本ブログは、お名前.com VPS(KVM) 上に構築した CentOS 7 + WordPress で提供しています。
契約プランは「メモリ 2GBプラン」 (CPU 3コア、メモリ 2GB、HDD 200GB) です。
ContOS 7 インストール直後に UnixBench を利用してサーバ性能 (パフォーマンス) を計測してみました。
@see 「UnixBench のインストール (CentOS 7)」
1. UnixBench 測定結果
比較対象は、MacBook Air Mid 2012 の VirtualBox 上に構築した ContOS 7 です。
| テスト項目 |
お名前.com |
【参考】MBA 2012 |
| single |
multi |
single |
multi |
| Dhrystone 2 using register variables |
3112.0 |
9213.4 |
1061.8 |
2093.1 |
| Double-Precision Whetstone |
823.9 |
2496.3 |
287.2 |
567.7 |
| Execl Throughput |
713.1 |
2540.6 |
133.9 |
323.8 |
| File Copy 1024 bufsize 2000 maxblocks |
3015.5 |
2364.7 |
856.4 |
1532.5 |
| File Copy 256 bufsize 500 maxblocks |
1937.7 |
1925.5 |
589.2 |
1024 |
| File Copy 4096 bufsize 8000 maxblocks |
5326.9 |
4146.2 |
1674.7 |
2929.1 |
| Pipe Throughput |
1361.2 |
4038.6 |
457.7 |
918.3 |
| Pipe-based Context Switching |
889.1 |
2244.6 |
9.3 |
108.8 |
| Process Creation |
707.6 |
2975.2 |
133.6 |
421.3 |
| Shell Scripts (1 concurrent) |
1634.1 |
3567.6 |
374.0 |
554.1 |
| Shell Scripts (8 concurrent) |
3485.7 |
3852.8 |
636.0 |
663.5 |
| System Call Overhead |
1776.4 |
2537.4 |
591.1 |
1009.5 |
|
|
|
|
|
| System Benchmarks Index Score |
1676.6 |
3172.0 |
344.1 |
741.5 |
2. 【参考】 サーバスペック
|
お名前.com |
【参考】MBA 2012 |
| OS |
CentOS 7 64bit |
CentOS 7 64bit |
| Kernel |
3.10.0-123.el7.x86_64 |
3.10.0-123.20.1.el7.x86_64 |
| CPU |
Intel(R) Core(TM)2 Duo T7700 |
Intel(R) Core(TM) i5-3427U |
| CPU Clock |
2.40 GHz |
1.80 GHz |
| CPU BogoMips |
5200.0 |
4598.0 |
| CPU 数 |
3 CPU |
2 CPU |
| Memory |
2 GB |
2 GB |
| 備考 |
お名前.com VPS(KVM) で稼働 |
VirtualBox 上で稼働 |
3. 【参考】 出力ログ
3.1. システム情報
お名前.com
BYTE UNIX Benchmarks (Version 5.1.3)
System: xxxxxxxxxxxxxxx: GNU/Linux
OS: GNU/Linux -- 3.10.0-123.el7.x86_64 -- #1 SMP Mon Jun 30 12:09:22 UTC 2014
Machine: x86_64 (x86_64)
Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
CPU 0: Intel(R) Core(TM)2 Duo CPU T7700 @ 2.40GHz (5200.0 bogomips)
x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
CPU 1: Intel(R) Core(TM)2 Duo CPU T7700 @ 2.40GHz (5200.0 bogomips)
x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
CPU 2: Intel(R) Core(TM)2 Duo CPU T7700 @ 2.40GHz (5200.0 bogomips)
x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
21:31:49 up 36 min, 2 users, load average: 0.08, 0.04, 0.05; runlevel 3
【参考】MBA 2012
BYTE UNIX Benchmarks (Version 5.1.3)
System: xxxxxxxxxxxxxxx: GNU/Linux
OS: GNU/Linux -- 3.10.0-123.20.1.el7.x86_64 -- #1 SMP Thu Jan 29 18:05:33 UTC 2015
Machine: x86_64 (x86_64)
Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
CPU 0: Intel(R) Core(TM) i5-3427U CPU @ 1.80GHz (4598.0 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
CPU 1: Intel(R) Core(TM) i5-3427U CPU @ 1.80GHz (4598.0 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
19:32:25 up 1:00, 2 users, load average: 0.00, 0.01, 0.09; runlevel 3
3.2 同時処理数： Single
お名前.com
3 CPUs in system; running 1 parallel copy of tests
Dhrystone 2 using register variables 36316545.5 lps (10.0 s, 7 samples)
Double-Precision Whetstone 4531.6 MWIPS (9.9 s, 7 samples)
Execl Throughput 3066.3 lps (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 1194126.1 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 320690.7 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 3089588.2 KBps (30.0 s, 2 samples)
Pipe Throughput 1693381.0 lps (10.0 s, 7 samples)
Pipe-based Context Switching 355659.6 lps (10.0 s, 7 samples)
Process Creation 8916.3 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 6928.7 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 2091.4 lpm (60.0 s, 2 samples)
System Call Overhead 2664578.7 lps (10.0 s, 7 samples)
System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 36316545.5 3112.0
Double-Precision Whetstone 55.0 4531.6 823.9
Execl Throughput 43.0 3066.3 713.1
File Copy 1024 bufsize 2000 maxblocks 3960.0 1194126.1 3015.5
File Copy 256 bufsize 500 maxblocks 1655.0 320690.7 1937.7
File Copy 4096 bufsize 8000 maxblocks 5800.0 3089588.2 5326.9
Pipe Throughput 12440.0 1693381.0 1361.2
Pipe-based Context Switching 4000.0 355659.6 889.1
Process Creation 126.0 8916.3 707.6
Shell Scripts (1 concurrent) 42.4 6928.7 1634.1
Shell Scripts (8 concurrent) 6.0 2091.4 3485.7
System Call Overhead 15000.0 2664578.7 1776.4
========
System Benchmarks Index Score 1676.6
