| 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
| ||
|
Message-ID: <20200923085544.GE28663@shao2-debian>
Date: Wed, 23 Sep 2020 16:55:44 +0800
From: kernel test robot <rong.a.chen@...el.com>
To: Kees Cook <keescook@...omium.org>
Cc: Thomas Gleixner <tglx@...utronix.de>,
Michael Ellerman <mpe@...erman.id.au>,
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: [core/entry] b6ec413461: will-it-scale.per_process_ops 5.0%
improvement
Greeting,
FYI, we noticed a 5.0% improvement of will-it-scale.per_process_ops due to commit:
commit: b6ec413461034d49f9e586845825adb35ba308f6 ("core/entry: Report syscall correctly for trace and audit")
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: 16
mode: process
test: lseek2
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
In addition to that, the commit also has significant impact on the following tests:
+------------------+---------------------------------------------------------------------------+
| testcase: change | will-it-scale: will-it-scale.per_process_ops 3.2% improvement |
| test machine | 192 threads Intel(R) Xeon(R) Platinum 9242 CPU @ 2.30GHz with 192G memory |
| test parameters | cpufreq_governor=performance |
| | mode=process |
| | nr_task=16 |
| | test=eventfd1 |
| | ucode=0x5002f01 |
+------------------+---------------------------------------------------------------------------+
Details are as below:
-------------------------------------------------------------------------------------------------->
To reproduce:
git clone https://github.com/intel/lkp-tests.git
cd lkp-tests
bin/lkp install job.yaml # job file is attached in this email
bin/lkp run job.yaml
=========================================================================================
compiler/cpufreq_governor/kconfig/mode/nr_task/rootfs/tbox_group/test/testcase/ucode:
gcc-9/performance/x86_64-rhel-8.3/process/16/debian-10.4-x86_64-20200603.cgz/lkp-csl-2ap2/lseek2/will-it-scale/0x5002f01
commit:
v5.9-rc5
b6ec413461 ("core/entry: Report syscall correctly for trace and audit")
v5.9-rc5 b6ec413461034d49f9e58684582
---------------- ---------------------------
%stddev %change %stddev
\ | \
9885233 +5.0% 10378311 will-it-scale.per_process_ops
1.582e+08 +5.0% 1.661e+08 will-it-scale.workload
24202 ± 4% +8.4% 26235 ± 4% cpuidle.C1.usage
14616 ± 20% +18.7% 17353 ± 8% sched_debug.cfs_rq:/.load.avg
235.73 ± 31% -28.8% 167.73 ± 8% sched_debug.cfs_rq:/.load_avg.max
17260 ± 31% +44.7% 24968 ± 18% softirqs.CPU10.RCU
14774 ± 48% +62.3% 23974 ± 22% softirqs.NET_RX
17491 ± 6% +16.9% 20449 ± 6% meminfo.Active
17487 ± 6% +16.9% 20445 ± 6% meminfo.Active(anon)
37041 ± 3% +8.2% 40071 ± 3% meminfo.Shmem
148143 ± 74% -93.9% 9079 ± 6% numa-numastat.node0.local_node
160532 ± 62% -75.1% 40045 numa-numastat.node0.numa_hit
