| 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: Tue, 25 May 2021 15:03:54 +0800
From: kernel test robot <oliver.sang@...el.com>
To: Yejune Deng <yejune.deng@...il.com>
Cc: 0day robot <lkp@...el.com>, Yejune Deng <yejunedeng@...il.com>,
LKML <linux-kernel@...r.kernel.org>, lkp@...ts.01.org,
ying.huang@...el.com, feng.tang@...el.com, zhengjun.xing@...el.com,
peterz@...radead.org, tglx@...utronix.de, mingo@...nel.org,
rafael.j.wysocki@...el.com, rostedt@...dmis.org, npiggin@...il.com,
mark.rutland@....com, elver@...gle.com
Subject: [irqflags] 21db66c4ff: will-it-scale.per_process_ops -4.5%
regression
Greeting,
FYI, we noticed a -4.5% regression of will-it-scale.per_process_ops due to commit:
commit: 21db66c4ff4e737875727ee7a1af94fd30c2a2f4 ("[PATCH] irqflags: Remove the CONFIG_TRACE_IRQFLAGS")
url: https://github.com/0day-ci/linux/commits/Yejune-Deng/irqflags-Remove-the-CONFIG_TRACE_IRQFLAGS/20210524-105251
base: https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git c4681547bcce777daf576925a966ffa824edd09d
in testcase: will-it-scale
on test machine: 192 threads 4 sockets Intel(R) Xeon(R) Platinum 9242 CPU @ 2.30GHz with 192G memory
with following parameters:
nr_task: 16
mode: process
test: dup1
cpufreq_governor: performance
ucode: 0x5003006
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 -1.2% regression |
| test machine | 104 threads 2 sockets Skylake with 192G memory |
| test parameters | cpufreq_governor=performance |
| | mode=process |
| | nr_task=50% |
| | test=futex3 |
| | ucode=0x2006a0a |
+------------------+---------------------------------------------------------------+
FYI, we have identical kconfig for both 21db66c4ff and parent (config file is attached)
and the CONFIG_TRACE_IRQFLAGS is disabled.
If you fix the issue, kindly add following tag
Reported-by: kernel test robot <oliver.sang@...el.com>
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 split-job --compatible job.yaml # generate the yaml file for lkp run
bin/lkp run generated-yaml-file
=========================================================================================
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/dup1/will-it-scale/0x5003006
commit:
v5.13-rc3
21db66c4ff ("irqflags: Remove the CONFIG_TRACE_IRQFLAGS")
v5.13-rc3 21db66c4ff4e737875727ee7a1a
---------------- ---------------------------
%stddev %change %stddev
\ | \
78047414 -4.5% 74526776 will-it-scale.16.processes
4877962 -4.5% 4657922 will-it-scale.per_process_ops
78047414 -4.5% 74526776 will-it-scale.workload
54046 ± 2% -7.2% 50161 ± 2% meminfo.Active
54046 ± 2% -7.2% 50161 ± 2% meminfo.Active(anon)
30554 ± 6% -14.2% 26213 ± 14% softirqs.CPU104.SCHED
28598 ± 4% -12.9% 24899 ± 10% softirqs.CPU109.SCHED
16002 ± 12% -21.4% 12576 ± 17% softirqs.CPU162.RCU
5.04e+10 ± 7% -46.6% 2.692e+10 ± 78% cpuidle.C1E.time
1.04e+08 ± 5% -29.7% 73111874 ± 29% cpuidle.C1E.usage
1.755e+09 ±208% +1300.9% 2.459e+10 ± 85% cpuidle.C6.time
3699595 ±209% +689.3% 29200515 ± 84% cpuidle.C6.usage
0.02 ± 20% +144.3% 0.05 ± 67% perf-sched.sch_delay.max.ms.do_task_dead.do_exit.do_group_exit.__x64_sys_exit_group.do_syscall_64
0.01 ± 19% +665.6% 0.08 ± 85% perf-sched.sch_delay.max.ms.do_wait.kernel_wait4.__do_sys_wait4.do_syscall_64
532.87 ± 10% +27.9% 681.63 ± 5% perf-sched.wait_and_delay.avg.ms.schedule_hrtimeout_range_clock.poll_schedule_timeout.constprop.0.do_sys_poll
