Greeting, FYI, we noticed a 8.4% improvement of will-it-scale.per_process_ops due to commit: commit: d002b8bc6dbc20e9043e279196cff8795dba05fe ("kprobes: Add symbols for kprobe insn pages") https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git master in testcase: will-it-scale on test machine: 192 threads Intel(R) Xeon(R) Platinum 9242 CPU @ 2.30GHz with 192G memory with following parameters: nr_task: 50% mode: process test: signal1 cpufreq_governor: performance ucode: 0x5002f01 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 bin/lkp install job.yaml # job file is attached in this email bin/lkp run job.yaml ========================================================================================= compiler/cpufreq_governor/kconfig/mode/nr_task/rootfs/tbox_group/test/testcase/ucode: gcc-9/performance/x86_64-rhel-8.3/process/50%/debian-10.4-x86_64-20200603.cgz/lkp-csl-2ap3/signal1/will-it-scale/0x5002f01 commit: d769811ca9 ("perf/x86: Add support for perf text poke event for text_poke_bp_batch() callers") d002b8bc6d ("kprobes: Add symbols for kprobe insn pages") d769811ca93303de d002b8bc6dbc20e9043e279196c ---------------- --------------------------- %stddev %change %stddev \ | \ 66730 +8.4% 72357 will-it-scale.per_process_ops 6406174 +8.4% 6946354 will-it-scale.workload 97204 ± 11% +18.6% 115301 ± 12% numa-meminfo.node3.Slab 2676 ± 18% -14.4% 2291 ± 20% numa-vmstat.node0.nr_mapped 2033 +4.2% 2118 vmstat.system.cs 0.08 -0.0 0.07 ± 3% mpstat.cpu.all.soft% 1.45 +2.0 3.49 ± 80% mpstat.cpu.all.usr% 34109 ± 2% -25.8% 25301 ± 12% sched_debug.cfs_rq:/.min_vruntime.min 21.56 ± 27% -33.4% 14.35 ± 14% sched_debug.cpu.clock.stddev 2624648 ± 7% +28.7% 3376703 ± 20% cpuidle.C1.time 59424 ± 15% +69.5% 100738 ± 35% cpuidle.C1.usage 15470 ± 18% +172.1% 42101 ± 91% cpuidle.POLL.time 6956 ± 3% -11.4% 6166 ± 6% proc-vmstat.nr_inactive_anon 12235 ± 3% -8.1% 11249 ± 2% proc-vmstat.nr_mapped 6956 ± 3% -11.4% 6166 ± 6% proc-vmstat.nr_zone_inactive_anon 376.00 ± 35% -51.1% 184.00 ± 7% slabinfo.biovec-64.active_objs 376.00 ± 35% -51.1% 184.00 ± 7% slabinfo.biovec-64.num_objs 14671 ± 7% +14.9% 16854 ± 6% slabinfo.pde_opener.active_objs 14671 ± 7% +14.9% 16854 ± 6% slabinfo.pde_opener.num_objs 1406 ± 4% -11.0% 1252 ± 5% slabinfo.task_group.active_objs 1406 ± 4% -11.0% 1252 ± 5% slabinfo.task_group.num_objs 5.17 ± 4% -10.1% 4.65 ± 4% perf-stat.i.MPKI 6.287e+09 +7.7% 6.773e+09 perf-stat.i.branch-instructions 58369272 +12.9% 65882689 ± 13% perf-stat.i.branch-misses 39.48 ± 2% -1.7 37.78 perf-stat.i.cache-miss-rate% 2005 +4.0% 2086 perf-stat.i.context-switches 9.66 -8.7% 8.82 perf-stat.i.cpi 3.049e+11 -1.4% 3.005e+11 perf-stat.i.cpu-cycles 9.617e+09 +8.1% 1.039e+10 perf-stat.i.dTLB-loads 0.00 ± 4% +0.0 0.00 ± 45% perf-stat.i.dTLB-store-miss-rate% 