<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Benchmark on What's done is done</title><link>https://igawa.io/tags/benchmark/</link><description>Recent content in Benchmark on What's done is done</description><generator>Hugo</generator><language>ja</language><lastBuildDate>Tue, 03 Apr 2012 20:04:00 +0900</lastBuildDate><atom:link href="https://igawa.io/tags/benchmark/index.xml" rel="self" type="application/rss+xml"/><item><title>さくらのVPS(2G)でUnixBench(5.1.3)を実行してみた。結果：値段そのままなのに、大幅に性能アップ！</title><link>https://igawa.io/posts/2012/04/%E3%81%95%E3%81%8F%E3%82%89%E3%81%AEvps2g%E3%81%A7unixbench513%E3%82%92%E5%AE%9F%E8%A1%8C%E3%81%97%E3%81%A6%E3%81%BF%E3%81%9F%E7%B5%90%E6%9E%9C%E5%80%A4%E6%AE%B5%E3%81%9D%E3%81%AE%E3%81%BE%E3%81%BE%E3%81%AA%E3%81%AE%E3%81%AB%E5%A4%A7%E5%B9%85%E3%81%AB%E6%80%A7%E8%83%BD%E3%82%A2%E3%83%83%E3%83%97/</link><pubDate>Tue, 03 Apr 2012 20:04:00 +0900</pubDate><guid>https://igawa.io/posts/2012/04/%E3%81%95%E3%81%8F%E3%82%89%E3%81%AEvps2g%E3%81%A7unixbench513%E3%82%92%E5%AE%9F%E8%A1%8C%E3%81%97%E3%81%A6%E3%81%BF%E3%81%9F%E7%B5%90%E6%9E%9C%E5%80%A4%E6%AE%B5%E3%81%9D%E3%81%AE%E3%81%BE%E3%81%BE%E3%81%AA%E3%81%AE%E3%81%AB%E5%A4%A7%E5%B9%85%E3%81%AB%E6%80%A7%E8%83%BD%E3%82%A2%E3%83%83%E3%83%97/</guid><description>&lt;h1 id="はじめに"&gt;はじめに&lt;/h1&gt;
&lt;h2 id="なお15gで評価した結果はさくらのvpsでunixbench513を実施してみた"&gt;というわけで、早速、 さくらのVPS(2G)で、UnixBenchを実行してみました。
なお、1.5Gで評価した結果は、[&amp;ldquo;さくらのVPSでUnixBench(5.1.3)を実施してみた&lt;/h2&gt;
&lt;p&gt;part2(結果編)&amp;rdquo;](/posts/2011/03/sakuranovpsdeunixbench513woshi-shi-shitemita-part2jie-guo-bian/)を参照して下さい。&lt;/p&gt;
&lt;pre&gt;&lt;code&gt;========================================================================
BYTE UNIX Benchmarks (Version 5.1.3)
System: localhost.localdomain: GNU/Linux
OS: GNU/Linux -- 3.3.0-8.fc16.x86_64 -- #1 SMP Thu Mar 29 18:37:19 UTC 2012
Machine: x86_64 (x86_64)
Language: en_US.utf8 (charmap=&amp;quot;UTF-8&amp;quot;, collate=&amp;quot;UTF-8&amp;quot;)
CPU 0: Intel(R) Xeon(R) CPU E5645 (4800.2 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSCALL/SYSRET
CPU 1: Intel(R) Xeon(R) CPU E5645 (4800.2 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSCALL/SYSRET
CPU 2: Intel(R) Xeon(R) CPU E5645 (4800.2 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSCALL/SYSRET
20:22:38 up 2:57, 2 users, load average: 0.53, 0.41, 0.21; runlevel 3
------------------------------------------------------------------------
Benchmark Run: Tue Apr 03 2012 20:22:38 - 20:49:59
3 CPUs in system; running 1 parallel copy of tests
Dhrystone 2 using register variables 24322317.4 lps (10.0 s, 7 samples)
Double-Precision Whetstone 2961.2 MWIPS (7.0 s, 7 samples)
Execl Throughput 1451.8 lps (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 787751.5 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 223048.0 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 1639344.8 KBps (30.0 s, 2 samples)
Pipe Throughput 1385086.0 lps (10.0 s, 7 samples)
Pipe-based Context Switching 226423.8 lps (10.0 s, 7 samples)
Process Creation 3676.0 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 3725.1 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 1646.1 lpm (60.0 s, 2 samples)