61.17 ± 2% -18.0% 50.14 ± 4% perf-sched.wait_and_delay.count.schedule_hrtimeout_range_clock.poll_schedule_timeout.constprop.0.do_sys_poll
532.87 ± 10% +27.9% 681.63 ± 5% perf-sched.wait_time.avg.ms.schedule_hrtimeout_range_clock.poll_schedule_timeout.constprop.0.do_sys_poll
13487 ± 2% -7.2% 12517 ± 2% proc-vmstat.nr_active_anon
18501 -5.2% 17532 proc-vmstat.nr_shmem
13487 ± 2% -7.2% 12517 ± 2% proc-vmstat.nr_zone_active_anon
48140 ± 21% -28.9% 34224 ± 39% proc-vmstat.numa_pte_updates
17766 ± 2% -5.7% 16757 proc-vmstat.pgactivate
15.33 ± 6% +56.5% 24.00 ± 27% turbostat.Avg_MHz
57931556 ± 5% -31.7% 39572049 ± 32% turbostat.C1E
48.22 ± 6% -23.6 24.59 ± 86% turbostat.C1E%
2118971 ±212% +693.9% 16821659 ± 85% turbostat.C6
1.56 ±211% +23.0 24.54 ± 85% turbostat.C6%
0.06 ± 11% +27348.2% 16.01 ± 88% turbostat.CPU%c6
0.11 +941.1% 1.17 ± 77% perf-stat.i.MPKI
1.217e+10 -4.3% 1.164e+10 perf-stat.i.branch-instructions
11.21 ± 3% -4.8 6.41 ± 49% perf-stat.i.cache-miss-rate%
6914647 +914.4% 70145425 ± 77% perf-stat.i.cache-references
0.85 +8.8% 0.93 ± 3% perf-stat.i.cpi
5.347e+10 +4.6% 5.595e+10 ± 3% perf-stat.i.cpu-cycles
0.00 ± 83% +0.0 0.01 ± 85% perf-stat.i.dTLB-load-miss-rate%
2.002e+10 -3.1% 1.941e+10 perf-stat.i.dTLB-loads
0.00 ± 20% +0.0 0.00 ± 77% perf-stat.i.dTLB-store-miss-rate%
31277 ± 22% +800.4% 281623 ± 77% perf-stat.i.dTLB-store-misses
1.347e+10 -3.3% 1.302e+10 perf-stat.i.dTLB-stores
6.284e+10 -3.9% 6.041e+10 perf-stat.i.instructions
1.17 -8.0% 1.08 ± 3% perf-stat.i.ipc
0.28 +4.6% 0.29 ± 3% perf-stat.i.metric.GHz
51.86 +631.4% 379.32 ± 74% perf-stat.i.metric.K/sec
237.76 -3.5% 229.53 perf-stat.i.metric.M/sec
190143 ± 3% -9.6% 171895 ± 7% perf-stat.i.node-load-misses
94.23 ± 6% -16.6 77.65 ± 18% perf-stat.i.node-store-miss-rate%
0.11 +955.6% 1.16 ± 77% perf-stat.overall.MPKI
11.76 ± 3% -5.2 6.53 ± 50% perf-stat.overall.cache-miss-rate%
0.85 +8.8% 0.93 ± 3% perf-stat.overall.cpi
0.00 ± 86% +0.0 0.01 ± 85% perf-stat.overall.dTLB-load-miss-rate%
0.00 ± 21% +0.0 0.00 ± 77% perf-stat.overall.dTLB-store-miss-rate%
1.18 -8.0% 1.08 ± 3% perf-stat.overall.ipc
90.88 ± 5% -14.8 76.04 ± 16% perf-stat.overall.node-store-miss-rate%
1.213e+10 -4.3% 1.16e+10 perf-stat.ps.branch-instructions
6890069 +914.6% 69905237 ± 77% perf-stat.ps.cache-references
5.329e+10 +4.6% 5.576e+10 ± 3% perf-stat.ps.cpu-cycles
40856 ± 86% +5184.2% 2158934 ± 85% perf-stat.ps.dTLB-load-misses
1.995e+10 -3.1% 1.934e+10 perf-stat.ps.dTLB-loads
31163 ± 22% +800.6% 280650 ± 77% perf-stat.ps.dTLB-store-misses
1.342e+10 -3.3% 1.298e+10 perf-stat.ps.dTLB-stores
6.263e+10 -3.9% 6.021e+10 perf-stat.ps.instructions
189640 ± 3% -9.7% 171303 ± 7% perf-stat.ps.node-load-misses
1.891e+13 -3.9% 1.818e+13 perf-stat.total.instructions
0.69 ± 9% +0.2 0.86 ± 7% perf-profile.calltrace.cycles-pp.locks_remove_posix.filp_close.__x64_sys_close.do_syscall_64.entry_SYSCALL_64_after_hwframe
0.90 ± 8% +0.2 1.07 ± 5% perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_safe_stack.__close
0.09 ±223% +0.6 0.68 ± 10% perf-profile.calltrace.cycles-pp.dnotify_flush.filp_close.__x64_sys_close.do_syscall_64.entry_SYSCALL_64_after_hwframe
0.96 ± 18% +0.7 1.63 ± 7% perf-profile.calltrace.cycles-pp.hrtimer_interrupt.__sysvec_apic_timer_interrupt.sysvec_apic_timer_interrupt.asm_sysvec_apic_timer_interrupt.cpuidle_enter_state
0.21 ±141% +0.7 0.87 ± 16% perf-profile.calltrace.cycles-pp.menu_select.do_idle.cpu_startup_entry.start_secondary.secondary_startup_64_no_verify
