| 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: <20160328062933.GA4389@yexl-desktop>
Date: Mon, 28 Mar 2016 14:29:33 +0800
From: kernel test robot <xiaolong.ye@...el.com>
To: "Rafael J. Wysocki" <rafael.j.wysocki@...el.com>
Cc: Srinivas Pandruvada <srinivas.pandruvada@...ux.intel.com>,
LKML <linux-kernel@...r.kernel.org>, lkp@...org
Subject: [lkp] [cpufreq] a4675fbc4a:unixbench.score +37.4% improvement
FYI, we noticed that unixbench.score +37.4% improvement with your commit.
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git master
commit a4675fbc4a7abe072ac6ba38c252f22a91ebcd94 ("cpufreq: intel_pstate: Replace timers with utilization update callbacks")
commit:
34e2c555f3e13c90e9284e23d00f03be8a6e06c5
a4675fbc4a7abe072ac6ba38c252f22a91ebcd94
34e2c555f3e13c90 a4675fbc4a7abe072ac6ba38c2
---------------- --------------------------
%stddev %change %stddev
\ | \
471.50 ± 0% +37.4% 647.98 ± 0% unixbench.score
181102 ± 0% +36.8% 247709 ± 0% unixbench.time.involuntary_context_switches
8448017 ± 0% +36.6% 11542098 ± 0% unixbench.time.minor_page_faults
8726 ± 0% +21.9% 10639 ± 0% vmstat.system.cs
181102 ± 0% +36.8% 247709 ± 0% time.involuntary_context_switches
8448017 ± 0% +36.6% 11542098 ± 0% time.minor_page_faults
5958 ± 4% -7.9% 5488 ± 2% slabinfo.kmalloc-256.active_objs
6512 ± 6% -8.9% 5930 ± 1% slabinfo.kmalloc-256.num_objs
22373 ± 4% +8.6% 24291 ± 4% slabinfo.kmalloc-32.active_objs
22373 ± 4% +8.6% 24291 ± 4% slabinfo.kmalloc-32.num_objs
4664 ± 19% -37.3% 2925 ± 26% cpuidle.C1-HSW.usage
886.25 ± 3% +50.4% 1333 ± 10% cpuidle.C1E-HSW.usage
45236605 ± 4% -52.0% 21702696 ± 4% cpuidle.C3-HSW.time
395591 ± 0% +22.6% 485056 ± 0% cpuidle.C6-HSW.usage
11660 ± 5% +33.9% 15610 ± 6% cpuidle.POLL.usage
6819262 ± 0% +36.2% 9290485 ± 0% proc-vmstat.numa_hit
6819262 ± 0% +36.2% 9290485 ± 0% proc-vmstat.numa_local
910141 ± 0% +36.2% 1239946 ± 0% proc-vmstat.pgalloc_dma32
5915149 ± 0% +36.2% 8057456 ± 0% proc-vmstat.pgalloc_normal
8533297 ± 0% +36.3% 11626985 ± 0% proc-vmstat.pgfault
6821913 ± 0% +36.2% 9293880 ± 0% proc-vmstat.pgfree
6.19 ± 0% -1.9% 6.07 ± 0% turbostat.%Busy
85.75 ± 0% +54.8% 132.75 ± 0% turbostat.Avg_MHz
1384 ± 0% +58.1% 2188 ± 0% turbostat.Bzy_MHz
16.87 ± 0% +11.1% 18.74 ± 0% turbostat.CPU%c1
4.39 ± 4% -57.3% 1.88 ± 4% turbostat.CPU%c3
17.55 ± 0% +14.4% 20.07 ± 0% turbostat.PkgWatt
31.10 ± 10% +48.0% 46.02 ± 16% sched_debug.cfs_rq:/.load_avg.avg
29.51 ± 21% +110.2% 62.02 ± 36% sched_debug.cfs_rq:/.load_avg.stddev
132.14 ± 6% +11.6% 147.44 ± 2% sched_debug.cfs_rq:/.util_avg.avg
630069 ± 13% -30.9% 435560 ± 5% sched_debug.cpu.avg_idle.min
116621 ± 17% +51.1% 176162 ± 2% sched_debug.cpu.avg_idle.stddev
4052 ± 3% +17.5% 4763 ± 4% sched_debug.cpu.nr_load_updates.min
18741 ± 1% +19.3% 22354 ± 0% sched_debug.cpu.nr_switches.avg
33330 ± 6% +20.5% 40157 ± 9% sched_debug.cpu.nr_switches.max
8418 ± 4% +30.5% 10985 ± 5% sched_debug.cpu.nr_switches.min
