| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Fri, 2 Oct 2020 16:20:23 +0800
From: kernel test robot <rong.a.chen@...el.com>
To: Adrian Hunter <adrian.hunter@...el.com>
Cc: Peter Zijlstra <peterz@...radead.org>,
Masami Hiramatsu <mhiramat@...nel.org>,
LKML <linux-kernel@...r.kernel.org>, lkp@...ts.01.org,
lkp@...el.com, ying.huang@...el.com, feng.tang@...el.com,
zhengjun.xing@...el.com
Subject: [kprobes] d002b8bc6d: will-it-scale.per_process_ops 8.4% improvement
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
View attachment "config-5.8.0-rc1-00004-gd002b8bc6dbc2" of type "text/plain" (158289 bytes)
View attachment "job-script" of type "text/plain" (7540 bytes)
View attachment "job.yaml" of type "text/plain" (5196 bytes)
View attachment "reproduce" of type "text/plain" (339 bytes)
Powered by blists - more mailing lists