0.30 ±100% +0.7 0.98 ± 16% perf-profile.calltrace.cycles-pp.__hrtimer_run_queues.hrtimer_interrupt.__sysvec_apic_timer_interrupt.sysvec_apic_timer_interrupt.asm_sysvec_apic_timer_interrupt
0.98 ± 18% +0.7 1.66 ± 7% perf-profile.calltrace.cycles-pp.__sysvec_apic_timer_interrupt.sysvec_apic_timer_interrupt.asm_sysvec_apic_timer_interrupt.cpuidle_enter_state.cpuidle_enter
1.48 ± 8% +0.8 2.31 ± 3% perf-profile.calltrace.cycles-pp.syscall_exit_to_user_mode.do_syscall_64.entry_SYSCALL_64_after_hwframe.dup
1.66 ± 13% +0.9 2.55 ± 7% perf-profile.calltrace.cycles-pp.sysvec_apic_timer_interrupt.asm_sysvec_apic_timer_interrupt.cpuidle_enter_state.cpuidle_enter.do_idle
1.87 ± 12% +1.0 2.85 ± 7% perf-profile.calltrace.cycles-pp.asm_sysvec_apic_timer_interrupt.cpuidle_enter_state.cpuidle_enter.do_idle.cpu_startup_entry
0.81 ± 8% +1.7 2.47 ± 5% perf-profile.calltrace.cycles-pp.exit_to_user_mode_prepare.syscall_exit_to_user_mode.do_syscall_64.entry_SYSCALL_64_after_hwframe.__close
1.50 ± 8% +2.6 4.14 ± 6% perf-profile.calltrace.cycles-pp.syscall_exit_to_user_mode.do_syscall_64.entry_SYSCALL_64_after_hwframe.__close
11.46 ± 8% +4.0 15.49 ± 5% perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.__close
13.30 ± 8% +4.2 17.50 ± 5% perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.__close
0.09 ± 10% +0.0 0.12 ± 10% perf-profile.children.cycles-pp.read_tsc
0.11 ± 6% +0.0 0.15 ± 9% perf-profile.children.cycles-pp.process_simple
0.04 ± 72% +0.0 0.09 ± 23% perf-profile.children.cycles-pp.update_rq_clock
0.02 ±141% +0.0 0.06 ± 7% perf-profile.children.cycles-pp.perf_session__deliver_event
0.10 ± 9% +0.0 0.15 ± 7% perf-profile.children.cycles-pp.native_sched_clock
0.06 ± 14% +0.1 0.11 ± 15% perf-profile.children.cycles-pp.load_balance
0.02 ±142% +0.1 0.07 ± 11% perf-profile.children.cycles-pp.update_sd_lb_stats
0.02 ±141% +0.1 0.07 ± 18% perf-profile.children.cycles-pp.hrtimer_next_event_without
0.00 +0.1 0.05 ± 9% perf-profile.children.cycles-pp.__ordered_events__flush
0.10 ± 16% +0.1 0.15 ± 15% perf-profile.children.cycles-pp.perf_mux_hrtimer_handler
0.13 ± 11% +0.1 0.19 ± 8% perf-profile.children.cycles-pp.rebalance_domains
0.11 ± 9% +0.1 0.17 ± 8% perf-profile.children.cycles-pp.sched_clock_cpu
0.00 +0.1 0.06 ± 16% perf-profile.children.cycles-pp.arch_scale_freq_tick
0.02 ±142% +0.1 0.08 ± 10% perf-profile.children.cycles-pp.find_busiest_group
0.01 ±223% +0.1 0.07 ± 17% perf-profile.children.cycles-pp.get_next_timer_interrupt
0.00 +0.1 0.08 ± 29% perf-profile.children.cycles-pp.rcu_idle_exit
0.03 ± 99% +0.1 0.11 ± 23% perf-profile.children.cycles-pp.rcu_sched_clock_irq
0.00 +0.1 0.08 ± 31% perf-profile.children.cycles-pp.__hrtimer_next_event_base
0.01 ±223% +0.1 0.09 ± 33% perf-profile.children.cycles-pp.hrtimer_update_next_event
0.39 ± 7% +0.1 0.48 ± 8% perf-profile.children.cycles-pp.rcu_nocb_flush_deferred_wakeup
0.22 ± 8% +0.1 0.33 ± 11% perf-profile.children.cycles-pp.__softirqentry_text_start
0.29 ± 9% +0.1 0.43 ± 10% perf-profile.children.cycles-pp.irq_exit_rcu
0.37 ± 15% +0.1 0.51 ± 7% perf-profile.children.cycles-pp.scheduler_tick
0.73 ± 9% +0.2 0.90 ± 8% perf-profile.children.cycles-pp.locks_remove_posix
0.45 ± 11% +0.2 0.68 ± 10% perf-profile.children.cycles-pp.dnotify_flush
0.53 ± 14% +0.3 0.79 ± 8% perf-profile.children.cycles-pp.update_process_times
0.58 ± 9% +0.3 0.85 ± 6% perf-profile.children.cycles-pp.syscall_exit_to_user_mode_prepare
0.54 ± 14% +0.3 0.84 ± 9% perf-profile.children.cycles-pp.tick_sched_handle
