VirtualBoxのCentOSでUnixBenchを試してみる

VirtualBoxにCentOSをとりあえずインストール
の続き


Mac Book ProのVirtualBoxで入れたCentOS上で、
UnixBenchを試してみる。

UnixBenchのインストール

下記の手順でUnixBenchをインストールして、実行する。

# yum -y install wget gcc perl perl-Time-HiRes
# wget http://byte-unixbench.googlecode.com/files/UnixBench5.1.3.tgz
# tar zxvf UnixBench5.1.3.tgz
# cd UnixBench
# make
# ./Run

Mac Book Proのスペック

今回使ってるMac Book Proのスペックは、下記の通り。

CPU 2.5 GHz Intel Core i5
メモリ 8GB


VirtualBoxで指定可能な、
プロセッサー数の最大は4、
メモリの最大は約5.6GB。

結果

条件 スコア
プロセッサー数4、メモリ約5.6GB 1270
プロセッサー数2、メモリ約5.6GB 1115
プロセッサー数1、メモリ約5.6GB 1063
プロセッサー数4、メモリ1GB 1285

プロセッサー数4、メモリ約5.6GB

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

   System: localhost.localdomain: GNU/Linux
   OS: GNU/Linux -- 2.6.32-431.el6.x86_64 -- #1 SMP Fri Nov 22 03:15:09 UTC 2013
   Machine: x86_64 (x86_64)
   Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
   CPU 0: Intel(R) Core(TM) i5-3210M CPU @ 2.50GHz (4805.9 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
   CPU 1: Intel(R) Core(TM) i5-3210M CPU @ 2.50GHz (4805.9 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
   CPU 2: Intel(R) Core(TM) i5-3210M CPU @ 2.50GHz (4805.9 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
   CPU 3: Intel(R) Core(TM) i5-3210M CPU @ 2.50GHz (4805.9 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
   23:33:40 up 1 min,  1 user,  load average: 0.15, 0.03, 0.01; runlevel 3

------------------------------------------------------------------------
Benchmark Run: 金  725 2014 23:33:40 - 00:01:38
4 CPUs in system; running 1 parallel copy of tests

Dhrystone 2 using register variables       25246447.1 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     2754.8 MWIPS (9.0 s, 7 samples)
Execl Throughput                               1281.3 lps   (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        602545.9 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks          204258.7 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks       1635593.5 KBps  (30.0 s, 2 samples)
Pipe Throughput                             1318027.2 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                   4475.8 lps   (10.0 s, 7 samples)
Process Creation                               3056.1 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                   2880.2 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                    854.9 lpm   (60.0 s, 2 samples)
System Call Overhead                        1790041.3 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0   25246447.1   2163.4
Double-Precision Whetstone                       55.0       2754.8    500.9
Execl Throughput                                 43.0       1281.3    298.0
File Copy 1024 bufsize 2000 maxblocks          3960.0     602545.9   1521.6
File Copy 256 bufsize 500 maxblocks            1655.0     204258.7   1234.2
File Copy 4096 bufsize 8000 maxblocks          5800.0    1635593.5   2820.0
Pipe Throughput                               12440.0    1318027.2   1059.5
Pipe-based Context Switching                   4000.0       4475.8     11.2
Process Creation                                126.0       3056.1    242.5
Shell Scripts (1 concurrent)                     42.4       2880.2    679.3
Shell Scripts (8 concurrent)                      6.0        854.9   1424.9
System Call Overhead                          15000.0    1790041.3   1193.4
                                                                   ========
System Benchmarks Index Score                                         649.9

------------------------------------------------------------------------
Benchmark Run: 土  726 2014 00:01:38 - 00:29:41
4 CPUs in system; running 4 parallel copies of tests

Dhrystone 2 using register variables       50130809.3 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     8174.9 MWIPS (9.5 s, 7 samples)
Execl Throughput                               5076.3 lps   (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        302805.5 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks           82495.3 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks        998625.7 KBps  (30.0 s, 2 samples)
Pipe Throughput                             2481139.4 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                 113394.2 lps   (10.0 s, 7 samples)
Process Creation                              13707.6 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                   6829.8 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                    920.5 lpm   (60.2 s, 2 samples)
System Call Overhead                        3534760.6 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0   50130809.3   4295.7
Double-Precision Whetstone                       55.0       8174.9   1486.4
Execl Throughput                                 43.0       5076.3   1180.5
File Copy 1024 bufsize 2000 maxblocks          3960.0     302805.5    764.7
File Copy 256 bufsize 500 maxblocks            1655.0      82495.3    498.5
File Copy 4096 bufsize 8000 maxblocks          5800.0     998625.7   1721.8
Pipe Throughput                               12440.0    2481139.4   1994.5
Pipe-based Context Switching                   4000.0     113394.2    283.5
Process Creation                                126.0      13707.6   1087.9
Shell Scripts (1 concurrent)                     42.4       6829.8   1610.8
Shell Scripts (8 concurrent)                      6.0        920.5   1534.2
System Call Overhead                          15000.0    3534760.6   2356.5
                                                                   ========
System Benchmarks Index Score                                        1270.7

