| 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: <20191127005459.GE20422@shao2-debian>
Date: Wed, 27 Nov 2019 08:54:59 +0800
From: kernel test robot <rong.a.chen@...el.com>
To: Joseph Lo <josephl@...dia.com>
Cc: Daniel Lezcano <daniel.lezcano@...aro.org>,
Thomas Gleixner <tglx@...utronix.de>,
Thierry Reding <treding@...dia.com>,
Jon Hunter <jonathanh@...dia.com>,
LKML <linux-kernel@...r.kernel.org>,
Linus Torvalds <torvalds@...ux-foundation.org>,
lkp@...ts.01.org
Subject: [clocksource/drivers/tegra] b4822dc756: stress-ng.sockfd.ops_per_sec
-14.2% regression
Greeting,
FYI, we noticed a -14.2% regression of stress-ng.sockfd.ops_per_sec due to commit:
commit: b4822dc7564f007e7a9b5188b791b7a923e34104 ("clocksource/drivers/tegra: Add Tegra210 timer support")
https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git master
in testcase: stress-ng
on test machine: 96 threads Intel(R) Xeon(R) Gold 6252 CPU @ 2.10GHz with 192G memory
with following parameters:
nr_threads: 100%
disk: 1HDD
testtime: 30s
class: network
cpufreq_governor: performance
ucode: 0x500002c
If you fix the issue, kindly add following tag
Reported-by: kernel test robot <rong.a.chen@...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
=========================================================================================
class/compiler/cpufreq_governor/disk/kconfig/nr_threads/rootfs/tbox_group/testcase/testtime/ucode:
network/gcc-7/performance/1HDD/x86_64-rhel-7.6/100%/debian-x86_64-2019-11-14.cgz/lkp-csl-2sp5/stress-ng/30s/0x500002c
commit:
87e0a45596 ("dt-bindings: timer: add Tegra210 timer")
b4822dc756 ("clocksource/drivers/tegra: Add Tegra210 timer support")
87e0a455960a383a b4822dc7564f007e7a9b5188b79
---------------- ---------------------------
fail:runs %reproduction fail:runs
| | |
:4 25% 1:4 kmsg.Negotiation_of_local_Allow_Short_Seqnos_failed_in_state_CHANGING_at_net/dccp/feat.c:#/dccp_feat_activate_values()
:4 25% 1:4 dmesg.WARNING:at#for_ip_swapgs_restore_regs_and_return_to_usermode/0x
:4 25% 1:4 dmesg.WARNING:stack_recursion
%stddev %change %stddev
\ | \
751303 -14.2% 644647 stress-ng.sockfd.ops
25042 -14.2% 21487 stress-ng.sockfd.ops_per_sec
1.617e+08 -5.2% 1.533e+08 ± 2% stress-ng.time.involuntary_context_switches
1283886 -4.4% 1227018 ± 2% vmstat.system.cs
39600 ± 11% +68.3% 66664 ± 28% numa-vmstat.node0.nr_anon_pages
56.75 ± 18% +94.3% 110.25 ± 37% numa-vmstat.node0.nr_anon_transparent_hugepages
0.23 ± 2% -0.0 0.21 ± 2% perf-profile.children.cycles-pp.selinux_file_ioctl
0.23 ± 2% -0.0 0.22 perf-profile.children.cycles-pp.security_file_ioctl
1288777 -4.4% 1231929 ± 2% perf-stat.i.context-switches
1284857 -4.4% 1228527 ± 2% perf-stat.ps.context-switches
376581 ± 5% +45.0% 545935 ± 25% meminfo.Active
375201 ± 5% +45.1% 544551 ± 25% meminfo.Active(anon)