System Call Overhead 1578386.4 lps (10.0 s, 7 samples)
System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 24322317.4 2084.2
Double-Precision Whetstone 55.0 2961.2 538.4
Execl Throughput 43.0 1451.8 337.6
File Copy 1024 bufsize 2000 maxblocks 3960.0 787751.5 1989.3
File Copy 256 bufsize 500 maxblocks 1655.0 223048.0 1347.7
File Copy 4096 bufsize 8000 maxblocks 5800.0 1639344.8 2826.5
Pipe Throughput 12440.0 1385086.0 1113.4
Pipe-based Context Switching 4000.0 226423.8 566.1
Process Creation 126.0 3676.0 291.7
Shell Scripts (1 concurrent) 42.4 3725.1 878.6
Shell Scripts (8 concurrent) 6.0 1646.1 2743.5
System Call Overhead 15000.0 1578386.4 1052.3
========
System Benchmarks Index Score 1024.6
------------------------------------------------------------------------
Benchmark Run: Tue Apr 03 2012 20:49:59 - 21:17:27
3 CPUs in system; running 3 parallel copies of tests
Dhrystone 2 using register variables 72068041.9 lps (10.0 s, 7 samples)
Double-Precision Whetstone 8846.1 MWIPS (7.2 s, 7 samples)
Execl Throughput 8582.7 lps (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 1071208.3 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 285035.8 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 2289930.0 KBps (30.0 s, 2 samples)
Pipe Throughput 4059296.6 lps (10.0 s, 7 samples)
Pipe-based Context Switching 654058.4 lps (10.0 s, 7 samples)
Process Creation 28607.3 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 14152.2 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 1953.0 lpm (60.0 s, 2 samples)
System Call Overhead 4106210.8 lps (10.0 s, 7 samples)
System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 72068041.9 6175.5
Double-Precision Whetstone 55.0 8846.1 1608.4
Execl Throughput 43.0 8582.7 1996.0
File Copy 1024 bufsize 2000 maxblocks 3960.0 1071208.3 2705.1
File Copy 256 bufsize 500 maxblocks 1655.0 285035.8 1722.3
File Copy 4096 bufsize 8000 maxblocks 5800.0 2289930.0 3948.2
Pipe Throughput 12440.0 4059296.6 3263.1
Pipe-based Context Switching 4000.0 654058.4 1635.1
Process Creation 126.0 28607.3 2270.4
Shell Scripts (1 concurrent) 42.4 14152.2 3337.8
Shell Scripts (8 concurrent) 6.0 1953.0 3254.9
System Call Overhead 15000.0 4106210.8 2737.5
========
System Benchmarks Index Score 2670.2
&lt;/code&gt;&lt;/pre&gt;
&lt;h1 id="まとめ"&gt;まとめ&lt;/h1&gt;
&lt;p&gt;テスト内容 旧システム(1.5G) 新システム(2G)&lt;/p&gt;</description></item><item><title>さくらのVPSでUnixBench(5.1.3)を実施してみた - part2(結果編)</title><link>https://igawa.io/posts/2011/03/%E3%81%95%E3%81%8F%E3%82%89%E3%81%AEvps%E3%81%A7unixbench513%E3%82%92%E5%AE%9F%E6%96%BD%E3%81%97%E3%81%A6%E3%81%BF%E3%81%9F-part2%E7%B5%90%E6%9E%9C%E7%B7%A8/</link><pubDate>Sun, 06 Mar 2011 06:30:00 +0900</pubDate><guid>https://igawa.io/posts/2011/03/%E3%81%95%E3%81%8F%E3%82%89%E3%81%AEvps%E3%81%A7unixbench513%E3%82%92%E5%AE%9F%E6%96%BD%E3%81%97%E3%81%A6%E3%81%BF%E3%81%9F-part2%E7%B5%90%E6%9E%9C%E7%B7%A8/</guid><description>&lt;p&gt;&lt;a href="http://www.flickr.com/photos/31362181@N08/5500656344/" title="result of sakura vps benchmark"&gt;&lt;img alt="result of sakura vps\nbenchmark" loading="lazy" src="http://farm6.static.flickr.com/5136/5500656344_6a9db11cd9_m.jpg"&gt;{.alignnone}&lt;/a&gt;&lt;/p&gt;