0.60 ± 13% +0.3 0.91 ± 7% perf-profile.children.cycles-pp.tick_sched_timer
0.45 ± 32% +0.4 0.88 ± 15% perf-profile.children.cycles-pp.menu_select
0.79 ± 12% +0.5 1.29 ± 11% perf-profile.children.cycles-pp.__hrtimer_run_queues
1.32 ± 13% +0.7 2.02 ± 3% perf-profile.children.cycles-pp.hrtimer_interrupt
1.34 ± 13% +0.7 2.06 ± 3% perf-profile.children.cycles-pp.__sysvec_apic_timer_interrupt
2.05 ± 11% +0.9 2.98 ± 5% perf-profile.children.cycles-pp.sysvec_apic_timer_interrupt
2.29 ± 11% +1.0 3.32 ± 5% perf-profile.children.cycles-pp.asm_sysvec_apic_timer_interrupt
1.86 ± 8% +1.6 3.46 ± 4% perf-profile.children.cycles-pp.exit_to_user_mode_prepare
3.41 ± 8% +3.5 6.91 ± 4% perf-profile.children.cycles-pp.syscall_exit_to_user_mode
27.46 ± 8% +6.1 33.56 ± 4% perf-profile.children.cycles-pp.do_syscall_64
31.32 ± 8% +6.4 37.72 ± 4% perf-profile.children.cycles-pp.entry_SYSCALL_64_after_hwframe
0.09 ± 10% +0.0 0.14 ± 8% perf-profile.self.cycles-pp.native_sched_clock
0.00 +0.1 0.06 ± 16% perf-profile.self.cycles-pp.arch_scale_freq_tick
0.02 ±142% +0.1 0.08 ± 57% perf-profile.self.cycles-pp.tick_nohz_next_event
0.00 +0.1 0.08 ± 28% perf-profile.self.cycles-pp.do_idle
0.01 ±223% +0.1 0.09 ± 25% perf-profile.self.cycles-pp.rcu_sched_clock_irq
0.23 ± 7% +0.1 0.37 ± 8% perf-profile.self.cycles-pp.rcu_nocb_flush_deferred_wakeup
0.26 ± 10% +0.1 0.41 ± 9% perf-profile.self.cycles-pp.cpuidle_enter_state
0.19 ± 30% +0.2 0.42 ± 10% perf-profile.self.cycles-pp.menu_select
0.44 ± 13% +0.2 0.67 ± 11% perf-profile.self.cycles-pp.dnotify_flush
0.52 ± 9% +0.3 0.81 ± 6% perf-profile.self.cycles-pp.syscall_exit_to_user_mode_prepare
1.44 ± 8% +1.4 2.87 ± 4% perf-profile.self.cycles-pp.exit_to_user_mode_prepare
1.16 ± 8% +1.6 2.81 ± 4% perf-profile.self.cycles-pp.syscall_exit_to_user_mode
7117 ± 24% -48.3% 3677 ± 59% interrupts.CPU1.NMI:Non-maskable_interrupts
7117 ± 24% -48.3% 3677 ± 59% interrupts.CPU1.PMI:Performance_monitoring_interrupts
6322 ± 27% -58.1% 2650 ± 23% interrupts.CPU101.NMI:Non-maskable_interrupts
6322 ± 27% -58.1% 2650 ± 23% interrupts.CPU101.PMI:Performance_monitoring_interrupts
6929 ± 18% -52.8% 3272 ± 41% interrupts.CPU104.NMI:Non-maskable_interrupts
6929 ± 18% -52.8% 3272 ± 41% interrupts.CPU104.PMI:Performance_monitoring_interrupts
68.00 ± 6% +90.3% 129.43 ± 33% interrupts.CPU120.NMI:Non-maskable_interrupts
68.00 ± 6% +90.3% 129.43 ± 33% interrupts.CPU120.PMI:Performance_monitoring_interrupts
62.67 ± 23% +92.6% 120.71 ± 31% interrupts.CPU137.NMI:Non-maskable_interrupts
62.67 ± 23% +92.6% 120.71 ± 31% interrupts.CPU137.PMI:Performance_monitoring_interrupts
66.33 ± 28% +86.7% 123.86 ± 33% interrupts.CPU138.NMI:Non-maskable_interrupts
66.33 ± 28% +86.7% 123.86 ± 33% interrupts.CPU138.PMI:Performance_monitoring_interrupts
61.17 ± 24% +93.4% 118.29 ± 44% interrupts.CPU139.NMI:Non-maskable_interrupts
61.17 ± 24% +93.4% 118.29 ± 44% interrupts.CPU139.PMI:Performance_monitoring_interrupts
66.33 ± 6% +91.9% 127.29 ± 73% interrupts.CPU142.NMI:Non-maskable_interrupts
66.33 ± 6% +91.9% 127.29 ± 73% interrupts.CPU142.PMI:Performance_monitoring_interrupts
76.50 ± 11% +51.8% 116.14 ± 29% interrupts.CPU147.NMI:Non-maskable_interrupts
76.50 ± 11% +51.8% 116.14 ± 29% interrupts.CPU147.PMI:Performance_monitoring_interrupts
68.83 ± 6% +75.0% 120.43 ± 32% interrupts.CPU148.NMI:Non-maskable_interrupts
68.83 ± 6% +75.0% 120.43 ± 32% interrupts.CPU148.PMI:Performance_monitoring_interrupts