24064 +61.8% 38925 ± 51% perf-stat.i.dTLB-store-misses 6.093e+09 +8.0% 6.582e+09 perf-stat.i.dTLB-stores 4021310 -1.5% 3962341 perf-stat.i.iTLB-loads 3.153e+10 +7.9% 3.403e+10 perf-stat.i.instructions 0.10 +9.7% 0.11 perf-stat.i.ipc 1.59 -1.4% 1.56 perf-stat.i.metric.GHz 0.18 +44.1% 0.26 ± 41% perf-stat.i.metric.K/sec 115.47 +7.9% 124.57 perf-stat.i.metric.M/sec 4162504 ± 4% -13.0% 3620423 ± 4% perf-stat.i.node-load-misses 306045 ± 7% -11.5% 270791 ± 8% perf-stat.i.node-loads 8667363 +5.9% 9178413 perf-stat.i.node-store-misses 5.16 ± 4% -10.1% 4.64 ± 4% perf-stat.overall.MPKI 39.47 ± 2% -1.7 37.76 perf-stat.overall.cache-miss-rate% 9.67 -8.7% 8.83 perf-stat.overall.cpi 0.00 +0.0 0.00 ± 52% perf-stat.overall.dTLB-store-miss-rate% 0.10 +9.5% 0.11 perf-stat.overall.ipc 6.264e+09 +7.7% 6.75e+09 perf-stat.ps.branch-instructions 58091547 +12.9% 65595433 ± 13% perf-stat.ps.branch-misses 1980 +4.2% 2064 perf-stat.ps.context-switches 3.038e+11 -1.4% 2.995e+11 perf-stat.ps.cpu-cycles 9.584e+09 +8.1% 1.036e+10 perf-stat.ps.dTLB-loads 23872 +62.1% 38707 ± 51% perf-stat.ps.dTLB-store-misses 6.072e+09 +8.0% 6.56e+09 perf-stat.ps.dTLB-stores 4004347 -1.4% 3948418 perf-stat.ps.iTLB-loads 3.142e+10 +7.9% 3.391e+10 perf-stat.ps.instructions 4145982 ± 4% -13.0% 3608888 ± 5% perf-stat.ps.node-load-misses 304945 ± 8% -11.2% 270885 ± 8% perf-stat.ps.node-loads 8637191 +5.9% 9147176 perf-stat.ps.node-store-misses 9.486e+12 +7.9% 1.024e+13 perf-stat.total.instructions 26.01 ± 8% -5.9 20.06 ± 16% perf-profile.calltrace.cycles-pp.aa_get_task_label.apparmor_task_kill.security_task_kill.do_send_specific.do_tkill 0.57 ± 10% +0.1 0.64 ± 11% perf-profile.calltrace.cycles-pp.__prepare_exit_to_usermode.do_syscall_64.entry_SYSCALL_64_after_hwframe.handler 0.55 ± 11% +0.1 0.63 ± 10% perf-profile.calltrace.cycles-pp.do_signal.__prepare_exit_to_usermode.do_syscall_64.entry_SYSCALL_64_after_hwframe.handler 0.55 ± 9% +0.1 0.63 ± 9% perf-profile.calltrace.cycles-pp.entry_SYSCALL_64.raise 0.62 ± 9% +0.1 0.70 ± 10% perf-profile.calltrace.cycles-pp.__fpu__restore_sig.restore_sigcontext.__x64_sys_rt_sigreturn.do_syscall_64.entry_SYSCALL_64_after_hwframe 0.57 ± 10% +0.1 0.66 ± 11% perf-profile.calltrace.cycles-pp.__x64_sys_rt_sigprocmask.do_syscall_64.entry_SYSCALL_64_after_hwframe.raise 0.64 ± 9% +0.1 0.73 ± 10% perf-profile.calltrace.cycles-pp.restore_sigcontext.__x64_sys_rt_sigreturn.do_syscall_64.entry_SYSCALL_64_after_hwframe.raise 0.78 ± 10% +0.1 0.88 ± 10% perf-profile.calltrace.cycles-pp.__x64_sys_rt_sigreturn.do_syscall_64.entry_SYSCALL_64_after_hwframe.raise 0.15 ±173% +0.4 0.58 ± 10% perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe 0.57 ± 10% +0.6 1.12 ± 69% perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.handler 0.57 ± 10% +0.6 1.13 ± 70% perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.handler 2.56 ± 10% +1.2 3.74 ± 12% perf-profile.calltrace.cycles-pp.handler 3.40 ± 12% +2.5 5.95 ± 14% perf-profile.calltrace.cycles-pp.