unixbench

1。測出 linux 系統整體的效能
2。結果不只取決於硬體,系統及libraries、compiler都有關系

unixbench 現在在 http://code.google.com/p/byte-unixbench/ 生活著

也已出到 5.1.3 版本了,比 4 版 多了測試顯示的功能

測試的硬體規格:

。Intel(R) Pentium(R) CPU G6950 2.80GHz
。RAM: 2G
。CentOS 5.6

我用 4.1 版及  5.1.3 版測,4 版的分數竟是 0

測試所花的時間快一個小時,真久!

4.1 版的分數

                     INDEX VALUES
TEST                                        BASELINE     RESULT      INDEX

Dhrystone 2 using register variables        116700.0 15441218.3     1323.2
Double-Precision Whetstone                      55.0     3055.3      555.5
Execl Throughput                                43.0        0.0        0.0
File Copy 1024 bufsize 2000 maxblocks         3960.0   592308.0     1495.7
File Copy 256 bufsize 500 maxblocks           1655.0   177533.0     1072.7
File Copy 4096 bufsize 8000 maxblocks         5800.0  1224604.0     2111.4
Pipe Throughput                              12440.0  1180382.9      948.9
Process Creation                               126.0    10370.2      823.0
Shell Scripts (8 concurrent)                     6.0     1957.0     3261.7
System Call Overhead                         15000.0   965449.5      643.6
=========
FINAL SCORE                                                       0.0

real    52m10.323s
user    19m51.941s
sys     24m45.498s

5.1.3 版

不知為何有兩個分數,是因為雙核的關系嗎 !?

————————————————————————
Benchmark Run: 六  9月 17 2011 22:12:18 – 22:40:50
2 CPUs in system; running 1 parallel copy of tests

Dhrystone 2 using register variables       15587038.5 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     3078.7 MWIPS (9.9 s, 7 samples)
Execl Throughput                               3924.5 lps   (29.7 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        594677.3 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks          178827.4 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks       1245328.8 KBps  (30.0 s, 2 samples)
Pipe Throughput                             1197015.9 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                 228417.8 lps   (10.0 s, 7 samples)
Process Creation                              11341.3 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                   4149.9 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                   1838.3 lpm   (60.0 s, 2 samples)
System Call Overhead                         979365.3 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0   15587038.5   1335.7
Double-Precision Whetstone                       55.0       3078.7    559.8
Execl Throughput                                 43.0       3924.5    912.7
File Copy 1024 bufsize 2000 maxblocks          3960.0     594677.3   1501.7
File Copy 256 bufsize 500 maxblocks            1655.0     178827.4   1080.5
File Copy 4096 bufsize 8000 maxblocks          5800.0    1245328.8   2147.1
Pipe Throughput                               12440.0    1197015.9    962.2
Pipe-based Context Switching                   4000.0     228417.8    571.0
Process Creation                                126.0      11341.3    900.1
Shell Scripts (1 concurrent)                     42.4       4149.9    978.7
Shell Scripts (8 concurrent)                      6.0       1838.3   3063.8
System Call Overhead                          15000.0     979365.3    652.9
========
System Benchmarks Index Score                                        1072.0

————————————————————————
Benchmark Run: 六  9月 17 2011 22:40:50 – 23:09:25
2 CPUs in system; running 2 parallel copies of tests

Dhrystone 2 using register variables       32247456.4 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     6401.8 MWIPS (9.9 s, 7 samples)
Execl Throughput                              11189.3 lps   (29.6 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        331133.8 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks           98082.2 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks       1078543.2 KBps  (30.0 s, 2 samples)
Pipe Throughput                             2474684.8 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                 785465.9 lps   (10.0 s, 7 samples)
Process Creation                              33406.3 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                  14822.3 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                   2070.9 lpm   (60.0 s, 2 samples)
System Call Overhead                        1916200.7 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0   32247456.4   2763.3
Double-Precision Whetstone                       55.0       6401.8   1164.0
Execl Throughput                                 43.0      11189.3   2602.2
File Copy 1024 bufsize 2000 maxblocks          3960.0     331133.8    836.2
File Copy 256 bufsize 500 maxblocks            1655.0      98082.2    592.6
File Copy 4096 bufsize 8000 maxblocks          5800.0    1078543.2   1859.6
Pipe Throughput                               12440.0    2474684.8   1989.3
Pipe-based Context Switching                   4000.0     785465.9   1963.7
Process Creation                                126.0      33406.3   2651.3
Shell Scripts (1 concurrent)                     42.4      14822.3   3495.8
Shell Scripts (8 concurrent)                      6.0       2070.9   3451.5
System Call Overhead                          15000.0    1916200.7   1277.5
========
System Benchmarks Index Score                                        1809.4

real    57m7.387s
user    28m38.594s
sys     36m40.151s

 

Related posts 相關文章
升級 AlmaLinux 8.4 到 AlmaLinux 8.5
More...
Google 對於 Linux 的高效能調校實作
More...
可以督促你快點升級 PHP 7.4 的測試報告
More...
硬碟分割方式 2016
More...

作者

留言

撰寫回覆或留言

發佈留言必須填寫的電子郵件地址不會公開。