Linuxのベンチマーク調査について

Linuxサーバーのベンチマークをとりたい場合は「UnixBench」というソフトを使うのが一般的のようです。 https://code.google.com/archive/p/byte-unixbench/ 今流行のラズベリーパイや、クラウドのサーバースペックや、自宅で構築したサーバーなど、UNIXでもLinuxでもいけるっぽいです。

インストール

$ wget https://storage.googleapis.com/google-code-archive-downloads/v2/code.google.com/byte-unixbench/UnixBench5.1.3.tgz $ tar zxf UnixBench5.1.3.tgz $ cd UnixBench5.1.3 $ make 現時点(2016.3.11)の最新版が5.1.3だったんですが、ページで確認してwgetしてください。

実行

「UnixBench5.1.3」ディレクトリに入った状態で下記コマンドをたたく。 $ ./Run

ideacompoの実行結果

make all make[1]: Entering directory '/home/foo/UnixBench' Checking distribution of files ./pgms exists ./src exists ./testdir exists ./tmp exists ./results exists make[1]: Leaving directory '/home/foo/UnixBench' sh: 1: 3dinfo: not found # # # # # # # ##### ###### # # #### # # # # ## # # # # # # # ## # # # # # # # # # # # ## ##### ##### # # # # ###### # # # # # # ## # # # # # # # # # # # # ## # # # # # # # ## # # # # #### # # # # # ##### ###### # # #### # # Version 5.1.3 Based on the Byte Magazine Unix Benchmark Multi-CPU version Version 5 revisions by Ian Smith, Sunnyvale, CA, USA January 13, 2011 johantheghost at yahoo period com 1 x Dhrystone 2 using register variables 1 2 3 4 5 6 7 8 9 10 1 x Double-Precision Whetstone 1 2 3 4 5 6 7 8 9 10 1 x Execl Throughput 1 2 3 1 x File Copy 1024 bufsize 2000 maxblocks 1 2 3 1 x File Copy 256 bufsize 500 maxblocks 1 2 3 1 x File Copy 4096 bufsize 8000 maxblocks 1 2 3 1 x Pipe Throughput 1 2 3 4 5 6 7 8 9 10 1 x Pipe-based Context Switching 1 2 3 4 5 6 7 8 9 10 1 x Process Creation 1 2 3 1 x System Call Overhead 1 2 3 4 5 6 7 8 9 10 1 x Shell Scripts (1 concurrent) 1 2 3 1 x Shell Scripts (8 concurrent) 1 2 3 4 x Dhrystone 2 using register variables 1 2 3 4 5 6 7 8 9 10 4 x Double-Precision Whetstone 1 2 3 4 5 6 7 8 9 10 4 x Execl Throughput 1 2 3 4 x File Copy 1024 bufsize 2000 maxblocks 1 2 3 4 x File Copy 256 bufsize 500 maxblocks 1 2 3 4 x File Copy 4096 bufsize 8000 maxblocks 1 2 3 4 x Pipe Throughput 1 2 3 4 5 6 7 8 9 10 4 x Pipe-based Context Switching 1 2 3 4 5 6 7 8 9 10 4 x Process Creation 1 2 3 4 x System Call Overhead 1 2 3 4 5 6 7 8 9 10 4 x Shell Scripts (1 concurrent) 1 2 3 4 x Shell Scripts (8 concurrent) 1 2 3 ======================================================================== BYTE UNIX Benchmarks (Version 5.1.3) System: debian: GNU/Linux OS: GNU/Linux -- 3.16.0-4-686-pae -- #1 SMP Debian 3.16.7-ckt11-1 (2015-05-24) Machine: i686 (unknown) Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8") CPU 0: Intel(R) Atom(TM) CPU D525 @ 1.80GHz (3590.9 bogomips) Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT CPU 1: Intel(R) Atom(TM) CPU D525 @ 1.80GHz (3590.9 bogomips) Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT CPU 2: Intel(R) Atom(TM) CPU D525 @ 1.80GHz (3590.9 bogomips) Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT CPU 3: Intel(R) Atom(TM) CPU D525 @ 1.80GHz (3590.9 bogomips) Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT 02:55:45 up 241 days, 2:55, 1 user, load average: 0.11, 0.13, 0.17; runlevel 5 ------------------------------------------------------------------------ Benchmark Run: Fri Mar 11 2016 02:55:45 - 03:24:15 4 CPUs in system; running 1 parallel copy of tests Dhrystone 2 using register variables 5509451.1 lps (10.0 s, 7 samples) Double-Precision Whetstone 972.6 