8423 ± 4% +30.5% 10991 ± 5% sched_debug.cpu.sched_count.min
7484 ± 1% +15.7% 8655 ± 0% sched_debug.cpu.sched_goidle.avg
13946 ± 7% +18.9% 16585 ± 10% sched_debug.cpu.sched_goidle.max
3078 ± 4% +28.0% 3941 ± 4% sched_debug.cpu.sched_goidle.min
7645 ± 1% +15.5% 8831 ± 0% sched_debug.cpu.ttwu_count.avg
2614 ± 4% +33.9% 3500 ± 3% sched_debug.cpu.ttwu_count.min
4499 ± 0% +27.2% 5723 ± 0% sched_debug.cpu.ttwu_local.avg
8842 ± 4% +14.6% 10134 ± 8% sched_debug.cpu.ttwu_local.max
2322 ± 3% +30.8% 3038 ± 5% sched_debug.cpu.ttwu_local.min
2220 ± 4% +13.8% 2527 ± 7% sched_debug.cpu.ttwu_local.stddev
unixbench.score
700 ++--------------------------------------------------------------------+
OO OO OO OO OO OO OOO OO OO OO OO OOO OO OO OO OO OO OOO OO OO OO |
600 ++ |
| |
500 ++ |
**.**.**.**.** *.***.**.**.**.**.***.**.**.**.**.**.***.**.**.**.**.**
400 ++ : : |
| : : |
300 ++ : : |
| : : |
200 ++ :: |
| :: |
100 ++ : |
| : |
0 ++-------------*------------------------------------------------------+
unixbench.time.minor_page_faults
1.2e+07 OO-OO-O-O-OOO-OO-OOO-OOO-OO-OOO-OOO--O---O--O------OO-OO-----O----+
| O O OO O O OO O O OO |
1e+07 ++ |
| |
**.**.***.*** *.***.***.**.***.***.**.***.***.**.***.***.**.***.**
8e+06 ++ : : |
| : : |
6e+06 ++ : : |
| : : |
4e+06 ++ : : |
| :: |
| :: |
2e+06 ++ : |
| : |
0 ++------------*---------------------------------------------------+
unixbench.time.involuntary_context_switches
300000 ++-----------------------------------------------------------------+
| |
250000 OO O O O OO OO OOO OO OOO OO OOO OO O OO OO OOO OO O O |
| O O OO O O O O O |
| |
200000 ++ |
**.**.***.**.* *.**.***.**.***.**.***.***.**.***.**.***.**.***.**.**
150000 ++ : : |
| : : |
100000 ++ : : |
| :: |
| : |
50000 ++ : |
| : |
0 ++------------*----------------------------------------------------+
time.minor_page_faults
1.2e+07 OO-OO-O-O-OOO-OO-OOO-OOO-OO-OOO-OOO--O---O--O------OO-OO-----O----+
| O O OO O O OO O O OO |
1e+07 ++ |
| |
**.**.***.*** *.***.***.**.***.***.**.***.***.**.***.***.**.***.**
8e+06 ++ : : |
| : : |
6e+06 ++ : : |
| : : |
4e+06 ++ : : |
| :: |
| :: |
2e+06 ++ : |
| : |
0 ++------------*---------------------------------------------------+
time.involuntary_context_switches
300000 ++-----------------------------------------------------------------+
| |
250000 OO O O O OO OO OOO OO OOO OO OOO OO O OO OO OOO OO O O |
| O O OO O O O O O |
| |
200000 ++ |
**.**.***.**.* *.**.***.**.***.**.***.***.**.***.**.***.**.***.**.**
150000 ++ : : |
| : : |
100000 ++ : : |
| :: |
| : |
50000 ++ : |
| : |
0 ++------------*----------------------------------------------------+
[*] bisect-good sample
[O] bisect-bad sample
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
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 Ye
View attachment "job.yaml" of type "text/plain" (3319 bytes)
View attachment "reproduce" of type "text/plain" (1500 bytes)
Powered by blists - more mailing lists