| 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: Mon, 29 Jul 2019 17:52:13 +0800
From: kernel test robot <rong.a.chen@...el.com>
To: Ido Schimmel <idosch@...sch.org>
Cc: netdev@...r.kernel.org, davem@...emloft.net, nhorman@...driver.com,
dsahern@...il.com, roopa@...ulusnetworks.com,
nikolay@...ulusnetworks.com, jakub.kicinski@...ronome.com,
toke@...hat.com, andy@...yhouse.net, f.fainelli@...il.com,
andrew@...n.ch, vivien.didelot@...il.com, mlxsw@...lanox.com,
Ido Schimmel <idosch@...lanox.com>, lkp@...org
Subject: [drop_monitor] 98ffbd6cd2: will-it-scale.per_thread_ops -17.5%
regression
Greeting,
FYI, we noticed a -17.5% regression of will-it-scale.per_thread_ops due to commit:
commit: 98ffbd6cd2b25fc6cbb0695e03b4fd43b5e116e6 ("[RFC PATCH net-next 10/12] drop_monitor: Add packet alert mode")
url: https://github.com/0day-ci/linux/commits/Ido-Schimmel/drop_monitor-Capture-dropped-packets-and-metadata/20190723-135834
in testcase: will-it-scale
on test machine: 288 threads Intel(R) Xeon Phi(TM) CPU 7295 @ 1.50GHz with 80G memory
with following parameters:
nr_task: 100%
mode: thread
test: lock1
cpufreq_governor: performance
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:
gcc-7/performance/x86_64-rhel-7.6/thread/100%/debian-x86_64-2019-05-14.cgz/lkp-knm01/lock1/will-it-scale
commit:
6bb91c4db1 ("drop_monitor: Require CAP_NET_ADMIN for drop monitor configuration")
98ffbd6cd2 ("drop_monitor: Add packet alert mode")
6bb91c4db105160c 98ffbd6cd2b25fc6cbb0695e03b
---------------- ---------------------------
fail:runs %reproduction fail:runs
| | |
1:4 -25% :4 dmesg.WARNING:at#for_ip_swapgs_restore_regs_and_return_to_usermode/0x
:4 25% 1:4 dmesg.WARNING:at_ip__fsnotify_parent/0x
%stddev %change %stddev
\ | \
5160 ± 2% -17.5% 4259 will-it-scale.per_thread_ops
672.94 ± 5% -14.1% 577.83 will-it-scale.time.user_time
1486179 ± 2% -17.4% 1226919 will-it-scale.workload
29442 -0.7% 29239 proc-vmstat.nr_slab_reclaimable
13523 ± 45% -32.3% 9153 ± 2% softirqs.CPU0.SCHED
2.46 -23.7% 1.87 ± 2% turbostat.RAMWatt
0.00 ± 6% -0.0 0.00 ± 13% mpstat.cpu.all.soft%
0.88 ± 5% -0.1 0.77 mpstat.cpu.all.usr%
1283 ± 2% +26.6% 1624 ± 4% sched_debug.cfs_rq:/.exec_clock.stddev
748596 ± 8% +24.5% 931656 ± 2% sched_debug.cfs_rq:/.min_vruntime.stddev
91.95 ± 9% +17.2% 107.75 ± 7% sched_debug.cfs_rq:/.nr_spread_over.max
7.14 ± 4% +16.3% 8.30 ± 6% sched_debug.cfs_rq:/.nr_spread_over.stddev
647587 ± 11% +16.5% 754309 ± 5% sched_debug.cfs_rq:/.spread0.stddev
6355144 ± 16% +50.5% 9563156 ± 8% sched_debug.cpu.avg_idle.max
1010 ± 3% +36.7% 1381 ± 4% sched_debug.cpu.clock.stddev
1010 ± 3% +36.7% 1381 ± 4% sched_debug.cpu.clock_task.stddev
1464112 ± 14% +31.1% 1918789 ± 5% sched_debug.cpu.max_idle_balance_cost.max
