| 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: Sat, 6 Jun 2020 23:52:16 +0800
From: kernel test robot <rong.a.chen@...el.com>
To: Ian Kent <raven@...maw.net>
Cc: Andrew Morton <akpm@...ux-foundation.org>,
Al Viro <viro@...IV.linux.org.uk>,
Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
Tejun Heo <tj@...nel.org>,
Rick Lindsley <ricklind@...ux.vnet.ibm.com>,
Stephen Rothwell <sfr@...b.auug.org.au>,
David Howells <dhowells@...hat.com>,
Miklos Szeredi <miklos@...redi.hu>,
linux-fsdevel <linux-fsdevel@...r.kernel.org>,
Kernel Mailing List <linux-kernel@...r.kernel.org>,
lkp@...ts.01.org
Subject: [kernfs] ea7c5fc39a: stress-ng.stream.ops_per_sec 11827.2%
improvement
Greeting,
FYI, we noticed a 11827.2% improvement of stress-ng.stream.ops_per_sec due to commit:
commit: ea7c5fc39ab005b501e0c7666c29db36321e4f74 ("[PATCH 1/4] kernfs: switch kernfs to use an rwsem")
url: https://github.com/0day-ci/linux/commits/Ian-Kent/kernfs-proposed-locking-and-concurrency-improvement/20200525-134849
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: 1s
class: cpu-cache
cpufreq_governor: performance
ucode: 0x500002c
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:
cpu-cache/gcc-9/performance/1HDD/x86_64-rhel-7.6/100%/debian-x86_64-20191114.cgz/lkp-csl-2sp5/stress-ng/1s/0x500002c
commit:
fefcfc9687 ("driver core: Remove check in driver_deferred_probe_force_trigger()")
ea7c5fc39a ("kernfs: switch kernfs to use an rwsem")
fefcfc968723caf9 ea7c5fc39ab005b501e0c7666c2
---------------- ---------------------------
fail:runs %reproduction fail:runs
| | |
:4 25% 1:4 kmsg.debugfs:Directory'#'with_parent'rpc_clnt'already_present
%stddev %change %stddev
\ | \
96.00 +6353.9% 6195 stress-ng.stream.ops
51.71 ± 4% +11827.2% 6167 stress-ng.stream.ops_per_sec
29.54 -3.1% 28.63 stress-ng.time.elapsed_time
29.54 -3.1% 28.63 stress-ng.time.elapsed_time.max
317.00 ± 2% -40.2% 189.51 stress-ng.time.system_time
1949 +1.9% 1985 stress-ng.time.user_time
11150 -5.2% 10567 stress-ng.time.voluntary_context_switches
11.08 ± 2% -4.3 6.81 mpstat.cpu.all.sys%
24835 ± 24% -49.8% 12464 ±105% numa-numastat.node1.other_node
64.00 +4.7% 67.00 vmstat.cpu.us
10.52 -38.7% 6.45 iostat.cpu.system
64.78 +3.5% 67.03 iostat.cpu.user
108378 -4.0% 104009 proc-vmstat.nr_mapped
45571 +0.8% 45938 proc-vmstat.nr_slab_unreclaimable
17488 ± 4% -9.0% 15918 softirqs.CPU25.TIMER
18563 ± 13% -14.3% 15908 ± 4% softirqs.CPU62.TIMER
-8501 -40.8% -5031 sched_debug.cfs_rq:/.spread0.min
65.25 ± 4% -17.6% 53.75 ± 13% sched_debug.cpu.nr_uninterruptible.max
13.75 ± 4% -17.3% 11.38 ± 11% sched_debug.cpu.nr_uninterruptible.stddev
28031 ± 2% +20.4% 33753 ± 5% slabinfo.filp.active_objs
903.50 ± 2% +20.5% 1088 ± 4% slabinfo.filp.active_slabs
28934 ± 2% +20.5% 34854 ± 4% slabinfo.filp.num_objs
903.50 ± 2% +20.5% 1088 ± 4% slabinfo.filp.num_slabs
4218 ± 6% -13.1% 3666 ± 3% slabinfo.kmalloc-rcl-64.active_objs
4218 ± 6% -13.1% 3666 ± 3% slabinfo.kmalloc-rcl-64.num_objs
957.00 ± 11% -25.1% 717.25 ± 10% interrupts.CPU0.RES:Rescheduling_interrupts
119.75 ±106% -75.6% 29.25 ± 20% interrupts.CPU22.RES:Rescheduling_interrupts
26.50 ± 9% +785.8% 234.75 ± 80% interrupts.CPU33.RES:Rescheduling_interrupts
6341 ± 3% -17.8% 5212 ± 24% interrupts.CPU52.NMI:Non-maskable_interrupts
6341 ± 3% -17.8% 5212 ± 24% interrupts.CPU52.PMI:Performance_monitoring_interrupts
6329 ± 4% -28.4% 4534 ± 34% interrupts.CPU70.NMI:Non-maskable_interrupts
6329 ± 4% -28.4% 4534 ± 34% interrupts.CPU70.PMI:Performance_monitoring_interrupts
5458 ± 23% -29.0% 3877 ± 34% interrupts.CPU83.NMI:Non-maskable_interrupts
5458 ± 23% -29.0% 3877 ± 34% interrupts.CPU83.PMI:Performance_monitoring_interrupts
stress-ng.time.system_time
360 +---------------------------------------------------------------------+
340 |-+ + .. : |
| + + .+ .+ : .+.. .+ |
320 |.+..+ +..+ + .+. .+..+. .+.+.+..+.+ + + + .+.|
300 |-+ +..+ +..+.+ +.+. +. |
| |
280 |-+ |
260 |-+ |
240 |-+ |
| |
220 |-+ O |
200 |-+ O O O |
| O O O O O O O O O O O O O O O O O O |
180 |-+ O O |
160 +---------------------------------------------------------------------+
stress-ng.stream.ops
7000 +--------------------------------------------------------------------+
| O O O O O O O O O O O O |
6000 |-+ O O O O O O O O O O O |
| |
5000 |-+ |
| |
4000 |-+ |
| |
3000 |-+ |
| |
2000 |-+ |
| |
1000 |-+ |
| |
0 +--------------------------------------------------------------------+
stress-ng.stream.ops_per_sec
7000 +--------------------------------------------------------------------+
| O O O O O O O O O O |
6000 |-+ O O O O O O O O O O O O O |
| |
5000 |-+ |
| |
4000 |-+ |
| |
3000 |-+ |
| |
2000 |-+ |
| |
1000 |-+ |
| |
0 +--------------------------------------------------------------------+
[*] 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-5.7.0-rc5-00019-gea7c5fc39ab00" of type "text/plain" (202568 bytes)
View attachment "job-script" of type "text/plain" (7899 bytes)
View attachment "job.yaml" of type "text/plain" (5505 bytes)
View attachment "reproduce" of type "text/plain" (394 bytes)
Powered by blists - more mailing lists