__sigqueue_free.__dequeue_signal.dequeue_signal.get_signal.do_signal 3.47 ± 12% +2.6 6.03 ± 14% perf-profile.calltrace.cycles-pp.__dequeue_signal.dequeue_signal.get_signal.do_signal.__prepare_exit_to_usermode 3.52 ± 12% +2.6 6.08 ± 14% perf-profile.calltrace.cycles-pp.dequeue_signal.get_signal.do_signal.__prepare_exit_to_usermode.do_syscall_64 3.63 ± 12% +2.6 6.25 ± 14% perf-profile.calltrace.cycles-pp.get_signal.do_signal.__prepare_exit_to_usermode.do_syscall_64.entry_SYSCALL_64_after_hwframe 3.40 ± 12% +2.6 6.05 ± 14% perf-profile.calltrace.cycles-pp.__sigqueue_alloc.__send_signal.do_send_sig_info.do_send_specific.do_tkill 3.46 ± 12% +2.7 6.12 ± 14% perf-profile.calltrace.cycles-pp.__send_signal.do_send_sig_info.do_send_specific.do_tkill.__x64_sys_tgkill 3.62 ± 12% +2.7 6.32 ± 14% perf-profile.calltrace.cycles-pp.do_send_sig_info.do_send_specific.do_tkill.__x64_sys_tgkill.do_syscall_64 4.56 ± 11% +2.7 7.28 ± 14% perf-profile.calltrace.cycles-pp.do_signal.__prepare_exit_to_usermode.do_syscall_64.entry_SYSCALL_64_after_hwframe.raise 4.63 ± 11% +2.7 7.36 ± 14% perf-profile.calltrace.cycles-pp.__prepare_exit_to_usermode.do_syscall_64.entry_SYSCALL_64_after_hwframe.raise 26.02 ± 8% -5.9 20.08 ± 16% perf-profile.children.cycles-pp.aa_get_task_label 0.11 ± 8% +0.0 0.12 ± 10% perf-profile.children.cycles-pp.___might_sleep 0.05 ± 8% +0.0 0.07 ± 17% perf-profile.children.cycles-pp.__lock_text_start 0.16 ± 8% +0.0 0.18 ± 11% perf-profile.children.cycles-pp.__task_pid_nr_ns 0.18 ± 11% +0.0 0.21 ± 12% perf-profile.children.cycles-pp.__set_task_blocked 0.24 ± 10% +0.0 0.27 ± 10% perf-profile.children.cycles-pp.copy_user_generic_unrolled 0.18 ± 13% +0.0 0.21 ± 12% perf-profile.children.cycles-pp.recalc_sigpending 0.25 ± 10% +0.0 0.28 ± 10% perf-profile.children.cycles-pp.copy_user_enhanced_fast_string 0.23 ± 10% +0.0 0.27 ± 11% perf-profile.children.cycles-pp.sigprocmask 0.46 ± 10% +0.1 0.51 ± 9% perf-profile.children.cycles-pp.syscall_return_via_sysret 0.42 ± 11% +0.1 0.48 ± 10% perf-profile.children.cycles-pp.fpu__clear 0.44 ± 10% +0.1 0.51 ± 10% perf-profile.children.cycles-pp._copy_from_user 0.40 ± 10% +0.1 0.46 ± 11% perf-profile.children.cycles-pp.__set_current_blocked 0.62 ± 9% +0.1 0.71 ± 10% perf-profile.children.cycles-pp.__fpu__restore_sig 0.58 ± 10% +0.1 0.66 ± 11% perf-profile.children.cycles-pp.__x64_sys_rt_sigprocmask 0.60 ± 9% +0.1 0.70 ± 10% perf-profile.children.cycles-pp.entry_SYSCALL_64 0.81 ± 9% +0.1 0.92 ± 10% perf-profile.children.cycles-pp.restore_sigcontext 1.20 ± 10% +0.2 1.36 ± 10% perf-profile.children.cycles-pp.