MWIPS (10.2 s, 7 samples) Execl Throughput 1214.5 lps (29.7 s, 2 samples) File Copy 1024 bufsize 2000 maxblocks 152436.6 KBps (30.0 s, 2 samples) File Copy 256 bufsize 500 maxblocks 43025.0 KBps (30.0 s, 2 samples) File Copy 4096 bufsize 8000 maxblocks 422238.5 KBps (30.0 s, 2 samples) Pipe Throughput 355206.8 lps (10.0 s, 7 samples) Pipe-based Context Switching 40517.4 lps (10.0 s, 7 samples) Process Creation 2950.0 lps (30.0 s, 2 samples) Shell Scripts (1 concurrent) 2434.8 lpm (60.0 s, 2 samples) Shell Scripts (8 concurrent) 619.1 lpm (60.0 s, 2 samples) System Call Overhead 770684.1 lps (10.0 s, 7 samples) System Benchmarks Index Values BASELINE RESULT INDEX Dhrystone 2 using register variables 116700.0 5509451.1 472.1 Double-Precision Whetstone 55.0 972.6 176.8 Execl Throughput 43.0 1214.5 282.4 File Copy 1024 bufsize 2000 maxblocks 3960.0 152436.6 384.9 File Copy 256 bufsize 500 maxblocks 1655.0 43025.0 260.0 File Copy 4096 bufsize 8000 maxblocks 5800.0 422238.5 728.0 Pipe Throughput 12440.0 355206.8 285.5 Pipe-based Context Switching 4000.0 40517.4 101.3 Process Creation 126.0 2950.0 234.1 Shell Scripts (1 concurrent) 42.4 2434.8 574.2 Shell Scripts (8 concurrent) 6.0 619.1 1031.9 System Call Overhead 15000.0 770684.1 513.8 ======== System Benchmarks Index Score 351.4 ------------------------------------------------------------------------ Benchmark Run: Fri Mar 11 2016 03:24:15 - 03:53:07 4 CPUs in system; running 4 parallel copies of tests Dhrystone 2 using register variables 13175658.9 lps (10.0 s, 7 samples) Double-Precision Whetstone 3414.5 MWIPS (10.2 s, 7 samples) Execl Throughput 3386.9 lps (29.6 s, 2 samples) File Copy 1024 bufsize 2000 maxblocks 167165.1 KBps (30.0 s, 2 samples) File Copy 256 bufsize 500 maxblocks 48873.8 KBps (30.0 s, 2 samples) File Copy 4096 bufsize 8000 maxblocks 481444.8 KBps (30.0 s, 2 samples) Pipe Throughput 624608.0 lps (10.0 s, 7 samples) Pipe-based Context Switching 155108.1 lps (10.0 s, 7 samples) Process Creation 7848.2 lps (30.0 s, 2 samples) Shell Scripts (1 concurrent) 5072.7 lpm (60.0 s, 2 samples) Shell Scripts (8 concurrent) 654.8 lpm (60.2 s, 2 samples) System Call Overhead 1689282.8 lps (10.0 s, 7 samples) System Benchmarks Index Values BASELINE RESULT INDEX Dhrystone 2 using register variables 116700.0 13175658.9 1129.0 Double-Precision Whetstone 55.0 3414.5 620.8 Execl Throughput 43.0 3386.9 787.6 File Copy 1024 bufsize 2000 maxblocks 3960.0 167165.1 422.1 File Copy 256 bufsize 500 maxblocks 1655.0 48873.8 295.3 File Copy 4096 bufsize 8000 maxblocks 5800.0 481444.8 830.1 Pipe Throughput 12440.0 624608.0 502.1 Pipe-based Context Switching 4000.0 155108.1 387.8 Process Creation 126.0 7848.2 622.9 Shell Scripts (1 concurrent) 42.4 5072.7 1196.4 Shell Scripts (8 concurrent) 6.0 654.8 1091.3 System Call Overhead 15000.0 1689282.8 1126.2 ======== System Benchmarks Index Score 682.3 You have new mail in /var/mail/root だいたい、５０分ぐらいかかりました。

このサーバーの性能

$ cat /etc/issue Debian GNU/Linux 8 \n \l $ cat /proc/cpuinfo vendor_id : GenuineIntel cpu family : 6 model : 28 model name : Intel(R) Atom(TM) CPU D525 @ 1.80GHz stepping : 10 microcode : 0x107 cpu MHz : 1795.442 cache size : 512 KB ※４コア分

まとめ

ベンチマークなので、比較対象がなければ高いのか低いのかわかりません・・・orz だけど、同一スペックで構成違いなどでベンチしたり、似たような性能でのテストを行なったりして、比較検討する事で、性能を理解していくといいのではないでしょうか。