040 ± 12% softirqs.CPU21.RCU 18477 ± 14% -42.3% 10655 ± 10% softirqs.CPU22.RCU 18551 ± 12% -43.4% 10507 ± 18% softirqs.CPU23.RCU 18638 ± 12% -42.0% 10805 ± 21% softirqs.CPU24.RCU 18602 ± 12% -42.8% 10642 ± 8% softirqs.CPU25.RCU 18739 ± 12% -41.3% 11006 ± 9% softirqs.CPU26.RCU 18763 ± 13% -41.9% 10900 ± 10% softirqs.CPU27.RCU 18268 ± 19% -40.3% 10898 ± 12% softirqs.CPU28.RCU 18584 ± 12% -42.4% 10706 ± 9% softirqs.CPU29.RCU 19256 ± 12% -43.5% 10889 ± 11% softirqs.CPU3.RCU 18713 ± 12% -41.8% 10887 ± 8% softirqs.CPU30.RCU 18710 ± 13% -41.4% 10960 ± 9% softirqs.CPU31.RCU 18442 ± 5% -40.2% 11023 ± 4% softirqs.CPU32.RCU 17972 ± 7% -38.1% 11126 ± 5% softirqs.CPU33.RCU 18139 ± 6% -39.4% 10986 ± 4% softirqs.CPU34.RCU 17619 ± 6% -38.7% 10795 ± 5% softirqs.CPU35.RCU 17452 ± 6% -38.1% 10795 ± 3% softirqs.CPU36.RCU 17860 ± 7% -38.0% 11079 ± 4% softirqs.CPU37.RCU 17703 ± 6% -39.5% 10710 ± 10% softirqs.CPU38.RCU 17733 ± 4% -39.9% 10655 ± 5% softirqs.CPU39.RCU 19506 ± 15% -43.6% 11001 ± 8% softirqs.CPU4.RCU 18044 ± 6% -39.7% 10882 ± 5% softirqs.CPU40.RCU 18256 ± 6% -40.4% 10881 ± 5% softirqs.CPU41.RCU 17318 ± 7% -37.5% 10823 ± 5% softirqs.CPU42.RCU 17660 ± 7% -40.3% 10539 ± 5% softirqs.CPU43.RCU 18660 ± 5% -41.9% 10844 ± 4% softirqs.CPU44.RCU 17768 ± 6% -38.9% 10852 ± 6% softirqs.CPU45.RCU 17655 ± 7% -39.3% 10713 ± 5% softirqs.CPU46.RCU 17747 ± 6% -39.1% 10816 ± 5% softirqs.CPU47.RCU 17656 ± 6% -39.8% 10636 ± 5% softirqs.CPU48.RCU 17592 ± 6% -39.5% 10646 ± 4% softirqs.CPU49.RCU 19129 ± 13% -39.4% 11599 ± 19% softirqs.CPU5.RCU 17586 ± 6% -40.1% 10540 ± 4% softirqs.CPU50.RCU 17758 ± 5% -40.5% 10570 ± 4% softirqs.CPU51.RCU 17960 ± 7% -40.1% 10765 ± 4% softirqs.CPU52.RCU 16892 ± 8% -39.3% 10256 ± 7% softirqs.CPU53.RCU 17597 ± 5% -40.2% 10524 ± 4% softirqs.CPU54.RCU 17614 ± 6% -40.9% 10412 ± 5% softirqs.CPU55.RCU 17682 ± 7% -40.0% 10600 ± 4% softirqs.CPU56.RCU 18064 ± 7% -40.1% 10816 ± 5% softirqs.CPU57.RCU 17623 ± 6% -40.4% 10500 ± 4% softirqs.CPU58.RCU 17585 ± 6% -40.6% 10450 ± 4% softirqs.CPU59.RCU 18840 ± 12% -40.9% 11139 ± 8% softirqs.CPU6.RCU 17667 ± 6% -39.1% 10761 ± 7% softirqs.CPU60.RCU 17780 ± 6% -37.0% 11206 ± 5% softirqs.CPU61.RCU 17766 ± 6% -37.9% 11029 ± 9% softirqs.CPU62.RCU 17961 ± 7% -42.4% 10348 ± 8% softirqs.CPU63.RCU 18806 ± 15% -43.0% 10724 ± 8% softirqs.CPU64.RCU 18615 ± 13% -39.7% 11220 ± 10% softirqs.CPU65.RCU 18447 ± 13% -37.8% 11482 ± 16% softirqs.CPU66.RCU 18479 ± 13% -40.7% 10960 ± 11% softirqs.CPU67.RCU 18815 ± 13% -42.0% 10916 ± 10% softirqs.CPU68.RCU 18691 ± 13% -41.6% 10912 ± 9% softirqs.CPU69.RCU 19163 ± 13% -40.6% 11392 ± 13% softirqs.CPU7.RCU 18358 ± 13% -40.2% 10982 ± 9% softirqs.CPU70.RCU 18096 ± 19% -40.1% 10848 ± 9% softirqs.CPU71.RCU 18737 ± 13% -42.4% 10789 ± 8% softirqs.CPU72.RCU 19085 ± 11% -43.1% 10864 ± 7% softirqs.CPU73.RCU 18868 ± 13% -37.1% 11868 ± 9% softirqs.CPU74.RCU 18523 ± 13% -41.3% 10876 ± 11% softirqs.CPU75.RCU 18366 ± 13% -40.9% 10850 ± 10% softirqs.CPU76.RCU 19087 ± 12% -43.1% 10869 ± 9% softirqs.CPU77.RCU 18624 ± 11% -41.4% 10910 ± 9% softirqs.CPU78.RCU 18660 ± 12% -41.6% 10889 ± 10% softirqs.CPU79.RCU 18591 ± 12% -41.0% 10971 ± 9% softirqs.CPU8.RCU 18670 ± 13% -42.9% 10654 ± 8% softirqs.CPU80.RCU 19309 ± 16% -44.8% 10652 ± 11% softirqs.CPU81.RCU 18675 ± 12% -42.4% 10753 ± 9% softirqs.CPU82.RCU 18285 ± 13% -41.3% 10735 ± 10% softirqs.CPU83.RCU 18831 ± 13% -41.6% 11003 ± 8% softirqs.CPU84.RCU 18235 ± 13% -41.1% 10734 ± 11% softirqs.CPU85.RCU 18344 ± 13% -41.6% 10721 ± 7% softirqs.CPU86.RCU 18706 ± 13% -41.9% 10860 ± 14% softirqs.CPU87.RCU 18387 ± 13% -41.2% 10809 ± 13% softirqs.CPU88.RCU 18812 ± 12% -42.0% 10904 ± 8% softirqs.CPU89.RCU 18664 ± 11% -40.3% 11136 ± 10% softirqs.CPU9.RCU 18902 ± 13% -41.9% 10976 ± 10% softirqs.CPU90.RCU 18687 ± 12% -39.1% 11374 ± 14% softirqs.CPU91.RCU 18283 ± 14% -40.3% 10915 ± 10% softirqs.CPU92.RCU 18476 ± 12% -41.7% 10766 ± 10% softirqs.CPU93.RCU 18580 ± 13% -40.2% 11119 ± 7% softirqs.CPU94.RCU 18675 ± 13% -40.3% 11149 ± 10% softirqs.CPU95.RCU 19611 ± 6% -38.8% 12003 ± 5% softirqs.CPU96.RCU 19352 ± 6% -37.9% 12016 ± 5% softirqs.CPU97.RCU 20041 ± 5% -40.3% 11974 ± 4% softirqs.CPU98.RCU 19370 ± 6% -39.1% 11792 ± 6% softirqs.CPU99.RCU 2358890 ± 9% -40.3% 1409034 ± 6% softirqs.RCU 732676 ± 8% -36.8% 463351 ± 9% softirqs.SCHED 33955 ± 5% -19.4% 27373 ± 9% softirqs.TIMER *************************************************************************************************** lkp-csl-2sp8: 96 threads 2 sockets Intel(R) Xeon(R) Gold 6252 CPU @ 2.10GHz with 128G memory ========================================================================================= compiler/cpufreq_governor/kconfig/option_a/option_b/rootfs/tbox_group/test/testcase/ucode: gcc-9/performance/x86_64-rhel-8.3/32/32/debian-x86_64-phoronix/lkp-csl-2sp8/schbench-1.0.0/phoronix-test-suite/0x5003006 commit: v5.16-rc6 b08e888d97 ("sched/fair: Force progress on min_vruntime") v5.16-rc6 b08e888d9715f01546da7a40ca3 ---------------- --------------------------- %stddev %change %stddev \ | \ 135133 -60.6% 53294 phoronix-test-suite.schbench.32.32.usec,_99.9th_latency_percentile 2038805 -15.1% 1730336 phoronix-test-suite.time.involuntary_context_switches 0.14 ± 2% -0.0 0.11 ± 4% mpstat.cpu.all.sys% 1096 ± 31% +45.4% 1594 ± 6% proc-vmstat.numa_huge_pte_updates 669991 ± 26% +38.5% 928203 ± 5% proc-vmstat.numa_pte_updates 11.39 ± 5% +1.7 13.12 ± 5% perf-stat.i.cache-miss-rate% 30800 -10.5% 27573 perf-stat.i.context-switches 3842 +22.1% 4690 perf-stat.i.cpu-migrations 609.10 -9.8% 549.40 vmstat.procs.r 29868 -9.4% 27049 vmstat.system.cs 201252 ± 9% +4.6% 210516 vmstat.system.in 0.84 ± 7% +0.2 1.07 ± 5% perf-profile.calltrace.cycles-pp.rebalance_domains.__softirqentry_text_start.irq_exit_rcu.sysvec_apic_timer_interrupt.asm_sysvec_apic_timer_interrupt 0.78 ± 7% +0.2 1.02 ± 5% perf-profile.calltrace.cycles-pp.load_balance.rebalance_domains.__softirqentry_text_start.irq_exit_rcu.sysvec_apic_timer_interrupt 0.72 ± 11% +0.3 1.03 ± 5% perf-profile.calltrace.cycles-pp.newidle_balance.pick_next_task_fair.__schedule.schedule.futex_wait_queue 0.69 ± 12% +0.3 1.00 ± 5% perf-profile.calltrace.cycles-pp.load_balance.newidle_balance.pick_next_task_fair.__schedule.schedule 0.90 ± 11% +0.3 1.22 ± 4% perf-profile.calltrace.cycles-pp.pick_next_task_fair.__schedule.schedule.futex_wait_queue.futex_wait 5.69 ± 3% +0.5 6.23 ± 4% perf-profile.calltrace.cycles-pp.__schedule.schedule.futex_wait_queue.futex_wait.do_futex 5.73 ± 3% +0.5 6.27 ± 4% perf-profile.calltrace.cycles-pp.schedule.futex_wait_queue.futex_wait.do_futex.__x64_sys_futex 5.82 ± 3% +0.6 6.38 ± 4% perf-profile.calltrace.cycles-pp.futex_wait_queue.futex_wait.do_futex.__x64_sys_futex.do_syscall_64 6.02 ± 3% +0.6 6.58 ± 3% perf-profile.calltrace.cycles-pp.futex_wait.do_futex.__x64_sys_futex.do_syscall_64.entry_SYSCALL_64_after_hwframe 6.50 ± 4% -1.5 5.04 ± 5% perf-profile.children.cycles-pp.exit_to_user_mode_prepare 6.19 ± 5% -1.3 4.89 ± 5% perf-profile.children.cycles-pp.irqentry_exit_to_user_mode 12.46 ± 2% -1.1 11.32 ± 3% perf-profile.children.cycles-pp.__schedule 12.52 ± 2% -1.1 11.39 ± 3% perf-profile.children.cycles-pp.schedule 1.00 ± 15% -0.8 0.20 ± 22% perf-profile.children.cycles-pp.asm_sysvec_reschedule_ipi 6.14 ± 6% -0.8 5.37 ± 4% perf-profile.children.cycles-pp.perf_trace_sched_switch 1.39 ± 10% -0.4 0.96 ± 10% perf-profile.children.cycles-pp._raw_spin_lock 0.89 ± 14% -0.4 0.49 ± 24% perf-profile.children.cycles-pp.native_queued_spin_lock_slowpath 0.69 ± 14% -0.2 0.48 ± 20% perf-profile.children.cycles-pp.__x64_sys_nanosleep 0.68 ± 14% -0.2 0.47 ± 20% perf-profile.children.cycles-pp.hrtimer_nanosleep 0.68 ± 14% -0.2 0.47 ± 20% perf-profile.children.cycles-pp.do_nanosleep 0.38 ± 17% -0.2 0.22 ± 24% perf-profile.children.cycles-pp.syscall_exit_to_user_mode 0.15 ± 19% -0.1 0.08 ± 48% perf-profile.children.cycles-pp.write 0.21 ± 19% +0.1 0.30 ± 12% perf-profile.children.cycles-pp.kvm_is_in_guest 0.84 ± 7% +0.2 1.07 ± 5% perf-profile.children.cycles-pp.rebalance_domains 0.45 ± 9% +0.3 0.70 ± 15% perf-profile.children.cycles-pp.__calc_delta 0.74 ± 11% +0.3 1.08 ± 6% perf-profile.children.cycles-pp.newidle_balance 1.49 ± 9% +0.6 2.07 ± 4% perf-profile.children.cycles-pp.load_balance 0.89 ± 15% -0.4 0.49 ± 23% perf-profile.self.cycles-pp.native_queued_spin_lock_slowpath 0.38 ± 11% -0.1 0.30 ± 9% perf-profile.self.cycles-pp.__schedule 0.19 ± 19% +0.1 0.28 ± 12% perf-profile.self.cycles-pp.kvm_is_in_guest 0.44 ± 8% +0.2 0.69 ± 15% perf-profile.self.cycles-pp.__calc_delta *************************************************************************************************** lkp-skl-fpga01: 104 threads 2 sockets Skylake with 192G memory ========================================================================================= compiler/cpufreq_governor/ipc/iterations/kconfig/mode/nr_threads/rootfs/tbox_group/testcase/ucode: gcc-9/performance/pipe/4/x86_64-rhel-8.3/threads/100%/debian-10.4-x86_64-20200603.cgz/lkp-skl-fpga01/hackbench/0x2006a0a commit: v5.16-rc6 b08e888d97 ("sched/fair: Force progress on min_vruntime") v5.16-rc6 b08e888d9715f01546da7a40ca3 ---------------- --------------------------- %stddev %change %stddev \ | \ 243924 +55.5% 379330 hackbench.throughput 15540713 ± 8% -60.4% 6160950 ± 3% cpuidle..usage 261.57 -29.5% 184.44 uptime.boot 1.18 -0.1 1.05 mpstat.cpu.all.irq% 0.04 ± 5% -0.0 0.04 ± 2% mpstat.cpu.all.soft% 73.85 -11.8 62.02 mpstat.cpu.all.sys% 22.89 +11.7 34.62 mpstat.cpu.all.usr% 20206732 +171.9% 54945573 numa-numastat.node0.local_node 20253752 +171.5% 54982565 numa-numastat.node0.numa_hit 21045850 ± 2% +183.3% 59621383 numa-numastat.node1.local_node 21058134 +183.2% 59642825 numa-numastat.node1.numa_hit 7043843 ± 12% -37.3% 4419834 ± 4% turbostat.C1 0.24 ± 12% +0.1 0.30 ± 4% turbostat.C1% 2.04e+08 ± 2% -84.8% 30989257 turbostat.IRQ 115.28 +14.7% 132.18 turbostat.RAMWatt 22.17 +53.4% 34.00 vmstat.cpu.us 5220877 ± 14% -41.6% 3050905 ± 2% vmstat.memory.cache 1204 +77.7% 2139 vmstat.procs.r 14664745 -95.2% 704900 ± 2% vmstat.system.cs 911202 -74.5% 232488 vmstat.system.in 2250 ± 15% -27.9% 1621 ± 10% numa-meminfo.node0.Active 2095 ± 16% -31.0% 1445 ± 11% numa-meminfo.node0.Active(anon) 188542 ± 50% -58.5% 78333 ± 13% numa-meminfo.node0.Mapped 67992 ± 7% -72.8% 18495 ± 50% numa-meminfo.node1.Active 67992 ± 7% -72.8% 18495 ± 50% numa-meminfo.node1.Active(anon) 72982 ± 46% -58.8% 30071 ± 88% numa-meminfo.node1.AnonHugePages 130528 ± 30% -47.3% 68777 ± 54% numa-meminfo.node1.AnonPages 2539845 ± 29% -81.1% 479406 ± 14% numa-meminfo.node1.Inactive 2539845 ± 29% -81.1% 479406 ± 14% numa-meminfo.node1.Inactive(anon) 502608 ± 21% -79.8% 101561 ± 18% numa-meminfo.node1.Mapped 2492 ± 10% -42.0% 1446 ± 12% numa-meminfo.node1.PageTables 2477433 ± 30% -82.7% 429019 ± 23% numa-meminfo.node1.Shmem 70018 ± 6% -72.8% 19048 ± 42% meminfo.Active 69863 ± 6% -73.0% 18872 ± 42% meminfo.Active(anon) 192446 -26.1% 142292 ± 2% meminfo.AnonHugePages 341625 -10.9% 304256 meminfo.AnonPages 5121644 ± 15% -42.7% 2935312 ± 3% meminfo.Cached 3116939 ± 25% -71.1% 899660 ± 10% meminfo.Committed_AS 2901201 ± 27% -74.9% 728894 ± 12% meminfo.Inactive 2901053 ± 27% -74.9% 728746 ± 12% meminfo.Inactive(anon) 687779 ± 14% -73.8% 180190 ± 11% meminfo.Mapped 7146592 ± 11% -30.2% 4990358 meminfo.Memused 5611 ± 3% -16.2% 4703 meminfo.PageTables 2629586 ± 29% -83.2% 442853 ± 20% meminfo.Shmem 7270248 ± 10% -30.2% 5074455 meminfo.max_used_kB 522.33 ± 16% -30.7% 362.17 ± 11% numa-vmstat.node0.nr_active_anon 46914 ± 50% -56.3% 20487 ± 15% numa-vmstat.node0.nr_mapped 522.33 ± 16% -30.7% 362.17 ± 11% numa-vmstat.node0.nr_zone_active_anon 12264878 +142.5% 29744174 ± 2% numa-vmstat.node0.numa_hit 12214256 +143.1% 29692277 ± 2% numa-vmstat.node0.numa_local 16894 ± 6% -72.1% 4714 ± 49% numa-vmstat.node1.nr_active_anon 32556 ± 30% -47.0% 17259 ± 55% numa-vmstat.node1.nr_anon_pages 631923 ± 30% -80.1% 125630 ± 15% numa-vmstat.node1.nr_inactive_anon 124390 ± 22% -78.5% 26774 ± 17% numa-vmstat.node1.nr_mapped 620.00 ± 10% -41.0% 366.00 ± 11% numa-vmstat.node1.nr_page_table_pages 616293 ± 31% -81.7% 113060 ± 21% numa-vmstat.node1.nr_shmem 16894 ± 6% -72.1% 4714 ± 49% numa-vmstat.node1.nr_zone_active_anon 631922 ± 30% -80.1% 125629 ± 15% numa-vmstat.node1.nr_zone_inactive_anon 11597593 ± 2% +170.4% 31363549 ± 2% numa-vmstat.node1.numa_hit 11533651 ± 2% +171.4% 31297047 ± 2% numa-vmstat.node1.numa_local 17516 ± 6% -73.4% 4662 ± 40% proc-vmstat.nr_active_anon 85408 -11.0% 76023 proc-vmstat.nr_anon_pages 4710721 +1.1% 4764703 proc-vmstat.nr_dirty_background_threshold 9432961 +1.1% 9541057 proc-vmstat.nr_dirty_threshold 1280589 ± 15% -42.8% 732711 ± 2% proc-vmstat.nr_file_pages 47394242 +1.1% 47934851 proc-vmstat.nr_free_pages 725395 ± 26% -75.0% 181084 ± 11% proc-vmstat.nr_inactive_anon 80621 -4.0% 77417 proc-vmstat.nr_kernel_stack 171686 ± 13% -73.8% 44975 ± 11% proc-vmstat.nr_mapped 1402 ± 3% -16.3% 1173 proc-vmstat.nr_page_table_pages 657573 ± 29% -83.3% 109596 ± 19% proc-vmstat.nr_shmem 28926 -5.7% 27281 proc-vmstat.nr_slab_reclaimable 67226 -1.6% 66140 proc-vmstat.nr_slab_unreclaimable 17516 ± 6% -73.4% 4662 ± 40% proc-vmstat.nr_zone_active_anon 725395 ± 26% -75.0% 181084 ± 11% proc-vmstat.nr_zone_inactive_anon 390080 ± 4% -62.6% 145788 ± 20% proc-vmstat.numa_hint_faults 284764 ± 6% -71.6% 80809 ± 21% proc-vmstat.numa_hint_faults_local 41317354 +177.4% 1.146e+08 proc-vmstat.numa_hit 41258052 +177.7% 1.146e+08 proc-vmstat.numa_local 36260 ± 42% -80.8% 6978 ± 47% proc-vmstat.numa_pages_migrated 627669 -50.8% 308691 ± 10% proc-vmstat.numa_pte_updates 41321465 +177.4% 1.146e+08 proc-vmstat.pgalloc_normal 1221322 ± 2% -38.8% 747607 ± 4% proc-vmstat.pgfault 39928898 +185.4% 1.14e+08 proc-vmstat.pgfree 36260 ± 42% -80.8% 6978 ± 47% proc-vmstat.pgmigrate_success 37167 ± 2% -36.7% 23533 ± 2% proc-vmstat.pgreuse 10.86 ± 2% -60.4% 4.30 perf-stat.i.MPKI 2.773e+10 -24.3% 2.098e+10 perf-stat.i.branch-instructions 1.46 -0.2 1.25 perf-stat.i.branch-miss-rate% 3.945e+08 -33.9% 2.609e+08 perf-stat.i.branch-misses 4.19 ± 5% +28.0 32.20 perf-stat.i.cache-miss-rate% 53454898 ± 5% +150.0% 1.336e+08 perf-stat.i.cache-misses 1.412e+09 -68.8% 4.407e+08 perf-stat.i.cache-references 14863174 -95.3% 698605 ± 2% perf-stat.i.context-switches 2.08 +26.7% 2.64 perf-stat.i.cpi 918790 -93.6% 58630 ± 3% perf-stat.i.cpu-migrations 5445 ± 5% -61.5% 2098 perf-stat.i.cycles-between-cache-misses 0.12 +0.1 0.24 perf-stat.i.dTLB-load-miss-rate% 48798801 +56.3% 76261572 perf-stat.i.dTLB-load-misses 3.971e+10 -19.4% 3.201e+10 perf-stat.i.dTLB-loads 0.00 ± 10% -0.0 0.00 ± 3% perf-stat.i.dTLB-store-miss-rate% 303926 ± 3% -46.0% 164007 ± 2% perf-stat.i.dTLB-store-misses 2.368e+10 -21.7% 1.855e+10 perf-stat.i.dTLB-stores 64515637 ± 5% +35.0% 87084500 ± 7% perf-stat.i.iTLB-load-misses 1.352e+11 -22.9% 1.043e+11 perf-stat.i.instructions 2402 ± 12% -48.6% 1235 ± 5% perf-stat.i.instructions-per-iTLB-miss 0.49 -22.8% 0.38 perf-stat.i.ipc 3.42 ± 32% -53.5% 1.59 perf-stat.i.major-faults 361.63 ± 3% +14.5% 413.95 ± 4% perf-stat.i.metric.K/sec 889.15 -22.1% 692.26 perf-stat.i.metric.M/sec 5580 ± 2% -9.5% 5049 ± 5% perf-stat.i.minor-faults 80.85 +2.0 82.88 perf-stat.i.node-load-miss-rate% 9339361 ± 4% +92.4% 17965649 ± 4% perf-stat.i.node-load-misses 2176060 ± 3% +71.5% 3731319 ± 2% perf-stat.i.node-loads 57.54 ± 2% +17.6 75.11 perf-stat.i.node-store-miss-rate% 3921170 ± 4% +231.4% 12995856 ± 3% perf-stat.i.node-store-misses 2780324 +55.0% 4310621 ± 2% perf-stat.i.node-stores 5583 ± 2% -9.5% 5051 ± 5% perf-stat.i.page-faults 10.40 -59.6% 4.20 perf-stat.overall.MPKI 1.42 -0.2 1.24 perf-stat.overall.branch-miss-rate% 3.80 ± 5% +26.8 30.57 perf-stat.overall.cache-miss-rate% 2.03 +30.1% 2.64 perf-stat.overall.cpi 5143 ± 5% -60.0% 2055 perf-stat.overall.cycles-between-cache-misses 0.12 +0.1 0.24 perf-stat.overall.dTLB-load-miss-rate% 0.00 ± 3% -0.0 0.00 ± 2% perf-stat.overall.dTLB-store-miss-rate% 95.23 +1.6 96.82 perf-stat.overall.iTLB-load-miss-rate% 2096 ± 5% -42.6% 1202 ± 7% perf-stat.overall.instructions-per-iTLB-miss 0.49 -23.2% 0.38 perf-stat.overall.ipc 81.04 +1.7 82.71 perf-stat.overall.node-load-miss-rate% 58.43 ± 2% +16.7 