| 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: <20200306023551.GE9382@xsang-OptiPlex-9020>
Date: Fri, 6 Mar 2020 10:35:51 +0800
From: kernel test robot <oliver.sang@...el.com>
To: Vincent Guittot <vincent.guittot@...aro.org>
Cc: Ingo Molnar <mingo@...nel.org>,
Mel Gorman <mgorman@...hsingularity.net>,
Peter Zijlstra <a.p.zijlstra@...llo.nl>,
Juri Lelli <juri.lelli@...hat.com>,
Valentin Schneider <valentin.schneider@....com>,
Phil Auld <pauld@...hat.com>, Hillf Danton <hdanton@...a.com>,
LKML <linux-kernel@...r.kernel.org>,
Andrew Morton <akpm@...ux-foundation.org>,
Stephen Rothwell <sfr@...b.auug.org.au>, lkp@...ts.01.org
Subject: [sched/numa] 6499b1b2dd:
phoronix-test-suite.aom-av1.0.frames_per_second -25.0% regression
Greeting,
FYI, we noticed a -25.0% regression of phoronix-test-suite.aom-av1.0.frames_per_second due to commit:
commit: 6499b1b2dd1b8d404a16b9fbbf1af6b9b3c1d83d ("sched/numa: Replace runnable_load_avg by load_avg")
https://git.kernel.org/cgit/linux/kernel/git/next/linux-next.git master
in testcase: phoronix-test-suite
on test machine: 16 threads Intel(R) Xeon(R) CPU X5570 @ 2.93GHz with 48G memory
with following parameters:
test: aom-av1-1.2.0
cpufreq_governor: performance
ucode: 0x1d
test-description: The Phoronix Test Suite is the most comprehensive testing and benchmarking platform available that provides an extensible framework for which new tests can be easily added.
test-url: http://www.phoronix-test-suite.com/
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 run job.yaml
=========================================================================================
compiler/cpufreq_governor/kconfig/rootfs/tbox_group/test/testcase/ucode:
gcc-7/performance/x86_64-rhel-7.6/debian-x86_64-phoronix/lkp-nhm-2ep1/aom-av1-1.2.0/phoronix-test-suite/0x1d
commit:
6d4d22468d ("sched/fair: Reorder enqueue/dequeue_task_fair path")
6499b1b2dd ("sched/numa: Replace runnable_load_avg by load_avg")
6d4d22468dae3d87 6499b1b2dd1b8d404a16b9fbbf1
---------------- ---------------------------
%stddev %change %stddev
\ | \
0.04 -25.0% 0.03 phoronix-test-suite.aom-av1.0.frames_per_second
1675 +24.1% 2078 phoronix-test-suite.time.elapsed_time
1675 +24.1% 2078 phoronix-test-suite.time.elapsed_time.max
1899 -19.5% 1529 meminfo.max_used_kB
1732547 ± 21% +64.4% 2848106 ± 15% numa-numastat.node0.local_node
1733945 ± 21% +64.3% 2849022 ± 15% numa-numastat.node0.numa_hit
68.25 -3.6% 65.80 vmstat.cpu.id
30.75 +7.3% 33.00 vmstat.cpu.us
34609 ± 4% -9.5% 31310 ± 7% vmstat.system.in
1202180 ± 9% +71.2% 2057794 ± 15% numa-vmstat.node0.numa_hit
1200245 ± 9% +68.1% 2018123 ± 15% numa-vmstat.node0.numa_local
1546244 ± 7% -39.9% 929553 ± 32% numa-vmstat.node1.numa_hit
1433950 ± 8% -40.4% 854993 ± 35% numa-vmstat.node1.numa_local
1.58 ± 17% -0.9 0.68 ± 89% perf-profile.calltrace.cycles-pp.__perf_event_read_value.perf_read.vfs_read.ksys_read.do_syscall_64