__x64_sys_rt_sigreturn 1.64 ± 10% +1.0 2.59 ± 13% perf-profile.children.cycles-pp.handler 3.41 ± 11% +2.5 5.95 ± 14% perf-profile.children.cycles-pp.__sigqueue_free 3.47 ± 12% +2.6 6.03 ± 14% perf-profile.children.cycles-pp.__dequeue_signal 3.52 ± 11% +2.6 6.08 ± 14% perf-profile.children.cycles-pp.dequeue_signal 3.65 ± 11% +2.6 6.26 ± 14% perf-profile.children.cycles-pp.get_signal 3.40 ± 12% +2.7 6.05 ± 14% perf-profile.children.cycles-pp.__sigqueue_alloc 3.46 ± 12% +2.7 6.13 ± 14% perf-profile.children.cycles-pp.__send_signal 3.62 ± 12% +2.7 6.32 ± 14% perf-profile.children.cycles-pp.do_send_sig_info 5.12 ± 11% +2.8 7.91 ± 14% perf-profile.children.cycles-pp.do_signal 5.21 ± 11% +2.8 8.01 ± 14% perf-profile.children.cycles-pp.__prepare_exit_to_usermode 25.92 ± 8% -5.9 19.97 ± 16% perf-profile.self.cycles-pp.aa_get_task_label 0.11 ± 8% +0.0 0.12 ± 10% perf-profile.self.cycles-pp.___might_sleep 0.16 ± 8% +0.0 0.18 ± 10% perf-profile.self.cycles-pp.__task_pid_nr_ns 0.15 ± 10% +0.0 0.17 ± 8% perf-profile.self.cycles-pp.__x64_sys_rt_sigreturn 0.24 ± 11% +0.0 0.26 ± 10% perf-profile.self.cycles-pp.copy_user_generic_unrolled 0.24 ± 10% +0.0 0.28 ± 9% perf-profile.self.cycles-pp.copy_user_enhanced_fast_string 0.28 ± 11% +0.0 0.32 ± 11% perf-profile.self.cycles-pp.fpu__clear 0.46 ± 10% +0.1 0.51 ± 10% perf-profile.self.cycles-pp.syscall_return_via_sysret 0.32 ± 10% +0.1 0.38 ± 10% perf-profile.self.cycles-pp.entry_SYSCALL_64 0.42 ± 9% +0.1 0.48 ± 9% perf-profile.self.cycles-pp.raise 0.48 ± 9% +0.1 0.55 ± 10% perf-profile.self.cycles-pp.__fpu__restore_sig 0.16 ± 10% +0.1 0.23 ± 26% perf-profile.self.cycles-pp.entry_SYSCALL_64_after_hwframe 0.26 ± 10% +2.2 2.47 ±152% perf-profile.self.cycles-pp.do_syscall_64 3.39 ± 11% +2.6 5.95 ± 14% perf-profile.self.cycles-pp.__sigqueue_free 3.36 ± 12% +2.7 6.01 ± 14% perf-profile.self.cycles-pp.__sigqueue_alloc 7168 ± 20% -49.8% 3598 ± 34% interrupts.CPU100.NMI:Non-maskable_interrupts 7168 ± 20% -49.8% 3598 ± 34% interrupts.CPU100.PMI:Performance_monitoring_interrupts 14.75 ± 83% +513.6% 90.50 ± 83% interrupts.CPU102.RES:Rescheduling_interrupts 4648 ± 25% +86.2% 8654 interrupts.CPU107.NMI:Non-maskable_interrupts 4648 ± 25% +86.2% 8654 interrupts.CPU107.PMI:Performance_monitoring_interrupts 4649 ± 25% +86.2% 8659 interrupts.CPU109.NMI:Non-maskable_interrupts 4649 ± 25% +86.2% 8659 interrupts.CPU109.PMI:Performance_monitoring_interrupts 815.00 ± 3% +7.5% 876.00 ± 7% interrupts.CPU11.CAL:Function_call_interrupts 7163 ± 20% -50.1% 3574 ± 34% interrupts.CPU112.NMI:Non-maskable_interrupts 7163 ± 20% -50.1% 3574 ± 34% interrupts.CPU112.PMI:Performance_monitoring_interrupts 7163 ± 20% -49.7% 3603 ± 33% interrupts.CPU116.NMI:Non-maskable_interrupts 7163 ± 20% -49.7% 