0.00 ± 3% +37.0% 0.00 ± 4% sched_debug.cpu.next_balance.stddev
34552 ± 13% +104.7% 70741 ± 60% sched_debug.cpu.sched_count.max
3147 ± 7% +57.7% 4963 ± 44% sched_debug.cpu.sched_count.stddev
1.00 -0.1 0.94 ± 2% perf-stat.i.branch-miss-rate%
88925913 -7.8% 82025606 perf-stat.i.branch-misses
2.001e+08 ± 2% -6.1% 1.879e+08 perf-stat.i.cache-references
0.21 -0.0 0.19 ± 2% perf-stat.i.iTLB-load-miss-rate%
77284434 -12.1% 67950981 perf-stat.i.iTLB-load-misses
473.52 +10.6% 523.50 ± 2% perf-stat.i.instructions-per-iTLB-miss
1.00 -0.1 0.95 ± 2% perf-stat.overall.branch-miss-rate%
0.21 -0.0 0.19 ± 2% perf-stat.overall.iTLB-load-miss-rate%
473.44 +10.5% 523.39 ± 2% perf-stat.overall.instructions-per-iTLB-miss
7458497 +17.8% 8789581 ± 3% perf-stat.overall.path-length
88598325 -7.8% 81725273 perf-stat.ps.branch-misses
1.994e+08 ± 2% -6.1% 1.872e+08 perf-stat.ps.cache-references
77002361 -12.1% 67703754 perf-stat.ps.iTLB-load-misses
1.10 -0.0 1.05 perf-profile.calltrace.cycles-pp.do_lock_file_wait.fcntl_setlk.do_fcntl.__x64_sys_fcntl.do_syscall_64
0.24 ± 4% -0.1 0.18 ± 2% perf-profile.children.cycles-pp.syscall_return_via_sysret
0.30 ± 4% -0.0 0.25 ± 5% perf-profile.children.cycles-pp.kmem_cache_free
0.24 ± 10% -0.0 0.20 ± 5% perf-profile.children.cycles-pp.perf_mux_hrtimer_handler
0.20 ± 4% -0.0 0.16 ± 2% perf-profile.children.cycles-pp.locks_release_private
1.10 ± 2% -0.0 1.06 perf-profile.children.cycles-pp.do_lock_file_wait
0.54 ± 2% -0.0 0.49 ± 3% perf-profile.children.cycles-pp.kmem_cache_alloc
0.19 ± 4% -0.0 0.16 ± 2% perf-profile.children.cycles-pp.entry_SYSCALL_64
0.09 ± 26% -0.0 0.06 perf-profile.children.cycles-pp.rb_next
0.64 ± 2% -0.0 0.61 ± 2% perf-profile.children.cycles-pp.locks_alloc_lock
0.15 ± 4% -0.0 0.13 ± 6% perf-profile.children.cycles-pp.memset_erms
0.16 ± 2% -0.0 0.15 ± 3% perf-profile.children.cycles-pp._copy_from_user
0.14 ± 6% -0.0 0.12 perf-profile.children.cycles-pp.security_file_lock
0.06 -0.0 0.05 perf-profile.children.cycles-pp.locks_delete_lock_ctx
0.08 +0.0 0.10 ± 9% perf-profile.children.cycles-pp.__might_sleep
0.03 ±100% +0.0 0.07 ± 7% perf-profile.children.cycles-pp.sched_clock_cpu
0.12 ± 24% +0.1 0.19 ± 2% perf-profile.children.cycles-pp.rcu_sched_clock_irq
0.04 ± 57% +0.1 0.11 ± 14% perf-profile.children.cycles-pp.account_process_tick
0.14 ± 27% +0.1 0.21 ± 20% perf-profile.children.cycles-pp.generic_perform_write
0.35 +0.1 0.45 ± 2% perf-profile.children.cycles-pp.file_has_perm
0.32 ± 2% +0.1 0.42 perf-profile.children.cycles-pp.security_file_fcntl
0.00 +0.1 0.10 ± 10% perf-profile.children.cycles-pp.fpregs_assert_state_consistent
0.12 ± 4% +0.1 0.23 perf-profile.children.cycles-pp.avc_has_perm