75.14 perf-stat.overall.node-store-miss-rate% 2.757e+10 -24.4% 2.085e+10 perf-stat.ps.branch-instructions 3.923e+08 -34.0% 2.59e+08 perf-stat.ps.branch-misses 53174568 ± 5% +150.3% 1.331e+08 perf-stat.ps.cache-misses 1.399e+09 -68.9% 4.354e+08 perf-stat.ps.cache-references 14787641 -95.4% 683155 ± 2% perf-stat.ps.context-switches 901548 -93.8% 55778 ± 3% perf-stat.ps.cpu-migrations 48660610 +55.8% 75815767 perf-stat.ps.dTLB-load-misses 3.951e+10 -19.5% 3.181e+10 perf-stat.ps.dTLB-loads 299532 ± 3% -46.0% 161819 ± 2% perf-stat.ps.dTLB-store-misses 2.356e+10 -21.8% 1.843e+10 perf-stat.ps.dTLB-stores 64330425 ± 5% +34.7% 86669158 ± 7% perf-stat.ps.iTLB-load-misses 1.345e+11 -22.9% 1.036e+11 perf-stat.ps.instructions 3.34 ± 32% -52.4% 1.59 perf-stat.ps.major-faults 5385 -8.5% 4929 ± 5% perf-stat.ps.minor-faults 9247666 ± 4% +93.1% 17857896 ± 4% perf-stat.ps.node-load-misses 2160605 ± 3% +72.6% 3728183 ± 2% perf-stat.ps.node-loads 3886969 ± 4% +232.3% 12914952 ± 3% perf-stat.ps.node-store-misses 2761577 +54.7% 4270821 ± 2% perf-stat.ps.node-stores 5388 -8.5% 4931 ± 5% perf-stat.ps.page-faults 2.83e+13 -51.6% 1.371e+13 perf-stat.total.instructions 35304 ± 9% -35.1% 22902 ± 4% softirqs.CPU0.RCU 34522 ± 10% -34.0% 22784 ± 9% softirqs.CPU1.RCU 7675 ± 19% -34.3% 5038 ± 19% softirqs.CPU1.SCHED 34716 ± 9% -36.7% 21979 ± 6% softirqs.CPU10.RCU 33713 ± 9% -37.0% 21228 ± 4% softirqs.CPU100.RCU 33959 ± 9% -37.6% 21176 ± 5% softirqs.CPU101.RCU 34338 ± 9% -38.6% 21077 ± 4% softirqs.CPU102.RCU 34548 ± 9% -38.1% 21387 ± 5% softirqs.CPU103.RCU 8452 ± 17% -44.1% 4728 ± 18% softirqs.CPU103.SCHED 34720 ± 8% -37.5% 21684 ± 4% softirqs.CPU11.RCU 35190 ± 9% -38.2% 21733 ± 3% softirqs.CPU12.RCU 35034 ± 7% -36.4% 22294 ± 4% softirqs.CPU13.RCU 34598 ± 9% -36.6% 21921 ± 3% softirqs.CPU14.RCU 37841 ± 8% -38.5% 23284 ± 5% softirqs.CPU15.RCU 37752 ± 8% -38.4% 23246 ± 4% softirqs.CPU16.RCU 37597 ± 8% -37.7% 23428 ± 2% softirqs.CPU17.RCU 37341 ± 8% -36.5% 23696 ± 4% softirqs.CPU18.RCU 36883 ± 8% -37.1% 23210 ± 4% softirqs.CPU19.RCU 34873 ± 8% -38.8% 21355 ± 6% softirqs.CPU2.RCU 37958 ± 9% -38.7% 23259 ± 4% softirqs.CPU20.RCU 38116 ± 8% -39.2% 23170 ± 4% softirqs.CPU21.RCU 37496 ± 8% -38.2% 23187 ± 4% softirqs.CPU22.RCU 37683 ± 7% -38.0% 23378 ± 4% softirqs.CPU23.RCU 37514 ± 7% -37.1% 23592 ± 4% softirqs.CPU24.RCU 37848 ± 8% -37.3% 23748 ± 6% softirqs.CPU25.RCU 33410 ± 9% -40.1% 20017 ± 3% softirqs.CPU26.RCU 33936 ± 9% -39.0% 20699 ± 6% softirqs.CPU27.RCU 10205 ± 11% -36.7% 6462 ± 28% softirqs.CPU27.SCHED 33054 ± 9% -40.4% 19714 ± 4% softirqs.CPU28.RCU 33007 ± 10% -39.9% 19836 ± 4% softirqs.CPU29.RCU 35600 ± 11% -40.0% 21365 ± 4% softirqs.CPU3.RCU 35544 ± 10% -36.8% 22467 ± 5% softirqs.CPU30.RCU 34897 ± 8% -36.9% 22011 ± 6% softirqs.CPU31.RCU 34213 ± 6% -36.5% 21719 ± 4% softirqs.CPU32.RCU 33298 ± 5% -36.0% 21323 ± 5% softirqs.CPU33.RCU 7987 ± 17% -42.5% 4595 ± 8% softirqs.CPU33.SCHED 34005 ± 9% -37.8% 21150 ± 4% softirqs.CPU34.RCU 34250 ± 9% -38.2% 21163 ± 4% softirqs.CPU35.RCU 34218 ± 9% -37.9% 21256 ± 4% softirqs.CPU36.RCU 34474 ± 9% -36.2% 22010 ± 5% softirqs.CPU37.RCU 34626 ± 9% -38.0% 21485 ± 5% softirqs.CPU38.RCU 34276 ± 9% -38.1% 21203 ± 5% softirqs.CPU39.RCU 34472 ± 9% -36.9% 21742 ± 4% softirqs.CPU4.RCU 33896 ± 9% -38.1% 20986 ± 5% softirqs.CPU40.RCU 34236 ± 9% -38.2% 21159 ± 4% softirqs.CPU41.RCU 34549 ± 9% -37.9% 21445 ± 5% softirqs.CPU42.RCU 34676 ± 9% -37.7% 21617 ± 6% softirqs.CPU43.RCU 34667 ± 9% -38.1% 21469 ± 4% softirqs.CPU44.RCU 34607 ± 9% -40.1% 20718 ± 4% softirqs.CPU45.RCU 34814 ± 9% -38.9% 21266 ± 6% softirqs.CPU46.RCU 34743 ± 10% -39.6% 20991 ± 4% softirqs.CPU47.RCU 34411 ± 10% -39.1% 20945 ± 5% softirqs.CPU48.RCU 34696 ± 10% -40.0% 20819 ± 4% softirqs.CPU49.RCU 35847 ± 8% -38.3% 22125 ± 4% softirqs.CPU5.RCU 34536 ± 9% -38.7% 21160 ± 6% softirqs.CPU50.RCU 34457 ± 9% -38.6% 21150 ± 4% softirqs.CPU51.RCU 36863 ± 8% -40.1% 22070 ± 3% softirqs.CPU52.RCU 35183 ± 14% -34.2% 23157 ± 5% softirqs.CPU53.RCU 37456 ± 8% -35.6% 24126 ± 8% softirqs.CPU54.RCU 36481 ± 12% -37.5% 22814 ± 5% softirqs.CPU55.RCU 37552 ± 8% -39.1% 22880 ± 5% softirqs.CPU56.RCU 38204 ± 12% -39.5% 23108 ± 4% softirqs.CPU57.RCU 37570 ± 8% -40.6% 22333 ± 5% softirqs.CPU58.RCU 37972 ± 7% -39.2% 23087 ± 5% softirqs.CPU59.RCU 35010 ± 9% -38.0% 21717 ± 5% softirqs.CPU6.RCU 34777 ± 9% -37.3% 21821 ± 4% softirqs.CPU60.RCU 34756 ± 8% -35.2% 22536 ± 6% softirqs.CPU61.RCU 35005 ± 7% -37.6% 21829 ± 5% softirqs.CPU62.RCU 35414 ± 9% -37.9% 21979 ± 4% softirqs.CPU63.RCU 35050 ± 8% -37.2% 22015 ± 4% softirqs.CPU64.RCU 35234 ± 9% -37.6% 21997 ± 4% softirqs.CPU65.RCU 34721 ± 9% -37.5% 21699 ± 3% softirqs.CPU66.RCU 35608 ± 7% -38.9% 21772 ± 5% softirqs.CPU67.RCU 34949 ± 8% -39.0% 21317 ± 4% softirqs.CPU68.RCU 35032 ± 9% -37.8% 21778 ± 4% softirqs.CPU69.RCU 34514 ± 9% -36.3% 21983 ± 9% softirqs.CPU7.RCU 35351 ± 9% -38.1% 21883 ± 2% softirqs.CPU70.RCU 33661 ± 9% -35.2% 21816 ± 4% softirqs.CPU71.RCU 34803 ± 8% -39.5% 21054 ± 7% softirqs.CPU72.RCU 34299 ± 8% -37.4% 21463 ± 2% softirqs.CPU73.RCU 34667 ± 9% -38.3% 21385 ± 3% softirqs.CPU74.RCU 32951 ± 8% -38.2% 20359 ± 7% softirqs.CPU75.RCU 33407 ± 8% -39.0% 20370 ± 4% softirqs.CPU76.RCU 33587 ± 7% -40.7% 19914 ± 4% softirqs.CPU77.RCU 34722 ± 8% -39.0% 21194 ± 7% softirqs.CPU78.RCU 33933 ± 10% -37.8% 21112 ± 4% softirqs.CPU79.RCU 34812 ± 7% -38.0% 21592 ± 5% softirqs.CPU8.RCU 35145 ± 9% -39.1% 21396 ± 4% softirqs.CPU80.RCU 34879 ± 8% -38.8% 21332 ± 5% softirqs.CPU81.RCU 34627 ± 8% -39.3% 21007 ± 4% softirqs.CPU82.RCU 34760 ± 8% -39.0% 21215 ± 4% softirqs.CPU83.RCU 34952 ± 8% -39.0% 21312 ± 4% softirqs.CPU84.RCU 34522 ± 8% -39.1% 21024 ± 5% softirqs.CPU85.RCU 34406 ± 9% -38.6% 21137 ± 5% softirqs.CPU86.RCU 34419 ± 8% -39.0% 20987 ± 4% softirqs.CPU87.RCU 34403 ± 8% -37.9% 21358 ± 3% softirqs.CPU88.RCU 35015 ± 9% -38.0% 21701 ± 4% softirqs.CPU89.RCU 35199 ± 9% -38.3% 21704 ± 6% softirqs.CPU9.RCU 34512 ± 9% -37.9% 21441 ± 4% softirqs.CPU90.RCU 34052 ± 9% -38.0% 21098 ± 4% softirqs.CPU91.RCU 34048 ± 9% -37.6% 21252 ± 4% softirqs.CPU92.RCU 34155 ± 8% -37.3% 21398 ± 5% softirqs.CPU93.RCU 34243 ± 8% -37.7% 21347 ± 4% softirqs.CPU94.RCU 34387 ± 9% -37.4% 21536 ± 5% softirqs.CPU95.RCU 34242 ± 8% -37.3% 21472 ± 4% softirqs.CPU96.RCU 34569 ± 8% -38.6% 21224 ± 4% softirqs.CPU97.RCU 34086 ± 9% -37.5% 21317 ± 4% softirqs.CPU98.RCU 34399 ± 9% -37.8% 21380 ± 5% softirqs.CPU99.RCU 3645591 ± 8% -38.0% 2259598 ± 4% softirqs.RCU 713024 ± 7% -37.9% 442950 ± 11% softirqs.SCHED 45382 ± 4% -22.4% 35207 ± 3% softirqs.TIMER 21.02 ± 10% -20.0 1.07 ± 50% perf-profile.calltrace.cycles-pp.__wake_up_common_lock.pipe_write.new_sync_write.vfs_write.ksys_write 20.54 ± 10% -19.5 1.05 ± 50% perf-profile.calltrace.cycles-pp.__wake_up_common.__wake_up_common_lock.pipe_write.new_sync_write.vfs_write 20.34 ± 10% -19.3 1.04 ± 51% perf-profile.calltrace.cycles-pp.autoremove_wake_function.__wake_up_common.__wake_up_common_lock.pipe_write.new_sync_write 20.02 ± 11% -19.0 1.02 ± 52% perf-profile.calltrace.cycles-pp.try_to_wake_up.autoremove_wake_function.__wake_up_common.__wake_up_common_lock.pipe_write 29.44 ± 5% -14.3 15.18 ± 3% perf-profile.calltrace.cycles-pp.pipe_write.new_sync_write.vfs_write.ksys_write.do_syscall_64 14.88 ± 15% -14.1 0.78 ± 88% perf-profile.calltrace.cycles-pp.schedule.pipe_read.new_sync_read.vfs_read.ksys_read 14.70 ± 15% -14.0 0.70 ±107% perf-profile.calltrace.cycles-pp.__schedule.schedule.pipe_read.new_sync_read.vfs_read 30.12 ± 5% -13.9 16.20 ± 3% perf-profile.calltrace.cycles-pp.new_sync_write.vfs_write.ksys_write.do_syscall_64.entry_SYSCALL_64_after_hwframe 31.81 ± 4% -12.3 19.49 ± 2% perf-profile.calltrace.cycles-pp.vfs_write.ksys_write.do_syscall_64.entry_SYSCALL_64_after_hwframe.__libc_write 11.62 ± 55% -11.2 0.40 ±223% perf-profile.calltrace.cycles-pp.perf_prepare_sample.perf_event_output_forward.__perf_event_overflow.perf_swevent_overflow.perf_tp_event 33.67 ± 4% -10.9 22.79 perf-profile.calltrace.cycles-pp.ksys_write.do_syscall_64.entry_SYSCALL_64_after_hwframe.__libc_write 10.54 ± 54% -10.3 0.29 ±223% perf-profile.calltrace.cycles-pp.perf_callchain.perf_prepare_sample.perf_event_output_forward.__perf_event_overflow.perf_swevent_overflow 44.47 ± 2% -10.1 34.37 perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.__libc_write 10.32 ± 54% -10.0 0.29 ±223% perf-profile.calltrace.cycles-pp.get_perf_callchain.perf_callchain.perf_prepare_sample.perf_event_output_forward.__perf_event_overflow 44.84 ± 2% -10.0 34.89 perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.__libc_write 9.40 ± 53% -9.2 0.19 ±223% perf-profile.calltrace.cycles-pp.perf_callchain_kernel.get_perf_callchain.perf_callchain.perf_prepare_sample.perf_event_output_forward 8.80 ± 14% -8.5 0.35 ±107% perf-profile.calltrace.cycles-pp.ttwu_do_activate.try_to_wake_up.autoremove_wake_function.__wake_up_common.__wake_up_common_lock 8.71 ± 15% -8.4 0.27 ±146% perf-profile.calltrace.cycles-pp.enqueue_task_fair.ttwu_do_activate.try_to_wake_up.autoremove_wake_function.__wake_up_common 24.75 ± 6% -7.1 17.70 perf-profile.calltrace.cycles-pp.pipe_read.new_sync_read.vfs_read.ksys_read.do_syscall_64 7.28 ± 14% -7.0 0.26 ±146% perf-profile.calltrace.cycles-pp.dequeue_task_fair.__schedule.schedule.pipe_read.new_sync_read 25.37 ± 6% -6.9 18.47 perf-profile.calltrace.cycles-pp.new_sync_read.vfs_read.ksys_read.do_syscall_64.entry_SYSCALL_64_after_hwframe 5.92 ± 54% -5.7 0.24 ±223% perf-profile.calltrace.cycles-pp.__perf_event_overflow.perf_swevent_overflow.perf_tp_event.perf_trace_sched_stat_runtime.update_curr 5.88 ± 54% -5.7 0.23 ±223% perf-profile.calltrace.cycles-pp.perf_event_output_forward.__perf_event_overflow.perf_swevent_overflow.perf_tp_event.perf_trace_sched_stat_runtime 5.85 ± 28% -5.6 0.23 ±148% perf-profile.calltrace.cycles-pp.enqueue_entity.enqueue_task_fair.ttwu_do_activate.try_to_wake_up.autoremove_wake_function 27.30 ± 5% -5.3 22.01 perf-profile.calltrace.cycles-pp.vfs_read.ksys_read.do_syscall_64.entry_SYSCALL_64_after_hwframe.__libc_read 52.39 -4.7 47.68 perf-profile.calltrace.cycles-pp.__libc_write 28.82 ± 4% -4.2 24.66 perf-profile.calltrace.cycles-pp.ksys_read.do_syscall_64.entry_SYSCALL_64_after_hwframe.__libc_read 0.71 ± 9% +0.3 0.96 perf-profile.calltrace.cycles-pp.__pthread_disable_asynccancel 0.68 ± 9% +0.3 0.96 ± 2% perf-profile.calltrace.cycles-pp.file_update_time.pipe_write.new_sync_write.vfs_write.ksys_write 10.15 ± 2% +0.4 10.53 perf-profile.calltrace.cycles-pp.syscall_exit_to_user_mode.do_syscall_64.entry_SYSCALL_64_after_hwframe.__libc_write 0.66 ± 11% +0.4 1.10 ± 2% perf-profile.calltrace.cycles-pp.mutex_unlock.pipe_write.new_sync_write.vfs_write.ksys_write 0.96 ± 9% +0.4 1.41 perf-profile.calltrace.cycles-pp.mutex_lock.pipe_read.new_sync_read.vfs_read.ksys_read 0.00 +0.5 0.52 ± 2% perf-profile.calltrace.cycles-pp.current_time.atime_needs_update.touch_atime.pipe_read.new_sync_read 0.00 +0.5 0.53 ± 2% perf-profile.calltrace.cycles-pp.__x64_sys_write.do_syscall_64.entry_SYSCALL_64_after_hwframe.__libc_write 0.00 +0.6 0.55 ± 2% perf-profile.calltrace.cycles-pp.fput_many.ksys_write.do_syscall_64.entry_SYSCALL_64_after_hwframe.__libc_write 0.00 +0.6 0.59 ± 2% perf-profile.calltrace.cycles-pp.fput_many.ksys_read.do_syscall_64.entry_SYSCALL_64_after_hwframe.__libc_read 0.82 ± 8% +0.6 1.42 ± 11% perf-profile.calltrace.cycles-pp.__fget_light.__fdget_pos.ksys_read.do_syscall_64.entry_SYSCALL_64_after_hwframe 1.03 ± 9% +0.6 1.65 perf-profile.calltrace.cycles-pp.copy_user_enhanced_fast_string.copyout.copy_page_to_iter.pipe_read.new_sync_read 0.82 ± 7% +0.6 1.47 ± 11% perf-profile.calltrace.cycles-pp.__fdget_pos.ksys_read.do_syscall_64.entry_SYSCALL_64_after_hwframe.__libc_read 0.39 ± 70% +0.7 1.05 ± 2% perf-profile.calltrace.cycles-pp.__pthread_enable_asynccancel 0.86 ± 9% +0.7 1.56 perf-profile.calltrace.cycles-pp.copy_user_enhanced_fast_string.copyin.copy_page_from_iter.pipe_write.new_sync_write 1.10 ± 7% +0.7 1.80 perf-profile.calltrace.cycles-pp.atime_needs_update.touch_atime.pipe_read.new_sync_read.vfs_read 1.39 ± 6% +0.7 2.10 ± 2% perf-profile.calltrace.cycles-pp.touch_atime.pipe_read.new_sync_read.vfs_read.ksys_read 0.00 +0.7 0.71 ± 4% perf-profile.calltrace.cycles-pp.mutex_unlock.pipe_read.new_sync_read.vfs_read.ksys_read 1.29 ± 8% +0.8 2.04 ± 7% perf-profile.calltrace.cycles-pp.__fget_light.__fdget_pos.ksys_write.do_syscall_64.entry_SYSCALL_64_after_hwframe 0.00 +0.8 0.76 ± 6% perf-profile.calltrace.cycles-pp.propagate_protected_usage.page_counter_charge.obj_cgroup_charge_pages.__memcg_kmem_charge_page.__alloc_pages 1.16 ± 9% +0.8 1.93 perf-profile.calltrace.cycles-pp.copyout.copy_page_to_iter.pipe_read.new_sync_read.vfs_read 0.83 ± 6% +0.8 1.61 ± 7% perf-profile.calltrace.cycles-pp.common_file_perm.security_file_permission.vfs_write.ksys_write.do_syscall_64 1.30 ± 8% +0.8 2.09 ± 7% perf-profile.calltrace.cycles-pp.__fdget_pos.ksys_write.do_syscall_64.entry_SYSCALL_64_after_hwframe.__libc_write 0.86 ± 7% +0.8 1.70 ± 7% perf-profile.calltrace.cycles-pp.common_file_perm.security_file_permission.vfs_read.ksys_read.do_syscall_64 1.02 ± 9% +0.9 1.90 ± 2% perf-profile.calltrace.cycles-pp.copyin.copy_page_from_iter.pipe_write.new_sync_write.vfs_write 1.66 ± 9% +1.0 2.67 ± 4% perf-profile.calltrace.cycles-pp.mutex_lock.pipe_write.new_sync_write.vfs_write.ksys_write 1.11 ± 8% +1.2 2.36 ± 6% perf-profile.calltrace.cycles-pp.security_file_permission.vfs_write.ksys_write.do_syscall_64.entry_SYSCALL_64_after_hwframe 1.35 ± 8% +1.5 2.82 ± 5% perf-profile.calltrace.cycles-pp.security_file_permission.vfs_read.ksys_read.do_syscall_64.entry_SYSCALL_64_after_hwframe 2.22 ± 9% +1.5 3.72 ± 2% perf-profile.calltrace.cycles-pp.copy_page_from_iter.pipe_write.new_sync_write.vfs_write.ksys_write 2.26 ± 9% +1.7 3.97 perf-profile.calltrace.cycles-pp.copy_page_to_iter.pipe_read.new_sync_read.vfs_read.ksys_read 0.00 +1.9 1.94 ± 4% perf-profile.calltrace.cycles-pp.page_counter_charge.obj_cgroup_charge_pages.__memcg_kmem_charge_page.__alloc_pages.pipe_write 2.78 ± 9% +2.1 4.86 perf-profile.calltrace.cycles-pp.syscall_return_via_sysret.__libc_write 2.86 ± 9% +2.1 4.95 perf-profile.calltrace.cycles-pp.syscall_return_via_sysret.__libc_read 0.00 +2.1 2.12 ± 4% perf-profile.calltrace.cycles-pp.obj_cgroup_charge_pages.__memcg_kmem_charge_page.__alloc_pages.pipe_write.new_sync_write 0.00 +2.2 2.16 ± 4% perf-profile.calltrace.cycles-pp.__memcg_kmem_charge_page.__alloc_pages.pipe_write.new_sync_write.vfs_write 1.26 ± 31% +2.3 3.54 perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_safe_stack.__libc_write 0.00 +2.3 2.30 ± 4% perf-profile.calltrace.cycles-pp.__alloc_pages.pipe_write.new_sync_write.vfs_write.ksys_write 2.50 ± 9% +2.4 4.91 perf-profile.calltrace.cycles-pp.__entry_text_start.__libc_read 2.51 ± 8% +2.5 5.03 perf-profile.calltrace.cycles-pp.__entry_text_start.__libc_write 0.00 +2.7 2.70 ± 2% perf-profile.calltrace.cycles-pp.page_counter_cancel.page_counter_uncharge.uncharge_batch.__mem_cgroup_uncharge.__put_page 1.61 ± 11% +2.8 4.41 ± 3% perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_safe_stack.__libc_read 0.00 +3.0 3.04 ± 4% perf-profile.calltrace.cycles-pp.propagate_protected_usage.page_counter_uncharge.uncharge_batch.__mem_cgroup_uncharge.__put_page 7.16 ± 7% +3.4 10.51 perf-profile.calltrace.cycles-pp.syscall_exit_to_user_mode.do_syscall_64.entry_SYSCALL_64_after_hwframe.__libc_read 45.21 +4.7 49.92 perf-profile.calltrace.cycles-pp.__libc_read 0.00 +6.0 6.05 ± 3% perf-profile.calltrace.cycles-pp.page_counter_uncharge.uncharge_batch.__mem_cgroup_uncharge.__put_page.pipe_read 0.00 +6.2 6.20 ± 3% perf-profile.calltrace.cycles-pp.uncharge_batch.__mem_cgroup_uncharge.__put_page.pipe_read.new_sync_read 0.00 +6.3 6.25 ± 3% perf-profile.calltrace.cycles-pp.__mem_cgroup_uncharge.__put_page.pipe_read.new_sync_read.vfs_read 0.00 +6.3 6.26 ± 3% perf-profile.calltrace.cycles-pp.__put_page.pipe_read.new_sync_read.vfs_read.ksys_read 22.50 ± 10% -21.3 1.16 ± 49% perf-profile.children.cycles-pp.__wake_up_common_lock 21.96 ± 11% -20.8 1.11 ± 50% perf-profile.children.cycles-pp.