| 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: <20170815013621.GE626@yexl-desktop>
Date: Tue, 15 Aug 2017 09:36:22 +0800
From: kernel test robot <xiaolong.ye@...el.com>
To: Jan Kara <jack@...e.cz>
Cc: Stephen Rothwell <sfr@...b.auug.org.au>,
Theodore Ts'o <tytso@....edu>,
Andrew Morton <akpm@...ux-foundation.org>,
LKML <linux-kernel@...r.kernel.org>, lkp@...org
Subject: [lkp-robot] [ext4] a7d3abb954: fio.write_bw_MBps 4% improvement
Greeting,
FYI, we noticed a 4% improvement of fio.write_bw_MBps due to commit:
commit: a7d3abb954e24955662133ce15260e1b1bd04eab ("ext4: use pagevec_lookup_range() in writeback code")
https://git.kernel.org/cgit/linux/kernel/git/next/linux-next.git master
in testcase: fio-basic
on test machine: 16 threads Intel(R) Xeon(R) CPU D-1541 @ 2.10GHz with 8G memory
with following parameters:
runtime: 300s
disk: 1SSD
fs: ext4
nr_task: 64
rw: randwrite
bs: 4k
ioengine: sync
test_size: 400g
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/01org/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: fio-basic/300s-1SSD-ext4-64-randwrite-4k-sync-400g-performance/lkp-bdw-de1
4cfe12b3736282ea a7d3abb954e24955662133ce15
---------------- --------------------------
%stddev change %stddev
\ | \
0.12 33% 0.16 fio.latency_100us%
0.09 33% 0.12 fio.latency_250us%
1.50 26% 1.89 ± 4% fio.latency_100ms%
91.00 4% 94.87 fio.write_bw_MBps
23296 4% 24285 fio.write_iops
3.67 3.71 fio.latency_20us%
16049 -4% 15441 fio.write_clat_stddev
2744 -4% 2633 fio.write_clat_mean_us
103936 -8% 95744 fio.write_clat_99%_us
1.24 -35% 0.80 ± 8% fio.latency_250ms%
270530 5% 283091 fio.time.voluntary_context_switches
55931458 4% 58302536 fio.time.file_system_outputs
222103 5% 233683 vmstat.io.bo
23801 7% 25412 vmstat.system.cs
44789 3% 46240 vmstat.system.in
3399 6% 3612 iostat.sda.wrqm/s
28483 5% 29922 iostat.sda.w/s
241664 5% 253317 iostat.sda.wkB/s
5.77 5.85 iostat.sda.avgqu-sz
13422417 12% 15028260 ± 3% perf-stat.iTLB-load-misses
4.11 ± 4% 10% 4.50 ± 4% perf-stat.iTLB-load-miss-rate%
36597 8% 39554 perf-stat.cpu-migrations
7206012 7% 7700707 perf-stat.context-switches
1.20 1.22 perf-stat.cpi
0.84 0.82 perf-stat.ipc
5.805e+11 -6% 5.45e+11 ± 3% perf-stat.cpu-cycles
4.854e+11 -8% 4.458e+11 ± 3% perf-stat.instructions
1.28 -9% 1.16 perf-stat.branch-miss-rate%
5.74e+09 ± 4% -12% 5.03e+09 ± 4% perf-stat.cache-misses
5.74e+09 ± 4% -12% 5.03e+09 ± 4% perf-stat.cache-references
9.671e+10 -13% 8.453e+10 ± 3% perf-stat.branch-instructions
36186 ± 4% -18% 29684 ± 3% perf-stat.instructions-per-iTLB-miss
1.237e+09 ± 3% -21% 9.791e+08 ± 4% perf-stat.branch-misses
fio.write_bw_MBps
95 ++----------O-O-O-O-OO-O-O-OO------------------------------------------+
| |
94 ++ |
O O OO O O O |
| |
93 ++ |
| |
92 ++ |
| |
91 ++ .* .* .*. .* .*. .*.*.**.*.*
*.* *.*.* *.* *.* **.*.* *.*.*.**.*.* ** |
| + + |
90 ++ *.*.**.*.*.** |
| |
89 ++---------------------------------------------------------------------+
fio.write_iops
24400 ++------------------------------------------------------------------+
| O OO O OO O O OO |
24200 ++ |
24000 O+ O O O |
| O OO |
23800 ++ |
| |
23600 ++ |
| |
23400 ++ .**. *.|