&lt;p&gt;と、いうわけで以下結果です。&lt;/p&gt;
&lt;p&gt;スコアとしては、1256.5。こんなもんなんでしょうか。&lt;/p&gt;
&lt;pre&gt;&lt;code&gt;========================================================================
BYTE UNIX Benchmarks (Version 5.1.3)
System: 0r2.info: GNU/Linux
OS: GNU/Linux -- 2.6.38-rc4-00106-gd247852 -- #1 SMP Sat Feb 12 05:11:57 JST 2011
Machine: x86_64 (x86_64)
Language: en_US.utf8 (charmap=&amp;quot;UTF-8&amp;quot;, collate=&amp;quot;UTF-8&amp;quot;)
CPU 0: Intel(R) Core(TM)2 Duo CPU T7700 @ 2.40GHz (5320.3 bogomips)
x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
CPU 1: Intel(R) Core(TM)2 Duo CPU T7700 @ 2.40GHz (5320.3 bogomips)
x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
05:26:55 up 18 days, 15:23, 1 user, load average: 0.02, 0.04, 0.05; runlevel 3
------------------------------------------------------------------------
Benchmark Run: 金 3月 04 2011 05:26:55 - 05:54:56
2 CPUs in system; running 1 parallel copy of tests
Dhrystone 2 using register variables 23992196.0 lps (10.0 s, 7 samples)
Double-Precision Whetstone 3085.0 MWIPS (9.1 s, 7 samples)
Execl Throughput 1307.9 lps (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 441004.0 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 122297.6 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 992115.9 KBps (30.0 s, 2 samples)
Pipe Throughput 1037608.4 lps (10.0 s, 7 samples)
Pipe-based Context Switching 145308.5 lps (10.0 s, 7 samples)
Process Creation 3073.2 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 2637.8 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 652.9 lpm (60.1 s, 2 samples)
System Call Overhead 1429308.8 lps (10.0 s, 7 samples)
System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 23992196.0 2055.9
Double-Precision Whetstone 55.0 3085.0 560.9
Execl Throughput 43.0 1307.9 304.2
File Copy 1024 bufsize 2000 maxblocks 3960.0 441004.0 1113.6
File Copy 256 bufsize 500 maxblocks 1655.0 122297.6 739.0
File Copy 4096 bufsize 8000 maxblocks 5800.0 992115.9 1710.5
Pipe Throughput 12440.0 1037608.4 834.1
Pipe-based Context Switching 4000.0 145308.5 363.3
Process Creation 126.0 3073.2 243.9
Shell Scripts (1 concurrent) 42.4 2637.8 622.1
Shell Scripts (8 concurrent) 6.0 652.9 1088.2
System Call Overhead 15000.0 1429308.8 952.9
========
System Benchmarks Index Score 731.7
------------------------------------------------------------------------
Benchmark Run: 金 3月 04 2011 05:54:56 - 06:23:16
2 CPUs in system; running 2 parallel copies of tests
Dhrystone 2 using register variables 45446984.0 lps (10.0 s, 7 samples)
Double-Precision Whetstone 6064.6 MWIPS (9.5 s, 7 samples)
Execl Throughput 3794.6 lps (29.9 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 465812.5 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 134853.9 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 1176253.0 KBps (30.0 s, 2 samples)
Pipe Throughput 1914346.3 lps (10.0 s, 7 samples)
Pipe-based Context Switching 272961.3 lps (10.0 s, 7 samples)