__wake_up_common 21.76 ± 11% -20.7 1.10 ± 51% perf-profile.children.cycles-pp.autoremove_wake_function 21.51 ± 11% -20.2 1.28 ± 47% perf-profile.children.cycles-pp.try_to_wake_up 20.25 ± 14% -19.1 1.12 ± 54% perf-profile.children.cycles-pp.schedule 20.08 ± 15% -19.0 1.13 ± 55% perf-profile.children.cycles-pp.__schedule 29.50 ± 5% -14.2 15.25 ± 3% perf-profile.children.cycles-pp.pipe_write 30.15 ± 5% -13.9 16.24 ± 3% perf-profile.children.cycles-pp.new_sync_write 14.55 ± 49% -13.5 1.08 ±117% perf-profile.children.cycles-pp.perf_tp_event 13.74 ± 51% -12.7 1.03 ±117% perf-profile.children.cycles-pp.perf_swevent_overflow 13.71 ± 51% -12.7 1.03 ±117% perf-profile.children.cycles-pp.__perf_event_overflow 13.62 ± 51% -12.6 1.02 ±117% perf-profile.children.cycles-pp.perf_event_output_forward 31.84 ± 4% -12.3 19.52 ± 2% perf-profile.children.cycles-pp.vfs_write 13.19 ± 51% -12.3 0.94 ±118% perf-profile.children.cycles-pp.perf_prepare_sample 12.04 ± 51% -11.2 0.86 ±118% perf-profile.children.cycles-pp.perf_callchain 11.96 ± 51% -11.1 0.86 ±118% perf-profile.children.cycles-pp.get_perf_callchain 33.70 ± 4% -10.9 22.84 perf-profile.children.cycles-pp.ksys_write 81.19 ± 2% -10.5 70.66 perf-profile.children.cycles-pp.do_syscall_64 11.08 ± 51% -10.3 0.80 ±118% perf-profile.children.cycles-pp.perf_callchain_kernel 81.93 ± 2% -10.3 71.67 perf-profile.children.cycles-pp.entry_SYSCALL_64_after_hwframe 9.70 ± 33% -8.9 0.81 ± 86% perf-profile.children.cycles-pp.update_curr 8.94 ± 13% -8.4 0.56 ± 53% perf-profile.children.cycles-pp.ttwu_do_activate 8.85 ± 14% -8.3 0.55 ± 54% perf-profile.children.cycles-pp.enqueue_task_fair 8.32 ± 51% -7.7 0.59 ±118% perf-profile.children.cycles-pp.unwind_next_frame 7.88 ± 14% -7.4 0.52 ± 60% perf-profile.children.cycles-pp.dequeue_task_fair 24.85 ± 6% -7.1 17.77 perf-profile.children.cycles-pp.pipe_read 25.41 ± 6% -6.9 18.52 perf-profile.children.cycles-pp.new_sync_read 7.05 ± 49% -6.4 0.60 ±117% perf-profile.children.cycles-pp.perf_trace_sched_stat_runtime 6.18 ± 24% -5.8 0.43 ± 70% perf-profile.children.cycles-pp.enqueue_entity 27.33 ± 5% -5.3 22.05 perf-profile.children.cycles-pp.vfs_read 5.83 ± 5% -5.2 0.62 ± 2% perf-profile.children.cycles-pp.exit_to_user_mode_prepare 52.87 -5.0 47.86 perf-profile.children.cycles-pp.__libc_write 5.14 ± 28% -4.8 0.38 ± 82% perf-profile.children.cycles-pp.dequeue_entity 4.87 ± 50% -4.5 0.34 ±117% perf-profile.children.cycles-pp.__unwind_start 28.87 ± 4% -4.2 24.71 perf-profile.children.cycles-pp.ksys_read 4.38 ± 50% -4.1 0.24 ±118% perf-profile.children.cycles-pp.perf_trace_sched_switch 4.28 ± 13% -4.1 0.14 ± 33% perf-profile.children.cycles-pp._raw_spin_lock 3.81 ± 38% -3.5 0.30 ± 91% perf-profile.children.cycles-pp.perf_trace_sched_wakeup_template 3.63 ± 11% -3.5 0.16 ± 3% perf-profile.children.cycles-pp.select_task_rq_fair 3.45 ± 19% -3.4 0.05 ±111% perf-profile.children.cycles-pp.native_queued_spin_lock_slowpath 3.07 ± 11% -2.9 0.19 ± 3% perf-profile.children.cycles-pp.update_load_avg 2.80 ± 11% -2.6 0.16 ± 5% perf-profile.children.cycles-pp.pick_next_task_fair 2.67 ± 11% -2.5 0.12 ± 3% perf-profile.children.cycles-pp.select_idle_sibling 2.08 ± 51% -1.9 0.15 ±116% perf-profile.children.cycles-pp.__orc_find 1.99 ± 12% -1.8 0.16 ± 13% perf-profile.children.cycles-pp.update_cfs_group 1.80 ± 11% -1.7 0.08 ± 6% perf-profile.children.cycles-pp.select_idle_cpu 1.50 ± 51% -1.4 0.11 ±118% perf-profile.children.cycles-pp.unwind_get_return_address 1.30 ± 11% -1.2 0.10 ± 3% perf-profile.children.cycles-pp.reweight_entity 1.25 ± 51% -1.2 0.09 ±118% perf-profile.children.cycles-pp.orc_find 1.21 ± 51% -1.1 0.09 ±118% perf-profile.children.cycles-pp.__kernel_text_address 1.17 ± 11% -1.1 0.10 ± 6% perf-profile.children.cycles-pp.switch_fpu_return 1.12 ± 12% -1.0 0.08 ± 6% perf-profile.children.cycles-pp.set_next_entity 1.01 ± 52% -0.9 0.07 ±117% perf-profile.children.cycles-pp.kernel_text_address 0.98 ± 12% -0.9 0.09 ± 5% perf-profile.children.cycles-pp.prepare_to_wait_event 0.95 ± 51% -0.9 0.06 ±118% perf-profile.children.cycles-pp.stack_access_ok 0.94 ± 11% -0.9 0.07 ± 8% perf-profile.children.cycles-pp.__switch_to_asm 1.05 ± 11% -0.9 0.18 ± 2% perf-profile.children.cycles-pp._raw_spin_lock_irqsave 0.85 ± 9% -0.8 0.07 perf-profile.children.cycles-pp.__update_load_avg_se 0.84 ± 12% -0.8 0.08 ± 4% perf-profile.children.cycles-pp.restore_fpregs_from_fpstate 0.80 ± 11% -0.7 0.06 ± 7% perf-profile.children.cycles-pp.__switch_to 0.78 ± 11% -0.7 0.04 ± 44% perf-profile.children.cycles-pp.__update_load_avg_cfs_rq 0.76 ± 12% -0.7 0.05 perf-profile.children.cycles-pp.update_rq_clock 0.56 ± 5% -0.5 0.03 ±105% perf-profile.children.cycles-pp.sched_clock_cpu 0.42 ± 12% -0.3 0.09 ± 4% perf-profile.children.cycles-pp.__calc_delta 0.39 ± 10% -0.3 0.07 ± 7% perf-profile.children.cycles-pp.__list_del_entry_valid 0.28 ± 11% -0.2 0.09 perf-profile.children.cycles-pp._raw_spin_lock_irq 0.27 ± 12% -0.2 0.09 ± 4% perf-profile.children.cycles-pp.anon_pipe_buf_release 0.11 ± 4% -0.1 0.06 ± 9% perf-profile.children.cycles-pp.generic_update_time 0.09 ± 4% -0.0 0.04 ± 45% perf-profile.children.cycles-pp.__mark_inode_dirty 0.10 ± 7% +0.0 0.13 ± 5% perf-profile.children.cycles-pp.kill_fasync 0.00 +0.1 0.05 ± 7% perf-profile.children.cycles-pp.uncharge_folio 0.00 +0.1 0.05 ± 8% perf-profile.children.cycles-pp.get_mem_cgroup_from_objcg 0.00 +0.1 0.06 ± 8% perf-profile.children.cycles-pp.__count_memcg_events 0.05 ± 46% +0.1 0.11 ± 5% perf-profile.children.cycles-pp.wake_q_add 0.16 ± 14% +0.1 0.22 ± 6% perf-profile.children.cycles-pp.ktime_get_coarse_real_ts64 0.00 +0.1 0.07 ± 5% perf-profile.children.cycles-pp.rmqueue 0.00 +0.1 0.07 ± 5% perf-profile.children.cycles-pp.free_unref_page 0.17 ± 5% +0.1 0.25 ± 2% perf-profile.children.cycles-pp.syscall_exit_to_user_mode_prepare 0.16 ± 25% +0.1 0.24 ± 3% perf-profile.children.cycles-pp.start_thread 0.10 ± 12% +0.1 0.18 ± 2% perf-profile.children.cycles-pp.iov_iter_init 0.00 +0.1 0.09 ± 4% perf-profile.children.cycles-pp.get_page_from_freelist 0.07 ± 10% +0.1 0.16 ± 4% perf-profile.children.cycles-pp.rw_verify_area 0.00 +0.1 0.10 ± 9% perf-profile.children.cycles-pp.page_counter_try_charge 0.22 ± 10% +0.1 0.33 ± 3% perf-profile.children.cycles-pp.rcu_all_qs 0.54 ± 11% +0.1 0.67 ± 2% perf-profile.children.cycles-pp.__cond_resched 0.33 ± 10% +0.1 0.48 perf-profile.children.cycles-pp.aa_file_perm 0.00 +0.1 0.15 ± 8% perf-profile.children.cycles-pp.try_charge_memcg 0.10 ± 16% +0.2 0.25 ± 17% perf-profile.children.cycles-pp.wake_up_q 0.26 ± 7% +0.2 0.42 perf-profile.children.cycles-pp.timestamp_truncate 0.23 ± 9% +0.2 0.40 ± 5% perf-profile.children.cycles-pp.make_kgid 0.24 ± 13% +0.2 0.42 ± 3% perf-profile.children.cycles-pp.syscall_enter_from_user_mode 0.23 ± 9% +0.2 0.42 ± 2% perf-profile.children.cycles-pp.make_kuid 0.28 ± 8% +0.2 0.49 ± 6% perf-profile.children.cycles-pp.__x64_sys_read 0.30 ± 6% +0.3 0.55 ± 3% perf-profile.children.cycles-pp.__x64_sys_write 0.71 ± 10% +0.3 0.97 perf-profile.children.cycles-pp.__pthread_disable_asynccancel 0.00 +0.3 0.27 ± 9% perf-profile.children.cycles-pp.mutex_spin_on_owner 0.70 ± 9% +0.3 0.98 ± 2% perf-profile.children.cycles-pp.file_update_time 0.78 ± 10% +0.3 1.06 perf-profile.children.cycles-pp.__might_sleep 0.26 ± 20% +0.3 0.55 ± 6% perf-profile.children.cycles-pp.__mutex_unlock_slowpath 0.40 ± 9% +0.3 0.73 ± 3% perf-profile.children.cycles-pp.map_id_range_down 0.50 ± 9% +0.4 0.89 ± 2% perf-profile.children.cycles-pp.__might_fault 0.68 ± 9% +0.4 1.09 ± 2% perf-profile.children.cycles-pp.current_time 0.16 ± 18% +0.5 0.65 ± 8% perf-profile.children.cycles-pp.__mutex_lock 0.55 ± 9% +0.5 1.05 ± 2% perf-profile.children.cycles-pp.__pthread_enable_asynccancel 0.45 ± 11% +0.6 1.00 ± 3% perf-profile.children.cycles-pp.apparmor_file_permission 0.56 ± 9% +0.6 1.14 ± 2% perf-profile.children.cycles-pp.fput_many 1.26 ± 8% +0.6 1.91 perf-profile.children.cycles-pp.__might_resched 1.13 ± 7% +0.7 1.84 perf-profile.children.cycles-pp.atime_needs_update 1.40 ± 6% +0.7 2.12 ± 2% perf-profile.children.cycles-pp.touch_atime 1.17 ± 9% +0.8 1.95 perf-profile.children.cycles-pp.copyout 1.08 ± 10% +0.8 1.85 perf-profile.children.cycles-pp.mutex_unlock 1.05 ± 9% +0.9 1.94 perf-profile.children.cycles-pp.copyin 2.12 ± 8% +1.4 3.49 ± 8% perf-profile.children.cycles-pp.__fget_light 2.20 ± 8% +1.4 3.64 ± 8% perf-profile.children.cycles-pp.__fdget_pos 2.69 ± 9% +1.5 4.18 ± 3% perf-profile.children.cycles-pp.mutex_lock 2.09 ± 9% +1.5 3.60 perf-profile.children.cycles-pp.copy_user_enhanced_fast_string 2.27 ± 9% +1.5 3.79 ± 2% perf-profile.children.cycles-pp.copy_page_from_iter 1.72 ± 6% +1.6 3.35 ± 7% perf-profile.children.cycles-pp.common_file_perm 2.30 ± 9% +1.7 4.03 perf-profile.children.cycles-pp.copy_page_to_iter 0.04 ± 71% +1.9 1.94 ± 4% perf-profile.children.cycles-pp.page_counter_charge 0.07 ± 18% +2.1 2.13 ± 4% perf-profile.children.cycles-pp.obj_cgroup_charge_pages 0.07 ± 15% +2.1 2.16 ± 4% perf-profile.children.cycles-pp.__memcg_kmem_charge_page 0.11 ± 16% +2.2 2.30 ± 4% perf-profile.children.cycles-pp.__alloc_pages 0.15 ± 18% +2.6 2.71 ± 2% perf-profile.children.cycles-pp.page_counter_cancel 2.48 ± 8% +2.7 5.21 ± 5% perf-profile.children.cycles-pp.security_file_permission 1.82 ± 11% +2.9 4.75 perf-profile.children.cycles-pp.entry_SYSCALL_64_safe_stack 17.36 ± 4% +3.8 21.12 perf-profile.children.cycles-pp.syscall_exit_to_user_mode 0.08 ± 16% +3.8 3.88 ± 4% perf-profile.children.cycles-pp.propagate_protected_usage 45.67 +4.4 50.06 perf-profile.children.cycles-pp.__libc_read 6.37 ± 9% +4.7 11.04 perf-profile.children.cycles-pp.syscall_return_via_sysret 6.22 ± 9% +5.8 11.98 perf-profile.children.cycles-pp.__entry_text_start 0.22 ± 16% +5.8 6.05 ± 3% perf-profile.children.cycles-pp.page_counter_uncharge 0.23 ± 16% +6.0 6.20 ± 3% perf-profile.children.cycles-pp.uncharge_batch 0.24 ± 15% +6.0 6.25 ± 3% perf-profile.children.cycles-pp.__mem_cgroup_uncharge 0.24 ± 16% +6.0 6.26 ± 3% perf-profile.children.cycles-pp.__put_page 3.97 ± 50% -3.7 0.28 ±117% perf-profile.self.cycles-pp.unwind_next_frame 3.44 ± 20% -3.4 0.05 ±111% perf-profile.self.cycles-pp.native_queued_spin_lock_slowpath 2.08 ± 51% -1.9 0.15 ±118% perf-profile.self.cycles-pp.__orc_find 1.97 ± 12% -1.8 0.16 ± 14% perf-profile.self.cycles-pp.update_cfs_group 1.51 ± 12% -1.4 0.09 ± 4% perf-profile.self.cycles-pp.__schedule 1.40 ± 13% -1.3 0.07 ± 5% perf-profile.self.cycles-pp.update_load_avg 1.19 ± 8% -1.1 0.06 ± 8% perf-profile.self.cycles-pp.update_curr 1.18 ± 51% -1.1 0.08 ±120% perf-profile.self.cycles-pp.orc_find 0.94 ± 11% -0.9 0.07 ± 8% perf-profile.self.cycles-pp.__switch_to_asm 1.01 ± 10% -0.8 0.16 ± 2% perf-profile.self.cycles-pp._raw_spin_lock_irqsave 0.86 ± 12% -0.8 0.09 ± 5% perf-profile.self.cycles-pp._raw_spin_lock 0.83 ± 9% -0.8 0.07 ± 7% perf-profile.self.cycles-pp.__update_load_avg_se 0.84 ± 12% -0.8 0.08 ± 4% perf-profile.self.cycles-pp.restore_fpregs_from_fpstate 0.80 ± 50% -0.8 0.06 ±119% perf-profile.self.cycles-pp.perf_callchain_kernel 0.80 ± 50% -0.7 0.06 ±119% perf-profile.self.cycles-pp.stack_access_ok 0.74 ± 10% -0.7 0.03 ± 70% perf-profile.self.cycles-pp.__update_load_avg_cfs_rq 0.76 ± 11% -0.7 0.06 perf-profile.self.cycles-pp.__switch_to 0.62 ± 9% -0.6 0.06 ± 6% perf-profile.self.cycles-pp.try_to_wake_up 0.42 ± 11% -0.3 0.08 ± 5% perf-profile.self.cycles-pp.__calc_delta 0.34 ± 10% -0.3 0.06 ± 7% perf-profile.self.cycles-pp.__list_del_entry_valid 0.27 ± 12% -0.2 0.09 ± 4% perf-profile.self.cycles-pp._raw_spin_lock_irq 0.26 ± 12% -0.2 0.08 ± 5% perf-profile.self.cycles-pp.anon_pipe_buf_release 0.09 ± 4% -0.0 0.04 ± 45% perf-profile.self.cycles-pp.__mark_inode_dirty 0.18 ± 5% +0.1 0.24 ± 5% perf-profile.self.cycles-pp.touch_atime 0.00 +0.1 0.05 ± 8% perf-profile.self.cycles-pp.wake_up_q 0.00 +0.1 0.05 ± 8% perf-profile.self.cycles-pp.get_mem_cgroup_from_objcg 0.00 +0.1 0.05 ± 8% perf-profile.self.cycles-pp.__count_memcg_events 0.05 ± 46% +0.1 0.11 ± 3% perf-profile.self.cycles-pp.wake_q_add 0.13 ± 14% +0.1 0.19 ± 7% perf-profile.self.cycles-pp.ktime_get_coarse_real_ts64 0.13 ± 11% +0.1 0.19 ± 5% perf-profile.self.cycles-pp.__fdget_pos 0.06 ± 11% +0.1 0.12 ± 3% perf-profile.self.cycles-pp.copyout 0.06 ± 49% +0.1 0.13 ± 8% perf-profile.self.cycles-pp.__mutex_unlock_slowpath 0.16 ± 7% +0.1 0.23 perf-profile.self.cycles-pp.syscall_exit_to_user_mode_prepare 0.09 ± 9% +0.1 0.17 ± 2% perf-profile.self.cycles-pp.__might_fault 0.25 ± 7% +0.1 0.33 ± 2% perf-profile.self.cycles-pp.__cond_resched 0.09 ± 11% +0.1 0.17 ± 2% perf-profile.self.cycles-pp.iov_iter_init 0.00 +0.1 0.08 ± 4% perf-profile.self.cycles-pp.uncharge_batch 0.06 ± 9% +0.1 0.14 ± 5% perf-profile.self.cycles-pp.rw_verify_area 0.17 ± 11% +0.1 0.26 ± 2% perf-profile.self.cycles-pp.rcu_all_qs 0.06 ± 11% +0.1 0.16 ± 4% perf-profile.self.cycles-pp.copyin 0.28 ± 10% +0.1 0.39 ± 2% perf-profile.self.cycles-pp.file_update_time 0.41 ± 8% +0.1 0.52 ± 2% perf-profile.self.cycles-pp.do_syscall_64 0.50 ± 13% +0.1 0.62 ± 2% perf-profile.self.cycles-pp.new_sync_read 0.55 ± 9% +0.1 0.67 ± 3% perf-profile.self.cycles-pp.vfs_read 0.08 ± 23% +0.1 0.21 ± 8% perf-profile.self.cycles-pp.__mutex_lock 0.31 ± 10% +0.1 0.45 perf-profile.self.cycles-pp.aa_file_perm 0.18 ± 14% +0.1 0.32 ± 3% perf-profile.self.cycles-pp.syscall_enter_from_user_mode 0.24 ± 7% +0.1 0.38 perf-profile.self.cycles-pp.timestamp_truncate 0.33 ± 8% +0.2 0.48 ± 3% perf-profile.self.cycles-pp.atime_needs_update 0.25 ± 7% +0.2 0.43 ± 7% perf-profile.self.cycles-pp.__x64_sys_read 1.29 ± 9% +0.2 1.48 perf-profile.self.cycles-pp.pipe_read 0.29 ± 9% +0.2 0.48 ± 3% perf-profile.self.cycles-pp.current_time 0.36 ± 11% +0.2 0.56 ± 8% perf-profile.self.cycles-pp.ksys_read 0.27 ± 5% +0.2 0.49 ± 4% perf-profile.self.cycles-pp.__x64_sys_write 0.65 ± 10% +0.2 0.89 perf-profile.self.cycles-pp.__pthread_disable_asynccancel 0.69 ± 9% +0.2 0.93 perf-profile.self.cycles-pp.__might_sleep 0.76 ± 10% +0.2 1.01 ± 3% perf-profile.self.cycles-pp.entry_SYSCALL_64_after_hwframe 0.00 +0.3 0.27 ± 9% perf-profile.self.cycles-pp.mutex_spin_on_owner 0.00 +0.3 0.29 ± 5% perf-profile.self.cycles-pp.page_counter_uncharge 0.53 ± 7% +0.3 0.84 ± 4% perf-profile.self.cycles-pp.new_sync_write 0.38 ± 8% +0.3 0.70 ± 3% perf-profile.self.cycles-pp.map_id_range_down 0.56 ± 6% +0.3 0.88 ± 2% perf-profile.self.cycles-pp.vfs_write 0.29 ± 10% +0.3 0.62 ± 5% perf-profile.self.cycles-pp.ksys_write 0.42 ± 8% +0.4 0.79 ± 2% perf-profile.self.cycles-pp.copy_page_from_iter 0.65 ± 10% +0.4 1.07 perf-profile.self.cycles-pp.__libc_read 0.54 ± 9% +0.4 0.98 perf-profile.self.cycles-pp.copy_page_to_iter 0.63 ± 10% +0.5 1.12 ± 2% perf-profile.self.cycles-pp.__libc_write 0.53 ± 9% +0.5 1.03 ± 2% perf-profile.self.cycles-pp.__pthread_enable_asynccancel 0.40 ± 11% +0.5 0.93 ± 3% perf-profile.self.cycles-pp.apparmor_file_permission 0.33 ± 11% +0.6 0.88 ± 13% perf-profile.self.cycles-pp.security_file_permission 0.54 ± 9% +0.6 1.11 ± 2% perf-profile.self.cycles-pp.fput_many 1.24 ± 8% +0.6 1.88 perf-profile.self.cycles-pp.__might_resched 1.46 ± 9% +0.7 2.20 ± 2% perf-profile.self.cycles-pp.pipe_write 1.05 ± 10% +0.8 1.82 perf-profile.self.cycles-pp.mutex_unlock 0.60 ± 11% +0.9 1.51 ± 4% perf-profile.self.cycles-pp.entry_SYSCALL_64_safe_stack 1.66 ± 10% +1.1 2.79 ± 4% perf-profile.self.cycles-pp.mutex_lock 0.03 ± 70% +1.1 1.17 ± 3% perf-profile.self.cycles-pp.page_counter_charge 2.04 ± 8% +1.4 3.41 ± 8% perf-profile.self.cycles-pp.__fget_light 1.37 ± 6% +1.5 2.83 ± 9% perf-profile.self.cycles-pp.common_file_perm 2.07 ± 9% +1.5 3.56 perf-profile.self.cycles-pp.copy_user_enhanced_fast_string 0.15 ± 18% +2.5 2.69 ± 2% perf-profile.self.cycles-pp.page_counter_cancel 0.08 ± 19% +3.8 3.85 ± 4% perf-profile.self.cycles-pp.propagate_protected_usage 6.36 ± 9% +4.7 11.02 perf-profile.self.cycles-pp.syscall_return_via_sysret 5.50 ± 9% +5.3 10.78 perf-profile.self.cycles-pp.__entry_text_start 11.40 ± 9% +8.9 20.30 perf-profile.self.cycles-pp.syscall_exit_to_user_mode 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. --- 0DAY/LKP+ Test Infrastructure Open Source Technology Center https://lists.01.org/hyperkitty/list/[email protected] Intel Corporation Thanks, Oliver Sang