12401 ±122% +149.7% 30966 numa-numastat.node0.other_node
2079 ± 61% -94.0% 125.00 ± 52% numa-meminfo.node0.Active
2078 ± 61% -94.0% 125.00 ± 52% numa-meminfo.node0.Active(anon)
79197 ± 18% -28.5% 56601 ± 15% numa-meminfo.node1.SUnreclaim
13420 ± 7% +25.0% 16775 ± 16% numa-meminfo.node3.Active
13420 ± 7% +25.0% 16774 ± 16% numa-meminfo.node3.Active(anon)
519.40 ± 61% -94.1% 30.50 ± 54% numa-vmstat.node0.nr_active_anon
519.40 ± 61% -94.1% 30.50 ± 54% numa-vmstat.node0.nr_zone_active_anon
29263 ±127% +188.4% 84386 ± 35% numa-vmstat.node0.numa_other
19799 ± 18% -28.5% 14150 ± 15% numa-vmstat.node1.nr_slab_unreclaimable
3349 ± 7% +25.0% 4186 ± 16% numa-vmstat.node3.nr_active_anon
3349 ± 7% +25.0% 4186 ± 16% numa-vmstat.node3.nr_zone_active_anon
4372 ± 6% +16.9% 5109 ± 6% proc-vmstat.nr_active_anon
9269 ± 3% +8.2% 10026 ± 3% proc-vmstat.nr_shmem
31421 -2.4% 30681 proc-vmstat.nr_slab_reclaimable
72340 -3.8% 69626 proc-vmstat.nr_slab_unreclaimable
4372 ± 6% +16.9% 5109 ± 6% proc-vmstat.nr_zone_active_anon
4838 ± 8% +24.9% 6045 ± 9% proc-vmstat.pgactivate
8152 ± 6% -16.4% 6812 ± 6% slabinfo.Acpi-State.active_objs
8152 ± 6% -16.4% 6812 ± 6% slabinfo.Acpi-State.num_objs
6952 ± 3% -18.4% 5674 ± 7% slabinfo.files_cache.active_objs
6952 ± 3% -18.4% 5674 ± 7% slabinfo.files_cache.num_objs
5555 ± 4% -12.6% 4854 ± 6% slabinfo.mm_struct.active_objs
5555 ± 4% -12.6% 4854 ± 6% slabinfo.mm_struct.num_objs
3792 ± 3% -11.5% 3357 ± 2% slabinfo.sighand_cache.active_objs
3865 ± 3% -10.6% 3454 slabinfo.sighand_cache.num_objs
6037 ± 2% -11.9% 5318 ± 4% slabinfo.signal_cache.num_objs
9626 ± 3% -14.6% 8218 ± 4% slabinfo.task_delay_info.active_objs
9626 ± 3% -14.6% 8218 ± 4% slabinfo.task_delay_info.num_objs
817.40 +80.0% 1471 ± 64% interrupts.CPU1.CAL:Function_call_interrupts
2575 ± 22% +94.1% 4999 ± 24% interrupts.CPU1.NMI:Non-maskable_interrupts
2575 ± 22% +94.1% 4999 ± 24% interrupts.CPU1.PMI:Performance_monitoring_interrupts
3166 ± 19% +95.3% 6184 ± 42% interrupts.CPU10.NMI:Non-maskable_interrupts
3166 ± 19% +95.3% 6184 ± 42% interrupts.CPU10.PMI:Performance_monitoring_interrupts
203.00 ± 97% -83.1% 34.25 ± 61% interrupts.CPU112.RES:Rescheduling_interrupts
244.60 ±193% -99.0% 2.50 ± 87% interrupts.CPU147.RES:Rescheduling_interrupts
49.80 ± 86% -95.0% 2.50 ±173% interrupts.CPU20.RES:Rescheduling_interrupts
824.20 ± 4% +32.6% 1092 ± 32% interrupts.CPU49.CAL:Function_call_interrupts
191937 ± 9% +22.9% 235809 ± 7% interrupts.NMI:Non-maskable_interrupts
191937 ± 9% +22.9% 235809 ± 7% interrupts.PMI:Performance_monitoring_interrupts
6526 ± 36% -38.0% 4047 ± 22% interrupts.RES:Rescheduling_interrupts
1.025e+10 +4.9% 1.076e+10 perf-stat.i.branch-instructions
1.13 -3.9% 1.09 perf-stat.i.cpi
1.54e+10 +4.5% 1.609e+10 perf-stat.i.dTLB-loads
