さくらのVPS 東京リージョン 1G/2G でUnixBenchしてみた

2013年10月31日より、サービスリニューアルした、さくらのVPS(http://vps.sakura.ad.jp/) 。

東京リージョンのパフォーマンスが気になっていたので、試用期間中に計測してみました。

お名前.comには負けそうですが、なかなか良いパフォーマンスではないでしょうか。

FreeBSD 10.0-BETA3 でも計測したかったのですが、「Pipe-based Context Switching」のテストに失敗するので諦めorz

UnixBench 5.1.3 インストール (CentOS)

yum install perl-Time-HiRes

wget https://byte-unixbench.googlecode.com/files/UnixBench5.1.3.tgz
tar xzvf UnixBench5.1.3.tgz
cd UnixBench
make
./Run

比較表

数値は System Benchmarks Index Score です。

計測OS 1CPU 2CPU
東京 2G CentOS release 6.4 (Final) 1回目 985.2 2525.8
CentOS release 6.4 (Final) 2回目 1049.9 2667.3
FreeBSD 9.2 amd64 746.1 1389.3
東京 1G CentOS release 6.4 (Final) 1回目 955.0 2055.5
CentOS release 6.4 (Final) 2回目 985.0 2114.0
FreeBSD 9.2 amd64 734.8 1090.8

UnixBench結果

CentOS release 6.4 (Final) 2回目のみです…。

東京 2G CentOS release 6.4 (Final) 2回目

   #    #  #    #  #  #    #          #####   ######  #    #   ####   #    #
   #    #  ##   #  #   #  #           #    #  #       ##   #  #    #  #    #
   #    #  # #  #  #    ##            #####   #####   # #  #  #       ######
   #    #  #  # #  #    ##            #    #  #       #  # #  #       #    #
   #    #  #   ##  #   #  #           #    #  #       #   ##  #    #  #    #
    ####   #    #  #  #    #          #####   ######  #    #   ####   #    #

   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

3 x Dhrystone 2 using register variables  1 2 3 4 5 6 7 8 9 10

3 x Double-Precision Whetstone  1 2 3 4 5 6 7 8 9 10

3 x Execl Throughput  1 2 3

3 x File Copy 1024 bufsize 2000 maxblocks  1 2 3

3 x File Copy 256 bufsize 500 maxblocks  1 2 3

3 x File Copy 4096 bufsize 8000 maxblocks  1 2 3

3 x Pipe Throughput  1 2 3 4 5 6 7 8 9 10

3 x Pipe-based Context Switching  1 2 3 4 5 6 7 8 9 10

3 x Process Creation  1 2 3

3 x System Call Overhead  1 2 3 4 5 6 7 8 9 10

3 x Shell Scripts (1 concurrent)  1 2 3

3 x Shell Scripts (8 concurrent)  1 2 3

========================================================================
   BYTE UNIX Benchmarks (Version 5.1.3)

   System: www1447up.sakura.ne.jp: GNU/Linux
   OS: GNU/Linux -- 2.6.32-358.23.2.el6.x86_64 -- #1 SMP Wed Oct 16 18:37:12 UTC 2013
   Machine: x86_64 (x86_64)
   Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
   CPU 0: Intel Xeon E312xx (Sandy Bridge) (5000.0 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSCALL/SYSRET
   CPU 1: Intel Xeon E312xx (Sandy Bridge) (5000.0 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSCALL/SYSRET
   CPU 2: Intel Xeon E312xx (Sandy Bridge) (5000.0 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSCALL/SYSRET
   13:46:20 up 13 min,  2 users,  load average: 0.07, 0.02, 0.00; runlevel 3

------------------------------------------------------------------------
Benchmark Run: Wed Nov 27 2013 13:46:20 - 14:14:39
3 CPUs in system; running 1 parallel copy of tests