7 months, 2 weeks

1
0
0 / 0

[genirq/msi] 43daaa9982: BUG:KASAN:use-after-free_in__pci_enable_msi_range

by kernel test robot

Greeting, FYI, we noticed the following commit (built with gcc-9): commit: 43daaa99829219efa59a6327839e692066abbe0f ("genirq/msi: Simplify sysfs handling") https://git.kernel.org/cgit/linux/kernel/git/tglx/devel.git msi in testcase: kernel-selftests version: kernel-selftests-x86_64-a1616593-1_20211225 with following parameters: group: group-00 ucode: 0x11 test-description: The kernel contains a set of "self tests" under the tools/testing/selftests/ directory. These are intended to be small unit tests to exercise individual code paths in the kernel. test-url: https://www.kernel.org/doc/Documentation/kselftest.txt on test machine: 288 threads 2 sockets Intel(R) Xeon Phi(TM) CPU 7295 @ 1.50GHz with 80G memory caused below changes (please refer to attached dmesg/kmsg for entire log/backtrace): If you fix the issue, kindly add following tag Reported-by: kernel test robot <oliver.sang(a)intel.com> [ 68.314909][ T12] BUG: KASAN: use-after-free in __pci_enable_msi_range (drivers/pci/msi/msi.h:36 drivers/pci/msi/msi.c:474 drivers/pci/msi/msi.c:905) [ 68.314909][ T12] Read of size 2 at addr ffff888100063664 by task kworker/0:1/12 [ 68.314909][ T12] [ 68.314909][ T12] CPU: 0 PID: 12 Comm: kworker/0:1 Not tainted 5.16.0-rc5-00094-g43daaa998292 #1 [ 68.314909][ T12] Hardware name: Intel Corp. GROVEPORT/GROVEPORT, BIOS GVPRCRB1.86B.0018.D06.1710190403 10/19/2017 [ 68.314909][ T12] Workqueue: events work_for_cpu_fn [ 68.314909][ T12] Call Trace: [ 68.314909][ T12] <TASK> [ 68.314909][ T12] dump_stack_lvl (lib/dump_stack.c:107) [ 68.314909][ T12] print_address_description+0x21/0x140 [ 68.314909][ T12] ? __pci_enable_msi_range (drivers/pci/msi/msi.h:36 drivers/pci/msi/msi.c:474 drivers/pci/msi/msi.c:905) [ 68.314909][ T12] ? __pci_enable_msi_range (drivers/pci/msi/msi.h:36 drivers/pci/msi/msi.c:474 drivers/pci/msi/msi.c:905) [ 68.314909][ T12] kasan_report.cold (mm/kasan/report.c:434 mm/kasan/report.c:450) [ 68.314909][ T12] ? __pci_enable_msi_range (drivers/pci/msi/msi.h:36 drivers/pci/msi/msi.c:474 drivers/pci/msi/msi.c:905) [ 68.314909][ T12] __pci_enable_msi_range (drivers/pci/msi/msi.h:36 drivers/pci/msi/msi.c:474 drivers/pci/msi/msi.c:905) [ 68.314909][ T12] pci_alloc_irq_vectors_affinity (drivers/pci/msi/msi.c:1029) [ 68.314909][ T12] ? pci_enable_msix_range (drivers/pci/msi/msi.c:1008) [ 68.314909][ T12] ? pci_address_to_pio+0x40/0x40 [ 68.314909][ T12] pcie_port_device_register (include/linux/pci.h:1882 drivers/pci/pcie/portdrv_core.c:107 drivers/pci/pcie/portdrv_core.c:178 drivers/pci/pcie/portdrv_core.c:353) [ 68.314909][ T12] ? lock_release (kernel/locking/lockdep.c:438 kernel/locking/lockdep.c:5659) [ 68.314909][ T12] ? pcie_port_service_unregister (drivers/pci/pcie/portdrv_core.c:316) [ 68.314909][ T12] ? pcie_portdrv_remove (drivers/pci/pcie/portdrv_pci.c:103) [ 68.314909][ T12] pcie_portdrv_probe (drivers/pci/pcie/portdrv_pci.c:117) [ 68.314909][ T12] ? pcie_portdrv_remove (drivers/pci/pcie/portdrv_pci.c:103) [ 68.314909][ T12] local_pci_probe (drivers/pci/pci-driver.c:323) [ 68.314909][ T12] ? pci_device_shutdown (drivers/pci/pci-driver.c:305) [ 68.314909][ T12] work_for_cpu_fn (kernel/workqueue.c:5194) [ 68.314909][ T12] process_one_work (arch/x86/include/asm/jump_label.h:27 include/linux/jump_label.h:212 include/trace/events/workqueue.h:108 kernel/workqueue.c:2303) [ 68.314909][ T12] ? rcu_read_unlock (include/linux/rcupdate.h:717 (discriminator 5)) [ 68.314909][ T12] ? pwq_dec_nr_in_flight (kernel/workqueue.c:2193) [ 68.314909][ T12] ? rwlock_bug+0xc0/0xc0 [ 68.314909][ T12] worker_thread (include/linux/list.h:284 kernel/workqueue.c:2446) [ 68.314909][ T12] ? process_one_work (kernel/workqueue.c:2388) [ 68.314909][ T12] kthread (kernel/kthread.c:327) [ 68.314909][ T12] ? set_kthread_struct (kernel/kthread.c:272) [ 68.314909][ T12] ret_from_fork (arch/x86/entry/entry_64.S:301) [ 68.314909][ T12] </TASK> [ 68.314909][ T12] [ 68.314909][ T12] Allocated by task 12: [ 68.314909][ T12] kasan_save_stack (mm/kasan/common.c:38) [ 68.314909][ T12] __kasan_kmalloc (mm/kasan/common.c:46 mm/kasan/common.c:434 mm/kasan/common.c:513 mm/kasan/common.c:522) [ 68.314909][ T12] msi_alloc_desc (include/linux/slab.h:590 include/linux/slab.h:724 kernel/irq/msi.c:39) [ 68.314909][ T12] msi_add_msi_desc (kernel/irq/msi.c:76 (discriminator 9)) [ 68.314909][ T12] msi_setup_msi_desc (drivers/pci/msi/msi.c:366) [ 68.314909][ T12] __pci_enable_msi_range (drivers/pci/msi/msi.c:448 drivers/pci/msi/msi.c:905) [ 68.314909][ T12] pci_alloc_irq_vectors_affinity (drivers/pci/msi/msi.c:1029) [ 68.314909][ T12] pcie_port_device_register (include/linux/pci.h:1882 drivers/pci/pcie/portdrv_core.c:107 drivers/pci/pcie/portdrv_core.c:178 drivers/pci/pcie/portdrv_core.c:353) [ 68.314909][ T12] pcie_portdrv_probe (drivers/pci/pcie/portdrv_pci.c:117) [ 68.314909][ T12] local_pci_probe (drivers/pci/pci-driver.c:323) [ 68.314909][ T12] work_for_cpu_fn (kernel/workqueue.c:5194) [ 68.314909][ T12] process_one_work (arch/x86/include/asm/jump_label.h:27 include/linux/jump_label.h:212 include/trace/events/workqueue.h:108 kernel/workqueue.c:2303) [ 68.314909][ T12] worker_thread (include/linux/list.h:284 kernel/workqueue.c:2446) [ 68.314909][ T12] kthread (kernel/kthread.c:327) [ 68.314909][ T12] ret_from_fork (arch/x86/entry/entry_64.S:301) [ 68.314909][ T12] [ 68.314909][ T12] Freed by task 12: [ 68.314909][ T12] kasan_save_stack (mm/kasan/common.c:38) [ 68.314909][ T12] kasan_set_track (mm/kasan/common.c:46) [ 68.314909][ T12] kasan_set_free_info (mm/kasan/generic.c:372) [ 68.314909][ T12] __kasan_slab_free (mm/kasan/common.c:368 mm/kasan/common.c:328 mm/kasan/common.c:374) [ 68.314909][ T12] kfree (mm/slub.c:1749 mm/slub.c:3513 mm/slub.c:4561) [ 68.314909][ T12] msi_free_msi_descs_range (kernel/irq/msi.c:136 (discriminator 2)) [ 68.314909][ T12] msi_domain_alloc_irqs_descs_locked (kernel/irq/msi.c:955) [ 68.314909][ T12] __pci_enable_msi_range (drivers/pci/msi/msi.c:458 drivers/pci/msi/msi.c:905) [ 68.314909][ T12] pci_alloc_irq_vectors_affinity (drivers/pci/msi/msi.c:1029) [ 68.314909][ T12] pcie_port_device_register (include/linux/pci.h:1882 drivers/pci/pcie/portdrv_core.c:107 drivers/pci/pcie/portdrv_core.c:178 drivers/pci/pcie/portdrv_core.c:353) [ 68.314909][ T12] pcie_portdrv_probe (drivers/pci/pcie/portdrv_pci.c:117) [ 68.314909][ T12] local_pci_probe (drivers/pci/pci-driver.c:323) [ 68.314909][ T12] work_for_cpu_fn (kernel/workqueue.c:5194) [ 68.314909][ T12] process_one_work (arch/x86/include/asm/jump_label.h:27 include/linux/jump_label.h:212 include/trace/events/workqueue.h:108 kernel/workqueue.c:2303) [ 68.314909][ T12] worker_thread (include/linux/list.h:284 kernel/workqueue.c:2446) [ 68.314909][ T12] kthread (kernel/kthread.c:327) [ 68.314909][ T12] ret_from_fork (arch/x86/entry/entry_64.S:301) [ 68.314909][ T12] [ 68.314909][ T12] The buggy address belongs to the object at ffff888100063600 [ 68.314909][ T12] which belongs to the cache kmalloc-128 of size 128 [ 68.314909][ T12] The buggy address is located 100 bytes inside of [ 68.314909][ T12] 128-byte region [ffff888100063600, ffff888100063680) [ 68.314909][ T12] The buggy address belongs to the page: [ 68.314909][ T12] page:00000000f9812823 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x100060 [ 68.314909][ T12] head:00000000f9812823 order:2 compound_mapcount:0 compound_pincount:0 [ 68.314909][ T12] flags: 0x17ffffc0010200(slab|head|node=0|zone=2|lastcpupid=0x1fffff) [ 68.314909][ T12] raw: 0017ffffc0010200 0000000000000000 dead000000000122 ffff88810004c8c0 [ 68.314909][ T12] raw: 0000000000000000 0000000080400040 00000001ffffffff 0000000000000000 [ 68.314909][ T12] page dumped because: kasan: bad access detected [ 68.314909][ T12] [ 68.314909][ T12] Memory state around the buggy address: [ 68.314909][ T12] ffff888100063500: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 fc fc [ 68.314909][ T12] ffff888100063580: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 68.314909][ T12] >ffff888100063600: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 68.314909][ T12] ^ [ 68.314909][ T12] ffff888100063680: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 68.314909][ T12] ffff888100063700: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 fc fc [ 68.314909][ T12] ================================================================== [ 68.314909][ T12] Disabling lock debugging due to kernel taint [ 68.906957][ T12] pcieport 0000:00:01.0: PME: Signaling with IRQ 24 [ 68.929322][ T12] pcieport 0000:00:01.0: AER: enabled with IRQ 24 [ 68.951517][ T12] sysfs: cannot create duplicate filename '/devices/pci0000:00/0000:00:02.0/msi_irqs/25' [ 68.962445][ T12] CPU: 0 PID: 12 Comm: kworker/0:1 Tainted: G B 5.16.0-rc5-00094-g43daaa998292 #1 [ 68.963411][ T12] Hardware name: Intel Corp. GROVEPORT/GROVEPORT, BIOS GVPRCRB1.86B.0018.D06.1710190403 10/19/2017 [ 68.963411][ T12] Workqueue: events work_for_cpu_fn To reproduce: git clone https://github.com/intel/lkp-tests.git cd lkp-tests sudo bin/lkp install job.yaml # job file is attached in this email bin/lkp split-job --compatible job.yaml # generate the yaml file for lkp run sudo bin/lkp run generated-yaml-file # if come across any failure that blocks the test, # please remove ~/.lkp and /lkp dir to run from a clean state. --- 0DAY/LKP+ Test Infrastructure Open Source Technology Center https://lists.01.org/hyperkitty/list/[email protected] Intel Corporation Thanks, Oliver Sang

