| 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: <20160824030458.GB6463@yexl-desktop>
Date: Wed, 24 Aug 2016 11:04:58 +0800
From: kernel test robot <xiaolong.ye@...el.com>
To: Aaron Lu <aaron.lu@...el.com>
Cc: Ingo Molnar <mingo@...nel.org>, Alex Shi <alex.shi@...aro.org>,
Andy Lutomirski <luto@...nel.org>,
Borislav Petkov <bp@...en8.de>,
Brian Gerst <brgerst@...il.com>,
Davidlohr Bueso <dave@...olabs.net>,
Denys Vlasenko <dvlasenk@...hat.com>,
"H. Peter Anvin" <hpa@...or.com>,
Huang Ying <ying.huang@...el.com>,
Josh Poimboeuf <jpoimboe@...hat.com>,
Linus Torvalds <torvalds@...ux-foundation.org>,
Peter Zijlstra <peterz@...radead.org>,
Thomas Gleixner <tglx@...utronix.de>,
Tomoki Sekiyama <tomoki.sekiyama.qu@...achi.com>,
LKML <linux-kernel@...r.kernel.org>, lkp@...org
Subject: [lkp] [x86/irq] 82ba4faca1: [No primary change] [unixbench]
FYI, we noticed interrupts.CAL:Function_call_interrupts +771.1% improvement due to commit:
commit 82ba4faca1bffad429f15c90c980ffd010366c25 ("x86/irq: Do not substract irq_tlb_count from irq_call_count")
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git master
in testcase: unixbench
on test machine: 8 threads Nehalem with 6G memory
with following parameters:
runtime: 300s
nr_task: 1
test: shell8
iN addition to that, the commit also has significant impact (interrupts.CAL:Function_call_interrupts +1822.5%)
on the following tests:
+------------------+----------------------------------+
| testcase | unixbench |
| test machine | 8 threads Nehalem with 6G memory |
| test parameters | nr_task=100% |
| | runtime=300s |
| | test=execl |
+------------------+----------------------------------+
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.
Details are as below:
-------------------------------------------------------------------------------------------------->
To reproduce:
git clone git://git.kernel.org/pub/scm/linux/kernel/git/wfg/lkp-tests.git
cd lkp-tests
bin/lkp install job.yaml # job file is attached in this email
bin/lkp run job.yaml
=========================================================================================
compiler/kconfig/nr_task/rootfs/runtime/tbox_group/test/testcase:
gcc-6/x86_64-rhel/1/debian-x86_64-2015-02-07.cgz/300s/nhm-white/shell8/unixbench
commit:
ace7fab7a6 ("x86/mm: Fix swap entry comment and macro")
82ba4faca1 ("x86/irq: Do not substract irq_tlb_count from irq_call_count")
ace7fab7a6cdd363 82ba4faca1bffad429f15c90c9
---------------- --------------------------
%stddev %change %stddev
\ | \
48379 ± 0% +771.1% 421448 ± 0% interrupts.CAL:Function_call_interrupts
19934 ± 8% -10.3% 17882 ± 4% meminfo.AnonHugePages
177575 ± 8% -11.9% 156428 ± 7% sched_debug.cpu.avg_idle.min
0.36 ± 35% +431.2% 1.93 ± 55% sched_debug.cpu.cpu_load[0].min
25.84 ± 1% +11.3% 28.77 ± 4% sched_debug.cpu.cpu_load[1].min
5.38 ± 3% -13.9% 4.63 ± 5% sched_debug.cpu.cpu_load[1].stddev
interrupts.CAL:Function_call_interrupts
450000 ++-----------------------------------------------------------------+
O O OO O O OO O O OO O O OO O O O OO |
400000 ++ |
350000 ++ |
| |
300000 ++ |
250000 ++ |
| |
200000 ++ |
150000 ++ |
| |
100000 ++ |
50000 *+ .**.*.*.* .**.*.*. *.*.*.*.* .*. *.*.*.** .* .*.* .*.*
| * :.*.* * :.* * + .* *.* * |
0 ++----------*----------------------*---------------*---------------+
[*] bisect-good sample
[O] bisect-bad sample
***************************************************************************************************
nhm-white: 8 threads Nehalem with 6G memory
=========================================================================================
compiler/kconfig/nr_task/rootfs/runtime/tbox_group/test/testcase:
gcc-6/x86_64-rhel/100%/debian-x86_64-2015-02-07.cgz/300s/nhm-white/execl/unixbench
commit:
ace7fab7a6 ("x86/mm: Fix swap entry comment and macro")
82ba4faca1 ("x86/irq: Do not substract irq_tlb_count from irq_call_count")
ace7fab7a6cdd363 82ba4faca1bffad429f15c90c9
---------------- --------------------------
fail:runs %reproduction fail:runs
| | |
%stddev %change %stddev
\ | \
25890 ± 1% +1822.5% 497748 ± 1% interrupts.CAL:Function_call_interrupts
15522 ± 80% +354.6% 70567 ±146% latency_stats.avg.max
0.28 ± 11% +23.9% 0.34 ± 4% sched_debug.cfs_rq:/.nr_running.stddev
535.29 ± 0% +2071.2% 11622 ± 55% sched_debug.cfs_rq:/.runnable_load_avg.max
18.12 ± 35% -66.9% 6.00 ± 85% sched_debug.cfs_rq:/.runnable_load_avg.min
159.21 ± 0% +2305.2% 3829 ± 55% sched_debug.cfs_rq:/.runnable_load_avg.stddev
109.46 ± 3% +1268.4% 1497 ± 53% sched_debug.cpu.cpu_load[0].avg
535.25 ± 0% +2071.2% 11621 ± 55% sched_debug.cpu.cpu_load[0].max
536.29 ± 0% +2067.3% 11623 ± 55% sched_debug.cpu.cpu_load[1].max
158.13 ± 0% +2317.9% 3823 ± 55% sched_debug.cpu.cpu_load[1].stddev
535.92 ± 0% +2068.9% 11623 ± 55% sched_debug.cpu.cpu_load[2].max
158.04 ± 0% +2319.1% 3823 ± 55% sched_debug.cpu.cpu_load[2].stddev
535.00 ± 0% +2072.4% 11622 ± 55% sched_debug.cpu.cpu_load[3].max
157.68 ± 0% +2324.3% 3822 ± 55% sched_debug.cpu.cpu_load[3].stddev
533.17 ± 0% +2079.7% 11621 ± 55% sched_debug.cpu.cpu_load[4].max
157.11 ± 0% +2332.9% 3822 ± 55% sched_debug.cpu.cpu_load[4].stddev
168510 ± 2% +840.5% 1584778 ± 51% sched_debug.cpu.load.avg
600190 ± 1% +1904.9% 12033432 ± 54% sched_debug.cpu.load.max
197074 ± 1% +1909.8% 3960765 ± 54% sched_debug.cpu.load.stddev
-1804 ±-12% -28.0% -1299 ±-13% sched_debug.cpu.nr_uninterruptible.min
1327 ± 19% -24.6% 1000 ± 19% sched_debug.cpu.nr_uninterruptible.stddev
Thanks,
Xiaolong
View attachment "config-4.8.0-rc1-00067-g82ba4fa" of type "text/plain" (152780 bytes)
View attachment "job.yaml" of type "text/plain" (3873 bytes)
View attachment "reproduce" of type "text/plain" (25 bytes)
Powered by blists - more mailing lists