Dhrystone 2 using register variables       27134828.8 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     2677.8 MWIPS (9.9 s, 7 samples)
Execl Throughput                               2849.5 lps   (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        858335.3 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks          247335.3 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks       1085096.6 KBps  (30.0 s, 2 samples)
Pipe Throughput                             1876736.8 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                  22595.5 lps   (10.0 s, 7 samples)
Process Creation                               8156.5 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                   5202.5 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                   1622.1 lpm   (60.0 s, 2 samples)
System Call Overhead                        3235181.5 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0   27134828.8   2325.2
Double-Precision Whetstone                       55.0       2677.8    486.9
Execl Throughput                                 43.0       2849.5    662.7
File Copy 1024 bufsize 2000 maxblocks          3960.0     858335.3   2167.5
File Copy 256 bufsize 500 maxblocks            1655.0     247335.3   1494.5
File Copy 4096 bufsize 8000 maxblocks          5800.0    1085096.6   1870.9
Pipe Throughput                               12440.0    1876736.8   1508.6
Pipe-based Context Switching                   4000.0      22595.5     56.5
Process Creation                                126.0       8156.5    647.3
Shell Scripts (1 concurrent)                     42.4       5202.5   1227.0
Shell Scripts (8 concurrent)                      6.0       1622.1   2703.5
System Call Overhead                          15000.0    3235181.5   2156.8
                                                                   ========
System Benchmarks Index Score                                        1049.9

------------------------------------------------------------------------
Benchmark Run: Wed Nov 27 2013 14:14:39 - 14:43:04
3 CPUs in system; running 3 parallel copies of tests

Dhrystone 2 using register variables       79516222.3 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     8018.4 MWIPS (10.0 s, 7 samples)
Execl Throughput                              10799.3 lps   (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        809095.1 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks          181273.6 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks       1757990.9 KBps  (30.0 s, 2 samples)
Pipe Throughput                             5628681.4 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                 746204.4 lps   (10.0 s, 7 samples)
Process Creation                              32902.2 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                  13924.8 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                   1823.8 lpm   (60.0 s, 2 samples)
System Call Overhead                        5224260.1 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0   79516222.3   6813.7
Double-Precision Whetstone                       55.0       8018.4   1457.9
Execl Throughput                                 43.0      10799.3   2511.5
File Copy 1024 bufsize 2000 maxblocks          3960.0     809095.1   2043.2
File Copy 256 bufsize 500 maxblocks            1655.0     181273.6   1095.3
File Copy 4096 bufsize 8000 maxblocks          5800.0    1757990.9   3031.0
Pipe Throughput                               12440.0    5628681.4   4524.7
Pipe-based Context Switching                   4000.0     746204.4   1865.5
Process Creation                                126.0      32902.2   2611.3
Shell Scripts (1 concurrent)                     42.4      13924.8   3284.2
Shell Scripts (8 concurrent)                      6.0       1823.8   3039.6
System Call Overhead                          15000.0    5224260.1   3482.8
                                                                   ========
System Benchmarks Index Score                                        2667.3

東京 1G CentOS release 6.4 (Final) 2回目

   #    #  #    #  #  #    #          #####   ######  #    #   ####   #    #
   #    #  ##   #  #   #  #           #    #  #       ##   #  #    #  #    #
   #    #  # #  #  #    ##            #####   #####   # #  #  #       ######
   #    #  #  # #  #    ##            #    #  #       #  # #  #       #    #
   #    #  #   ##  #   #  #           #    #  #       #   ##  #    #  #    #
    ####   #    #  #  #    #          #####   ######  #    #   ####   #    #

   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

2 x Dhrystone 2 using register variables  1 2 3 4 5 6 7 8 9 10

2 x Double-Precision Whetstone  1 2 3 4 5 6 7 8 9 10

2 x Execl Throughput  1 2 3

2 x File Copy 1024 bufsize 2000 maxblocks  1 2 3

2 x File Copy 256 bufsize 500 maxblocks  1 2 3

2 x File Copy 4096 bufsize 8000 maxblocks  1 2 3

2 x Pipe Throughput  1 2 3 4 5 6 7 8 9 10

2 x Pipe-based Context Switching  1 2 3 4 5 6 7 8 9 10

2 x Process Creation  1 2 3

2 x System Call Overhead  1 2 3 4 5 6 7 8 9 10

2 x Shell Scripts (1 concurrent)  1 2 3

2 x Shell Scripts (8 concurrent)  1 2 3

========================================================================
   BYTE UNIX Benchmarks (Version 5.1.3)