7 months, 2 weeks

1
0
0 / 0

[signal] 6c3118c321: will-it-scale.per_thread_ops 13.2% improvement

by kernel test robot

(for previous report "[x86/signal] 3aac3ebea0: will-it-scale.per_thread_ops -11.9% regression" [1] which this 6c3118c321 is targeting for, we found we only tested tglx’s diff shown in here: https://lore.kernel.org/lkml/[email protected]/, but didn't test this patch, so still send out this report FYI [1] https://lore.kernel.org/lkml/[email protected]/) Greeting, FYI, we noticed a 13.2% improvement of will-it-scale.per_thread_ops due to commit: commit: 6c3118c32129b4197999a8928ba776bcabd0f5c4 ("signal: Skip the altstack update when not needed") https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git master in testcase: will-it-scale on test machine: 144 threads 4 sockets Intel(R) Xeon(R) CPU E7-8890 v3 @ 2.50GHz with 512G memory with following parameters: nr_task: 100% mode: thread test: signal1 cpufreq_governor: performance ucode: 0x16 test-description: Will It Scale takes a testcase and runs it from 1 through to n parallel copies to see if the testcase will scale. It builds both a process and threads based test in order to see any differences between the two. test-url: https://github.com/antonblanchard/will-it-scale Details are as below: --------------------------------------------------------------------------------------------------> To reproduce: git clone https://github.com/intel/lkp-tests.git cd lkp-tests sudo bin/lkp install job.yaml # job file is attached in this email bin/lkp split-job --compatible job.yaml # generate the yaml file for lkp run sudo bin/lkp run generated-yaml-file # if come across any failure that blocks the test, # please remove ~/.lkp and /lkp dir to run from a clean state. ========================================================================================= compiler/cpufreq_governor/kconfig/mode/nr_task/rootfs/tbox_group/test/testcase/ucode: gcc-9/performance/x86_64-rhel-8.3/thread/100%/debian-10.4-x86_64-20200603.cgz/lkp-hsw-4ex1/signal1/will-it-scale/0x16 commit: cabdc3a847 ("sched,x86: Don't use cluster topology for x86 hybrid CPUs") 6c3118c321 ("signal: Skip the altstack update when not needed") cabdc3a8475b918e 6c3118c32129b4197999a8928ba ---------------- --------------------------- %stddev %change %stddev \ | \ 252712 +13.2% 286175 will-it-scale.144.threads 1754 +13.2% 1987 will-it-scale.per_thread_ops 252712 +13.2% 286175 will-it-scale.workload 45399 ± 49% +65.3% 75024 ± 5% numa-numastat.node1.other_node 1461 ± 31% -43.9% 820.50 ± 25% numa-meminfo.node1.Active 1461 ± 31% -43.9% 820.50 ± 25% numa-meminfo.node1.Active(anon) 2010729 ± 44% -99.8% 3939 ± 96% numa-meminfo.node2.FilePages 2006836 ± 44% -100.0% 135.17 ± 88% numa-meminfo.node2.Unevictable 361.83 ± 30% -43.3% 205.00 ± 26% numa-vmstat.node1.nr_active_anon 361.83 ± 30% -43.3% 205.00 ± 26% numa-vmstat.node1.nr_zone_active_anon 67182 ± 32% +43.4% 96361 ± 4% numa-vmstat.node1.numa_other 502682 ± 44% -99.8% 984.83 ± 96% numa-vmstat.node2.nr_file_pages 501709 ± 44% -100.0% 33.33 ± 89% numa-vmstat.node2.nr_unevictable 501709 ± 44% -100.0% 33.33 ± 89% numa-vmstat.node2.nr_zone_unevictable 30244982 -3.0% 29346668 perf-stat.i.cache-references 1689 +1.2% 1709 perf-stat.i.context-switches 6.01e+08 ± 2% +9.4% 6.572e+08 perf-stat.i.dTLB-stores 0.33 -3.3% 0.32 perf-stat.overall.MPKI 1.104e+08 -11.6% 97613125 perf-stat.overall.path-length 30288439 -2.7% 29479951 perf-stat.ps.cache-references 1680 +1.3% 1701 perf-stat.ps.context-switches 5.995e+08 ± 2% +9.4% 6.557e+08 perf-stat.ps.dTLB-stores 10120822 ± 3% -9.2e+05 9195947 ± 2% syscalls.sys_getpid.noise.2% 9318091 ± 4% -1.1e+06 8255028 ± 3% syscalls.sys_getpid.noise.25% 10007277 ± 3% -9.4e+05 9071322 ± 2% syscalls.sys_getpid.noise.5% 10229292 ± 3% -7.6e+05 9466206 ± 3% syscalls.sys_gettid.noise.2% 9734831 ± 3% -8e+05 8938625 ± 3% syscalls.sys_gettid.noise.25% 10103340 ± 3% -7.8e+05 9322792 ± 3% syscalls.sys_gettid.noise.5% 1.597e+09 ± 9% -7.3e+08 8.641e+08 ± 22% syscalls.sys_rt_sigprocmask.noise.2% 4.123e+08 ± 41% -3.6e+08 52527108 ± 85% syscalls.sys_rt_sigprocmask.noise.25% 1.552e+09 ± 9% -7.8e+08 7.753e+08 ± 27% syscalls.sys_rt_sigprocmask.noise.5% 349534 -10.1% 314361 ± 4% syscalls.sys_tgkill.max 1.551e+09 ± 6% -6.2e+08 9.279e+08 ± 20% syscalls.sys_tgkill.noise.2% 3.251e+08 ± 35% -2.6e+08 66880605 ± 79% syscalls.sys_tgkill.noise.25% 1.503e+09 ± 7% -6.6e+08 8.453e+08 ± 24% syscalls.sys_tgkill.noise.5% 12.27 -12.3 0.00 perf-profile.calltrace.cycles-pp.__x64_sys_rt_sigreturn.do_syscall_64.entry_SYSCALL_64_after_hwframe.raise 12.24 -12.2 0.00 perf-profile.calltrace.cycles-pp.restore_altstack.__x64_sys_rt_sigreturn.do_syscall_64.entry_SYSCALL_64_after_hwframe.raise 12.23 -12.2 0.00 perf-profile.calltrace.cycles-pp.do_sigaltstack.restore_altstack.__x64_sys_rt_sigreturn.do_syscall_64.entry_SYSCALL_64_after_hwframe 12.14 -12.1 0.00 perf-profile.calltrace.cycles-pp._raw_spin_lock_irq.do_sigaltstack.restore_altstack.__x64_sys_rt_sigreturn.do_syscall_64 12.11 -12.1 0.00 perf-profile.calltrace.cycles-pp.native_queued_spin_lock_slowpath._raw_spin_lock_irq.do_sigaltstack.restore_altstack.__x64_sys_rt_sigreturn 72.76 -4.8 67.94 perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.raise 72.78 -4.8 67.96 perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.raise 72.97 -4.8 68.18 perf-profile.calltrace.cycles-pp.raise 15.95 +1.1 17.02 perf-profile.calltrace.cycles-pp.native_queued_spin_lock_slowpath._raw_spin_lock_irqsave.__lock_task_sighand.do_send_sig_info.do_send_specific 15.99 +1.1 17.06 perf-profile.calltrace.cycles-pp._raw_spin_lock_irqsave.__lock_task_sighand.do_send_sig_info.do_send_specific.do_tkill 15.99 +1.1 17.06 perf-profile.calltrace.cycles-pp.__lock_task_sighand.do_send_sig_info.do_send_specific.do_tkill.__x64_sys_tgkill 16.22 +1.1 17.33 perf-profile.calltrace.cycles-pp.do_send_sig_info.do_send_specific.do_tkill.__x64_sys_tgkill.do_syscall_64 16.30 +1.1 17.40 perf-profile.calltrace.cycles-pp.__x64_sys_tgkill.do_syscall_64.entry_SYSCALL_64_after_hwframe.raise 16.28 +1.1 17.39 perf-profile.calltrace.cycles-pp.do_send_specific.do_tkill.__x64_sys_tgkill.do_syscall_64.entry_SYSCALL_64_after_hwframe 16.30 +1.1 17.40 perf-profile.calltrace.cycles-pp.do_tkill.__x64_sys_tgkill.do_syscall_64.entry_SYSCALL_64_after_hwframe.raise 14.11 +1.9 16.01 perf-profile.calltrace.cycles-pp.native_queued_spin_lock_slowpath._raw_spin_lock_irq.__set_current_blocked.signal_setup_done.arch_do_signal_or_restart 14.14 +1.9 16.04 perf-profile.calltrace.cycles-pp._raw_spin_lock_irq.__set_current_blocked.signal_setup_done.arch_do_signal_or_restart.exit_to_user_mode_prepare 14.27 +1.9 16.20 perf-profile.calltrace.cycles-pp.signal_setup_done.arch_do_signal_or_restart.exit_to_user_mode_prepare.syscall_exit_to_user_mode.do_syscall_64 14.26 +1.9 16.19 perf-profile.calltrace.cycles-pp.__set_current_blocked.signal_setup_done.arch_do_signal_or_restart.exit_to_user_mode_prepare.syscall_exit_to_user_mode 14.29 +1.9 16.22 perf-profile.calltrace.cycles-pp.exit_to_user_mode_prepare.syscall_exit_to_user_mode.do_syscall_64.entry_SYSCALL_64_after_hwframe.handler 14.34 +1.9 16.28 perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.handler 14.53 +1.9 16.46 perf-profile.calltrace.cycles-pp.native_queued_spin_lock_slowpath._raw_spin_lock_irq.get_signal.arch_do_signal_or_restart.exit_to_user_mode_prepare 14.34 +1.9 16.28 perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.handler 14.34 +1.9 16.28 perf-profile.calltrace.cycles-pp.syscall_exit_to_user_mode.do_syscall_64.entry_SYSCALL_64_after_hwframe.handler 14.56 +1.9 16.50 perf-profile.calltrace.cycles-pp._raw_spin_lock_irq.get_signal.arch_do_signal_or_restart.exit_to_user_mode_prepare.syscall_exit_to_user_mode 14.40 +1.9 16.35 perf-profile.calltrace.cycles-pp.handler 14.88 +2.0 16.84 perf-profile.calltrace.cycles-pp.exit_to_user_mode_prepare.syscall_exit_to_user_mode.do_syscall_64.entry_SYSCALL_64_after_hwframe.raise 14.74 +2.0 16.72 perf-profile.calltrace.cycles-pp.get_signal.arch_do_signal_or_restart.exit_to_user_mode_prepare.syscall_exit_to_user_mode.do_syscall_64 15.26 +2.0 17.30 perf-profile.calltrace.cycles-pp.syscall_exit_to_user_mode.do_syscall_64.entry_SYSCALL_64_after_hwframe.raise 12.25 +2.8 15.03 perf-profile.calltrace.cycles-pp.native_queued_spin_lock_slowpath._raw_spin_lock_irq.__set_current_blocked.__x64_sys_rt_sigreturn.do_syscall_64 12.28 +2.8 15.07 perf-profile.calltrace.cycles-pp._raw_spin_lock_irq.__set_current_blocked.__x64_sys_rt_sigreturn.do_syscall_64.entry_SYSCALL_64_after_hwframe 12.39 +2.8 15.22 perf-profile.calltrace.cycles-pp.__set_current_blocked.__x64_sys_rt_sigreturn.do_syscall_64.entry_SYSCALL_64_after_hwframe.__restore_rt 12.42 +2.8 15.25 perf-profile.calltrace.cycles-pp.__x64_sys_rt_sigreturn.do_syscall_64.entry_SYSCALL_64_after_hwframe.__restore_rt 12.46 +2.8 15.30 perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.__restore_rt 12.46 +2.8 15.30 perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.__restore_rt 12.47 +2.8 15.31 perf-profile.calltrace.cycles-pp.__restore_rt 29.10 +3.9 33.02 perf-profile.calltrace.cycles-pp.arch_do_signal_or_restart.exit_to_user_mode_prepare.syscall_exit_to_user_mode.do_syscall_64.entry_SYSCALL_64_after_hwframe 28.35 +4.2 32.52 perf-profile.calltrace.cycles-pp.native_queued_spin_lock_slowpath._raw_spin_lock_irq.__set_current_blocked.sigprocmask.__x64_sys_rt_sigprocmask 28.42 +4.2 32.61 perf-profile.calltrace.cycles-pp._raw_spin_lock_irq.__set_current_blocked.sigprocmask.__x64_sys_rt_sigprocmask.do_syscall_64 28.69 +4.2 32.92 perf-profile.calltrace.cycles-pp.sigprocmask.__x64_sys_rt_sigprocmask.do_syscall_64.entry_SYSCALL_64_after_hwframe.raise 28.68 +4.2 32.90 perf-profile.calltrace.cycles-pp.__set_current_blocked.sigprocmask.__x64_sys_rt_sigprocmask.do_syscall_64.entry_SYSCALL_64_after_hwframe 28.72 +4.2 32.96 perf-profile.calltrace.cycles-pp.__x64_sys_rt_sigprocmask.do_syscall_64.entry_SYSCALL_64_after_hwframe.raise 12.24 -12.2 0.00 perf-profile.children.cycles-pp.restore_altstack 12.24 -12.2 0.00 perf-profile.children.cycles-pp.do_sigaltstack 24.70 -9.4 15.30 perf-profile.children.cycles-pp.__x64_sys_rt_sigreturn 72.99 -4.8 68.20 perf-profile.children.cycles-pp.raise 81.54 -1.3 80.22 perf-profile.children.cycles-pp._raw_spin_lock_irq 97.30 -0.3 97.04 perf-profile.children.cycles-pp.native_queued_spin_lock_slowpath 99.66 -0.1 99.61 perf-profile.children.cycles-pp.entry_SYSCALL_64_after_hwframe 99.64 -0.1 99.59 perf-profile.children.cycles-pp.do_syscall_64 0.05 +0.0 0.06 perf-profile.children.cycles-pp.restore_sigcontext 0.06 +0.0 0.07 perf-profile.children.cycles-pp.__setup_rt_frame 0.11 +0.0 0.12 ± 3% perf-profile.children.cycles-pp.__send_signal 0.09 ± 5% +0.0 0.11 ± 3% perf-profile.children.cycles-pp.__rb_reserve_next 0.11 ± 4% +0.0 0.12 ± 3% perf-profile.children.cycles-pp.__entry_text_start 0.14 ± 3% +0.0 0.16 ± 3% perf-profile.children.cycles-pp.recalc_sigpending 0.13 ± 2% +0.0 0.15 ± 3% perf-profile.children.cycles-pp.__set_task_blocked 0.13 ± 3% +0.0 0.16 ± 3% perf-profile.children.cycles-pp.ring_buffer_lock_reserve 0.15 +0.0 0.17 ± 4% perf-profile.children.cycles-pp.ftrace_syscall_exit 0.18 ± 2% +0.0 0.20 ± 2% perf-profile.children.cycles-pp.syscall_exit_to_user_mode_prepare 0.17 ± 2% +0.0 0.20 ± 3% perf-profile.children.cycles-pp.trace_buffer_lock_reserve 0.20 ± 3% +0.0 0.24 ± 2% perf-profile.children.cycles-pp.syscall_trace_enter 0.18 ± 3% +0.0 0.21 ± 3% perf-profile.children.cycles-pp.ftrace_syscall_enter 16.00 +1.1 17.07 perf-profile.children.cycles-pp._raw_spin_lock_irqsave 15.99 +1.1 17.06 perf-profile.children.cycles-pp.__lock_task_sighand 16.23 +1.1 17.33 perf-profile.children.cycles-pp.do_send_sig_info 16.30 +1.1 17.40 perf-profile.children.cycles-pp.__x64_sys_tgkill 16.28 +1.1 17.39 perf-profile.children.cycles-pp.do_send_specific 16.30 +1.1 17.40 perf-profile.children.cycles-pp.do_tkill 14.27 +1.9 16.20 perf-profile.children.cycles-pp.signal_setup_done 14.40 +1.9 16.35 perf-profile.children.cycles-pp.handler 14.75 +2.0 16.73 perf-profile.children.cycles-pp.get_signal 12.47 +2.8 15.31 perf-profile.children.cycles-pp.__restore_rt 29.16 +3.9 33.06 perf-profile.children.cycles-pp.exit_to_user_mode_prepare 29.10 +3.9 33.02 perf-profile.children.cycles-pp.arch_do_signal_or_restart 29.62 +4.0 33.58 perf-profile.children.cycles-pp.syscall_exit_to_user_mode 28.69 +4.2 32.92 perf-profile.children.cycles-pp.sigprocmask 28.72 +4.2 32.96 perf-profile.children.cycles-pp.__x64_sys_rt_sigprocmask 55.35 +9.0 64.33 perf-profile.children.cycles-pp.__set_current_blocked 97.30 -0.3 97.04 perf-profile.self.cycles-pp.native_queued_spin_lock_slowpath 0.10 ± 4% +0.0 0.11 perf-profile.self.cycles-pp.recalc_sigpending 0.28 +0.0 0.32 perf-profile.self.cycles-pp.syscall_exit_to_user_mode 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. --- 0DAY/LKP+ Test Infrastructure Open Source Technology Center https://lists.01.org/hyperkitty/list/[email protected] Intel Corporation Thanks, Oliver Sang

7 months, 2 weeks

1
0
0 / 0

传统的薪酬模式为什么无法激励员工，反而只会增加企业成本？

by 股权激励官方报名处

如果您公司有遇到以下2个问题及以上，您应该尽快来学习了： ✦ 年底了，不知道怎么给核心人员分红？ ✦ 企业缺乏清晰的战略规划，因此无法确定人力资源战略和薪酬战略，薪酬管理迷失方向。 ✦ 优秀人才进不来，用不起，留不住！ ✦ 员工积极性不高，优秀人才不断流失，外部人才不愿加入？ ✦ 企业自身定位不清晰，上下理解不一致，部门和团队难以形成合力，没有业绩推动手段，目标达成率低。 ✦ 企业上下游无法形成产业链的共赢格局？形成利益、荣誉共同体？ ✦ 高工资、高奖金为什么还是留不住人，“另立高山”现象屡屡发生？如何避免有能力的员工跳槽，成为自己的竞争对手？ ✦ 一、二代交接班未雨绸缪、提上日程，如何在维稳的同时，实现企业持续增长？ ✦ 激发新员工梦想、激发老员工动力，企业元老级员工如何安置、如何股权释兵权？企业如何传？帮？带？保持和焕发企业的活力？ ✦ 股东之间、特别是出资不出力股东与出资又出力股东，以及不出资但出力的在职股东之间彼此猜忌、内耗不断？、 ✦ 员工、股东进入、退出机制约定及合同条款不清晰？ ✦ 找不到合伙人，不懂股权规划，不知怎么激励员工，不会处理股东之间的矛盾？ ✦ 公司章程应该怎么修订？哪些是可以自行约定的事项？ ✦ 如何确保股改方案在企业上市时的无缝衔接？保障企业的顺利上市？华一世纪《股权激励与股权布局方案班》帮您解决以上问题！华一世纪《股权激励与股权布局方案班》2天实战学习：【第一天】是内部团队股权什么时候分，分多少，怎么分，怎么进入，怎么考核，如何退出，怎么签协议，如何防范风险和雷区。【第一天晚上】有个性化的股权问题咨询环节，可以咨询解答自己的问题【第二天】是讲如何利用股权杠杆进行资源整合。如何股权布局，如何股权融资和众筹，实现产业升级，商业模式优化，让老板把握控制权同时，实现企业裂变！【课程价值】：【对内】：您将学会一套如何在企业导入一套股权激励机制，吸引和留住管理人才、营销人才、技术人才、让员工发自内心的忠诚于公司，和公司形成利益、事业的共同体，提高员工积极性？【对外】：您将学会基于未来发展做好股权布局，股权分配！优化和调整目前的股权设置！做好股权布局之后才能做股权融资，资源整合，实现企业裂变，整合有资金，有资源的人为您所用！【近期几天开课安排】： 12月23-24 厦门重庆深圳德州 12月24-25 海口宜昌扬州 12月25-26 长沙青岛贵阳邯郸常州株洲大连 12月27-28 东莞 12月28-29 上海济南南通沈阳佛山郑州义乌襄阳株洲深圳 12月29-30 成都广州杭州临沂 12月30-31 北京南宁昆明苏州武汉福州石家庄学习费用：现场报名1280元/位，提前线上报名仅需要980元/位近期课程安排点击【https://jinshuju.net/f/P0lbe4】报名成功赠送价值1980股权激励、股权合伙协议工具包马上咨询联系：13928826727林峰老师（Wechat、电话同号）