226368 ± 7% +71.0% 387062 ± 36% meminfo.AnonHugePages
116742 ± 17% +94.1% 226573 ± 36% numa-meminfo.node0.AnonHugePages
158230 ± 11% +68.5% 266666 ± 28% numa-meminfo.node0.AnonPages
1370369 ± 6% +22.8% 1682189 ± 5% numa-meminfo.node0.MemUsed
93828 ± 5% +44.9% 136003 ± 25% proc-vmstat.nr_active_anon
110.25 ± 7% +71.2% 188.75 ± 36% proc-vmstat.nr_anon_transparent_hugepages
93828 ± 5% +44.9% 136003 ± 25% proc-vmstat.nr_zone_active_anon
288.50 ± 33% +341.8% 1274 ± 69% proc-vmstat.thp_fault_alloc
702.50 ± 4% -15.9% 590.75 ± 3% slabinfo.file_lock_cache.active_objs
702.50 ± 4% -15.9% 590.75 ± 3% slabinfo.file_lock_cache.num_objs
4859 ± 10% -22.5% 3767 ± 10% slabinfo.kmalloc-rcl-64.active_objs
4859 ± 10% -22.5% 3767 ± 10% slabinfo.kmalloc-rcl-64.num_objs
351.50 ± 5% +26.9% 446.00 ± 9% slabinfo.kmem_cache.active_objs
351.50 ± 5% +26.9% 446.00 ± 9% slabinfo.kmem_cache.num_objs
682.00 ± 4% +21.1% 825.75 ± 7% slabinfo.kmem_cache_node.active_objs
728.00 ± 3% +19.7% 871.75 ± 7% slabinfo.kmem_cache_node.num_objs
35442 ± 46% -59.5% 14360 ± 32% interrupts.CPU11.RES:Rescheduling_interrupts
63378 ± 44% -57.3% 27081 ± 37% interrupts.CPU26.RES:Rescheduling_interrupts
70941 ± 52% -55.2% 31809 ± 60% interrupts.CPU33.RES:Rescheduling_interrupts
77310 ± 36% -53.1% 36270 ± 61% interrupts.CPU34.RES:Rescheduling_interrupts
59102 ± 23% -60.4% 23424 ± 40% interrupts.CPU54.RES:Rescheduling_interrupts
76941 ± 28% -74.0% 19990 ± 31% interrupts.CPU56.RES:Rescheduling_interrupts
87428 ± 42% -61.3% 33857 ± 68% interrupts.CPU6.RES:Rescheduling_interrupts
53133 ± 36% -53.3% 24808 ± 31% interrupts.CPU61.RES:Rescheduling_interrupts
20767 ± 17% +144.6% 50795 ± 16% interrupts.CPU63.RES:Rescheduling_interrupts
16906 ± 31% +208.0% 52070 ± 44% interrupts.CPU68.RES:Rescheduling_interrupts
92040 ± 32% -67.8% 29683 ± 34% interrupts.CPU77.RES:Rescheduling_interrupts
84549 ± 98% -75.4% 20818 ± 67% interrupts.CPU78.RES:Rescheduling_interrupts
4939 ± 34% +60.7% 7939 interrupts.CPU82.NMI:Non-maskable_interrupts
4939 ± 34% +60.7% 7939 interrupts.CPU82.PMI:Performance_monitoring_interrupts
51353 ± 73% -60.6% 20254 ± 60% interrupts.CPU88.RES:Rescheduling_interrupts
4661542 ± 9% -22.0% 3635159 ± 12% interrupts.RES:Rescheduling_interrupts
149972 ± 3% +29.7% 194472 ± 18% softirqs.CPU14.RCU
18486 ± 4% +8.6% 20078 ± 9% softirqs.CPU17.SCHED
4450692 ± 4% -8.3% 4081585 ± 4% softirqs.CPU27.NET_RX
149037 ± 6% +40.8% 209788 ± 5% softirqs.CPU27.RCU
4598629 ± 6% -17.5% 3794414 ± 8% softirqs.CPU31.NET_RX
180791 ± 22% -18.4% 147584 ± 3% softirqs.CPU32.RCU
193339 ± 15% -15.3% 163696 ± 19% softirqs.CPU33.RCU
3691957 ± 4% -15.8% 3109708 ± 10% softirqs.CPU48.NET_RX
17979 +23.6% 22221 ± 21% softirqs.CPU48.SCHED
165183 ± 13% +31.0% 216456 ± 13% softirqs.CPU49.RCU
18655 +7.5% 20058 ± 6% softirqs.CPU5.SCHED
18636 ± 6% +9.7% 20448 ± 8% softirqs.CPU51.SCHED