Process Creation 9831.0 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 5213.8 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 744.4 lpm (60.1 s, 2 samples)
System Call Overhead 2521800.8 lps (10.0 s, 7 samples)
System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 45446984.0 3894.3
Double-Precision Whetstone 55.0 6064.6 1102.7
Execl Throughput 43.0 3794.6 882.5
File Copy 1024 bufsize 2000 maxblocks 3960.0 465812.5 1176.3
File Copy 256 bufsize 500 maxblocks 1655.0 134853.9 814.8
File Copy 4096 bufsize 8000 maxblocks 5800.0 1176253.0 2028.0
Pipe Throughput 12440.0 1914346.3 1538.9
Pipe-based Context Switching 4000.0 272961.3 682.4
Process Creation 126.0 9831.0 780.2
Shell Scripts (1 concurrent) 42.4 5213.8 1229.7
Shell Scripts (8 concurrent) 6.0 744.4 1240.7
System Call Overhead 15000.0 2521800.8 1681.2
========
System Benchmarks Index Score 1256.5
&lt;/code&gt;&lt;/pre&gt;</description></item><item><title>さくらのVPSでUnixBench(5.1.3)を実施してみた - part1(準備編)</title><link>https://igawa.io/posts/2011/03/%E3%81%95%E3%81%8F%E3%82%89%E3%81%AEvps%E3%81%A7unixbench513%E3%82%92%E5%AE%9F%E6%96%BD%E3%81%97%E3%81%A6%E3%81%BF%E3%81%9F-part1%E6%BA%96%E5%82%99%E7%B7%A8/</link><pubDate>Fri, 04 Mar 2011 06:07:00 +0900</pubDate><guid>https://igawa.io/posts/2011/03/%E3%81%95%E3%81%8F%E3%82%89%E3%81%AEvps%E3%81%A7unixbench513%E3%82%92%E5%AE%9F%E6%96%BD%E3%81%97%E3%81%A6%E3%81%BF%E3%81%9F-part1%E6%BA%96%E5%82%99%E7%B7%A8/</guid><description>&lt;p&gt;さくらのVPSでベンチマークをやってみた。&lt;/p&gt;
&lt;p&gt;[php]
$ wget &lt;a href="http://byte-unixbench.googlecode.com/files/UnixBench5.1.3.tgz"&gt;http://byte-unixbench.googlecode.com/files/UnixBench5.1.3.tgz&lt;/a&gt;
&amp;ndash;2011-03-04 05:12:00&amp;ndash;
&lt;a href="http://byte-unixbench.googlecode.com/files/UnixBench5.1.3.tgz"&gt;http://byte-unixbench.googlecode.com/files/UnixBench5.1.3.tgz&lt;/a&gt;
byte-unixbench.googlecode.com をDNSに問いあわせています&amp;hellip;
64.233.183.82
byte-unixbench.googlecode.com|64.233.183.82|:80 に接続しています&amp;hellip;
接続しました。
HTTP による接続要求を送信しました、応答を待っています&amp;hellip; 200 OK
長さ: 143259 (140K) [application/x-gzip]
`UnixBench5.1.3.tgz&amp;rsquo; に保存中&lt;/p&gt;
&lt;p&gt;100%[======================================&amp;gt;] 143,259 203K/s 時間
0.7s&lt;/p&gt;
&lt;p&gt;2011-03-04 05:12:06 (203 KB/s) - `UnixBench5.1.3.tgz&amp;rsquo; へ保存完了
[143259/143259]&lt;/p&gt;
&lt;p&gt;$ tar xf UnixBench5.1.3.tgz
$ make
Checking distribution of files
./pgms exists
./src exists
./testdir exists
./results exists
gcc -o ./pgms/arithoh -DTIME -Wall -pedantic -ansi -O2
-fomit-frame-pointer -fforce-addr -ffast-math -Wall -Darithoh
./src/arith.c
(中略)
gcc -o ./pgms/whetstone-double -DTIME -Wall -pedantic -ansi -O2
-fomit-frame-pointer -fforce-addr -ffast-math -Wall -DDP -DUNIX
-DUNIXBENCH ./src/whets.c -lm
$ echo $?
0
$ ./Run
make all
make[1]: Entering directory `/home/masayuki/src/UnixBench'
Checking distribution of files
./pgms exists
./src exists
./testdir exists
./tmp exists
./results exists
make[1]: Leaving directory `/home/masayuki/src/UnixBench'
sh: 3dinfo: command not found&lt;/p&gt;</description></item></channel></rss>