0.27 ± 12% +0.1 0.38 ± 6% perf-profile.children.cycles-pp.irq_enter
0.15 ± 13% +0.1 0.26 ± 9% perf-profile.children.cycles-pp.rcu_irq_enter
0.37 ± 2% -0.1 0.26 ± 2% perf-profile.self.cycles-pp.fcntl_setlk
0.17 ± 2% -0.1 0.10 ± 4% perf-profile.self.cycles-pp.do_syscall_64
0.24 ± 5% -0.1 0.18 ± 2% perf-profile.self.cycles-pp.syscall_return_via_sysret
0.28 ± 4% -0.0 0.23 ± 5% perf-profile.self.cycles-pp.kmem_cache_free
0.17 ± 4% -0.0 0.14 ± 3% perf-profile.self.cycles-pp.entry_SYSCALL_64
0.09 ± 23% -0.0 0.06 perf-profile.self.cycles-pp.rb_next
0.21 ± 3% -0.0 0.18 ± 2% perf-profile.self.cycles-pp.kmem_cache_alloc
0.10 ± 10% -0.0 0.08 ± 10% perf-profile.self.cycles-pp.perf_mux_hrtimer_handler
0.11 ± 7% -0.0 0.09 ± 5% perf-profile.self.cycles-pp.locks_release_private
0.13 ± 3% -0.0 0.11 ± 3% perf-profile.self.cycles-pp.memset_erms
0.11 -0.0 0.10 perf-profile.self.cycles-pp.___might_sleep
0.06 ± 6% +0.0 0.08 ± 6% perf-profile.self.cycles-pp.__x86_indirect_thunk_rax
0.07 +0.0 0.09 ± 10% perf-profile.self.cycles-pp.__might_sleep
0.15 ± 7% +0.0 0.17 ± 4% perf-profile.self.cycles-pp.do_fcntl
0.18 ± 10% +0.0 0.22 ± 5% perf-profile.self.cycles-pp._raw_spin_lock
0.17 ± 4% +0.1 0.22 ± 6% perf-profile.self.cycles-pp.posix_lock_inode
0.08 ± 34% +0.1 0.14 perf-profile.self.cycles-pp.rcu_sched_clock_irq
0.04 ± 57% +0.1 0.11 ± 14% perf-profile.self.cycles-pp.account_process_tick
0.12 ± 3% +0.1 0.21 ± 2% perf-profile.self.cycles-pp.avc_has_perm
0.00 +0.1 0.10 ± 8% perf-profile.self.cycles-pp.fpregs_assert_state_consistent
0.15 ± 13% +0.1 0.26 ± 9% perf-profile.self.cycles-pp.rcu_irq_enter
3856 +76.0% 6787 ± 23% interrupts.CPU104.NMI:Non-maskable_interrupts
3856 +76.0% 6787 ± 23% interrupts.CPU104.PMI:Performance_monitoring_interrupts
5779 ± 31% -32.1% 3924 interrupts.CPU117.NMI:Non-maskable_interrupts
5779 ± 31% -32.1% 3924 interrupts.CPU117.PMI:Performance_monitoring_interrupts
5750 ± 31% -32.0% 3912 interrupts.CPU119.NMI:Non-maskable_interrupts
5750 ± 31% -32.0% 3912 interrupts.CPU119.PMI:Performance_monitoring_interrupts
6704 ± 23% -42.1% 3880 interrupts.CPU120.NMI:Non-maskable_interrupts
6704 ± 23% -42.1% 3880 interrupts.CPU120.PMI:Performance_monitoring_interrupts
6708 ± 23% -41.9% 3899 interrupts.CPU121.NMI:Non-maskable_interrupts
6708 ± 23% -41.9% 3899 interrupts.CPU121.PMI:Performance_monitoring_interrupts
6705 ± 23% -41.3% 3933 interrupts.CPU122.NMI:Non-maskable_interrupts
6705 ± 23% -41.3% 3933 interrupts.CPU122.PMI:Performance_monitoring_interrupts
5735 ± 31% -32.0% 3899 interrupts.CPU123.NMI:Non-maskable_interrupts
5735 ± 31% -32.0% 3899 interrupts.CPU123.PMI:Performance_monitoring_interrupts
3980 +49.3% 5943 ± 32% interrupts.CPU13.NMI:Non-maskable_interrupts
3980 +49.3% 5943 ± 32% interrupts.CPU13.PMI:Performance_monitoring_interrupts