プロセッサー数2、メモリ約5.6GB

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

   System: localhost.localdomain: GNU/Linux
   OS: GNU/Linux -- 2.6.32-431.el6.x86_64 -- #1 SMP Fri Nov 22 03:15:09 UTC 2013
   Machine: x86_64 (x86_64)
   Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
   CPU 0: Intel(R) Core(TM) i5-3210M CPU @ 2.50GHz (5084.0 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
   CPU 1: Intel(R) Core(TM) i5-3210M CPU @ 2.50GHz (5084.0 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
   07:49:34 up 1 min,  1 user,  load average: 0.14, 0.04, 0.01; runlevel 3

------------------------------------------------------------------------
Benchmark Run: 土  726 2014 07:49:34 - 08:17:30
2 CPUs in system; running 1 parallel copy of tests

Dhrystone 2 using register variables       25244310.6 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     2731.9 MWIPS (9.2 s, 7 samples)
Execl Throughput                               1390.8 lps   (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        610895.2 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks          200707.9 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks       1651413.1 KBps  (30.0 s, 2 samples)
Pipe Throughput                             1335265.3 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                   4648.8 lps   (10.0 s, 7 samples)
Process Creation                               3224.1 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                   3314.4 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                    653.5 lpm   (60.0 s, 2 samples)
System Call Overhead                        1795257.0 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0   25244310.6   2163.2
Double-Precision Whetstone                       55.0       2731.9    496.7
Execl Throughput                                 43.0       1390.8    323.4
File Copy 1024 bufsize 2000 maxblocks          3960.0     610895.2   1542.7
File Copy 256 bufsize 500 maxblocks            1655.0     200707.9   1212.7
File Copy 4096 bufsize 8000 maxblocks          5800.0    1651413.1   2847.3
Pipe Throughput                               12440.0    1335265.3   1073.4
Pipe-based Context Switching                   4000.0       4648.8     11.6
Process Creation                                126.0       3224.1    255.9
Shell Scripts (1 concurrent)                     42.4       3314.4    781.7
Shell Scripts (8 concurrent)                      6.0        653.5   1089.2
System Call Overhead                          15000.0    1795257.0   1196.8
                                                                   ========
System Benchmarks Index Score                                         653.1

------------------------------------------------------------------------
Benchmark Run: 土  726 2014 08:17:30 - 08:45:30
2 CPUs in system; running 2 parallel copies of tests

Dhrystone 2 using register variables       34779686.3 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     4752.0 MWIPS (9.4 s, 7 samples)
Execl Throughput                               3581.5 lps   (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        545116.5 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks          149213.3 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks       1642083.5 KBps  (30.0 s, 2 samples)
Pipe Throughput                             1728813.8 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                  86960.5 lps   (10.0 s, 7 samples)
Process Creation                              10154.0 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                   4921.5 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                    658.1 lpm   (60.0 s, 2 samples)
System Call Overhead                        2374666.2 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0   34779686.3   2980.3
Double-Precision Whetstone                       55.0       4752.0    864.0
Execl Throughput                                 43.0       3581.5    832.9
File Copy 1024 bufsize 2000 maxblocks          3960.0     545116.5   1376.6
File Copy 256 bufsize 500 maxblocks            1655.0     149213.3    901.6
File Copy 4096 bufsize 8000 maxblocks          5800.0    1642083.5   2831.2
Pipe Throughput                               12440.0    1728813.8   1389.7
Pipe-based Context Switching                   4000.0      86960.5    217.4
Process Creation                                126.0      10154.0    805.9
Shell Scripts (1 concurrent)                     42.4       4921.5   1160.7
Shell Scripts (8 concurrent)                      6.0        658.1   1096.8
System Call Overhead                          15000.0    2374666.2   1583.1
                                                                   ========
System Benchmarks Index Score                                        1115.1

プロセッサー数1、メモリ約5.6GB

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

   System: localhost.localdomain: GNU/Linux
   OS: GNU/Linux -- 2.6.32-431.el6.x86_64 -- #1 SMP Fri Nov 22 03:15:09 UTC 2013
   Machine: x86_64 (x86_64)
   Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
   CPU 0: Intel(R) Core(TM) i5-3210M CPU @ 2.50GHz (5005.4 bogomips)
          x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
   00:49:25 up 2 min,  1 user,  load average: 0.01, 0.01, 0.00; runlevel 3

------------------------------------------------------------------------
Benchmark Run: 土  726 2014 00:49:25 - 01:17:13
1 CPU in system; running 1 parallel copy of tests