61.33 ± 22% +85.2% 113.57 ± 31% interrupts.CPU149.NMI:Non-maskable_interrupts
61.33 ± 22% +85.2% 113.57 ± 31% interrupts.CPU149.PMI:Performance_monitoring_interrupts
61.33 ± 21% +84.2% 113.00 ± 32% interrupts.CPU162.NMI:Non-maskable_interrupts
61.33 ± 21% +84.2% 113.00 ± 32% interrupts.CPU162.PMI:Performance_monitoring_interrupts
63.17 ± 22% +54.7% 97.71 ± 35% interrupts.CPU172.NMI:Non-maskable_interrupts
63.17 ± 22% +54.7% 97.71 ± 35% interrupts.CPU172.PMI:Performance_monitoring_interrupts
63.00 ± 19% +82.8% 115.14 ± 39% interrupts.CPU174.NMI:Non-maskable_interrupts
63.00 ± 19% +82.8% 115.14 ± 39% interrupts.CPU174.PMI:Performance_monitoring_interrupts
56.33 ± 27% +113.8% 120.43 ± 32% interrupts.CPU178.NMI:Non-maskable_interrupts
56.33 ± 27% +113.8% 120.43 ± 32% interrupts.CPU178.PMI:Performance_monitoring_interrupts
62.50 ± 20% +98.4% 124.00 ± 35% interrupts.CPU180.NMI:Non-maskable_interrupts
62.50 ± 20% +98.4% 124.00 ± 35% interrupts.CPU180.PMI:Performance_monitoring_interrupts
63.17 ± 16% +86.8% 118.00 ± 31% interrupts.CPU182.NMI:Non-maskable_interrupts
63.17 ± 16% +86.8% 118.00 ± 31% interrupts.CPU182.PMI:Performance_monitoring_interrupts
62.67 ± 19% +93.1% 121.00 ± 33% interrupts.CPU183.NMI:Non-maskable_interrupts
62.67 ± 19% +93.1% 121.00 ± 33% interrupts.CPU183.PMI:Performance_monitoring_interrupts
62.50 ± 19% +86.3% 116.43 ± 30% interrupts.CPU184.NMI:Non-maskable_interrupts
62.50 ± 19% +86.3% 116.43 ± 30% interrupts.CPU184.PMI:Performance_monitoring_interrupts
57.67 ± 29% +106.1% 118.86 ± 31% interrupts.CPU185.NMI:Non-maskable_interrupts
57.67 ± 29% +106.1% 118.86 ± 31% interrupts.CPU185.PMI:Performance_monitoring_interrupts
65.67 ± 23% +89.1% 124.14 ± 33% interrupts.CPU29.NMI:Non-maskable_interrupts
65.67 ± 23% +89.1% 124.14 ± 33% interrupts.CPU29.PMI:Performance_monitoring_interrupts
60.83 ± 21% +89.3% 115.14 ± 40% interrupts.CPU30.NMI:Non-maskable_interrupts
60.83 ± 21% +89.3% 115.14 ± 40% interrupts.CPU30.PMI:Performance_monitoring_interrupts
60.50 ± 21% +88.7% 114.14 ± 40% interrupts.CPU31.NMI:Non-maskable_interrupts
60.50 ± 21% +88.7% 114.14 ± 40% interrupts.CPU31.PMI:Performance_monitoring_interrupts
55.33 ± 31% +120.0% 121.71 ± 32% interrupts.CPU33.NMI:Non-maskable_interrupts
55.33 ± 31% +120.0% 121.71 ± 32% interrupts.CPU33.PMI:Performance_monitoring_interrupts
54.50 ± 31% +120.7% 120.29 ± 33% interrupts.CPU34.NMI:Non-maskable_interrupts
54.50 ± 31% +120.7% 120.29 ± 33% interrupts.CPU34.PMI:Performance_monitoring_interrupts
54.67 ± 31% +130.5% 126.00 ± 35% interrupts.CPU35.NMI:Non-maskable_interrupts
54.67 ± 31% +130.5% 126.00 ± 35% interrupts.CPU35.PMI:Performance_monitoring_interrupts
54.83 ± 31% +139.4% 131.29 ± 38% interrupts.CPU36.NMI:Non-maskable_interrupts
54.83 ± 31% +139.4% 131.29 ± 38% interrupts.CPU36.PMI:Performance_monitoring_interrupts
54.83 ± 31% +122.5% 122.00 ± 33% interrupts.CPU37.NMI:Non-maskable_interrupts
54.83 ± 31% +122.5% 122.00 ± 33% interrupts.CPU37.PMI:Performance_monitoring_interrupts
55.83 ± 32% +115.9% 120.57 ± 33% interrupts.CPU38.NMI:Non-maskable_interrupts
55.83 ± 32% +115.9% 120.57 ± 33% interrupts.CPU38.PMI:Performance_monitoring_interrupts
57.67 ± 35% +112.6% 122.57 ± 32% interrupts.CPU39.NMI:Non-maskable_interrupts
57.67 ± 35% +112.6% 122.57 ± 32% interrupts.CPU39.PMI:Performance_monitoring_interrupts
68.67 ± 4% +61.4% 110.86 ± 35% interrupts.CPU41.NMI:Non-maskable_interrupts
68.67 ± 4% +61.4% 110.86 ± 35% interrupts.CPU41.PMI:Performance_monitoring_interrupts
