| 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: <20170917013949.GA30476@yexl-desktop>
Date: Sun, 17 Sep 2017 09:39:49 +0800
From: kernel test robot <xiaolong.ye@...el.com>
To: Huang Ying <ying.huang@...el.com>
Cc: Linus Torvalds <torvalds@...ux-foundation.org>,
Andi Kleen <andi.kleen@...el.com>, Jan Kara <jack@...e.cz>,
Michal Hocko <mhocko@...e.com>,
Andrea Arcangeli <aarcange@...hat.com>,
"Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>,
Nadia Yvette Chambers <nyc@...omorphy.com>,
Matthew Wilcox <mawilcox@...rosoft.com>,
Hugh Dickins <hughd@...gle.com>,
Minchan Kim <minchan@...nel.org>, Shaohua Li <shli@...com>,
Christopher Lameter <cl@...ux.com>,
Mike Kravetz <mike.kravetz@...cle.com>,
Andrew Morton <akpm@...ux-foundation.org>,
LKML <linux-kernel@...r.kernel.org>, lkp@...org
Subject: [lkp-robot] [mm] c79b57e462: vm-scalability.throughput 25%
improvement
Greeting,
FYI, we noticed a +25% improvement of vm-scalability.throughput due to commit:
commit: c79b57e462b5d2f47afa5f175cf1828f16e18612 ("mm: hugetlb: clear target sub-page last when clearing huge page")
https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git master
in testcase: vm-scalability
on test machine: 88 threads Intel(R) Xeon(R) CPU E5-2699 v4 @ 2.20GHz with 128G memory
with following parameters:
runtime: 300s
size: 8T
test: anon-w-seq-mt
cpufreq_governor: performance
test-description: The motivation behind this suite is to exercise functions and regions of the mm/ of the Linux kernel which are of interest to us.
test-url: https://git.kernel.org/cgit/linux/kernel/git/wfg/vm-scalability.git/
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
testcase/path_params/tbox_group/run: vm-scalability/300s-8T-anon-w-seq-mt-performance/lkp-bdw-ep2
212925802454672e c79b57e462b5d2f47afa5f175c
---------------- --------------------------
%stddev change %stddev
\ | \
34081895 25% 42690377 vm-scalability.throughput
373299 24% 463391 vm-scalability.median
513295 22% 627873 vm-scalability.time.voluntary_context_switches
9548109 20% 11489781 vm-scalability.time.minor_page_faults
9.052e+09 20% 1.089e+10 vm-scalability.workload
8178 8349 vm-scalability.time.system_time
64389077 -4% 61913989 vm-scalability.time.maximum_resident_set_size
0.01 -4% 0.00 vm-scalability.free_time
6872 -9% 6273 vm-scalability.time.percent_of_cpu_this_job_got
12564 -16% 10595 vm-scalability.time.user_time
132010 -8% 120993 vmstat.system.in
12161911 -26% 8950198 interrupts.CAL:Function_call_interrupts
72723 27% 92011 pmeter.performance_per_watt
468 464 pmeter.Average_Active_Power
37.97 -3% 36.78 boot-time.boot
2996 -4% 2887 boot-time.idle
23.10 ± 4% -5% 21.96 boot-time.kernel_boot
19.97 ± 5% -5% 18.89 ± 3% boot-time.dhcp
0.57 ± 6% 36% 0.77 ± 11% perf-stat.node-store-miss-rate%
1.003e+09 32% 1.329e+09 perf-stat.node-loads
0.51 32% 0.67 perf-stat.ipc
169613 26% 212878 perf-stat.cpu-migrations
67010904 25% 83501581 perf-stat.iTLB-loads
2.42e+08 21% 2.929e+08 perf-stat.dTLB-load-misses
95290199 21% 1.152e+08 perf-stat.dTLB-store-misses
6.316e+12 21% 7.631e+12 perf-stat.dTLB-loads
2.945e+13 21% 3.555e+13 perf-stat.instructions
9.374e+12 21% 1.132e+13 perf-stat.branch-instructions
1.433e+09 21% 1.729e+09 perf-stat.branch-misses
2.432e+12 20% 2.926e+12 perf-stat.dTLB-stores
10269271 19% 12214968 perf-stat.minor-faults
10269275 19% 12214968 perf-stat.page-faults
5.543e+08 18% 6.559e+08 perf-stat.node-load-misses
1.064e+08 18% 1.257e+08 ± 3% perf-stat.iTLB-load-misses
3.017e+11 15% 3.458e+11 perf-stat.cache-references
35.58 -7% 33.05 perf-stat.node-load-miss-rate%
5.825e+13 -8% 5.337e+13 perf-stat.cpu-cycles
1.02e+11 -16% 8.544e+10 perf-stat.cache-misses
1.731e+10 -20% 1.381e+10 perf-stat.node-stores
1.98 -24% 1.50 perf-stat.cpi
33.80 -27% 24.70 perf-stat.cache-miss-rate%
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,
Xiaolong
View attachment "config-4.13.0-04373-gc79b57e" of type "text/plain" (162516 bytes)
View attachment "job-script" of type "text/plain" (7334 bytes)
View attachment "job.yaml" of type "text/plain" (4934 bytes)
View attachment "reproduce" of type "text/plain" (9760 bytes)
Powered by blists - more mailing lists