1.016e+10 +4.9% 1.066e+10 perf-stat.i.dTLB-stores
1.616e+08 +1.7% 1.644e+08 perf-stat.i.iTLB-load-misses
5.044e+10 +4.9% 5.292e+10 perf-stat.i.instructions
313.59 +3.1% 323.35 perf-stat.i.instructions-per-iTLB-miss
0.88 +4.1% 0.92 perf-stat.i.ipc
186.80 +4.7% 195.64 perf-stat.i.metric.M/sec
1.13 -3.9% 1.09 perf-stat.overall.cpi
312.10 +3.2% 321.96 perf-stat.overall.instructions-per-iTLB-miss
0.88 +4.1% 0.92 perf-stat.overall.ipc
1.022e+10 +4.9% 1.072e+10 perf-stat.ps.branch-instructions
1.535e+10 +4.5% 1.604e+10 perf-stat.ps.dTLB-loads
1.012e+10 +4.9% 1.062e+10 perf-stat.ps.dTLB-stores
1.611e+08 +1.7% 1.638e+08 perf-stat.ps.iTLB-load-misses
5.027e+10 +4.9% 5.275e+10 perf-stat.ps.instructions
1.517e+13 +5.0% 1.592e+13 perf-stat.total.instructions
33.08 ± 6% -4.7 28.41 ± 9% perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.llseek
24.83 ± 7% -4.4 20.40 ± 9% perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.llseek
4.24 ± 7% -1.2 3.08 ± 5% perf-profile.calltrace.cycles-pp.asm_sysvec_apic_timer_interrupt.cpuidle_enter_state.cpuidle_enter.do_idle.cpu_startup_entry
30.98 ± 14% +6.4 37.39 ± 12% perf-profile.calltrace.cycles-pp.cpuidle_enter.do_idle.cpu_startup_entry.start_secondary.secondary_startup_64
29.97 ± 15% +6.8 36.78 ± 12% perf-profile.calltrace.cycles-pp.cpuidle_enter_state.cpuidle_enter.do_idle.cpu_startup_entry.start_secondary
27.84 ± 16% +8.0 35.88 ± 15% perf-profile.calltrace.cycles-pp.intel_idle.cpuidle_enter_state.cpuidle_enter.do_idle.cpu_startup_entry
33.38 ± 6% -4.7 28.66 ± 9% perf-profile.children.cycles-pp.entry_SYSCALL_64_after_hwframe
24.90 ± 6% -4.2 20.66 ± 9% perf-profile.children.cycles-pp.do_syscall_64
2.49 ± 6% -2.1 0.40 ± 11% perf-profile.children.cycles-pp.__x64_sys_lseek
3.56 ± 7% -0.8 2.77 ± 10% perf-profile.children.cycles-pp.asm_sysvec_apic_timer_interrupt
0.21 ± 7% -0.0 0.18 ± 10% perf-profile.children.cycles-pp.rebalance_domains
0.31 ± 6% -0.0 0.28 ± 3% perf-profile.children.cycles-pp.lseek@plt
0.67 ± 7% +0.1 0.82 ± 9% perf-profile.children.cycles-pp.__x86_indirect_thunk_rax
32.34 ± 14% +7.0 39.30 ± 14% perf-profile.children.cycles-pp.cpuidle_enter_state
32.35 ± 14% +7.0 39.31 ± 14% perf-profile.children.cycles-pp.cpuidle_enter
27.83 ± 16% +8.0 35.88 ± 15% perf-profile.children.cycles-pp.intel_idle
2.26 ± 6% -2.1 0.21 ± 13% perf-profile.self.cycles-pp.__x64_sys_lseek
3.02 ± 6% -0.9 2.09 ± 9% perf-profile.self.cycles-pp.ksys_lseek
1.69 ± 6% -0.7 1.02 ± 9% perf-profile.self.cycles-pp.do_syscall_64
0.11 ± 9% -0.0 0.09 ± 7% perf-profile.self.cycles-pp.read_tsc
27.83 ± 16% +8.0 35.88 ± 15% perf-profile.self.cycles-pp.intel_idle
will-it-scale.per_process_ops
1.04e+07 +----------------------------------------------------------------+
| O O O O O O O O O O |