7 months, 2 weeks

1
0
0 / 0

WE FINANCE YOUR PROJECT

by Vander Sergiy

7 months, 2 weeks

1
0
0 / 0

[tcp] f35f821935: netperf.Throughput_Mbps 2.7% improvement

by kernel test robot

Greeting, FYI, we noticed a 2.7% improvement of netperf.Throughput_Mbps due to commit: commit: f35f821935d8df76f9c92e2431a225bdff938169 ("tcp: defer skb freeing after socket lock is released") https://git.kernel.org/cgit/linux/kernel/git/next/linux-next.git master in testcase: netperf on test machine: 128 threads 2 sockets Intel(R) Xeon(R) Gold 6338 CPU @ 2.00GHz with 256G memory with following parameters: ip: ipv4 runtime: 900s nr_threads: 25% cluster: cs-localhost test: TCP_MAERTS cpufreq_governor: performance ucode: 0xd000280 test-description: Netperf is a benchmark that can be use to measure various aspect of networking performance. test-url: http://www.netperf.org/netperf/ Details are as below: --------------------------------------------------------------------------------------------------> To reproduce: git clone https://github.com/intel/lkp-tests.git cd lkp-tests sudo bin/lkp install job.yaml # job file is attached in this email bin/lkp split-job --compatible job.yaml # generate the yaml file for lkp run sudo bin/lkp run generated-yaml-file # if come across any failure that blocks the test, # please remove ~/.lkp and /lkp dir to run from a clean state. ========================================================================================= cluster/compiler/cpufreq_governor/ip/kconfig/nr_threads/rootfs/runtime/tbox_group/test/testcase/ucode: cs-localhost/gcc-9/performance/ipv4/x86_64-rhel-8.3/25%/debian-10.4-x86_64-20200603.cgz/900s/lkp-icl-2sp2/TCP_MAERTS/netperf/0xd000280 commit: 3df684c1a3 ("tcp: avoid indirect calls to sock_rfree") f35f821935 ("tcp: defer skb freeing after socket lock is released") 3df684c1a3d08a4f f35f821935d8df76f9c92e2431a ---------------- --------------------------- %stddev %change %stddev \ | \ 46835 +2.7% 48102 netperf.Throughput_Mbps 1498722 +2.7% 1539295 netperf.Throughput_total_Mbps 1.029e+10 +2.7% 1.057e+10 netperf.workload 3226364 -6.4% 3020699 vmstat.system.cs 1847551 -5.7% 1742171 vmstat.system.in 249851 ± 4% -21.7% 195749 ± 5% proc-vmstat.numa_hint_faults 155725 ± 12% -36.3% 99250 ± 10% proc-vmstat.numa_hint_faults_local 5.172e+09 +2.7% 5.311e+09 proc-vmstat.numa_hit 5.178e+09 +2.7% 5.316e+09 proc-vmstat.numa_local 454125 ± 5% -16.3% 379962 ± 8% proc-vmstat.numa_pte_updates 5.151e+09 +2.7% 5.29e+09 proc-vmstat.pgalloc_normal 3022267 -2.5% 2945931 proc-vmstat.pgfault 5.151e+09 +2.7% 5.29e+09 proc-vmstat.pgfree 0.87 +0.0 0.88 perf-stat.i.branch-miss-rate% 1.703e+08 +2.4% 1.744e+08 perf-stat.i.branch-misses 2.00 ± 10% -1.4 0.59 ± 16% perf-stat.i.cache-miss-rate% 1.379e+08 ± 10% -70.2% 41095249 ± 16% perf-stat.i.cache-misses 7.008e+09 +2.2% 7.166e+09 perf-stat.i.cache-references 3235319 -6.3% 3030634 perf-stat.i.context-switches 1402 ± 11% +214.0% 4402 ± 14% perf-stat.i.cycles-between-cache-misses 0.01 ± 13% -0.0 0.01 ± 7% perf-stat.i.dTLB-load-miss-rate% 3104591 ± 12% -40.1% 1859125 ± 6% perf-stat.i.dTLB-load-misses 0.02 ± 19% -0.0 0.01 ± 11% perf-stat.i.dTLB-store-miss-rate% 2650589 ± 18% -55.1% 1190688 ± 10% perf-stat.i.dTLB-store-misses 695.73 ± 10% -69.3% 213.38 ± 13% perf-stat.i.metric.K/sec 3198 -2.4% 3120 perf-stat.i.minor-faults 4115098 ± 33% -63.6% 1496146 ± 68% perf-stat.i.node-load-misses 17026585 ± 8% -88.3% 1984294 ± 15% perf-stat.i.node-loads 8.20 ± 31% -5.0 3.25 ± 33% perf-stat.i.node-store-miss-rate% 6326873 ± 36% -90.1% 624025 ± 38% perf-stat.i.node-store-misses 57132109 ± 8% -66.8% 18949773 ± 12% perf-stat.i.node-stores 3198 -2.4% 3120 perf-stat.i.page-faults 0.87 +0.0 0.88 perf-stat.overall.branch-miss-rate% 1.97 ± 10% -1.4 0.57 ± 16% perf-stat.overall.cache-miss-rate% 1190 ± 10% +243.7% 4090 ± 14% perf-stat.overall.cycles-between-cache-misses 0.01 ± 13% -0.0 0.01 ± 7% perf-stat.overall.dTLB-load-miss-rate% 0.02 ± 19% -0.0 0.01 ± 11% perf-stat.overall.dTLB-store-miss-rate% 9.68 ± 27% -6.5 3.14 ± 33% perf-stat.overall.node-store-miss-rate% 1.701e+08 +2.4% 1.742e+08 perf-stat.ps.branch-misses 1.38e+08 ± 10% -70.2% 41085412 ± 16% perf-stat.ps.cache-misses 7e+09 +2.3% 7.157e+09 perf-stat.ps.cache-references 3231102 -6.3% 3025956 perf-stat.ps.context-switches 3103499 ± 12% -40.1% 1857818 ± 6% perf-stat.ps.dTLB-load-misses 2650378 ± 18% -55.1% 1189961 ± 10% perf-stat.ps.dTLB-store-misses 3196 -2.6% 3113 perf-stat.ps.minor-faults 4109696 ± 33% -63.6% 1494968 ± 68% perf-stat.ps.node-load-misses 17063381 ± 8% -88.4% 1986897 ± 15% perf-stat.ps.node-loads 6315533 ± 36% -90.1% 623973 ± 38% perf-stat.ps.node-store-misses 57192293 ± 8% -66.9% 18946848 ± 12% perf-stat.ps.node-stores 3196 -2.6% 3113 perf-stat.ps.page-faults 11764009 ± 12% +20.7% 14204549 ± 13% softirqs.CPU0.NET_RX 34928829 -22.5% 27073978 ± 10% softirqs.CPU104.NET_RX 34165378 ± 2% -19.7% 27440714 ± 17% softirqs.CPU106.NET_RX 181590 ± 5% -24.8% 136623 ± 12% softirqs.CPU108.SCHED 35585826 ± 8% -18.9% 28875458 ± 12% softirqs.CPU112.NET_RX 183936 ± 6% -23.6% 140579 ± 20% softirqs.CPU117.SCHED 26078 ± 25% +46.3% 38164 ± 31% softirqs.CPU117.TIMER 17440694 ± 16% +41.5% 24682279 ± 11% softirqs.CPU13.NET_RX 23054 ± 10% +51.6% 34955 ± 15% softirqs.CPU13.TIMER 18420656 ± 12% +37.6% 25349298 ± 21% softirqs.CPU14.NET_RX 17898702 ± 13% +45.1% 25968154 ± 11% softirqs.CPU15.NET_RX 18887452 ± 17% +45.8% 27533668 ± 22% softirqs.CPU17.NET_RX 18180397 ± 12% +32.9% 24155147 ± 16% softirqs.CPU18.NET_RX 23970 ± 16% +34.9% 32347 ± 23% softirqs.CPU18.TIMER 19496397 ± 15% +41.6% 27603702 ± 19% softirqs.CPU19.NET_RX 26590 ± 18% +44.8% 38510 ± 30% softirqs.CPU19.TIMER 22703 ± 16% +60.4% 36414 ± 20% softirqs.CPU2.TIMER 14881139 ± 11% +58.7% 23621724 ± 17% softirqs.CPU20.NET_RX 19409 ± 7% +73.1% 33600 ± 22% softirqs.CPU20.TIMER 16771121 ± 16% +60.5% 26922665 ± 12% softirqs.CPU21.NET_RX 22836 ± 21% +71.9% 39258 ± 16% softirqs.CPU21.TIMER 16462080 ± 18% +43.5% 23626143 ± 15% softirqs.CPU22.NET_RX 21350 ± 13% +53.1% 32683 ± 18% softirqs.CPU22.TIMER 15693571 ± 22% +34.7% 21145540 ± 12% softirqs.CPU23.NET_RX 20908 ± 22% +49.9% 31344 ± 12% softirqs.CPU23.TIMER 18354997 ± 16% +33.8% 24561687 ± 16% softirqs.CPU27.NET_RX 25486 ± 20% +40.2% 35731 ± 14% softirqs.CPU27.TIMER 17721360 ± 15% +46.4% 25948374 ± 21% softirqs.CPU31.NET_RX 24652 ± 15% +47.8% 36438 ± 19% softirqs.CPU31.TIMER 13410554 ± 18% +45.2% 19467979 ± 18% softirqs.CPU34.NET_RX 19563 ± 15% +50.2% 29378 ± 32% softirqs.CPU35.TIMER 15622945 ± 23% +61.7% 25258280 ± 24% softirqs.CPU36.NET_RX 20829 ± 22% +61.2% 33574 ± 30% softirqs.CPU36.TIMER 117910 ± 5% +12.6% 132808 ± 6% softirqs.CPU37.SCHED 15935254 ± 11% +53.1% 24389416 ± 20% softirqs.CPU38.NET_RX 16079423 ± 22% +48.6% 23886577 ± 19% softirqs.CPU4.NET_RX 21214 ± 17% +67.3% 35500 ± 37% softirqs.CPU4.TIMER 17006848 ± 4% +64.4% 27959393 ± 15% softirqs.CPU40.NET_RX 17195796 ± 17% +55.2% 26683265 ± 20% softirqs.CPU41.NET_RX 17966784 ± 16% +46.8% 26373369 ± 14% softirqs.CPU44.NET_RX 18457404 ± 12% +36.7% 25239284 ± 15% softirqs.CPU45.NET_RX 19177345 ± 16% +54.2% 29571248 ± 19% softirqs.CPU46.NET_RX 18985369 ± 23% +44.6% 27459447 ± 15% softirqs.CPU47.NET_RX 17056056 ± 17% +61.7% 27579120 ± 16% softirqs.CPU48.NET_RX 22173 ± 10% +46.9% 32567 ± 16% softirqs.CPU48.TIMER 17139885 ± 15% +35.2% 23169696 ± 10% softirqs.CPU49.NET_RX 16322396 ± 13% +52.7% 24921271 ± 23% softirqs.CPU5.NET_RX 19461476 ± 15% +26.0% 24514431 ± 12% softirqs.CPU55.NET_RX 17683552 ± 14% +42.6% 25224539 ± 16% softirqs.CPU56.NET_RX 114424 ± 3% +16.0% 132721 ± 15% softirqs.CPU57.SCHED 18801936 ± 14% +36.8% 25729831 ± 11% softirqs.CPU58.NET_RX 25708 ± 10% +31.3% 33749 ± 16% softirqs.CPU58.TIMER 20627892 ± 9% +38.7% 28609438 ± 17% softirqs.CPU59.NET_RX 27916 ± 7% +37.3% 38323 ± 23% softirqs.CPU59.TIMER 38977568 ± 7% -20.5% 30985289 ± 15% softirqs.CPU65.NET_RX 139605 ± 10% +35.7% 189440 ± 10% softirqs.CPU65.SCHED 21179 ± 16% +60.9% 34079 ± 18% softirqs.CPU7.TIMER 22889 ± 10% +39.5% 31942 ± 7% softirqs.CPU8.TIMER 37894950 ± 7% -20.9% 29992338 ± 8% softirqs.CPU85.NET_RX 171760 ± 9% -25.7% 127536 ± 9% softirqs.CPU87.SCHED 25519 ± 15% +41.6% 36143 ± 23% softirqs.CPU9.TIMER 144906 ± 10% +30.8% 189539 ± 13% softirqs.CPU97.SCHED 40907512 ± 5% -20.7% 32423004 ± 9% softirqs.CPU98.NET_RX 136196 ± 11% +32.3% 180133 ± 16% softirqs.CPU98.SCHED 46885 ± 14% -43.3% 26606 ± 31% softirqs.CPU98.TIMER 3.63 ± 2% -1.0 2.66 ± 11% perf-profile.calltrace.cycles-pp.tcp_v4_do_rcv.tcp_v4_rcv.ip_protocol_deliver_rcu.ip_local_deliver_finish.ip_local_deliver 3.58 ± 2% -1.0 2.63 ± 11% perf-profile.calltrace.cycles-pp.tcp_rcv_established.tcp_v4_do_rcv.tcp_v4_rcv.ip_protocol_deliver_rcu.ip_local_deliver_finish 10.75 ± 2% -0.8 9.90 ± 2% perf-profile.calltrace.cycles-pp.asm_sysvec_reschedule_ipi.acpi_idle_do_entry.acpi_idle_enter.cpuidle_enter_state.cpuidle_enter 10.59 -0.7 9.88 ± 2% perf-profile.calltrace.cycles-pp.start_secondary.secondary_startup_64_no_verify 10.62 -0.7 9.91 ± 2% perf-profile.calltrace.cycles-pp.secondary_startup_64_no_verify 10.58 -0.7 9.87 ± 2% perf-profile.calltrace.cycles-pp.cpu_startup_entry.start_secondary.secondary_startup_64_no_verify 10.54 -0.7 9.84 ± 2% perf-profile.calltrace.cycles-pp.do_idle.cpu_startup_entry.start_secondary.secondary_startup_64_no_verify 4.92 ± 5% -0.6 4.31 ± 3% perf-profile.calltrace.cycles-pp.__ip_queue_xmit.__tcp_transmit_skb.tcp_recvmsg_locked.tcp_recvmsg.inet_recvmsg 4.56 ± 5% -0.5 4.02 ± 4% perf-profile.calltrace.cycles-pp.ip_output.__ip_queue_xmit.__tcp_transmit_skb.tcp_recvmsg_locked.tcp_recvmsg 4.20 ± 5% -0.5 3.66 ± 4% perf-profile.calltrace.cycles-pp.ip_finish_output2.ip_output.__ip_queue_xmit.__tcp_transmit_skb.tcp_recvmsg_locked 7.68 -0.5 7.18 ± 2% perf-profile.calltrace.cycles-pp.cpuidle_enter.do_idle.cpu_startup_entry.start_secondary.secondary_startup_64_no_verify 7.66 -0.5 7.17 ± 2% perf-profile.calltrace.cycles-pp.cpuidle_enter_state.cpuidle_enter.do_idle.cpu_startup_entry.start_secondary 1.92 ± 2% -0.5 1.42 ± 21% perf-profile.calltrace.cycles-pp.try_to_wake_up.__wake_up_common.__wake_up_common_lock.sock_def_readable.tcp_rcv_established 7.36 -0.5 6.88 ± 2% perf-profile.calltrace.cycles-pp.acpi_idle_enter.cpuidle_enter_state.cpuidle_enter.do_idle.cpu_startup_entry 0.83 ± 6% -0.3 0.51 ± 44% perf-profile.calltrace.cycles-pp.get_page_from_freelist.__alloc_pages.skb_page_frag_refill.sk_page_frag_refill.tcp_sendmsg_locked 1.48 ± 4% -0.3 1.16 ± 14% perf-profile.calltrace.cycles-pp.sk_page_frag_refill.tcp_sendmsg_locked.tcp_sendmsg.sock_sendmsg.__sys_sendto 1.46 ± 4% -0.3 1.14 ± 14% perf-profile.calltrace.cycles-pp.skb_page_frag_refill.sk_page_frag_refill.tcp_sendmsg_locked.tcp_sendmsg.sock_sendmsg 1.02 ± 5% -0.3 0.75 ± 14% perf-profile.calltrace.cycles-pp.__alloc_pages.skb_page_frag_refill.sk_page_frag_refill.tcp_sendmsg_locked.tcp_sendmsg 2.33 ± 2% -0.2 2.11 ± 10% perf-profile.calltrace.cycles-pp.sock_def_readable.tcp_rcv_established.tcp_v4_do_rcv.tcp_v4_rcv.ip_protocol_deliver_rcu 2.25 ± 2% -0.2 2.04 ± 10% perf-profile.calltrace.cycles-pp.__wake_up_common_lock.sock_def_readable.tcp_rcv_established.tcp_v4_do_rcv.tcp_v4_rcv 2.18 ± 2% -0.2 1.97 ± 10% perf-profile.calltrace.cycles-pp.__wake_up_common.__wake_up_common_lock.sock_def_readable.tcp_rcv_established.tcp_v4_do_rcv 0.75 ± 4% -0.2 0.55 ± 44% perf-profile.calltrace.cycles-pp.native_queued_spin_lock_slowpath._raw_spin_lock_bh.lock_sock_nested.tcp_sendmsg.sock_sendmsg 1.43 -0.1 1.33 ± 2% perf-profile.calltrace.cycles-pp.schedule_idle.do_idle.cpu_startup_entry.start_secondary.secondary_startup_64_no_verify 1.38 -0.1 1.28 ± 2% perf-profile.calltrace.cycles-pp.__schedule.schedule_idle.do_idle.cpu_startup_entry.start_secondary 0.87 -0.1 0.79 ± 14% perf-profile.calltrace.cycles-pp.__alloc_skb.tcp_stream_alloc_skb.tcp_sendmsg_locked.tcp_sendmsg.sock_sendmsg 0.99 -0.1 0.90 ± 14% perf-profile.calltrace.cycles-pp.tcp_stream_alloc_skb.tcp_sendmsg_locked.tcp_sendmsg.sock_sendmsg.__sys_sendto 0.63 ± 5% -0.1 0.56 ± 4% perf-profile.calltrace.cycles-pp.__tcp_send_ack.tcp_recvmsg_locked.tcp_recvmsg.inet_recvmsg.__sys_recvfrom 0.60 ± 5% -0.1 0.53 ± 3% perf-profile.calltrace.cycles-pp.__alloc_skb.__tcp_send_ack.tcp_recvmsg_locked.tcp_recvmsg.inet_recvmsg 0.68 -0.0 0.64 ± 2% perf-profile.calltrace.cycles-pp.pick_next_task_fair.__schedule.schedule_idle.do_idle.cpu_startup_entry 0.66 ± 4% +0.2 0.83 ± 6% perf-profile.calltrace.cycles-pp.__release_sock.release_sock.tcp_recvmsg.inet_recvmsg.__sys_recvfrom 0.90 ± 4% +0.2 1.09 ± 5% perf-profile.calltrace.cycles-pp.release_sock.tcp_recvmsg.inet_recvmsg.__sys_recvfrom.__x64_sys_recvfrom 3.18 ± 3% +0.3 3.51 ± 4% perf-profile.calltrace.cycles-pp.ip_output.__ip_queue_xmit.__tcp_transmit_skb.tcp_write_xmit.tcp_sendmsg_locked 3.45 ± 3% +0.3 3.79 ± 4% perf-profile.calltrace.cycles-pp.__ip_queue_xmit.__tcp_transmit_skb.tcp_write_xmit.tcp_sendmsg_locked.tcp_sendmsg 7.79 +0.4 8.21 perf-profile.calltrace.cycles-pp.ip_finish_output2.ip_output.__ip_queue_xmit.__tcp_transmit_skb.tcp_write_xmit 4.06 ± 2% +0.4 4.50 ± 4% perf-profile.calltrace.cycles-pp.__tcp_transmit_skb.tcp_write_xmit.tcp_sendmsg_locked.tcp_sendmsg.sock_sendmsg 0.15 ±158% +0.5 0.61 ± 7% perf-profile.calltrace.cycles-pp.tcp_v4_do_rcv.