| 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: <20171012063550.GM26196@yexl-desktop>
Date: Thu, 12 Oct 2017 14:35:50 +0800
From: kernel test robot <xiaolong.ye@...el.com>
To: Dan Williams <dan.j.williams@...el.com>
Cc: Theodore Ts'o <tytso@....edu>,
Andreas Dilger <adilger.kernel@...ger.ca>,
Jan Kara <jack@...e.cz>, Christoph Hellwig <hch@....de>,
LKML <linux-kernel@...r.kernel.org>,
Linus Torvalds <torvalds@...ux-foundation.org>, lkp@...org
Subject: [lkp-robot] [ext4] 5e405595e5: fio.read_bw_MBps +408.4% improvement
Greeting,
FYI, we noticed a +408.4% improvement of fio.read_bw_MBps due to commit:
commit: 5e405595e5bf4c09fab9ca1e7dbe5b62872757b5 ("ext4: perform dax_device lookup at mount")
https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git master
in testcase: fio-basic
on test machine: 56 threads Intel(R) Xeon(R) CPU E5-2695 v3 @ 2.30GHz with 256G memory
with following parameters:
disk: 2pmem
fs: ext4
mount_option: dax
runtime: 200s
nr_task: 50%
time_based: tb
rw: read
bs: 4k
ioengine: libaio
test_size: 200G
cpufreq_governor: performance
test-description: Fio is a tool that will spawn a number of threads or processes doing a particular type of I/O action as specified by the user.
test-url: https://github.com/axboe/fio
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
commit:
8cf037a8b22f71c6659bd0246bfaba9e79766f64
5e405595e5bf4c09fab9ca1e7dbe5b62872757b5
8cf037a8b22f71c6 5e405595e5bf4c09fab9ca1e7d
---------------- --------------------------
%stddev %change %stddev
\ | \
8736 +408.4% 44415 ± 2% fio.read_bw_MBps
0.06 ± 26% -0.1 0.01 fio.latency_1000us%
0.01 +93.8 93.84 ± 2% fio.latency_100us%
0.01 +6.1 6.15 ± 42% fio.latency_250us%
0.02 -0.0 0.01 fio.latency_2ms%
99.48 -99.5 0.01 fio.latency_500us%
0.43 ± 16% -0.4 0.01 fio.latency_750us%
401.00 -76.2% 95.25 ± 4% fio.read_clat_90%_us
405.00 -75.3% 100.00 ± 4% fio.read_clat_95%_us
438.00 ± 5% -74.8% 110.50 ± 4% fio.read_clat_99%_us
388.34 -80.3% 76.63 ± 2% fio.read_clat_mean_us
66.36 ± 42% -63.6% 24.19 ± 40% fio.read_clat_stddev
2236559 +408.4% 11370293 ± 2% fio.read_iops
12.03 -83.8% 1.95 ± 3% fio.read_slat_mean_us
11.30 ± 47% -70.2% 3.36 ± 60% fio.read_slat_stddev
5410 -15.7% 4559 fio.time.system_time
196.09 +434.7% 1048 ± 2% fio.time.user_time
114234 ± 2% -5.2% 108318 ± 3% interrupts.CAL:Function_call_interrupts
209464 ± 9% -13.8% 180474 ± 10% meminfo.Active
1627 ± 2% +5.0% 1708 ± 2% vmstat.system.cs
1931138 ± 2% -28.5% 1381485 ± 10% cpuidle.C1.time
2328227 ± 14% -27.9% 1679316 ± 4% cpuidle.C1E.time
5410 -15.7% 4559 time.system_time
196.09 +434.7% 1048 ± 2% time.user_time
fio.read_bw_MBps
60000 +-+-----------------------------------------------------------------+
| |
50000 +-+O |
| O O O O O O O O O |
O O O O O O O O O O O |
40000 +-+ |
| |
30000 +-+ |
| |
20000 +-+ |
| |
| |
10000 +-++..+..+..+..+...+..+..+..+..+..+..+..+..+..+..+...+..+..+..+..+..|
|.. |
0 +-+-----------------------------------------------------------------+
fio.read_iops
1.4e+07 +-+---------------------------------------------------------------+
| O |
1.2e+07 +-+ O O O O O O O O O |
O O O O O O O O O O O |
1e+07 +-+ |
| |
8e+06 +-+ |
| |
6e+06 +-+ |
| |
4e+06 +-+ |
| |
2e+06 +-++..+..+..+..+..+..+..+..+..+..+..+..+..+..+..+..+..+..+..+..+..|
|.. |
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,
Xiaolong
View attachment "config-4.13.0-rc6-00004-g5e40559" of type "text/plain" (161843 bytes)
View attachment "job-script" of type "text/plain" (7414 bytes)
View attachment "job.yaml" of type "text/plain" (5062 bytes)
View attachment "reproduce" of type "text/plain" (840 bytes)
Powered by blists - more mailing lists