70.17 ± 9% +77.5% 124.57 ± 33% interrupts.CPU42.NMI:Non-maskable_interrupts
70.17 ± 9% +77.5% 124.57 ± 33% interrupts.CPU42.PMI:Performance_monitoring_interrupts
66.17 ± 5% +87.2% 123.86 ± 34% interrupts.CPU43.NMI:Non-maskable_interrupts
66.17 ± 5% +87.2% 123.86 ± 34% interrupts.CPU43.PMI:Performance_monitoring_interrupts
52.67 ± 32% +132.7% 122.57 ± 33% interrupts.CPU44.NMI:Non-maskable_interrupts
52.67 ± 32% +132.7% 122.57 ± 33% interrupts.CPU44.PMI:Performance_monitoring_interrupts
67.33 ± 44% +80.1% 121.29 ± 32% interrupts.CPU45.NMI:Non-maskable_interrupts
67.33 ± 44% +80.1% 121.29 ± 32% interrupts.CPU45.PMI:Performance_monitoring_interrupts
56.00 ± 32% +263.3% 203.43 ±106% interrupts.CPU46.NMI:Non-maskable_interrupts
56.00 ± 32% +263.3% 203.43 ±106% interrupts.CPU46.PMI:Performance_monitoring_interrupts
57.00 ± 33% +113.3% 121.57 ± 33% interrupts.CPU47.NMI:Non-maskable_interrupts
57.00 ± 33% +113.3% 121.57 ± 33% interrupts.CPU47.PMI:Performance_monitoring_interrupts
57.83 ± 29% +139.1% 138.29 ± 29% interrupts.CPU50.NMI:Non-maskable_interrupts
57.83 ± 29% +139.1% 138.29 ± 29% interrupts.CPU50.PMI:Performance_monitoring_interrupts
55.17 ± 39% +131.0% 127.43 ± 27% interrupts.CPU51.NMI:Non-maskable_interrupts
55.17 ± 39% +131.0% 127.43 ± 27% interrupts.CPU51.PMI:Performance_monitoring_interrupts
50.83 ± 36% +150.7% 127.43 ± 27% interrupts.CPU52.NMI:Non-maskable_interrupts
50.83 ± 36% +150.7% 127.43 ± 27% interrupts.CPU52.PMI:Performance_monitoring_interrupts
56.33 ± 29% +141.2% 135.86 ± 37% interrupts.CPU54.NMI:Non-maskable_interrupts
56.33 ± 29% +141.2% 135.86 ± 37% interrupts.CPU54.PMI:Performance_monitoring_interrupts
55.17 ± 30% +124.3% 123.71 ± 30% interrupts.CPU55.NMI:Non-maskable_interrupts
55.17 ± 30% +124.3% 123.71 ± 30% interrupts.CPU55.PMI:Performance_monitoring_interrupts
43.83 ± 35% +366.1% 204.29 ± 86% interrupts.CPU56.NMI:Non-maskable_interrupts
43.83 ± 35% +366.1% 204.29 ± 86% interrupts.CPU56.PMI:Performance_monitoring_interrupts
51.67 ± 27% +121.5% 114.43 ± 35% interrupts.CPU59.NMI:Non-maskable_interrupts
51.67 ± 27% +121.5% 114.43 ± 35% interrupts.CPU59.PMI:Performance_monitoring_interrupts
49.33 ± 31% +131.9% 114.43 ± 34% interrupts.CPU60.NMI:Non-maskable_interrupts
49.33 ± 31% +131.9% 114.43 ± 34% interrupts.CPU60.PMI:Performance_monitoring_interrupts
49.83 ± 32% +135.1% 117.14 ± 40% interrupts.CPU61.NMI:Non-maskable_interrupts
49.83 ± 32% +135.1% 117.14 ± 40% interrupts.CPU61.PMI:Performance_monitoring_interrupts
54.50 ± 28% +125.7% 123.00 ± 31% interrupts.CPU62.NMI:Non-maskable_interrupts
54.50 ± 28% +125.7% 123.00 ± 31% interrupts.CPU62.PMI:Performance_monitoring_interrupts
55.50 ± 29% +121.9% 123.14 ± 30% interrupts.CPU63.NMI:Non-maskable_interrupts
55.50 ± 29% +121.9% 123.14 ± 30% interrupts.CPU63.PMI:Performance_monitoring_interrupts
54.67 ± 27% +246.8% 189.57 ± 81% interrupts.CPU64.NMI:Non-maskable_interrupts
54.67 ± 27% +246.8% 189.57 ± 81% interrupts.CPU64.PMI:Performance_monitoring_interrupts
71.33 ± 14% +116.3% 154.29 ± 55% interrupts.CPU67.NMI:Non-maskable_interrupts
71.33 ± 14% +116.3% 154.29 ± 55% interrupts.CPU67.PMI:Performance_monitoring_interrupts
75.83 ± 18% +66.3% 126.14 ± 28% interrupts.CPU68.NMI:Non-maskable_interrupts
75.83 ± 18% +66.3% 126.14 ± 28% interrupts.CPU68.PMI:Performance_monitoring_interrupts
57.83 ± 32% +118.4% 126.29 ± 28% interrupts.CPU70.NMI:Non-maskable_interrupts