23200 *+**.*.*.**.*.* *.**.*.**.*.*.**.*.**.*. *.*.* *.* *
| : + * |
23000 ++ *.*. *.*. .** |
| * * |
22800 ++------------------------------------------------------------------+
fio.write_clat_mean_us
2800 ++-------------------------------------------------------------------+
| **.*.* .*.*. |
2780 ++ : * * |
2760 ++ : : *. |
*.**.*.*.**.*.* *.*.*.**.*.**.*.*.**.*.* *.*.* .*.**.*
2740 ++ *.* |
2720 ++ |
| |
2700 ++ |
2680 ++ |
| O OO |
2660 O+ O O O |
2640 ++ |
| O O OO O OO O O O |
2620 ++-------------------------------------------------------------------+
fio.write_clat_stddev
16300 ++--------------------*---**----------------------------------------+
16200 ++ *.*.** * : |
| .* : |
16100 ++* .*.*. .* :.* .*.* .*. .**. .**. .* .*. *.*.* |
16000 *+ * ** * * * * * * *.* * *.*
| |
15900 ++ |
15800 ++ |
15700 ++ |
| O |
15600 O+OO O O O |
15500 ++ O O |
| O O OO |
15400 ++ O O OO |
15300 ++------------------------------------------------------------------+
fio.latency_100us_
0.16 ++----------O-O-OO-O-OO-O-O-O----------------------------------------+
| |
| |
0.15 O+OO O O OO |
| |
| |
0.14 ++ |
| |
0.13 ++ * |
| :: |
| : : |
0.12 *+**.*.*.**.*.* *.*.**.*.*.**.*.*.**.*.**.*.*.**.* *.*.*.**.*.*.**.*
| : : |
| :: |
0.11 ++--------------*----------------------------------------------------+
fio.latency_250us_
0.12 O+OO-O-O-OO-O-OO-O-OO-O-O-OO----------------------------------------+
| |
0.115 ++ |
| |
| |
0.11 ++ |
| |
0.105 ++ |
| |
0.1 ++ |
| |
| |
0.095 ++ |
| |
0.09 *+**-*-*-**-*-**-*-**-*-*-**-*-**-*-**-*-*-**-*-**-*-**-*-*-**-*-**-*
perf-stat.context-switches
7.8e+06 ++----------------------------------------------------------------+
| O O |
7.7e+06 ++ O OO OO O OO |
| |
7.6e+06 O+OO O OO O |
7.5e+06 ++ |
| |
7.4e+06 ++ |
| |
7.3e+06 ++ |
7.2e+06 ++ *. *.*. *. .* .**. .**.*
*.* *.* ** .*.* *.**.* *.*.**.*.* .**.* * |
7.1e+06 ++ + .**. * * |
| *.** *.* |
7e+06 ++----------------------------------------------------------------+
fio.time.voluntary_context_switches
284000 ++----------------O-O------O---------------------------------------+
| OO O O OO O |
282000 ++ O O O |
280000 O+O OO |
| |
278000 ++ |
276000 ++ |
| *. |
274000 *+**. .**.*. *.*.*. *.*.**. .**. .* .* * |
272000 ++ * ** : * * * *.* + |
| + : **. .**.|
270000 ++ *. .*. .* * *
268000 ++ ** * .* |
| * |
266000 ++-----------------------------------------------------------------+
fio.time.file_system_outputs
5.85e+07 ++---------------------------------------------------------------+
| O O OO O OO OO O |
5.8e+07 ++ |
O O O O |
5.75e+07 ++O O O |
| |
5.7e+07 ++ |
| |
5.65e+07 ++ |
| |
5.6e+07 ++ *. *.* .*. .*. .*. *.*.**.**.*
*.* *.* *.* ** **.** **.*.**.** * |
5.55e+07 ++ + + |
| **.*.**. *.* |
5.5e+07 ++---------------------*-----------------------------------------+
[*] 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-rc4-00257-ga7d3abb9" of type "text/plain" (161024 bytes)
View attachment "job-script" of type "text/plain" (7283 bytes)
View attachment "job.yaml" of type "text/plain" (4885 bytes)
View attachment "reproduce" of type "text/plain" (586 bytes)
Powered by blists - more mailing lists