3603 ± 33% interrupts.CPU116.PMI:Performance_monitoring_interrupts 7917 ± 16% -50.2% 3943 ± 30% interrupts.CPU120.NMI:Non-maskable_interrupts 7917 ± 16% -50.2% 3943 ± 30% interrupts.CPU120.PMI:Performance_monitoring_interrupts 5733 ± 35% +51.8% 8702 interrupts.CPU123.NMI:Non-maskable_interrupts 5733 ± 35% +51.8% 8702 interrupts.CPU123.PMI:Performance_monitoring_interrupts 5737 ± 35% +51.6% 8701 interrupts.CPU125.NMI:Non-maskable_interrupts 5737 ± 35% +51.6% 8701 interrupts.CPU125.PMI:Performance_monitoring_interrupts 5738 ± 35% +51.6% 8698 interrupts.CPU127.NMI:Non-maskable_interrupts 5738 ± 35% +51.6% 8698 interrupts.CPU127.PMI:Performance_monitoring_interrupts 6815 ± 27% -47.6% 3573 ± 34% interrupts.CPU13.NMI:Non-maskable_interrupts 6815 ± 27% -47.6% 3573 ± 34% interrupts.CPU13.PMI:Performance_monitoring_interrupts 7210 ± 20% -55.4% 3215 ± 48% interrupts.CPU132.NMI:Non-maskable_interrupts 7210 ± 20% -55.4% 3215 ± 48% interrupts.CPU132.PMI:Performance_monitoring_interrupts 7929 ± 16% -50.4% 3934 ± 47% interrupts.CPU138.NMI:Non-maskable_interrupts 7929 ± 16% -50.4% 3934 ± 47% interrupts.CPU138.PMI:Performance_monitoring_interrupts 73.25 ± 73% -47.4% 38.50 ±117% interrupts.CPU14.RES:Rescheduling_interrupts 286.25 ±168% -99.3% 2.00 ±106% interrupts.CPU142.RES:Rescheduling_interrupts 7928 ± 16% -50.4% 3934 ± 47% interrupts.CPU148.NMI:Non-maskable_interrupts 7928 ± 16% -50.4% 3934 ± 47% interrupts.CPU148.PMI:Performance_monitoring_interrupts 11.00 ± 86% +2211.4% 254.25 ±147% interrupts.CPU160.RES:Rescheduling_interrupts 7928 ± 16% -54.9% 3573 ± 34% interrupts.CPU178.NMI:Non-maskable_interrupts 7928 ± 16% -54.9% 3573 ± 34% interrupts.CPU178.PMI:Performance_monitoring_interrupts 5381 ± 39% +61.6% 8698 interrupts.CPU183.NMI:Non-maskable_interrupts 5381 ± 39% +61.6% 8698 interrupts.CPU183.PMI:Performance_monitoring_interrupts 5385 ± 39% +61.5% 8698 interrupts.CPU185.NMI:Non-maskable_interrupts 5385 ± 39% +61.5% 8698 interrupts.CPU185.PMI:Performance_monitoring_interrupts 5384 ± 39% +61.5% 8698 interrupts.CPU187.NMI:Non-maskable_interrupts 5384 ± 39% +61.5% 8698 interrupts.CPU187.PMI:Performance_monitoring_interrupts 5732 ± 35% +51.7% 8698 interrupts.CPU189.NMI:Non-maskable_interrupts 5732 ± 35% +51.7% 8698 interrupts.CPU189.PMI:Performance_monitoring_interrupts 7167 ± 20% -49.9% 3590 ± 34% interrupts.CPU23.NMI:Non-maskable_interrupts 7167 ± 20% -49.9% 3590 ± 34% interrupts.CPU23.PMI:Performance_monitoring_interrupts 801.75 +9.3% 876.50 ± 7% interrupts.CPU31.CAL:Function_call_interrupts 4687 ± 50% +62.4% 7611 ± 24% interrupts.CPU40.NMI:Non-maskable_interrupts 4687 ± 50% +62.4% 7611 ± 24% interrupts.CPU40.PMI:Performance_monitoring_interrupts 6456 ± 19% -44.7% 3573 ± 34% interrupts.CPU41.NMI:Non-maskable_interrupts 