RHEL5がまだリリースされそうに無いため気晴らしにベンチマーク を採ってみる
環境
CPU:Cel@1.4GHz
Mem:320MB
ベンチソフト
UNIXBench Version 4.1.0
RHEL4 ES U4
TEST | BASELINE | RESULT | INDEX |
Dhrystone 2 using register variables | 116700.0 | 2374371.6 | 203.5 |
Double-Precision Whetstone | 55.0 | 564.1 | 102.6 |
Execl Throughput | 43.0 | 689.8 | 160.4 |
File Copy 1024 bufsize 2000 maxblocks | 3960.0 | 125484.0 | 316.9 |
File Copy 256 bufsize 500 maxblocks | 1655.0 | 52745.0 | 318.7 |
File Copy 4096 bufsize 8000 maxblocks | 5800.0 | 158915.0 | 274.0 |
Pipe Throughput | 12440.0 | 321438.6 | 258.4 |
Pipe-based Context Switching | 4000.0 | 98206.8 | 245.5 |
Process Creation | 126.0 | 2108.6 | 167.3 |
Shell Scripts (8 concurrent) | 6.0 | 130.7 | 217.8 |
System Call Overhead | 15000.0 | 240709.6 | 160.5 |
========= | |||
FINAL SCORE | 209.6 |
RHEL5 Server
TEST | BASELINE | RESULT | INDEX |
Dhrystone 2 using register variables | 116700.0 | 2461248.9 | 210.9 |
Double-Precision Whetstone | 55.0 | 632.9 | 115.1 |
Execl Throughput | 43.0 | 648.3 | 150.8 |
File Copy 1024 bufsize 2000 maxblocks | 3960.0 | 124151.0 | 313.5 |
File Copy 256 bufsize 500 maxblocks | 1655.0 | 41302.0 | 249.6 |
File Copy 4096 bufsize 8000 maxblocks | 5800.0 | 229527.0 | 395.7 |
Pipe Throughput | 12440.0 | 240572.6 | 193.4 |
Pipe-based Context Switching | 4000.0 | 64629.4 | 161.6 |
Process Creation | 126.0 | 1722.7 | 136.7 |
Shell Scripts (8 concurrent) | 6.0 | 137.0 | 228.3 |
System Call Overhead | 15000.0 | 197569.7 | 131.7 |
========= | |||
FINAL SCORE | 193.9 |
結果はRHEL4の方がやっぱりスコアは高いです。
RHEL4のベースがFedora3なのに対し
RHEL5はベースがFedora5となるわけですがどうなんでしょう?
RHEL5はpipe処理が弱いようですw
それ以外はどうなんでしょw
と、おもっていたら発売決定しちゃいました・・・