57.83 ± 32% +118.4% 126.29 ± 28% interrupts.CPU70.PMI:Performance_monitoring_interrupts
62.67 ± 21% +75.5% 110.00 ± 35% interrupts.CPU77.NMI:Non-maskable_interrupts
62.67 ± 21% +75.5% 110.00 ± 35% interrupts.CPU77.PMI:Performance_monitoring_interrupts
61.67 ± 21% +79.5% 110.71 ± 35% interrupts.CPU78.NMI:Non-maskable_interrupts
61.67 ± 21% +79.5% 110.71 ± 35% interrupts.CPU78.PMI:Performance_monitoring_interrupts
61.83 ± 20% +79.3% 110.86 ± 33% interrupts.CPU79.NMI:Non-maskable_interrupts
61.83 ± 20% +79.3% 110.86 ± 33% interrupts.CPU79.PMI:Performance_monitoring_interrupts
67.67 ± 3% +120.6% 149.29 ± 46% interrupts.CPU80.NMI:Non-maskable_interrupts
67.67 ± 3% +120.6% 149.29 ± 46% interrupts.CPU80.PMI:Performance_monitoring_interrupts
67.50 ± 4% +79.3% 121.00 ± 31% interrupts.CPU81.NMI:Non-maskable_interrupts
67.50 ± 4% +79.3% 121.00 ± 31% interrupts.CPU81.PMI:Performance_monitoring_interrupts
62.00 ± 21% +73.3% 107.43 ± 34% interrupts.CPU92.NMI:Non-maskable_interrupts
62.00 ± 21% +73.3% 107.43 ± 34% interrupts.CPU92.PMI:Performance_monitoring_interrupts
61.83 ± 22% +73.0% 107.00 ± 34% interrupts.CPU93.NMI:Non-maskable_interrupts
61.83 ± 22% +73.0% 107.00 ± 34% interrupts.CPU93.PMI:Performance_monitoring_interrupts
62.00 ± 21% +132.5% 144.14 ± 76% interrupts.CPU94.NMI:Non-maskable_interrupts
62.00 ± 21% +132.5% 144.14 ± 76% interrupts.CPU94.PMI:Performance_monitoring_interrupts
6253 ± 12% -50.2% 3114 ± 40% interrupts.CPU98.NMI:Non-maskable_interrupts
6253 ± 12% -50.2% 3114 ± 40% interrupts.CPU98.PMI:Performance_monitoring_interrupts
227499 ± 8% -21.0% 179728 ± 9% interrupts.NMI:Non-maskable_interrupts
227499 ± 8% -21.0% 179728 ± 9% interrupts.PMI:Performance_monitoring_interrupts
1042 ± 27% -68.5% 328.00 ± 86% interrupts.TLB:TLB_shootdowns
will-it-scale.16.processes
7.85e+07 +----------------------------------------------------------------+
| .+..+.+.+.+.+.+ .+.+.+.+.. .+.+.+.+ |
7.8e+07 |.+ + .+.+ +.+ |
7.75e+07 |-+ + .+.+. .+. |
| + +.+ |
7.7e+07 |-+ |
7.65e+07 |-+ |
| |
7.6e+07 |-+ |
7.55e+07 |-+ |
| |
7.5e+07 |-+ O O O O O O |
7.45e+07 |-O O O O O O O O O O O O O O O O O O |
| O O O O |
7.4e+07 +----------------------------------------------------------------+
will-it-scale.per_process_ops
4.9e+06 +----------------------------------------------------------------+
|.+.+..+.+.+ + + +.+.+.+.+.+..+.+.+.+.+.+ |
4.85e+06 |-+ + .. |
| +.+.+.+.+.+ |
| |
4.8e+06 |-+ |
| |
4.75e+06 |-+ |
| |
4.7e+06 |-+ |
| O O O O O O |
| O O O O O O O O O O O O O O O O O O O O |
4.65e+06 |-+ O O |
| O |
4.6e+06 +----------------------------------------------------------------+
will-it-scale.workload
7.85e+07 +----------------------------------------------------------------+
| .+..+.+.+.+.+.+ .+.+.+.+.. .+.+.+.+ |
7.8e+07 |.+ + .+.+ +.+ |
7.75e+07 |-+ + .+.+. .+. |
| + +.+ |
7.7e+07 |-+ |
7.65e+07 |-+ |
| |
7.6e+07 |-+ |
7.55e+07 |-+ |
| |
7.5e+07 |-+ O O O O O O |
7.45e+07 |-O O O O O O O O O O O O O O O O O O |
| O O O O |
7.4e+07 +----------------------------------------------------------------+
[*] bisect-good sample
[O] bisect-bad sample
***************************************************************************************************
lkp-skl-fpga01: 104 threads 2 sockets Skylake 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/50%/debian-10.4-x86_64-20200603.cgz/lkp-skl-fpga01/futex3/will-it-scale/0x2006a0a
commit:
v5.13-rc3
21db66c4ff ("irqflags: Remove the CONFIG_TRACE_IRQFLAGS")
v5.13-rc3 21db66c4ff4e737875727ee7a1a