4838 ± 32% +20.2% 5818 ± 31% interrupts.CPU130.NMI:Non-maskable_interrupts
4838 ± 32% +20.2% 5818 ± 31% interrupts.CPU130.PMI:Performance_monitoring_interrupts
9080 ± 6% -6.6% 8485 ± 5% interrupts.CPU139.CAL:Function_call_interrupts
150.00 ±153% -95.5% 6.75 ± 48% interrupts.CPU141.RES:Rescheduling_interrupts
6758 ± 23% -27.5% 4899 ± 33% interrupts.CPU142.NMI:Non-maskable_interrupts
6758 ± 23% -27.5% 4899 ± 33% interrupts.CPU142.PMI:Performance_monitoring_interrupts
5777 ± 31% -32.2% 3916 interrupts.CPU147.NMI:Non-maskable_interrupts
5777 ± 31% -32.2% 3916 interrupts.CPU147.PMI:Performance_monitoring_interrupts
288.75 ±114% -86.3% 39.50 ± 88% interrupts.CPU151.RES:Rescheduling_interrupts
62.25 ± 85% +223.7% 201.50 ± 35% interrupts.CPU152.RES:Rescheduling_interrupts
6753 ± 23% -42.2% 3906 ± 2% interrupts.CPU156.NMI:Non-maskable_interrupts
6753 ± 23% -42.2% 3906 ± 2% interrupts.CPU156.PMI:Performance_monitoring_interrupts
6704 ± 23% -27.3% 4875 ± 33% interrupts.CPU161.NMI:Non-maskable_interrupts
6704 ± 23% -27.3% 4875 ± 33% interrupts.CPU161.PMI:Performance_monitoring_interrupts
5789 ± 31% -33.1% 3871 interrupts.CPU172.NMI:Non-maskable_interrupts
5789 ± 31% -33.1% 3871 interrupts.CPU172.PMI:Performance_monitoring_interrupts
6685 ± 23% -41.5% 3909 interrupts.CPU181.NMI:Non-maskable_interrupts
6685 ± 23% -41.5% 3909 interrupts.CPU181.PMI:Performance_monitoring_interrupts
3880 +50.5% 5840 ± 32% interrupts.CPU197.NMI:Non-maskable_interrupts
3880 +50.5% 5840 ± 32% interrupts.CPU197.PMI:Performance_monitoring_interrupts
5741 ± 30% -31.8% 3914 interrupts.CPU203.NMI:Non-maskable_interrupts
5741 ± 30% -31.8% 3914 interrupts.CPU203.PMI:Performance_monitoring_interrupts
6703 ± 23% -41.9% 3897 interrupts.CPU205.NMI:Non-maskable_interrupts
6703 ± 23% -41.9% 3897 interrupts.CPU205.PMI:Performance_monitoring_interrupts
9130 ± 6% -7.3% 8463 ± 6% interrupts.CPU211.CAL:Function_call_interrupts
9128 ± 5% -7.8% 8413 ± 6% interrupts.CPU22.CAL:Function_call_interrupts
6729 ± 23% -41.6% 3928 interrupts.CPU225.NMI:Non-maskable_interrupts
6729 ± 23% -41.6% 3928 interrupts.CPU225.PMI:Performance_monitoring_interrupts
54.00 ±147% +253.2% 190.75 ± 77% interrupts.CPU225.RES:Rescheduling_interrupts
5766 ± 31% -32.3% 3905 interrupts.CPU228.NMI:Non-maskable_interrupts
5766 ± 31% -32.3% 3905 interrupts.CPU228.PMI:Performance_monitoring_interrupts
148.00 ± 43% -48.6% 76.00 ± 90% interrupts.CPU232.RES:Rescheduling_interrupts
4751 ± 33% +42.8% 6786 ± 24% interrupts.CPU240.NMI:Non-maskable_interrupts
4751 ± 33% +42.8% 6786 ± 24% interrupts.CPU240.PMI:Performance_monitoring_interrupts
7614 ± 2% -36.2% 4860 ± 33% interrupts.CPU255.NMI:Non-maskable_interrupts