6456 ± 19% -44.7% 3573 ± 34% interrupts.CPU41.PMI:Performance_monitoring_interrupts 3960 ± 29% +92.3% 7615 ± 24% interrupts.CPU42.NMI:Non-maskable_interrupts 3960 ± 29% +92.3% 7615 ± 24% interrupts.CPU42.PMI:Performance_monitoring_interrupts 38.25 ±139% -94.1% 2.25 ±148% interrupts.CPU51.RES:Rescheduling_interrupts 5735 ± 35% +51.7% 8700 interrupts.CPU52.NMI:Non-maskable_interrupts 5735 ± 35% +51.7% 8700 interrupts.CPU52.PMI:Performance_monitoring_interrupts 4.50 ± 57% +816.7% 41.25 ±107% interrupts.CPU52.RES:Rescheduling_interrupts 6.00 ± 23% +666.7% 46.00 ± 82% interrupts.CPU65.RES:Rescheduling_interrupts 5732 ± 35% +51.7% 8697 interrupts.CPU68.NMI:Non-maskable_interrupts 5732 ± 35% +51.7% 8697 interrupts.CPU68.PMI:Performance_monitoring_interrupts 5733 ± 35% +51.7% 8697 interrupts.CPU82.NMI:Non-maskable_interrupts 5733 ± 35% +51.7% 8697 interrupts.CPU82.PMI:Performance_monitoring_interrupts 5380 ± 47% +61.7% 8697 interrupts.CPU84.NMI:Non-maskable_interrupts 5380 ± 47% +61.7% 8697 interrupts.CPU84.PMI:Performance_monitoring_interrupts 5728 ± 35% +51.9% 8701 interrupts.CPU86.NMI:Non-maskable_interrupts 5728 ± 35% +51.9% 8701 interrupts.CPU86.PMI:Performance_monitoring_interrupts 7191 ± 20% -50.3% 3573 ± 34% interrupts.CPU87.NMI:Non-maskable_interrupts 7191 ± 20% -50.3% 3573 ± 34% interrupts.CPU87.PMI:Performance_monitoring_interrupts 7193 ± 20% -49.5% 3634 ± 33% interrupts.CPU89.NMI:Non-maskable_interrupts 7193 ± 20% -49.5% 3634 ± 33% interrupts.CPU89.PMI:Performance_monitoring_interrupts 4646 ± 25% +87.3% 8699 interrupts.CPU92.NMI:Non-maskable_interrupts 4646 ± 25% +87.3% 8699 interrupts.CPU92.PMI:Performance_monitoring_interrupts 4495 ± 3% +54.7% 6953 ± 47% softirqs.CPU101.RCU 4421 ± 2% +56.4% 6914 ± 49% softirqs.CPU105.RCU 4350 ± 4% +50.5% 6548 ± 46% softirqs.CPU106.RCU 28330 ± 51% -87.0% 3677 ± 2% softirqs.CPU107.SCHED 4304 +49.8% 6449 ± 47% softirqs.CPU108.RCU 4301 +57.7% 6784 ± 52% softirqs.CPU109.RCU 5020 ± 3% +39.4% 7000 ± 38% softirqs.CPU11.RCU 14544 ± 98% +168.7% 39074 softirqs.CPU11.SCHED 4315 ± 3% +46.9% 6339 ± 48% softirqs.CPU110.RCU 4430 ± 4% +54.9% 6865 ± 51% softirqs.CPU113.RCU 4522 ± 7% +85.0% 8365 ± 44% softirqs.CPU119.RCU 4851 ± 13% +51.0% 7326 ± 40% softirqs.CPU121.RCU 4544 +53.8% 6988 ± 44% softirqs.CPU122.RCU 4472 ± 8% +61.9% 7243 ± 47% softirqs.CPU123.RCU 4531 ± 5% +65.5% 7498 ± 45% softirqs.CPU125.RCU 4387 +64.2% 7202 ± 48% softirqs.CPU127.RCU 4428 +55.1% 6868 ± 53% softirqs.CPU129.RCU 14515 ± 98% +168.9% 39037 softirqs.CPU13.SCHED 4401 ± 3% +64.4% 7235 ± 62% softirqs.CPU130.RCU 4439 ± 6% +66.6% 7394 ± 47% softirqs.CPU133.RCU 4308 ± 3% +68.7% 7269 ± 46% softirqs.CPU135.RCU 12652 ±117% +203.4% 38388 softirqs.CPU138.SCHED 4642 ± 7% +60.8% 7465 ± 44% softirqs.CPU139.RCU 21066 ± 82% -82.8% 3626 