1.03e+07 |-+ |
| |
| |
1.02e+07 |-+ |
| |
1.01e+07 |-+ |
| |
1e+07 |-+ |
| |
| +. +. |
9.9e+06 |..+.+..+.. .. +.. .. +..+.. .+.+..+..+.+..+..+. .+..+..+.+..|
| + + +. +. |
9.8e+06 +----------------------------------------------------------------+
will-it-scale.workload
1.67e+08 +----------------------------------------------------------------+
1.66e+08 |-+O O O O O O O O O O O O O |
| O |
1.65e+08 |-+ |
1.64e+08 |-+ |
| |
1.63e+08 |-+ |
1.62e+08 |-+ |
1.61e+08 |-+ |
| |
1.6e+08 |-+ |
1.59e+08 |-+ |
|..+.+..+.. .+.+.. .+. .+.. .+. .+..+.+..+..+. .+..+..+.+..|
1.58e+08 |-+ +. +. +. +. +. +. |
1.57e+08 +----------------------------------------------------------------+
[*] bisect-good sample
[O] bisect-bad sample
***************************************************************************************************
lkp-csl-2ap2: 192 threads Intel(R) Xeon(R) Platinum 9242 CPU @ 2.30GHz with 192G memory
=========================================================================================
compiler/cpufreq_governor/kconfig/mode/nr_task/rootfs/tbox_group/test/testcase/ucode:
gcc-9/performance/x86_64-rhel-8.3/process/16/debian-10.4-x86_64-20200603.cgz/lkp-csl-2ap2/eventfd1/will-it-scale/0x5002f01
commit:
v5.9-rc5
b6ec413461 ("core/entry: Report syscall correctly for trace and audit")
v5.9-rc5 b6ec413461034d49f9e58684582
---------------- ---------------------------
%stddev %change %stddev
\ | \
2798280 +3.2% 2887533 will-it-scale.per_process_ops
44772485 +3.2% 46200540 will-it-scale.workload
87.60 ± 24% +82.1% 159.50 ± 28% numa-vmstat.node3.nr_page_table_pages
20657 ± 22% +28.0% 26436 ± 15% sched_debug.cfs_rq:/.min_vruntime.min
2161 +2.3% 2210 vmstat.system.cs
191992 ±105% +165.2% 509166 ± 44% numa-numastat.node1.local_node
216868 ± 88% +142.0% 524722 ± 40% numa-numastat.node1.numa_hit
7105 ± 11% +17.0% 8311 ± 13% slabinfo.eventpoll_pwq.active_objs
7105 ± 11% +17.0% 8311 ± 13% slabinfo.eventpoll_pwq.num_objs
1.43 ± 9% +0.3 1.72 ± 8% perf-profile.calltrace.cycles-pp.__fget_light.__fdget_pos.ksys_read.do_syscall_64.entry_SYSCALL_64_after_hwframe
0.82 ± 12% -0.7 0.12 ± 12% perf-profile.children.cycles-pp.__x64_sys_read
0.77 ± 10% -0.7 0.12 ± 7% perf-profile.children.cycles-pp.__x64_sys_write
0.52 ± 10% -0.1 0.41 ± 8% perf-profile.children.cycles-pp.apparmor_file_permission
0.47 ± 10% +0.1 0.61 ± 6% perf-profile.children.cycles-pp.__x86_indirect_thunk_rax
0.77 ± 11% -0.7 0.07 ± 21% perf-profile.self.cycles-pp.__x64_sys_read
0.71 ± 10% -0.7 0.06 ± 14% perf-profile.self.cycles-pp.__x64_sys_write
0.76 ± 9% -0.3 0.48 ± 6% perf-profile.self.cycles-pp.do_syscall_64
0.84 ± 10% -0.2 0.61 ± 11% perf-profile.self.cycles-pp.ksys_write
0.84 ± 11% -0.2 0.64 ± 9% perf-profile.self.cycles-pp.ksys_read
0.41 ± 11% -0.1 0.30 ± 8% perf-profile.self.cycles-pp.apparmor_file_permission