1.57 ± 18% -0.9 0.68 ± 89% perf-profile.calltrace.cycles-pp.smp_call_function_single.perf_event_read.__perf_event_read_value.perf_read.vfs_read
1.57 ± 18% -0.9 0.68 ± 89% perf-profile.calltrace.cycles-pp.perf_event_read.__perf_event_read_value.perf_read.vfs_read.ksys_read
1.58 ± 17% -0.9 0.68 ± 89% perf-profile.children.cycles-pp.__perf_event_read_value
0.00 +2.0 1.96 ±102% perf-profile.children.cycles-pp.task_numa_work
0.00 +2.0 1.96 ±102% perf-profile.children.cycles-pp.change_prot_numa
0.00 +2.0 1.96 ±102% perf-profile.children.cycles-pp.change_protection
0.06 ± 14% +2.0 2.01 ±100% perf-profile.children.cycles-pp.swapgs_restore_regs_and_return_to_usermode
0.00 +2.0 1.97 ±102% perf-profile.children.cycles-pp.task_work_run
0.00 +2.0 1.97 ±101% perf-profile.children.cycles-pp.exit_to_usermode_loop
0.01 ±173% +2.0 1.99 ±101% perf-profile.children.cycles-pp.prepare_exit_to_usermode
0.32 ± 65% -0.2 0.11 ± 70% perf-profile.self.cycles-pp.vprintk_emit
92.75 +15.4% 107.00 proc-vmstat.nr_dirtied
469.50 +4.8% 492.00 proc-vmstat.nr_mlock
486.50 +4.6% 509.00 proc-vmstat.nr_unevictable
91.50 +15.0% 105.20 proc-vmstat.nr_written
486.50 +4.6% 509.00 proc-vmstat.nr_zone_unevictable
3440653 +81.6% 6248111 ± 4% proc-vmstat.numa_hint_faults
2427026 +149.7% 6059831 ± 4% proc-vmstat.numa_hint_faults_local
3682431 +12.7% 4150258 proc-vmstat.numa_hit
81757 ± 4% +84.5% 150855 ± 4% proc-vmstat.numa_huge_pte_updates
3679066 +12.7% 4146838 proc-vmstat.numa_local
3675531 ± 6% -84.2% 581327 ± 9% proc-vmstat.numa_pages_migrated
45347697 ± 3% +84.0% 83458095 ± 4% proc-vmstat.numa_pte_updates
8070109 ± 2% -29.4% 5694110 proc-vmstat.pgalloc_normal
7772146 +48.8% 11566635 ± 2% proc-vmstat.pgfault
8024278 ± 2% -29.6% 5648333 proc-vmstat.pgfree
1152 ± 72% -91.1% 102.40 ±200% proc-vmstat.pgmigrate_fail
3675531 ± 6% -84.2% 581327 ± 9% proc-vmstat.pgmigrate_success
157656 ± 5% +65.2% 260451 ± 9% softirqs.CPU1.SCHED
584896 ± 7% +29.3% 756169 ± 8% softirqs.CPU1.TIMER
172301 ± 16% +43.2% 246663 ± 15% softirqs.CPU10.SCHED
594656 ± 4% +32.7% 789291 ± 18% softirqs.CPU10.TIMER
169533 ± 23% +46.4% 248267 ± 16% softirqs.CPU12.SCHED
596152 ± 4% +23.3% 735194 ± 9% softirqs.CPU12.TIMER
588117 ± 8% +42.1% 835794 ± 8% softirqs.CPU13.TIMER
169965 ± 19% +44.9% 246278 ± 16% softirqs.CPU14.SCHED
605742 ± 5% +22.2% 740007 ± 9% softirqs.CPU14.TIMER
603731 ± 6% +34.8% 814092 ± 11% softirqs.CPU15.TIMER
182358 ± 17% +51.6% 276393 ± 4% softirqs.CPU2.SCHED
579307 ± 5% +31.7% 762748 ± 15% softirqs.CPU2.TIMER
181275 ± 10% +36.9% 248078 ± 7% softirqs.CPU3.SCHED
619254 ± 3% +22.7% 759687 ± 8% softirqs.CPU3.TIMER
180867 ± 22% +50.4% 271944 ± 12% softirqs.CPU4.SCHED
590615 ± 3% +34.1% 792136 ± 17% softirqs.CPU4.TIMER
608993 ± 4% +27.8% 778515 ± 10% softirqs.CPU5.TIMER
182556 ± 13% +44.9% 264489 ± 13% softirqs.CPU6.SCHED
596735 ± 4% +23.3% 735485 ± 10% softirqs.CPU6.TIMER
606583 ± 6% +31.4% 797143 ± 10% softirqs.CPU7.TIMER