---------------- ---------------------------
%stddev %change %stddev
\ | \
1.051e+08 -1.2% 1.038e+08 will-it-scale.52.processes
2020588 -1.2% 1995983 will-it-scale.per_process_ops
1.051e+08 -1.2% 1.038e+08 will-it-scale.workload
80.35 ± 4% -48.3 32.04 ± 19% turbostat.PKG_%
0.00 +1.2 1.21 ± 11% perf-profile.calltrace.cycles-pp.exit_to_user_mode_prepare.syscall_exit_to_user_mode.do_syscall_64.entry_SYSCALL_64_after_hwframe.syscall
0.45 ± 12% +0.8 1.22 ± 11% perf-profile.children.cycles-pp.exit_to_user_mode_prepare
0.03 ±100% +0.1 0.09 ± 11% perf-profile.self.cycles-pp.rcu_nocb_flush_deferred_wakeup
0.35 ± 13% +0.7 1.08 ± 11% perf-profile.self.cycles-pp.exit_to_user_mode_prepare
7.508e+09 -1.2% 7.418e+09 perf-stat.i.branch-instructions
1.103e+08 -1.2% 1.089e+08 perf-stat.i.branch-misses
1.047e+08 -1.2% 1.035e+08 perf-stat.i.dTLB-load-misses
1.106e+08 -5.2% 1.048e+08 perf-stat.i.iTLB-load-misses
476.13 +4.4% 497.12 perf-stat.i.instructions-per-iTLB-miss
473.01 +4.6% 494.76 perf-stat.overall.instructions-per-iTLB-miss
7.484e+09 -1.2% 7.394e+09 perf-stat.ps.branch-instructions
1.1e+08 -1.3% 1.086e+08 perf-stat.ps.branch-misses
1.044e+08 -1.2% 1.032e+08 perf-stat.ps.dTLB-load-misses
1.102e+08 -5.2% 1.045e+08 perf-stat.ps.iTLB-load-misses
205.83 ± 27% -38.9% 125.71 ± 50% interrupts.CPU102.RES:Rescheduling_interrupts
579.17 ± 14% +40.0% 810.57 ± 41% interrupts.CPU18.CAL:Function_call_interrupts
250.17 ± 10% -50.4% 124.00 ± 50% interrupts.CPU21.RES:Rescheduling_interrupts
333.00 ± 33% -39.0% 203.29 ± 20% interrupts.CPU36.RES:Rescheduling_interrupts
240.33 ± 28% -46.1% 129.43 ± 65% interrupts.CPU44.RES:Rescheduling_interrupts
918.33 ± 18% -26.8% 672.29 ± 11% interrupts.CPU5.CAL:Function_call_interrupts
222.00 ± 26% -46.8% 118.14 ± 66% interrupts.CPU57.RES:Rescheduling_interrupts
6182 ± 22% -36.6% 3917 ± 43% interrupts.CPU59.NMI:Non-maskable_interrupts
6182 ± 22% -36.6% 3917 ± 43% interrupts.CPU59.PMI:Performance_monitoring_interrupts
168.50 ± 42% -58.3% 70.29 ± 50% interrupts.CPU63.RES:Rescheduling_interrupts
797.17 ± 11% -21.8% 623.57 ± 15% interrupts.CPU73.CAL:Function_call_interrupts
85.00 ± 47% +138.0% 202.29 ± 33% interrupts.CPU73.RES:Rescheduling_interrupts
30941 ± 40% -46.7% 16493 ± 20% softirqs.CPU102.RCU
38860 ± 41% -49.2% 19737 ± 20% softirqs.CPU21.RCU
12439 ± 40% +121.2% 27510 ± 30% softirqs.CPU21.SCHED
35338 ± 46% -44.5% 19600 ± 17% softirqs.CPU33.RCU
31104 ± 38% -40.5% 18512 ± 24% softirqs.CPU35.RCU
34441 ± 39% -41.7% 20065 ± 16% softirqs.CPU36.RCU
29595 ± 34% -40.3% 17662 ± 17% softirqs.CPU39.RCU
31616 ± 22% -53.0% 14858 ± 55% softirqs.CPU5.SCHED
28193 ± 24% -44.1% 15756 ± 50% softirqs.CPU50.SCHED
37243 ± 43% -50.0% 18618 ± 20% softirqs.CPU57.RCU
13945 ± 51% +104.9% 28576 ± 32% softirqs.CPU57.SCHED
28293 ± 34% -46.7% 15075 ± 6% softirqs.CPU63.RCU
33311 ± 16% -47.2% 17572 ± 47% softirqs.CPU73.SCHED
29970 ± 38% -43.6% 16895 ± 20% softirqs.CPU76.RCU
30102 ± 36% -40.2% 17988 ± 11% softirqs.CPU77.RCU
27180 ± 37% -36.0% 17407 ± 16% softirqs.CPU93.RCU
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/lkp@lists.01.org Intel Corporation
Thanks,
Oliver Sang
View attachment "config-5.13.0-rc3-00001-g21db66c4ff4e" of type "text/plain" (174118 bytes)
View attachment "job-script" of type "text/plain" (8074 bytes)
View attachment "job.yaml" of type "text/plain" (5368 bytes)
View attachment "reproduce" of type "text/plain" (336 bytes)
Powered by blists - more mailing lists