0.58 ± 89% -48.3% 0.30 ± 3% perf-stat.i.MPKI
1.506e+10 +3.1% 1.553e+10 perf-stat.i.branch-instructions
2117 +2.3% 2165 perf-stat.i.context-switches
0.74 -3.8% 0.71 perf-stat.i.cpi
0.00 ±185% -0.0 0.00 ± 11% perf-stat.i.dTLB-load-miss-rate%
699002 ±185% -94.3% 40038 ± 12% perf-stat.i.dTLB-load-misses
2.279e+10 +2.9% 2.346e+10 perf-stat.i.dTLB-loads
1.478e+10 +3.2% 1.525e+10 perf-stat.i.dTLB-stores
1.767e+08 ± 2% -2.6% 1.722e+08 perf-stat.i.iTLB-load-misses
3908623 ± 14% +8.4% 4235861 perf-stat.i.iTLB-loads
7.678e+10 +3.1% 7.919e+10 perf-stat.i.instructions
436.22 ± 2% +5.7% 461.03 perf-stat.i.instructions-per-iTLB-miss
1.35 +3.9% 1.40 perf-stat.i.ipc
274.35 +3.0% 282.62 perf-stat.i.metric.M/sec
0.58 ± 90% -48.6% 0.30 ± 3% perf-stat.overall.MPKI
0.74 -3.8% 0.71 perf-stat.overall.cpi
0.00 ±185% -0.0 0.00 ± 12% perf-stat.overall.dTLB-load-miss-rate%
434.74 ± 2% +5.8% 459.94 perf-stat.overall.instructions-per-iTLB-miss
1.35 +3.9% 1.40 perf-stat.overall.ipc
1.501e+10 +3.1% 1.548e+10 perf-stat.ps.branch-instructions
2110 +2.3% 2158 perf-stat.ps.context-switches
696387 ±185% -94.3% 39917 ± 12% perf-stat.ps.dTLB-load-misses
2.271e+10 +2.9% 2.338e+10 perf-stat.ps.dTLB-loads
1.473e+10 +3.2% 1.519e+10 perf-stat.ps.dTLB-stores
1.761e+08 ± 2% -2.6% 1.716e+08 perf-stat.ps.iTLB-load-misses
3895475 ± 14% +8.4% 4221532 perf-stat.ps.iTLB-loads
7.652e+10 +3.1% 7.892e+10 perf-stat.ps.instructions
2.31e+13 +3.1% 2.382e+13 perf-stat.total.instructions
12126 ± 28% +39.2% 16874 ± 34% softirqs.CPU100.RCU
11840 ± 31% +55.4% 18401 ± 39% softirqs.CPU102.RCU
10572 ± 11% +55.6% 16448 ± 35% softirqs.CPU104.RCU
11684 ± 29% +40.2% 16381 ± 34% softirqs.CPU106.RCU
11734 ± 31% +45.6% 17086 ± 36% softirqs.CPU108.RCU
10703 ± 7% +51.0% 16164 ± 30% softirqs.CPU11.RCU
13037 ± 30% +25.5% 16363 ± 35% softirqs.CPU110.RCU
9291 ± 6% +9.0% 10126 ± 6% softirqs.CPU115.RCU
9701 ± 9% +10.9% 10755 softirqs.CPU121.RCU
9730 ± 7% +9.9% 10689 ± 3% softirqs.CPU122.RCU
11788 ± 28% +42.5% 16796 ± 32% softirqs.CPU13.RCU
10971 ± 10% +18.5% 12996 ± 11% softirqs.CPU156.RCU
10974 ± 9% +10.8% 12158 ± 3% softirqs.CPU160.RCU
10794 ± 13% +14.6% 12365 ± 3% softirqs.CPU162.RCU
11211 ± 9% +10.2% 12359 ± 3% softirqs.CPU163.RCU
11176 ± 7% +9.5% 12240 ± 3% softirqs.CPU165.RCU
11092 ± 8% +9.7% 12168 ± 3% softirqs.CPU167.RCU
10702 ± 8% +10.7% 11842 ± 4% softirqs.CPU168.RCU
10387 ± 10% +13.2% 11756 ± 3% softirqs.CPU169.RCU
10337 ± 9% +12.9% 11672 ± 3% softirqs.CPU170.RCU
10579 ± 9% +12.6% 11911 ± 5% softirqs.CPU171.RCU
10539 ± 9% +13.9% 12000 ± 7% softirqs.CPU172.RCU
10516 ± 9% +10.2% 11592 ± 4% softirqs.CPU173.RCU
10491 ± 10% +11.3% 11682 ± 5% softirqs.CPU174.RCU
10410 ± 10% +11.7% 11628 ± 4% softirqs.CPU175.RCU
10714 ± 9% +11.8% 11973 ± 3% softirqs.CPU181.RCU