Dhrystone 2 using register variables       28490744.7 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     2760.0 MWIPS (9.0 s, 7 samples)
Execl Throughput                               3063.3 lps   (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        724044.5 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks          192593.5 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks       1729600.8 KBps  (30.0 s, 2 samples)
Pipe Throughput                             1421968.9 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                 224469.2 lps   (10.0 s, 7 samples)
Process Creation                               8539.4 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                   3673.6 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                    486.2 lpm   (60.0 s, 2 samples)
System Call Overhead                        1849770.6 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0   28490744.7   2441.4
Double-Precision Whetstone                       55.0       2760.0    501.8
Execl Throughput                                 43.0       3063.3    712.4
File Copy 1024 bufsize 2000 maxblocks          3960.0     724044.5   1828.4
File Copy 256 bufsize 500 maxblocks            1655.0     192593.5   1163.7
File Copy 4096 bufsize 8000 maxblocks          5800.0    1729600.8   2982.1
Pipe Throughput                               12440.0    1421968.9   1143.1
Pipe-based Context Switching                   4000.0     224469.2    561.2
Process Creation                                126.0       8539.4    677.7
Shell Scripts (1 concurrent)                     42.4       3673.6    866.4
Shell Scripts (8 concurrent)                      6.0        486.2    810.3
System Call Overhead                          15000.0    1849770.6   1233.2
                                                                   ========
System Benchmarks Index Score                                        1063.1

プロセッサー数4、メモリ1GB

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

   System: localhost.localdomain: GNU/Linux
   OS: GNU/Linux -- 2.6.32-431.el6.x86_64 -- #1 SMP Fri Nov 22 03:15:09 UTC 2013
   Machine: x86_64 (x86_64)
   Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
   CPU 0: Intel(R) Core(TM) i5-3210M CPU @ 2.50GHz (4955.1 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
   CPU 1: Intel(R) Core(TM) i5-3210M CPU @ 2.50GHz (4955.1 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
   CPU 2: Intel(R) Core(TM) i5-3210M CPU @ 2.50GHz (4955.1 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
   CPU 3: Intel(R) Core(TM) i5-3210M CPU @ 2.50GHz (4955.1 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
   08:49:03 up 1 min,  1 user,  load average: 0.02, 0.01, 0.00; runlevel 3

------------------------------------------------------------------------
Benchmark Run: 土  726 2014 08:49:03 - 09:17:04
4 CPUs in system; running 1 parallel copy of tests

Dhrystone 2 using register variables       28237034.4 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     2713.4 MWIPS (9.3 s, 7 samples)
Execl Throughput                               1259.1 lps   (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        594080.5 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks          198421.9 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks       1635074.7 KBps  (30.0 s, 2 samples)
Pipe Throughput                             1327297.6 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                   4367.6 lps   (10.0 s, 7 samples)
Process Creation                               3062.9 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                   2877.0 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                    852.2 lpm   (60.0 s, 2 samples)
System Call Overhead                        1780247.8 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0   28237034.4   2419.6
Double-Precision Whetstone                       55.0       2713.4    493.3
Execl Throughput                                 43.0       1259.1    292.8
File Copy 1024 bufsize 2000 maxblocks          3960.0     594080.5   1500.2
File Copy 256 bufsize 500 maxblocks            1655.0     198421.9   1198.9
File Copy 4096 bufsize 8000 maxblocks          5800.0    1635074.7   2819.1
Pipe Throughput                               12440.0    1327297.6   1067.0
Pipe-based Context Switching                   4000.0       4367.6     10.9
Process Creation                                126.0       3062.9    243.1
Shell Scripts (1 concurrent)                     42.4       2877.0    678.5
Shell Scripts (8 concurrent)                      6.0        852.2   1420.3
System Call Overhead                          15000.0    1780247.8   1186.8
                                                                   ========
System Benchmarks Index Score                                         650.5

------------------------------------------------------------------------
Benchmark Run: 土  726 2014 09:17:04 - 09:45:07
4 CPUs in system; running 4 parallel copies of tests

Dhrystone 2 using register variables       49642261.7 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     8115.1 MWIPS (9.8 s, 7 samples)
Execl Throughput                               5117.0 lps   (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        324481.5 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks           86343.5 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks       1031804.1 KBps  (30.0 s, 2 samples)
Pipe Throughput                             2498208.5 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                 112109.8 lps   (10.0 s, 7 samples)
Process Creation                              13955.6 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                   6867.8 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                    920.4 lpm   (60.1 s, 2 samples)
System Call Overhead                        3482600.8 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0   49642261.7   4253.8
Double-Precision Whetstone                       55.0       8115.1   1475.5
Execl Throughput                                 43.0       5117.0   1190.0
File Copy 1024 bufsize 2000 maxblocks          3960.0     324481.5    819.4
File Copy 256 bufsize 500 maxblocks            1655.0      86343.5    521.7
File Copy 4096 bufsize 8000 maxblocks          5800.0    1031804.1   1779.0
Pipe Throughput                               12440.0    2498208.5   2008.2
Pipe-based Context Switching                   4000.0     112109.8    280.3
Process Creation                                126.0      13955.6   1107.6
Shell Scripts (1 concurrent)                     42.4       6867.8   1619.8
Shell Scripts (8 concurrent)                      6.0        920.4   1534.0
System Call Overhead                          15000.0    3482600.8   2321.7
                                                                   ========
System Benchmarks Index Score                                        1285.8