ConoHa の900円VPS サーバーのベンチマークを取ってみた。
UnixBench を使用。
Benchmark of www.makotoiwasaki.com / GNU/Linux on Tue Mar 21 2017
BYTE UNIX Benchmarks (Version 5.1.3)
Test System Information
System: | www.makotoiwasaki.com: GNU/Linux | |
OS: | GNU/Linux -- 3.10.0-514.10.2.el7.x86_64 -- #1 SMP Fri Mar 3 00:04:05 UTC 2017 | |
Machine: | x86_64: x86_64 | |
Language: | en_US.utf8 (charmap="UTF-8", collate="UTF-8") | |
CPUs: | 0: | Intel(R) Xeon(R) CPU E5-2660 v3 @ 2.60GHz (5200.0 bogomips) x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET |
1: | Intel(R) Xeon(R) CPU E5-2660 v3 @ 2.60GHz (5200.0 bogomips) x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET | |
Uptime: | 17:02:19 up 4 days, 6:47, 2 users, load average: 0.08, 0.08, 0.12; runlevel 3 |
Benchmark Run: 2 CPUs; 1 parallel process
Time: 17:02:19 - 17:30:25; 28m 06s
System Benchmarks
Test | Score | Unit | Time | Iters. | Baseline | Index |
---|---|---|---|---|---|---|
Dhrystone 2 using register variables | 30943394.3 | lps | 10.0 s | 7 | 116700.0 | 2651.5 |
Double-Precision Whetstone | 3876.7 | MWIPS | 9.9 s | 7 | 55.0 | 704.9 |
Execl Throughput | 2436.2 | lps | 29.6 s | 2 | 43.0 | 566.6 |
File Copy 1024 bufsize 2000 maxblocks | 1070685.8 | KBps | 30.0 s | 2 | 3960.0 | 2703.8 |
File Copy 256 bufsize 500 maxblocks | 284783.2 | KBps | 30.0 s | 2 | 1655.0 | 1720.7 |
File Copy 4096 bufsize 8000 maxblocks | 2790774.9 | KBps | 30.0 s | 2 | 5800.0 | 4811.7 |
Pipe Throughput | 1734057.9 | lps | 10.0 s | 7 | 12440.0 | 1393.9 |
Pipe-based Context Switching | 332145.3 | lps | 10.0 s | 7 | 4000.0 | 830.4 |
Process Creation | 7487.1 | lps | 30.0 s | 2 | 126.0 | 594.2 |
Shell Scripts (1 concurrent) | 5771.9 | lpm | 60.0 s | 2 | 42.4 | 1361.3 |
Shell Scripts (8 concurrent) | 1415.3 | lpm | 60.0 s | 2 | 6.0 | 2358.8 |
System Call Overhead | 3243526.3 | lps | 10.0 s | 7 | 15000.0 | 2162.4 |
System Benchmarks Index Score: | 1483.0 |
Benchmark Run: 2 CPUs; 2 parallel processes
Time: 17:30:25 - 17:58:33; 28m 08s
System Benchmarks
Test | Score | Unit | Time | Iters. | Baseline | Index |
---|---|---|---|---|---|---|
Dhrystone 2 using register variables | 63896922.0 | lps | 10.0 s | 7 | 116700.0 | 5475.3 |
Double-Precision Whetstone | 8002.4 | MWIPS | 9.9 s | 7 | 55.0 | 1455.0 |
Execl Throughput | 7521.4 | lps | 29.9 s | 2 | 43.0 | 1749.2 |
File Copy 1024 bufsize 2000 maxblocks | 1577049.4 | KBps | 30.0 s | 2 | 3960.0 | 3982.4 |
File Copy 256 bufsize 500 maxblocks | 446353.3 | KBps | 30.0 s | 2 | 1655.0 | 2697.0 |
File Copy 4096 bufsize 8000 maxblocks | 3532943.0 | KBps | 30.0 s | 2 | 5800.0 | 6091.3 |
Pipe Throughput | 3541496.0 | lps | 10.0 s | 7 | 12440.0 | 2846.9 |
Pipe-based Context Switching | 689556.1 | lps | 10.0 s | 7 | 4000.0 | 1723.9 |
Process Creation | 26117.0 | lps | 30.0 s | 2 | 126.0 | 2072.8 |
Shell Scripts (1 concurrent) | 9224.3 | lpm | 60.0 s | 2 | 42.4 | 2175.6 |
Shell Scripts (8 concurrent) | 1550.9 | lpm | 60.0 s | 2 | 6.0 | 2584.9 |
System Call Overhead | 4712350.7 | lps | 10.0 s | 7 | 15000.0 | 3141.6 |
System Benchmarks Index Score: | 2719.8 |
GCE 、Google Compute Engine の f1-micro など、使いものにならないようだ。