201534 ± 3% +28.0% 257923 ± 11% softirqs.CPU8.SCHED
584418 ± 3% +27.5% 745196 ± 4% softirqs.CPU8.TIMER
197227 ± 7% -26.7% 144661 ± 20% softirqs.CPU9.SCHED
588931 ± 9% +34.3% 791036 ± 10% softirqs.CPU9.TIMER
2851372 ± 2% +20.4% 3432068 ± 3% softirqs.SCHED
9678218 ± 5% +27.6% 12352476 ± 5% softirqs.TIMER
246566 ± 2% +32.5% 326807 sched_debug.cfs_rq:/.exec_clock.avg
428775 ± 15% +80.5% 773880 ± 13% sched_debug.cfs_rq:/.exec_clock.max
108138 ± 39% +142.9% 262648 ± 24% sched_debug.cfs_rq:/.exec_clock.stddev
1493630 ± 2% +35.8% 2028924 sched_debug.cfs_rq:/.min_vruntime.avg
2514708 ± 15% +77.4% 4460534 ± 13% sched_debug.cfs_rq:/.min_vruntime.max
-293894 -209.4% 321512 ± 57% sched_debug.cfs_rq:/.spread0.avg
727182 ± 62% +278.6% 2753121 ± 14% sched_debug.cfs_rq:/.spread0.max
850398 +24.1% 1055058 sched_debug.cpu.clock.avg
850398 +24.1% 1055059 sched_debug.cpu.clock.max
850397 +24.1% 1055057 sched_debug.cpu.clock.min
0.60 ± 4% -10.1% 0.54 ± 4% sched_debug.cpu.clock.stddev
850398 +24.1% 1055058 sched_debug.cpu.clock_task.avg
850398 +24.1% 1055059 sched_debug.cpu.clock_task.max
850397 +24.1% 1055057 sched_debug.cpu.clock_task.min
0.60 ± 4% -10.1% 0.54 ± 4% sched_debug.cpu.clock_task.stddev
6153 ± 6% +33.1% 8189 ± 4% sched_debug.cpu.curr->pid.avg
21612 +23.3% 26650 sched_debug.cpu.curr->pid.max
7770 ± 2% +26.1% 9802 ± 2% sched_debug.cpu.curr->pid.stddev
57320 ± 3% +25.7% 72031 sched_debug.cpu.nr_switches.avg
105747 ± 12% +34.3% 141996 ± 12% sched_debug.cpu.nr_switches.max
52509 ± 3% +27.8% 67105 sched_debug.cpu.sched_count.avg
101007 ± 12% +35.2% 136549 ± 13% sched_debug.cpu.sched_count.max
25737 ± 3% +25.3% 32244 sched_debug.cpu.sched_goidle.avg
50233 ± 12% +34.3% 67473 ± 14% sched_debug.cpu.sched_goidle.max
25004 ± 3% +26.1% 31538 sched_debug.cpu.ttwu_count.avg
51860 ± 15% +49.3% 77431 ± 11% sched_debug.cpu.ttwu_count.max
12318 ± 18% +68.9% 20803 ± 20% sched_debug.cpu.ttwu_count.stddev
11747 ± 7% +25.2% 14706 ± 2% sched_debug.cpu.ttwu_local.avg
6386 ± 30% +53.4% 9799 ± 19% sched_debug.cpu.ttwu_local.stddev
850397 +24.1% 1055058 sched_debug.cpu_clk
847811 +24.1% 1052456 sched_debug.ktime
852168 +24.0% 1056669 sched_debug.sched_clk
4.80 +20.9% 5.81 perf-stat.i.MPKI
1.598e+09 -18.4% 1.304e+09 ± 2% perf-stat.i.branch-instructions
1.67 ± 2% +0.1 1.76 perf-stat.i.branch-miss-rate%
26980113 -13.0% 23471525 perf-stat.i.branch-misses
3.29 ± 4% -0.2 3.07 perf-stat.i.cache-miss-rate%
0.68 ± 6% +16.1% 0.79 ± 5% perf-stat.i.cpi
15.25 ± 8% +169.2% 41.05 ± 4% perf-stat.i.cpu-migrations
0.05 ± 4% +0.0 0.07 ± 6% perf-stat.i.dTLB-load-miss-rate%
3218026 +23.2% 3963718 ± 4% perf-stat.i.dTLB-load-misses
7.128e+09 -18.9% 5.78e+09 perf-stat.i.dTLB-loads
0.19 ± 4% +0.0 0.24 ± 7% perf-stat.i.dTLB-store-miss-rate%
1.911e+09 -18.8% 1.551e+09 perf-stat.i.dTLB-stores
0.01 ± 8% +0.0 0.02 ± 5% perf-stat.i.iTLB-load-miss-rate%
2822223 +27.4% 3596911 perf-stat.i.iTLB-load-misses