10813 ± 10% +13.2% 12240 ± 7% softirqs.CPU189.RCU
10340 ± 6% +14.0% 11788 ± 3% softirqs.CPU22.RCU
10412 ± 6% +16.3% 12106 ± 3% softirqs.CPU23.RCU
10211 ± 8% +11.2% 11360 ± 4% softirqs.CPU25.RCU
10031 ± 8% +10.7% 11107 ± 2% softirqs.CPU26.RCU
11991 ± 9% +7.6% 12904 ± 3% softirqs.CPU34.RCU
11613 ± 9% +9.5% 12712 ± 3% softirqs.CPU38.RCU
11600 ±117% +91.6% 22232 ± 76% softirqs.CPU4.SCHED
11729 ± 8% +10.0% 12899 ± 3% softirqs.CPU40.RCU
11808 ± 9% +11.9% 13211 ± 4% softirqs.CPU45.RCU
14100 ± 33% +18.9% 16772 ± 30% softirqs.CPU5.RCU
11311 ± 9% +11.4% 12604 ± 2% softirqs.CPU64.RCU
11492 ± 9% +11.8% 12848 ± 5% softirqs.CPU65.RCU
11340 ± 9% +12.3% 12734 ± 4% softirqs.CPU71.RCU
10991 ± 10% +12.5% 12364 ± 5% softirqs.CPU73.RCU
10941 ± 8% +11.5% 12195 ± 4% softirqs.CPU74.RCU
11032 ± 9% +11.3% 12274 ± 5% softirqs.CPU75.RCU
11103 ± 9% +8.4% 12033 ± 4% softirqs.CPU76.RCU
10933 ± 9% +9.8% 12000 ± 4% softirqs.CPU77.RCU
10915 ± 9% +11.5% 12173 ± 5% softirqs.CPU78.RCU
10888 ± 8% +9.8% 11957 ± 4% softirqs.CPU79.RCU
17681 ± 3% +15.6% 20433 ± 8% softirqs.CPU96.RCU
17146 ± 22% +27.1% 21799 ± 10% softirqs.CPU97.RCU
10.60 ± 95% +725.5% 87.50 ±138% interrupts.CPU120.RES:Rescheduling_interrupts
1135 ± 36% -29.0% 806.25 interrupts.CPU121.CAL:Function_call_interrupts
810.20 +52.3% 1234 ± 44% interrupts.CPU127.CAL:Function_call_interrupts
4.40 ± 54% +621.6% 31.75 ±133% interrupts.CPU146.TLB:TLB_shootdowns
139.40 ± 15% -31.1% 96.00 ± 23% interrupts.CPU147.NMI:Non-maskable_interrupts
139.40 ± 15% -31.1% 96.00 ± 23% interrupts.CPU147.PMI:Performance_monitoring_interrupts
4.00 ± 54% +806.2% 36.25 ±142% interrupts.CPU149.TLB:TLB_shootdowns
133.60 ± 8% -38.2% 82.50 ± 32% interrupts.CPU165.NMI:Non-maskable_interrupts
133.60 ± 8% -38.2% 82.50 ± 32% interrupts.CPU165.PMI:Performance_monitoring_interrupts
133.20 ± 9% -38.1% 82.50 ± 33% interrupts.CPU166.NMI:Non-maskable_interrupts
133.20 ± 9% -38.1% 82.50 ± 33% interrupts.CPU166.PMI:Performance_monitoring_interrupts
155.40 ± 33% -46.6% 83.00 ± 33% interrupts.CPU167.NMI:Non-maskable_interrupts
155.40 ± 33% -46.6% 83.00 ± 33% interrupts.CPU167.PMI:Performance_monitoring_interrupts
134.20 ± 11% -36.1% 85.75 ± 34% interrupts.CPU168.NMI:Non-maskable_interrupts
134.20 ± 11% -36.1% 85.75 ± 34% interrupts.CPU168.PMI:Performance_monitoring_interrupts
160.40 ± 37% -46.7% 85.50 ± 31% interrupts.CPU169.NMI:Non-maskable_interrupts
160.40 ± 37% -46.7% 85.50 ± 31% interrupts.CPU169.PMI:Performance_monitoring_interrupts
133.00 ± 11% -36.7% 84.25 ± 34% interrupts.CPU170.NMI:Non-maskable_interrupts
133.00 ± 11% -36.7% 84.25 ± 34% interrupts.CPU170.PMI:Performance_monitoring_interrupts
138.60 ± 20% -48.8% 71.00 ± 39% interrupts.CPU171.NMI:Non-maskable_interrupts