【参考】MBA 2012
2 CPUs in system; running 1 parallel copy of tests
Dhrystone 2 using register variables 12391006.2 lps (10.0 s, 7 samples)
Double-Precision Whetstone 1579.4 MWIPS (10.0 s, 7 samples)
Execl Throughput 575.8 lps (29.9 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 339125.5 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 97512.2 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 971346.4 KBps (30.0 s, 2 samples)
Pipe Throughput 569399.2 lps (10.0 s, 7 samples)
Pipe-based Context Switching 3722.0 lps (10.0 s, 7 samples)
Process Creation 1683.2 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 1585.8 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 381.6 lpm (60.1 s, 2 samples)
System Call Overhead 886603.5 lps (10.0 s, 7 samples)
System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 12391006.2 1061.8
Double-Precision Whetstone 55.0 1579.4 287.2
Execl Throughput 43.0 575.8 133.9
File Copy 1024 bufsize 2000 maxblocks 3960.0 339125.5 856.4
File Copy 256 bufsize 500 maxblocks 1655.0 97512.2 589.2
File Copy 4096 bufsize 8000 maxblocks 5800.0 971346.4 1674.7
Pipe Throughput 12440.0 569399.2 457.7
Pipe-based Context Switching 4000.0 3722.0 9.3
Process Creation 126.0 1683.2 133.6
Shell Scripts (1 concurrent) 42.4 1585.8 374.0
Shell Scripts (8 concurrent) 6.0 381.6 636.0
System Call Overhead 15000.0 886603.5 591.1
========
System Benchmarks Index Score 344.1
3.3. 同時処理数： Multi
お名前.com
3 CPUs in system; running 3 parallel copies of tests
Dhrystone 2 using register variables 107519945.6 lps (10.0 s, 7 samples)
Double-Precision Whetstone 13729.5 MWIPS (9.7 s, 7 samples)
Execl Throughput 10924.6 lps (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 936415.9 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 318674.4 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 2404772.4 KBps (30.0 s, 2 samples)
Pipe Throughput 5023959.3 lps (10.0 s, 7 samples)
Pipe-based Context Switching 897831.7 lps (10.0 s, 7 samples)
Process Creation 37487.9 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 15126.4 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 2311.7 lpm (60.0 s, 2 samples)
System Call Overhead 3806127.4 lps (10.0 s, 7 samples)
System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 107519945.6 9213.4
Double-Precision Whetstone 55.0 13729.5 2496.3
Execl Throughput 43.0 10924.6 2540.6
File Copy 1024 bufsize 2000 maxblocks 3960.0 936415.9 2364.7
File Copy 256 bufsize 500 maxblocks 1655.0 318674.4 1925.5
File Copy 4096 bufsize 8000 maxblocks 5800.0 2404772.4 4146.2
Pipe Throughput 12440.0 5023959.3 4038.6
Pipe-based Context Switching 4000.0 897831.7 2244.6
Process Creation 126.0 37487.9 2975.2
Shell Scripts (1 concurrent) 42.4 15126.4 3567.6
Shell Scripts (8 concurrent) 6.0 2311.7 3852.8
System Call Overhead 15000.0 3806127.4 2537.4
========
System Benchmarks Index Score 3172.0
【参考】MBA 2012
2 CPUs in system; running 2 parallel copies of tests
Dhrystone 2 using register variables 24426548.5 lps (10.0 s, 7 samples)
Double-Precision Whetstone 3122.6 MWIPS (9.9 s, 7 samples)
Execl Throughput 1392.2 lps (29.7 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 606868.0 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 169471.0 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 1698888.7 KBps (30.0 s, 2 samples)
Pipe Throughput 1142378.7 lps (10.0 s, 7 samples)
Pipe-based Context Switching 43534.5 lps (10.0 s, 7 samples)
Process Creation 5307.9 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 2349.3 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 398.1 lpm (60.2 s, 2 samples)
System Call Overhead 1514276.7 lps (10.0 s, 7 samples)
System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 24426548.5 2093.1
Double-Precision Whetstone 55.0 3122.6 567.7
Execl Throughput 43.0 1392.2 323.8
File Copy 1024 bufsize 2000 maxblocks 3960.0 606868.0 1532.5
File Copy 256 bufsize 500 maxblocks 1655.0 169471.0 1024.0
File Copy 4096 bufsize 8000 maxblocks 5800.0 1698888.7 2929.1
Pipe Throughput 12440.0 1142378.7 918.3
Pipe-based Context Switching 4000.0 43534.5 108.8
Process Creation 126.0 5307.9 421.3
Shell Scripts (1 concurrent) 42.4 2349.3 554.1
Shell Scripts (8 concurrent) 6.0 398.1 663.5
System Call Overhead 15000.0 1514276.7 1009.5
========
System Benchmarks Index Score 741.5
[ END ]