   System: www2096uo.sakura.ne.jp: GNU/Linux
   OS: GNU/Linux -- 2.6.32-358.23.2.el6.x86_64 -- #1 SMP Wed Oct 16 18:37:12 UTC 2013
   Machine: x86_64 (x86_64)
   Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
   CPU 0: Intel Xeon E312xx (Sandy Bridge) (5000.2 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSCALL/SYSRET
   CPU 1: Intel Xeon E312xx (Sandy Bridge) (5000.2 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSCALL/SYSRET
   13:48:45 up 3 min,  2 users,  load average: 0.19, 0.05, 0.01; runlevel 3

------------------------------------------------------------------------
Benchmark Run: Wed Nov 27 2013 13:48:45 - 14:16:59
2 CPUs in system; running 1 parallel copy of tests

Dhrystone 2 using register variables       26351233.3 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     2676.8 MWIPS (9.9 s, 7 samples)
Execl Throughput                               2917.5 lps   (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        850198.5 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks          240191.0 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks        886819.5 KBps  (30.0 s, 2 samples)
Pipe Throughput                             1905619.0 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                  20473.4 lps   (10.0 s, 7 samples)
Process Creation                               7456.5 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                   5022.0 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                   1177.4 lpm   (60.0 s, 2 samples)
System Call Overhead                        3264465.2 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0   26351233.3   2258.0
Double-Precision Whetstone                       55.0       2676.8    486.7
Execl Throughput                                 43.0       2917.5    678.5
File Copy 1024 bufsize 2000 maxblocks          3960.0     850198.5   2147.0
File Copy 256 bufsize 500 maxblocks            1655.0     240191.0   1451.3
File Copy 4096 bufsize 8000 maxblocks          5800.0     886819.5   1529.0
Pipe Throughput                               12440.0    1905619.0   1531.8
Pipe-based Context Switching                   4000.0      20473.4     51.2
Process Creation                                126.0       7456.5    591.8
Shell Scripts (1 concurrent)                     42.4       5022.0   1184.4
Shell Scripts (8 concurrent)                      6.0       1177.4   1962.3
System Call Overhead                          15000.0    3264465.2   2176.3
                                                                   ========
System Benchmarks Index Score                                         985.0

------------------------------------------------------------------------
Benchmark Run: Wed Nov 27 2013 14:16:59 - 14:45:13
2 CPUs in system; running 2 parallel copies of tests

Dhrystone 2 using register variables       53484102.7 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     5344.5 MWIPS (9.9 s, 7 samples)
Execl Throughput                               7383.2 lps   (29.8 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks       1021244.6 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks          250745.4 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks       1624658.2 KBps  (30.0 s, 2 samples)
Pipe Throughput                             3778296.4 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                 561256.2 lps   (10.0 s, 7 samples)
Process Creation                              23309.7 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                   8691.7 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                   1195.8 lpm   (60.1 s, 2 samples)
System Call Overhead                        4434174.2 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0   53484102.7   4583.0
Double-Precision Whetstone                       55.0       5344.5    971.7
Execl Throughput                                 43.0       7383.2   1717.0
File Copy 1024 bufsize 2000 maxblocks          3960.0    1021244.6   2578.9
File Copy 256 bufsize 500 maxblocks            1655.0     250745.4   1515.1
File Copy 4096 bufsize 8000 maxblocks          5800.0    1624658.2   2801.1
Pipe Throughput                               12440.0    3778296.4   3037.2
Pipe-based Context Switching                   4000.0     561256.2   1403.1
Process Creation                                126.0      23309.7   1850.0
Shell Scripts (1 concurrent)                     42.4       8691.7   2049.9
Shell Scripts (8 concurrent)                      6.0       1195.8   1993.0
System Call Overhead                          15000.0    4434174.2   2956.1
                                                                   ========
System Benchmarks Index Score                                        2114.0