7614 ± 2% -36.2% 4860 ± 33% interrupts.CPU255.PMI:Performance_monitoring_interrupts
4782 ± 33% +21.7% 5820 ± 32% interrupts.CPU264.NMI:Non-maskable_interrupts
4782 ± 33% +21.7% 5820 ± 32% interrupts.CPU264.PMI:Performance_monitoring_interrupts
134.75 ±148% -94.2% 7.75 ± 32% interrupts.CPU268.RES:Rescheduling_interrupts
4870 ± 32% +41.7% 6900 ± 23% interrupts.CPU4.NMI:Non-maskable_interrupts
4870 ± 32% +41.7% 6900 ± 23% interrupts.CPU4.PMI:Performance_monitoring_interrupts
3906 +48.3% 5794 ± 31% interrupts.CPU40.NMI:Non-maskable_interrupts
3906 +48.3% 5794 ± 31% interrupts.CPU40.PMI:Performance_monitoring_interrupts
4816 ± 33% +41.1% 6794 ± 23% interrupts.CPU57.NMI:Non-maskable_interrupts
4816 ± 33% +41.1% 6794 ± 23% interrupts.CPU57.PMI:Performance_monitoring_interrupts
3820 ± 2% +53.3% 5857 ± 33% interrupts.CPU58.NMI:Non-maskable_interrupts
3820 ± 2% +53.3% 5857 ± 33% interrupts.CPU58.PMI:Performance_monitoring_interrupts
180.50 ±110% -85.6% 26.00 ± 73% interrupts.CPU68.RES:Rescheduling_interrupts
180.75 ±100% -90.3% 17.50 ±133% interrupts.CPU69.RES:Rescheduling_interrupts
42.50 ± 63% +330.0% 182.75 ± 18% interrupts.CPU80.RES:Rescheduling_interrupts
5781 ± 31% -32.0% 3932 interrupts.CPU92.NMI:Non-maskable_interrupts
5781 ± 31% -32.0% 3932 interrupts.CPU92.PMI:Performance_monitoring_interrupts
6676 ± 23% -41.2% 3924 interrupts.CPU93.NMI:Non-maskable_interrupts
6676 ± 23% -41.2% 3924 interrupts.CPU93.PMI:Performance_monitoring_interrupts
9099 ± 5% -12.0% 8006 ± 3% interrupts.CPU95.CAL:Function_call_interrupts
will-it-scale.per_thread_ops
5400 +-+------------------------------------------------------------------+
|.+.. .+.+..+. .+. .+. + + .+.. .+.+. .+. .+..+. .+. |
5200 +-+ + + +. +. + + + +. + +.+..+ + +.|
| + : + |
| : + |
5000 +-+ + |
| |
4800 +-+ |
| |
4600 +-+ |
| O |
O O O O O O O |
4400 +-+ O O O O O O O O O |
| O O O O O O O O |
4200 +-+----------------------------------------------------O----O--------+
will-it-scale.workload
1.55e+06 +-+--------------------------------------------------------------+
|.+. .+.+.+.+.+.+..+. + + .+.. .+.+. .+. .+.+. .+..+ |
1.5e+06 +-+ +. +.+ + + + +. +.+.+ : +.|
| : + |
1.45e+06 +-+ + |
| |
1.4e+06 +-+ |
| |
1.35e+06 +-+ |
| |
1.3e+06 +-+ O |
O O O O O O O O O O |
1.25e+06 +-O O O O O O O O O |
| O O O O O O O |
1.2e+06 +-+--------------------------------------------------------------+
[*] 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-5.3.0-rc1-00080-g98ffbd6cd2b25f" of type "text/plain" (199602 bytes)
View attachment "job-script" of type "text/plain" (7280 bytes)
View attachment "job.yaml" of type "text/plain" (4839 bytes)
View attachment "reproduce" of type "text/plain" (309 bytes)
Powered by blists - more mailing lists