__release_sock.release_sock.tcp_recvmsg.inet_recvmsg 8.02 +0.5 8.51 perf-profile.calltrace.cycles-pp.__netif_receive_skb_one_core.process_backlog.__napi_poll.net_rx_action.__softirqentry_text_start 8.63 ± 2% +0.5 9.12 perf-profile.calltrace.cycles-pp.__napi_poll.net_rx_action.__softirqentry_text_start.do_softirq.__local_bh_enable_ip 8.57 ± 2% +0.5 9.07 perf-profile.calltrace.cycles-pp.process_backlog.__napi_poll.net_rx_action.__softirqentry_text_start.do_softirq 13.32 ± 2% +0.5 13.82 perf-profile.calltrace.cycles-pp.release_sock.tcp_sendmsg.sock_sendmsg.__sys_sendto.__x64_sys_sendto 8.83 ± 2% +0.5 9.32 perf-profile.calltrace.cycles-pp.net_rx_action.__softirqentry_text_start.do_softirq.__local_bh_enable_ip.ip_finish_output2 12.59 ± 2% +0.5 13.10 ± 2% perf-profile.calltrace.cycles-pp.__release_sock.release_sock.tcp_sendmsg.sock_sendmsg.__sys_sendto 9.55 ± 2% +0.5 10.07 perf-profile.calltrace.cycles-pp.__softirqentry_text_start.do_softirq.__local_bh_enable_ip.ip_finish_output2.ip_output 9.76 ± 2% +0.5 10.28 perf-profile.calltrace.cycles-pp.__local_bh_enable_ip.ip_finish_output2.ip_output.__ip_queue_xmit.__tcp_transmit_skb 9.68 ± 2% +0.5 10.20 perf-profile.calltrace.cycles-pp.do_softirq.__local_bh_enable_ip.ip_finish_output2.ip_output.__ip_queue_xmit 4.82 ± 2% +0.5 5.35 ± 3% perf-profile.calltrace.cycles-pp.tcp_write_xmit.tcp_sendmsg_locked.tcp_sendmsg.sock_sendmsg.__sys_sendto 0.79 ± 9% +0.7 1.47 ± 4% perf-profile.calltrace.cycles-pp.tcp_rcv_established.tcp_v4_do_rcv.__release_sock.__sk_flush_backlog.tcp_recvmsg_locked 0.82 ± 9% +0.7 1.51 ± 4% perf-profile.calltrace.cycles-pp.tcp_v4_do_rcv.__release_sock.__sk_flush_backlog.tcp_recvmsg_locked.tcp_recvmsg 1.04 ± 8% +0.7 1.77 ± 4% perf-profile.calltrace.cycles-pp.__sk_flush_backlog.tcp_recvmsg_locked.tcp_recvmsg.inet_recvmsg.__sys_recvfrom 1.00 ± 9% +0.7 1.74 ± 4% perf-profile.calltrace.cycles-pp.__release_sock.__sk_flush_backlog.tcp_recvmsg_locked.tcp_recvmsg.inet_recvmsg 0.00 +0.8 0.84 ± 5% perf-profile.calltrace.cycles-pp.ip_finish_output2.ip_output.__ip_queue_xmit.__tcp_transmit_skb.tcp_rcv_established 0.00 +0.9 0.88 ± 5% perf-profile.calltrace.cycles-pp.ip_output.__ip_queue_xmit.__tcp_transmit_skb.tcp_rcv_established.tcp_v4_do_rcv 0.15 ±158% +0.9 1.06 ± 5% perf-profile.calltrace.cycles-pp.__tcp_transmit_skb.tcp_rcv_established.tcp_v4_do_rcv.__release_sock.__sk_flush_backlog 0.00 +0.9 0.94 ± 6% perf-profile.calltrace.cycles-pp.__ip_queue_xmit.__tcp_transmit_skb.tcp_rcv_established.tcp_v4_do_rcv.__release_sock 10.59 -0.7 9.88 ± 2% perf-profile.children.cycles-pp.start_secondary 10.62 -0.7 9.91 ± 2% perf-profile.children.cycles-pp.secondary_startup_64_no_verify 10.62 -0.7 9.91 ± 2% perf-profile.children.cycles-pp.cpu_startup_entry 10.59 -0.7 9.89 ± 2% perf-profile.children.cycles-pp.do_idle 7.70 -0.5 7.20 ± 2% perf-profile.children.cycles-pp.cpuidle_enter_state 7.72 -0.5 7.21 ± 2% perf-profile.children.cycles-pp.cpuidle_enter 7.39 -0.5 6.90 ± 2% perf-profile.children.cycles-pp.acpi_idle_enter 7.30 -0.5 6.83 ± 2% perf-profile.children.cycles-pp.acpi_idle_do_entry 5.69 -0.4 5.24 ± 2% perf-profile.children.cycles-pp.asm_sysvec_reschedule_ipi 1.50 ± 4% -0.2 1.26 perf-profile.children.cycles-pp.sk_page_frag_refill 1.47 ± 4% -0.2 1.22 perf-profile.children.cycles-pp.skb_page_frag_refill 1.03 ± 5% -0.2 0.81 ± 2% perf-profile.children.cycles-pp.__alloc_pages 0.85 ± 6% -0.2 0.63 ± 3% perf-profile.children.cycles-pp.get_page_from_freelist 2.88 -0.2 2.66 ± 3% perf-profile.children.cycles-pp.__schedule 2.47 -0.2 2.29 ± 3% perf-profile.children.cycles-pp.sk_wait_data 0.97 ± 4% -0.2 0.80 ± 2% perf-profile.children.cycles-pp.free_unref_page 0.25 ± 16% -0.2 0.10 ± 7% perf-profile.children.cycles-pp.rmqueue_bulk 0.48 ± 8% -0.2 0.33 ± 3% perf-profile.children.cycles-pp.rmqueue 1.03 ± 5% -0.1 0.88 ± 3% perf-profile.children.cycles-pp.native_queued_spin_lock_slowpath 2.27 ± 2% -0.1 2.13 ± 2% perf-profile.children.cycles-pp.__wake_up_common_lock 0.33 ± 3% -0.1 0.20 ± 3% perf-profile.children.cycles-pp.sock_rfree 2.19 ± 2% -0.1 2.06 ± 2% perf-profile.children.cycles-pp.__wake_up_common 1.74 -0.1 1.61 ± 3% perf-profile.children.cycles-pp.wait_woken 0.21 ± 12% -0.1 0.09 ± 4% perf-profile.children.cycles-pp.free_pcppages_bulk 1.51 -0.1 1.40 ± 3% perf-profile.children.cycles-pp.schedule 1.65 -0.1 1.53 ± 3% perf-profile.children.cycles-pp.schedule_timeout 1.93 -0.1 1.82 ± 2% perf-profile.children.cycles-pp.try_to_wake_up 1.44 -0.1 1.34 ± 2% perf-profile.children.cycles-pp.schedule_idle 1.02 ± 2% -0.1 0.92 perf-profile.children.cycles-pp._raw_spin_lock 1.62 ± 2% -0.1 1.52 ± 2% perf-profile.children.cycles-pp.lock_sock_nested 2.40 ± 2% -0.1 2.30 ± 2% perf-profile.children.cycles-pp.sock_def_readable 0.13 ± 14% -0.1 0.05 ± 8% perf-profile.children.cycles-pp.__free_one_page 0.39 ± 5% -0.1 0.33 ± 3% perf-profile.children.cycles-pp.__ip_local_out 0.42 ± 4% -0.1 0.36 ± 3% perf-profile.children.cycles-pp.ip_local_out 0.77 -0.1 0.71 ± 2% perf-profile.children.cycles-pp.pick_next_task_fair 0.28 ± 5% -0.0 0.23 ± 2% perf-profile.children.cycles-pp.__list_del_entry_valid 0.60 ± 2% -0.0 0.56 perf-profile.children.cycles-pp.enqueue_task_fair 0.29 ± 5% -0.0 0.25 ± 2% perf-profile.children.cycles-pp.ip_send_check 0.13 ± 5% -0.0 0.09 ± 6% perf-profile.children.cycles-pp.__zone_watermark_ok 0.62 ± 2% -0.0 0.58 ± 2% perf-profile.children.cycles-pp.ttwu_do_activate 0.57 ± 2% -0.0 0.53 ± 2% perf-profile.children.cycles-pp.menu_select 0.57 -0.0 0.54 ± 3% perf-profile.children.cycles-pp.update_rq_clock 0.26 -0.0 0.23 ± 3% perf-profile.children.cycles-pp.kfree_skbmem 0.34 -0.0 0.31 perf-profile.children.cycles-pp.syscall_exit_to_user_mode 0.50 ± 2% -0.0 0.46 ± 2% perf-profile.children.cycles-pp.sysvec_reschedule_ipi 0.52 -0.0 0.48 ± 3% perf-profile.children.cycles-pp.set_next_entity 0.44 ± 2% -0.0 0.41 perf-profile.children.cycles-pp.enqueue_entity 0.33 ± 2% -0.0 0.30 ± 3% perf-profile.children.cycles-pp.native_irq_return_iret 0.32 ± 2% -0.0 0.29 ± 2% perf-profile.children.cycles-pp.__might_sleep 0.20 ± 2% -0.0 0.18 ± 3% perf-profile.children.cycles-pp.finish_task_switch 0.15 ± 7% -0.0 0.12 ± 3% perf-profile.children.cycles-pp.free_unref_page_commit 0.39 ± 2% -0.0 0.37 ± 2% perf-profile.children.cycles-pp.kmalloc_reserve 0.18 -0.0 0.16 ± 2% perf-profile.children.cycles-pp.exit_to_user_mode_prepare 0.17 ± 2% -0.0 0.15 ± 5% perf-profile.children.cycles-pp.switch_mm_irqs_off 0.26 ± 2% -0.0 0.24 perf-profile.children.cycles-pp.tick_nohz_idle_exit 0.36 -0.0 0.34 ± 2% perf-profile.children.cycles-pp.update_curr 0.26 -0.0 0.24 ± 3% perf-profile.children.cycles-pp.sock_put 0.20 ± 2% -0.0 0.18 ± 3% perf-profile.children.cycles-pp.migrate_disable 0.08 ± 5% -0.0 0.07 ± 5% perf-profile.children.cycles-pp.switch_fpu_return 0.07 ± 6% -0.0 0.05 ± 7% perf-profile.children.cycles-pp.tcp_cleanup_rbuf 0.12 ± 3% -0.0 0.11 ± 3% perf-profile.children.cycles-pp.__update_load_avg_se 0.23 ± 2% -0.0 0.21 ± 3% perf-profile.children.cycles-pp.remove_wait_queue 0.10 ± 5% +0.0 0.11 perf-profile.children.cycles-pp.__tcp_select_window 0.69 +0.0 0.71 perf-profile.children.cycles-pp._raw_spin_lock_irqsave 0.10 ± 3% +0.0 0.12 ± 4% perf-profile.children.cycles-pp.syscall_enter_from_user_mode 0.22 ± 5% +0.0 0.25 ± 8% perf-profile.children.cycles-pp.__sk_dst_check 0.09 ± 6% +0.0 0.12 ± 4% perf-profile.children.cycles-pp.tcp_rbtree_insert 0.02 ±115% +0.0 0.06 ± 8% perf-profile.children.cycles-pp.__sock_wfree 0.00 +0.1 0.05 perf-profile.children.cycles-pp.eth_type_trans 0.55 ± 2% +0.1 0.60 ± 2% perf-profile.children.cycles-pp.__skb_clone 0.00 +0.1 0.06 ± 11% perf-profile.children.cycles-pp.llist_add_batch 0.28 ± 9% +0.1 0.34 ± 11% perf-profile.children.cycles-pp.ip_rcv_finish_core 0.24 +0.1 0.30 perf-profile.children.cycles-pp.lock_timer_base 0.33 ± 8% +0.1 0.40 ± 9% perf-profile.children.cycles-pp.ip_rcv_finish 0.56 ± 2% +0.1 0.64 perf-profile.children.cycles-pp.tcp_schedule_loss_probe 0.25 ± 5% +0.1 0.32 ± 2% perf-profile.children.cycles-pp.tcp_queue_rcv 0.35 ± 2% +0.1 0.43 ± 3% perf-profile.children.cycles-pp.tcp_eat_recv_skb 0.66 +0.1 0.75 perf-profile.children.cycles-pp.mod_timer 0.69 +0.1 0.78 perf-profile.children.cycles-pp.sk_reset_timer 3.61 +0.1 3.74 perf-profile.children.cycles-pp.skb_release_data 7.33 +0.1 7.47 perf-profile.children.cycles-pp.tcp_v4_rcv 3.79 +0.2 3.94 perf-profile.children.cycles-pp.__kfree_skb 7.51 +0.2 7.67 perf-profile.children.cycles-pp.ip_local_deliver_finish 7.47 +0.2 7.63 perf-profile.children.cycles-pp.ip_protocol_deliver_rcu 7.55 +0.2 7.71 perf-profile.children.cycles-pp.ip_local_deliver 10.17 +0.2 10.36 perf-profile.children.cycles-pp.__softirqentry_text_start 10.19 +0.2 10.39 perf-profile.children.cycles-pp.do_softirq 9.08 +0.2 9.28 perf-profile.children.cycles-pp.__napi_poll 9.29 +0.2 9.49 perf-profile.children.cycles-pp.net_rx_action 9.03 +0.2 9.23 perf-profile.children.cycles-pp.process_backlog 8.12 +0.2 8.33 perf-profile.children.cycles-pp.ip_rcv 10.46 +0.2 10.67 perf-profile.children.cycles-pp.__local_bh_enable_ip 8.43 +0.2 8.65 perf-profile.children.cycles-pp.__netif_receive_skb_one_core 12.68 +0.3 12.99 perf-profile.children.cycles-pp.ip_finish_output2 14.41 +0.3 14.73 perf-profile.children.cycles-pp.__ip_queue_xmit 13.47 +0.3 13.80 perf-profile.children.cycles-pp.ip_output 0.00 +0.4 0.42 ± 16% perf-profile.children.cycles-pp.__sk_defer_free_flush 16.41 +0.6 16.98 perf-profile.children.cycles-pp.__tcp_transmit_skb 12.72 +0.6 13.34 perf-profile.children.cycles-pp.tcp_write_xmit 15.33 +0.7 15.99 perf-profile.children.cycles-pp.tcp_rcv_established 15.58 +0.7 16.24 perf-profile.children.cycles-pp.tcp_v4_do_rcv 14.38 ± 2% +0.7 15.06 perf-profile.children.cycles-pp.release_sock 86.04 +0.7 86.74 perf-profile.children.cycles-pp.do_syscall_64 86.34 +0.7 87.05 perf-profile.children.cycles-pp.entry_SYSCALL_64_after_hwframe 1.13 ± 10% +0.7 1.86 ± 4% perf-profile.children.cycles-pp.__sk_flush_backlog 14.43 ± 2% +1.4 15.84 perf-profile.children.cycles-pp.__release_sock 5.86 -0.4 5.44 ± 2% perf-profile.self.cycles-pp.acpi_idle_do_entry 1.02 ± 5% -0.1 0.87 ± 4% perf-profile.self.cycles-pp.native_queued_spin_lock_slowpath 0.32 ± 4% -0.1 0.19 ± 2% perf-profile.self.cycles-pp.sock_rfree 0.26 ± 4% -0.1 0.21 ± 2% perf-profile.self.cycles-pp.__list_del_entry_valid 0.29 ± 5% -0.0 0.24 ± 2% perf-profile.self.cycles-pp.ip_send_check 0.13 ± 8% -0.0 0.08 ± 5% perf-profile.self.cycles-pp.__zone_watermark_ok 0.26 -0.0 0.22 ± 2% perf-profile.self.cycles-pp.kfree_skbmem 0.16 -0.0 0.12 ± 4% perf-profile.self.cycles-pp.tcp_event_new_data_sent 0.67 -0.0 0.64 ± 2% perf-profile.self.cycles-pp.tcp_recvmsg_locked 0.33 ± 2% -0.0 0.30 ± 3% perf-profile.self.cycles-pp.native_irq_return_iret 0.16 ± 3% -0.0 0.13 ± 8% perf-profile.self.cycles-pp.tcp_rcv_space_adjust 0.39 -0.0 0.36 ± 3% perf-profile.self.cycles-pp.set_next_entity 0.17 ± 2% -0.0 0.15 ± 4% perf-profile.self.cycles-pp.finish_task_switch 0.27 ± 2% -0.0 0.25 ± 2% perf-profile.self.cycles-pp.do_idle 0.15 ± 4% -0.0 0.12 ± 4% perf-profile.self.cycles-pp.get_page_from_freelist 0.17 ± 2% -0.0 0.15 ± 5% perf-profile.self.cycles-pp.switch_mm_irqs_off 0.11 ± 7% -0.0 0.09 ± 5% perf-profile.self.cycles-pp.free_unref_page_commit 0.17 ± 2% -0.0 0.14 ± 3% perf-profile.self.cycles-pp.__sys_recvfrom 0.26 ± 2% -0.0 0.24 perf-profile.self.cycles-pp.__might_sleep 0.08 ± 4% -0.0 0.06 perf-profile.self.cycles-pp.switch_fpu_return 0.09 ± 5% -0.0 0.07 ± 6% perf-profile.self.cycles-pp.__ip_local_out 0.25 -0.0 0.24 ± 3% perf-profile.self.cycles-pp.__switch_to 0.18 ± 2% -0.0 0.16 ± 3% perf-profile.self.cycles-pp.update_curr 0.18 -0.0 0.17 ± 2% perf-profile.self.cycles-pp.ip_rcv_core 0.15 ± 2% +0.0 0.16 ± 3% perf-profile.self.cycles-pp.release_sock 0.19 ± 2% +0.0 0.20 ± 2% perf-profile.self.cycles-pp.tcp_add_backlog 0.09 ± 5% +0.0 0.10 ± 4% perf-profile.self.cycles-pp.__tcp_select_window 0.68 +0.0 0.70 perf-profile.self.cycles-pp._raw_spin_lock_irqsave 0.15 ± 6% +0.0 0.17 ± 5% perf-profile.self.cycles-pp.__ip_finish_output 0.09 +0.0 0.11 ± 3% perf-profile.self.cycles-pp.syscall_enter_from_user_mode 0.13 ± 3% +0.0 0.16 ± 4% perf-profile.self.cycles-pp.sock_def_readable 0.09 ± 5% +0.0 0.12 ± 5% perf-profile.self.cycles-pp.tcp_rbtree_insert 0.47 ± 3% +0.0 0.51 perf-profile.self.cycles-pp.__skb_clone 0.29 ± 4% +0.0 0.34 ± 2% perf-profile.self.cycles-pp.ip_finish_output2 0.00 +0.1 0.05 ± 7% perf-profile.self.cycles-pp.__sk_defer_free_flush 0.00 +0.1 0.06 ± 9% perf-profile.self.cycles-pp.__sock_wfree 0.00 +0.1 0.06 ± 11% perf-profile.self.cycles-pp.llist_add_batch 0.27 ± 9% +0.1 0.33 ± 10% perf-profile.self.cycles-pp.ip_rcv_finish_core 1.05 +0.1 1.11 perf-profile.self.cycles-pp.tcp_rcv_established 0.19 ± 3% +0.1 0.27 perf-profile.self.cycles-pp.tcp_queue_rcv 1.02 +0.2 1.18 perf-profile.self.cycles-pp.__tcp_transmit_skb 0.45 ± 5% +0.2 0.65 perf-profile.self.cycles-pp.__release_sock 0.00 +0.2 0.23 ± 6% perf-profile.self.cycles-pp.tcp_eat_recv_skb 1.75 +0.3 2.04 perf-profile.self.cycles-pp.skb_release_data 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. --- 0DAY/LKP+ Test Infrastructure Open Source Technology Center https://lists.01.org/hyperkitty/list/[email protected] Intel Corporation Thanks, Oliver Sang