2.788e+10 -19.2% 2.253e+10 perf-stat.i.iTLB-loads
2.789e+10 -19.2% 2.253e+10 perf-stat.i.instructions
10835 -27.5% 7859 ± 3% perf-stat.i.instructions-per-iTLB-miss
1.61 ± 4% -16.6% 1.34 ± 5% perf-stat.i.ipc
0.08 ± 2% -17.8% 0.07 perf-stat.i.major-faults
4574 +20.2% 5497 ± 2% perf-stat.i.minor-faults
4574 +20.2% 5497 ± 2% perf-stat.i.page-faults
4.94 +22.3% 6.04 perf-stat.overall.MPKI
1.69 +0.1 1.80 perf-stat.overall.branch-miss-rate%
0.60 ± 2% +27.7% 0.76 ± 3% perf-stat.overall.cpi
0.05 +0.0 0.07 ± 4% perf-stat.overall.dTLB-load-miss-rate%
0.18 ± 3% +0.1 0.23 ± 8% perf-stat.overall.dTLB-store-miss-rate%
0.01 +0.0 0.02 perf-stat.overall.iTLB-load-miss-rate%
9882 -36.6% 6264 ± 2% perf-stat.overall.instructions-per-iTLB-miss
1.67 ± 2% -21.6% 1.31 ± 3% perf-stat.overall.ipc
1.596e+09 -18.4% 1.303e+09 ± 2% perf-stat.ps.branch-instructions
26960817 -13.0% 23460741 perf-stat.ps.branch-misses
15.26 ± 8% +168.9% 41.03 ± 4% perf-stat.ps.cpu-migrations
3215460 +23.2% 3961346 ± 4% perf-stat.ps.dTLB-load-misses
7.121e+09 -18.9% 5.776e+09 perf-stat.ps.dTLB-loads
1.909e+09 -18.8% 1.55e+09 perf-stat.ps.dTLB-stores
2819619 +27.5% 3594526 perf-stat.ps.iTLB-load-misses
2.785e+10 -19.2% 2.252e+10 perf-stat.ps.iTLB-loads
2.786e+10 -19.2% 2.251e+10 perf-stat.ps.instructions
0.08 ± 2% -17.6% 0.07 perf-stat.ps.major-faults
4571 +20.2% 5495 ± 2% perf-stat.ps.minor-faults
4572 +20.2% 5495 ± 2% perf-stat.ps.page-faults
1345 ± 6% +115.7% 2903 ± 72% interrupts.35:PCI-MSI.524289-edge.eth0-rx-0
914.25 ± 7% +22.0% 1115 ± 5% interrupts.37:PCI-MSI.524291-edge.eth0-rx-2
905.50 ± 5% +35.7% 1228 ± 19% interrupts.40:PCI-MSI.524294-edge.eth0-tx-1
947.25 ± 4% +31.2% 1242 ± 14% interrupts.42:PCI-MSI.524296-edge.eth0-tx-3
1869601 -29.8% 1311926 ± 2% interrupts.CAL:Function_call_interrupts
135372 ± 9% -60.1% 54051 ± 9% interrupts.CPU0.CAL:Function_call_interrupts
153983 ± 13% -67.0% 50825 ± 6% interrupts.CPU0.TLB:TLB_shootdowns
645590 ± 2% -60.4% 255502 ± 50% interrupts.CPU0.TRM:Thermal_event_interrupts
905.50 ± 5% +35.7% 1228 ± 19% interrupts.CPU1.40:PCI-MSI.524294-edge.eth0-tx-1
129830 ± 12% -59.6% 52505 ± 3% interrupts.CPU1.CAL:Function_call_interrupts
3093858 ± 5% +18.7% 3672916 ± 10% interrupts.CPU1.LOC:Local_timer_interrupts
149503 ± 14% -69.1% 46182 ± 13% interrupts.CPU1.TLB:TLB_shootdowns
3110762 ± 4% +18.4% 3682900 ± 11% interrupts.CPU10.LOC:Local_timer_interrupts
6054 ± 26% -37.1% 3807 ± 38% interrupts.CPU10.NMI:Non-maskable_interrupts
6054 ± 26% -37.1% 3807 ± 38% interrupts.CPU10.PMI:Performance_monitoring_interrupts
645651 ± 2% -60.3% 256141 ± 50% interrupts.CPU10.TRM:Thermal_event_interrupts
3052052 ± 6% +29.3% 3947110 ± 5% interrupts.CPU11.LOC:Local_timer_interrupts
1345 ± 6% +115.7% 2903 ± 72% interrupts.CPU12.35:PCI-MSI.524289-edge.eth0-rx-0
3146914 ± 4% +17.3% 3692838 ± 10% interrupts.CPU12.LOC:Local_timer_interrupts