softirqs.CPU141.SCHED 21082 ± 82% -81.4% 3925 ± 12% softirqs.CPU143.SCHED 3726 ± 4% +692.1% 29516 ± 50% softirqs.CPU144.SCHED 19021 ± 82% +101.4% 38309 softirqs.CPU146.SCHED 4481 +55.3% 6958 ± 51% softirqs.CPU147.RCU 5014 ± 7% +50.2% 7530 ± 39% softirqs.CPU15.RCU 4325 ± 3% +60.4% 6938 ± 52% softirqs.CPU151.RCU 4239 ± 2% +66.2% 7044 ± 50% softirqs.CPU153.RCU 4271 ± 2% +64.1% 7008 ± 52% softirqs.CPU155.RCU 4280 ± 2% +64.9% 7056 ± 50% softirqs.CPU157.RCU 4299 ± 3% +61.7% 6950 ± 53% softirqs.CPU159.RCU 5106 ± 4% +48.5% 7580 ± 47% softirqs.CPU16.RCU 4222 ± 2% +57.0% 6631 ± 52% softirqs.CPU160.RCU 4236 ± 2% +65.0% 6992 ± 55% softirqs.CPU161.RCU 4362 ± 2% +67.1% 7290 ± 52% softirqs.CPU163.RCU 12448 ±120% +208.1% 38355 softirqs.CPU164.SCHED 4116 ± 3% +76.2% 7251 ± 52% softirqs.CPU165.RCU 4309 +64.0% 7066 ± 54% softirqs.CPU167.RCU 4148 +72.8% 7169 ± 60% softirqs.CPU169.RCU 4168 ± 3% +55.7% 6491 ± 49% softirqs.CPU170.RCU 4239 +59.6% 6764 ± 54% softirqs.CPU171.RCU 4109 ± 3% +55.9% 6408 ± 50% softirqs.CPU172.RCU 4134 +67.5% 6925 ± 54% softirqs.CPU173.RCU 4152 +63.0% 6767 ± 59% softirqs.CPU174.RCU 4113 ± 2% +68.7% 6939 ± 58% softirqs.CPU175.RCU 4010 ± 4% +56.9% 6292 ± 53% softirqs.CPU176.RCU 4154 +63.0% 6773 ± 52% softirqs.CPU177.RCU 4098 ± 3% +55.2% 6360 ± 52% softirqs.CPU178.RCU 14878 ± 94% +158.1% 38406 softirqs.CPU178.SCHED 4045 ± 2% +61.7% 6540 ± 53% softirqs.CPU179.RCU 5016 ± 5% +49.7% 7507 ± 48% softirqs.CPU18.RCU 4103 ± 2% +51.7% 6224 ± 51% softirqs.CPU180.RCU 14117 ± 92% +171.8% 38371 softirqs.CPU180.SCHED 4076 ± 2% +60.8% 6553 ± 52% softirqs.CPU181.RCU 4091 ± 3% +52.2% 6226 ± 51% softirqs.CPU182.RCU 4055 ± 2% +62.1% 6575 ± 52% softirqs.CPU183.RCU 3987 ± 3% +56.7% 6248 ± 51% softirqs.CPU184.RCU 4082 ± 2% +66.1% 6780 ± 50% softirqs.CPU185.RCU 3981 ± 2% +96.4% 7819 ± 42% softirqs.CPU186.RCU 4104 ± 4% +58.3% 6495 ± 52% softirqs.CPU187.RCU 12405 ±120% +209.1% 38340 softirqs.CPU188.SCHED 4009 ± 2% +64.6% 6597 ± 52% softirqs.CPU189.RCU 4068 ± 4% +54.0% 6264 ± 51% softirqs.CPU190.RCU 4452 ± 15% +52.7% 6797 ± 44% softirqs.CPU191.RCU 21345 ± 81% -82.9% 3642 ± 2% softirqs.CPU20.SCHED 29570 ± 49% -58.6% 12256 ±119% softirqs.CPU24.SCHED 5202 ± 2% +48.4% 7721 ± 44% softirqs.CPU26.RCU 5237 ± 8% +46.9% 7692 ± 45% softirqs.CPU28.RCU 21112 ± 81% -81.9% 3827 ± 9% softirqs.CPU28.SCHED 13521 ±106% +184.0% 38404 softirqs.CPU29.SCHED 12846 ±114% +198.4% 38327 softirqs.CPU31.SCHED 4902 ± 3% +81.6% 8905 ± 63% softirqs.CPU35.RCU 5034 ± 3% +53.1% 7705 ± 45% softirqs.CPU36.RCU 4922 ± 3% +44.3% 7102 ± 46% softirqs.CPU37.RCU 14874 ± 95% +129.8% 34186 ± 20% softirqs.CPU37.SCHED 4915 +55.0% 7618 ± 46% softirqs.CPU38.RCU 4914 ± 2% +44.6% 7105 ± 46% softirqs.CPU39.RCU 4901 ± 2% +57.3% 7710 ± 42% softirqs.CPU40.RCU 4889 ± 2% +56.6% 7659 ± 