18063 +20.3% 21731 ± 16% softirqs.CPU57.SCHED
180802 ± 18% -12.4% 158328 ± 15% softirqs.CPU58.RCU
189662 ± 22% -24.2% 143744 ± 4% softirqs.CPU75.RCU
23583 ± 9% -18.6% 19208 softirqs.CPU77.SCHED
153164 ± 6% -8.3% 140393 ± 3% softirqs.CPU92.RCU
113634 ± 39% -69.1% 35137 ± 45% sched_debug.cfs_rq:/.MIN_vruntime.avg
756027 ± 17% -54.7% 342481 ± 45% sched_debug.cfs_rq:/.MIN_vruntime.stddev
15952 ± 14% -23.8% 12157 sched_debug.cfs_rq:/.load.avg
41020 ± 24% -50.2% 20427 sched_debug.cfs_rq:/.load.stddev
225.50 ± 2% -12.0% 198.54 ± 2% sched_debug.cfs_rq:/.load_avg.max
113634 ± 39% -69.1% 35137 ± 45% sched_debug.cfs_rq:/.max_vruntime.avg
756027 ± 17% -54.7% 342481 ± 45% sched_debug.cfs_rq:/.max_vruntime.stddev
0.11 ± 8% -31.8% 0.08 ± 16% sched_debug.cfs_rq:/.nr_running.stddev
56.83 ± 8% -46.5% 30.42 ± 18% sched_debug.cfs_rq:/.runnable_load_avg.max
7.31 ± 12% -40.4% 4.35 ± 10% sched_debug.cfs_rq:/.runnable_load_avg.stddev
14721 ± 15% -26.0% 10900 sched_debug.cfs_rq:/.runnable_weight.avg
41574 ± 24% -49.7% 20899 sched_debug.cfs_rq:/.runnable_weight.stddev
337450 ± 29% -42.4% 194494 ± 34% sched_debug.cfs_rq:/.spread0.avg
-171171 +108.7% -357315 sched_debug.cfs_rq:/.spread0.min
1566 ± 4% -16.1% 1314 ± 7% sched_debug.cfs_rq:/.util_avg.max
1287 ± 8% -16.8% 1071 ± 11% sched_debug.cfs_rq:/.util_est_enqueued.max
4100 ± 42% +197.5% 12196 ± 42% sched_debug.cpu.avg_idle.min
0.00 ± 37% -31.1% 0.00 ± 10% sched_debug.cpu.next_balance.stddev
793.53 ± 8% +44.6% 1147 ± 7% sched_debug.cpu.nr_load_updates.stddev
4.29 ± 11% -30.1% 3.00 ± 15% sched_debug.cpu.nr_running.max
0.60 ± 7% -21.7% 0.47 ± 9% sched_debug.cpu.nr_running.stddev
stress-ng.sockfd.ops
800000 +-+----------------------------------------------------------------+
| .+ +.+. |
750000 +-+.+.+.+.++.+ +.+.+.+.+.++.+.+.+.+.+.+.+.+.+.+.++.+.+.+.+.|
| |
700000 +-+ |
| O O O O O O O O OO O O O |
650000 +-+ O O O O O O O O O OO O O O |
O O O O O O |
600000 +-+ |
| |
550000 +-+ |
| |
500000 +-+ |
| O |
450000 +-+----------------------------------------------------------------+
stress-ng.sockfd.ops_per_sec
28000 +-+-----------------------------------------------------------------+
| +. |
26000 +-+ .+ +.+. |
|.+.+.+.+.+.+.+ +.+.+.+.+.+.+.+.+.+.+.+.+.+.++.+.+.+.+.+.+.+.|
24000 +-+ |
| O O O O O O O |
22000 +-+ OO O O O O O O O O O O O O O O |
O O O O O O O O O O |
20000 +-+ |
| |
18000 +-+ |
| |
16000 +-+ O |
| |
14000 +-+-----------------------------------------------------------------+
[*] 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-5.0.0-rc2-00023-gb4822dc7564f0" of type "text/plain" (187906 bytes)
View attachment "job-script" of type "text/plain" (7840 bytes)
View attachment "job.yaml" of type "text/plain" (5524 bytes)
View attachment "reproduce" of type "text/plain" (388 bytes)
Powered by blists - more mailing lists