7 months, 2 weeks

1
0
0 / 0

2021-12-26 03:24:04

by oiloncanvas＠foxmail.com

You email us a picture, we make an oil painting. 2021-12-26 03:24:04 Oil on canvas, 100% hand-painted. lkp Any picture will do. 5376F472-78D3-480D-87A9-480754295D5A Free shipping to your home address.

7 months, 2 weeks

1
0
0 / 0

What You Do Understand By Cash App Failed For My Protection?

by angelina laurel

Cash App Failed for My Protection and safeguard your account if anything wrong is taking place while working on your Cash App account. All you have to do is to get in touch with the trouble shooting professionals who will let you know about the same in a trouble-free manner. https://www.techjaadu.com/blog/how-do-i-fix-my-cash-app-failed-for-my-pro...

7 months, 2 weeks

1
0
0 / 0

Simple manual for fix cash app payment failed issues.

by angelina laurel

Numerous individuals face issues at the hour of sending cash from their records. Assuming you are additionally encountering cash app payment failed issues frequently; you can contact our lithe experts. Our delegates will disclose to you the least difficult yet powerful approach to fix this issue at the earliest opportunity. Likewise, they will control you to drop the payment to get a discount in the source account. https://www.techjaadu.com/blog/how-do-i-fix-my-cash-app-failed-for-my-pro...

7 months, 2 weeks

1
0
0 / 0

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

LKP December 2021