645648 ± 2% -60.3% 256141 ± 50% interrupts.CPU12.TRM:Thermal_event_interrupts
3060961 ± 6% +29.7% 3970956 ± 4% interrupts.CPU13.LOC:Local_timer_interrupts
914.25 ± 7% +22.0% 1115 ± 5% interrupts.CPU14.37:PCI-MSI.524291-edge.eth0-rx-2
3139919 ± 4% +17.6% 3693724 ± 11% interrupts.CPU14.LOC:Local_timer_interrupts
645575 ± 2% -60.3% 256140 ± 50% interrupts.CPU14.TRM:Thermal_event_interrupts
3072696 ± 6% +29.3% 3972657 ± 4% interrupts.CPU15.LOC:Local_timer_interrupts
108866 ± 38% -58.3% 45415 ± 13% interrupts.CPU2.CAL:Function_call_interrupts
118679 ± 42% -70.1% 35431 ± 21% interrupts.CPU2.TLB:TLB_shootdowns
645637 ± 2% -60.3% 256140 ± 50% interrupts.CPU2.TRM:Thermal_event_interrupts
947.25 ± 4% +31.2% 1242 ± 14% interrupts.CPU3.42:PCI-MSI.524296-edge.eth0-tx-3
3080936 ± 5% +20.6% 3714693 ± 10% interrupts.CPU3.LOC:Local_timer_interrupts
102464 ± 42% -51.4% 49751 ± 20% interrupts.CPU4.CAL:Function_call_interrupts
112287 ± 50% -62.2% 42401 ± 30% interrupts.CPU4.TLB:TLB_shootdowns
645566 ± 2% -60.3% 256140 ± 50% interrupts.CPU4.TRM:Thermal_event_interrupts
3063987 ± 5% +24.0% 3798351 ± 8% interrupts.CPU5.LOC:Local_timer_interrupts
101204 ± 31% -44.7% 55997 ± 25% interrupts.CPU6.CAL:Function_call_interrupts
3107707 ± 5% +18.0% 3667587 ± 11% interrupts.CPU6.LOC:Local_timer_interrupts
5979 ± 28% -47.1% 3166 ± 46% interrupts.CPU6.NMI:Non-maskable_interrupts
5979 ± 28% -47.1% 3166 ± 46% interrupts.CPU6.PMI:Performance_monitoring_interrupts
108315 ± 37% -55.3% 48376 ± 34% interrupts.CPU6.TLB:TLB_shootdowns
645653 ± 2% -60.3% 256140 ± 50% interrupts.CPU6.TRM:Thermal_event_interrupts
3066901 ± 5% +25.7% 3855810 ± 7% interrupts.CPU7.LOC:Local_timer_interrupts
95805 ± 15% -43.0% 54561 ± 32% interrupts.CPU8.CAL:Function_call_interrupts
3256186 ± 2% +23.8% 4030403 ± 3% interrupts.CPU8.LOC:Local_timer_interrupts
99864 ± 17% -52.3% 47620 ± 40% interrupts.CPU8.TLB:TLB_shootdowns
645610 ± 2% -60.3% 256096 ± 50% interrupts.CPU8.TRM:Thermal_event_interrupts
3023551 ± 7% +29.2% 3907922 ± 5% interrupts.CPU9.LOC:Local_timer_interrupts
49394077 ± 5% +22.3% 60395741 ± 8% interrupts.LOC:Local_timer_interrupts
2010439 ± 2% -37.2% 1263117 ± 3% interrupts.TLB:TLB_shootdowns
5164932 ± 2% -60.3% 2048443 ± 50% interrupts.TRM:Thermal_event_interrupts
phoronix-test-suite.aom-av1.0.frames_per_second
0.04 +-------------------------------------------------------------------+
| |
| |
0.038 |-+ |
| |
| |
0.036 |-+ |
| |
0.034 |-+ |
| |
| |
0.032 |-+ |
| |
| |
0.03 +-------------------------------------------------------------------+
[*] 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,
Oliver Sang
View attachment "config-5.6.0-rc3-00018-g6499b1b2dd1b8d" of type "text/plain" (203539 bytes)
View attachment "job-script" of type "text/plain" (7224 bytes)
View attachment "job.yaml" of type "text/plain" (4859 bytes)
View attachment "reproduce" of type "text/plain" (254 bytes)
Powered by blists - more mailing lists