138.60 ± 20% -48.8% 71.00 ± 39% interrupts.CPU171.PMI:Performance_monitoring_interrupts
132.20 ± 11% -35.9% 84.75 ± 35% interrupts.CPU172.NMI:Non-maskable_interrupts
132.20 ± 11% -35.9% 84.75 ± 35% interrupts.CPU172.PMI:Performance_monitoring_interrupts
20.60 ±145% +637.9% 152.00 ±124% interrupts.CPU18.RES:Rescheduling_interrupts
144.00 ± 9% -34.5% 94.25 ± 31% interrupts.CPU191.NMI:Non-maskable_interrupts
144.00 ± 9% -34.5% 94.25 ± 31% interrupts.CPU191.PMI:Performance_monitoring_interrupts
83.80 ±167% -99.1% 0.75 ±173% interrupts.CPU23.RES:Rescheduling_interrupts
806.40 +8.8% 877.50 ± 6% interrupts.CPU28.CAL:Function_call_interrupts
805.60 +205.7% 2463 ± 97% interrupts.CPU31.CAL:Function_call_interrupts
1.60 ±108% +4181.2% 68.50 ±123% interrupts.CPU31.RES:Rescheduling_interrupts
816.00 +29.5% 1056 ± 21% interrupts.CPU39.CAL:Function_call_interrupts
804.00 +16.6% 937.25 ± 15% interrupts.CPU42.CAL:Function_call_interrupts
803.00 +16.3% 934.25 ± 12% interrupts.CPU43.CAL:Function_call_interrupts
803.00 +231.5% 2662 ± 99% interrupts.CPU44.CAL:Function_call_interrupts
803.60 +25.1% 1005 ± 19% interrupts.CPU45.CAL:Function_call_interrupts
133.40 ± 11% -37.2% 83.75 ± 35% interrupts.CPU48.NMI:Non-maskable_interrupts
133.40 ± 11% -37.2% 83.75 ± 35% interrupts.CPU48.PMI:Performance_monitoring_interrupts
130.60 ± 10% -37.4% 81.75 ± 35% interrupts.CPU50.NMI:Non-maskable_interrupts
130.60 ± 10% -37.4% 81.75 ± 35% interrupts.CPU50.PMI:Performance_monitoring_interrupts
131.80 ± 10% -27.7% 95.25 ± 24% interrupts.CPU51.NMI:Non-maskable_interrupts
131.80 ± 10% -27.7% 95.25 ± 24% interrupts.CPU51.PMI:Performance_monitoring_interrupts
726.40 ± 20% +33.8% 971.75 ± 16% interrupts.CPU73.CAL:Function_call_interrupts
129.00 ± 11% -35.1% 83.75 ± 35% interrupts.CPU89.NMI:Non-maskable_interrupts
129.00 ± 11% -35.1% 83.75 ± 35% interrupts.CPU89.PMI:Performance_monitoring_interrupts
847.20 ± 10% +76.8% 1498 ± 46% interrupts.CPU9.CAL:Function_call_interrupts
129.80 ± 11% -25.3% 97.00 ± 23% interrupts.CPU90.NMI:Non-maskable_interrupts
129.80 ± 11% -25.3% 97.00 ± 23% interrupts.CPU90.PMI:Performance_monitoring_interrupts
128.40 ± 11% -35.4% 83.00 ± 35% interrupts.CPU91.NMI:Non-maskable_interrupts
128.40 ± 11% -35.4% 83.00 ± 35% interrupts.CPU91.PMI:Performance_monitoring_interrupts
128.80 ± 12% -25.3% 96.25 ± 23% interrupts.CPU92.NMI:Non-maskable_interrupts
128.80 ± 12% -25.3% 96.25 ± 23% interrupts.CPU92.PMI:Performance_monitoring_interrupts
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-5.9.0-rc5-00001-gb6ec413461034" of type "text/plain" (170290 bytes)
View attachment "job-script" of type "text/plain" (7737 bytes)
View attachment "job.yaml" of type "text/plain" (5335 bytes)
View attachment "reproduce" of type "text/plain" (338 bytes)
Powered by blists - more mailing lists