47% softirqs.CPU42.RCU 4821 ± 3% +52.8% 7367 ± 41% softirqs.CPU43.RCU 4895 +56.4% 7654 ± 45% softirqs.CPU46.RCU 4787 ± 2% +60.0% 7658 ± 48% softirqs.CPU50.RCU 4797 +58.2% 7589 ± 48% softirqs.CPU52.RCU 4765 +48.9% 7094 ± 46% softirqs.CPU53.RCU 4790 +59.0% 7619 ± 49% softirqs.CPU54.RCU 4784 ± 2% +59.4% 7625 ± 49% softirqs.CPU56.RCU 4766 ± 2% +65.6% 7892 ± 51% softirqs.CPU58.RCU 21044 ± 82% -82.6% 3656 ± 3% softirqs.CPU58.SCHED 4769 ± 2% +48.5% 7080 ± 47% softirqs.CPU59.RCU 4775 ± 2% +59.8% 7629 ± 49% softirqs.CPU60.RCU 4858 ± 2% +54.5% 7506 ± 50% softirqs.CPU62.RCU 21072 ± 82% -82.7% 3647 softirqs.CPU62.SCHED 4887 ± 3% +56.3% 7636 ± 51% softirqs.CPU64.RCU 14323 ± 99% -74.4% 3669 softirqs.CPU64.SCHED 4782 +62.1% 7750 ± 48% softirqs.CPU66.RCU 4715 +56.3% 7370 ± 46% softirqs.CPU67.RCU 4717 +61.8% 7631 ± 49% softirqs.CPU68.RCU 4789 +53.5% 7350 ± 46% softirqs.CPU69.RCU 4754 +71.9% 8171 ± 44% softirqs.CPU70.RCU 4740 ± 2% +52.9% 7249 ± 43% softirqs.CPU72.RCU 4642 +53.5% 7124 ± 49% softirqs.CPU74.RCU 4599 ± 2% +59.4% 7333 ± 54% softirqs.CPU75.RCU 4590 ± 2% +53.2% 7034 ± 50% softirqs.CPU77.RCU 4925 +53.0% 7535 ± 48% softirqs.CPU8.RCU 4617 +60.0% 7390 ± 51% softirqs.CPU80.RCU 4586 +57.7% 7232 ± 47% softirqs.CPU82.RCU 27442 ± 52% -86.5% 3692 softirqs.CPU82.SCHED 4624 ± 3% +49.8% 6925 ± 48% softirqs.CPU83.RCU 4560 ± 2% +55.0% 7066 ± 48% softirqs.CPU84.RCU 27984 ± 46% -86.9% 3660 ± 2% softirqs.CPU84.SCHED 4576 ± 2% +46.6% 6710 ± 45% softirqs.CPU85.RCU 4503 ± 2% +58.1% 7118 ± 47% softirqs.CPU86.RCU 4653 +54.3% 7181 ± 47% softirqs.CPU88.RCU 4957 ± 4% +42.5% 7062 ± 43% softirqs.CPU9.RCU 4537 ± 2% +54.9% 7028 ± 48% softirqs.CPU90.RCU 4451 ± 2% +58.5% 7055 ± 49% softirqs.CPU92.RCU 29714 ± 50% -87.7% 3642 softirqs.CPU92.SCHED 4535 ± 3% +53.1% 6942 ± 42% softirqs.CPU93.RCU 4505 +56.2% 7038 ± 50% softirqs.CPU94.RCU 4701 ± 2% +51.1% 7103 ± 47% softirqs.CPU95.RCU 4469 ± 3% +51.4% 6767 ± 50% softirqs.CPU97.RCU 4488 ± 3% +51.9% 6818 ± 40% softirqs.CPU98.RCU 4463 ± 3% +53.6% 6855 ± 49% softirqs.CPU99.RCU 2949 ± 33% +237.4% 9950 ± 53% softirqs.NET_RX will-it-scale.per_process_ops 74000 +-------------------------------------------------------------------+ | O O O O O O O O O O O O O O O O | 72000 |-O O O O O O O O O O O O | 70000 |-+ O | | .+. .+ | 68000 |-+ +. + + | |.+..+. .+ : +..+.+. .+. .+.+..+ | 66000 |-+ + : : +. + | | : : | 64000 |-+ : : | 62000 |-+ : : | | : : | 60000 |-+ : : | | : .+ | 58000 +-------------------------------------------------------------------+ [*] bisect-good sample [O] bisect-bad sample Disclaimer: Results have been estimated based on internal Intel analysis and are provided for informational purposes only. Any difference in system hardware or software design or configuration may affect actual performance. Thanks, Rong Chen