unixbench是一个用于测试unix系统性能的工具，也是一个比较通用的benchmark， 此测试的目的是对类Unix 系统提供一个基本的性能指示，很多测试用于系统性能的不同方面，这些测试的结果是一个指数值（index value，如520），这个值是测试系统的测试结果与一个基线系统测试结果比较得到的指数值，这样比原始值更容易得到参考价值，测试集合里面所有的测试得到的指数值结合起来得到整个系统的指数值。
各项的测试有得分，然后有一个综合的得分，这样可以很方便的通过分数去比较。
源于1995 年，基线系统是“George”，一个工作站：SPARCstation 20‐61，128MB RAM，Solaris2.3，此系统的指数值被设定为10，所以，如果一个系统的最后结果分数为520，意思是指此系统比基线系统运行快52 倍。
# yum -y install wget make gcc gcc-c automake autoconf libtool gcc-c++ time SDL-devel mesa-libGL-devel
# yum -y install perl-Time-HiRes
//下载
# wget https://s3.amazonaws.com/cloudbench/software/UnixBench5.1.3.tgz -O UnixBench5.1.3.tgz
# tar xzf UnixBench5.1.3.tgz
# cd UnixBench
//修改makefile, 不进行图型测试
# sed -i "s/GRAPHIC_TESTS = defined/#GRAPHIC_TESTS = defined/g" ./Makefile
//编译
# make
//执行
# ./Run========================================================================
BYTE UNIX Benchmarks (Version 5.1.3) 腾讯双核-two-cpu
System: VM-4-10-centos: GNU/Linux
OS: GNU/Linux -- 4.18.0-80.el8.x86_64 -- #1 SMP Tue Jun 4 09:19:46 UTC 2019
Machine: x86_64 (x86_64)
Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
CPU 0: Intel(R) Xeon(R) CPU E5-26xx v4 (4788.9 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
CPU 1: Intel(R) Xeon(R) CPU E5-26xx v4 (4788.9 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
08:45:50 up 11:30, 1 user, load average: 0.00, 0.00, 0.00; runlevel 3
------------------------------------------------------------------------
Benchmark Run: Sat Nov 07 2020 08:45:50 - 09:13:43
2 CPUs in system; running 1 parallel copy of tests
Dhrystone 2 using register variables 34770141.1 lps (10.0 s, 7 samples)
Double-Precision Whetstone 6699.4 MWIPS (9.0 s, 7 samples)
Execl Throughput 4244.6 lps (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 734072.8 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 191092.0 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 2105552.2 KBps (30.0 s, 2 samples)
Pipe Throughput 1016176.7 lps (10.0 s, 7 samples)
Pipe-based Context Switching 80313.1 lps (10.0 s, 7 samples)
Process Creation 8022.0 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 6737.8 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 1333.5 lpm (60.0 s, 2 samples)
System Call Overhead 722640.4 lps (10.0 s, 7 samples)
System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 34770141.1 2979.4
Double-Precision Whetstone 55.0 6699.4 1218.1
Execl Throughput 43.0 4244.6 987.1
File Copy 1024 bufsize 2000 maxblocks 3960.0 734072.8 1853.7
File Copy 256 bufsize 500 maxblocks 1655.0 191092.0 1154.6
File Copy 4096 bufsize 8000 maxblocks 5800.0 2105552.2 3630.3
Pipe Throughput 12440.0 1016176.7 816.9
Pipe-based Context Switching 4000.0 80313.1 200.8
Process Creation 126.0 8022.0 636.7
Shell Scripts (1 concurrent) 42.4 6737.8 1589.1
Shell Scripts (8 concurrent) 6.0 1333.5 2222.4
System Call Overhead 15000.0 722640.4 481.8
========
System Benchmarks Index Score 1142.5
------------------------------------------------------------------------
Benchmark Run: Sat Nov 07 2020 09:13:43 - 09:41:37
2 CPUs in system; running 2 parallel copies of tests
Dhrystone 2 using register variables 69647445.7 lps (10.0 s, 7 samples)
Double-Precision Whetstone 13419.3 MWIPS (9.0 s, 7 samples)
Execl Throughput 8055.5 lps (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 1199878.8 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 319215.8 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 3533263.4 KBps (30.0 s, 2 samples)
Pipe Throughput 2011550.7 lps (10.0 s, 7 samples)
Pipe-based Context Switching 468206.3 lps (10.0 s, 7 samples)
Process Creation 18889.3 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 9688.1 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 1369.3 lpm (60.0 s, 2 samples)
System Call Overhead 1336514.9 lps (10.0 s, 7 samples)
System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 69647445.7 5968.1
Double-Precision Whetstone 55.0 13419.3 2439.9
Execl Throughput 43.0 8055.5 1873.4
File Copy 1024 bufsize 2000 maxblocks 3960.0 1199878.8 3030.0
File Copy 256 bufsize 500 maxblocks 1655.0 319215.8 1928.8
File Copy 4096 bufsize 8000 maxblocks 5800.0 3533263.4 6091.8
Pipe Throughput 12440.0 2011550.7 1617.0
Pipe-based Context Switching 4000.0 468206.3 1170.5
Process Creation 126.0 18889.3 1499.1
Shell Scripts (1 concurrent) 42.4 9688.1 2284.9
Shell Scripts (8 concurrent) 6.0 1369.3 2282.2
System Call Overhead 15000.0 1336514.9 891.0
========
System Benchmarks Index Score 2199.3========================================================================
BYTE UNIX Benchmarks (Version 5.1.3) ali-two-cpu
System: izj6c3wfx7kz9p75jmiimgz: GNU/Linux
OS: GNU/Linux -- 3.10.0-514.26.2.el7.x86_64 -- #1 SMP Tue Jul 4 15:04:05 UTC 2017
Machine: x86_64 (x86_64)
Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
CPU 0: Intel(R) Xeon(R) Platinum 8163 CPU @ 2.50GHz (4999.9 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
CPU 1: Intel(R) Xeon(R) Platinum 8163 CPU @ 2.50GHz (4999.9 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
09:14:12 up 36 days, 17:42, 1 user, load average: 1.03, 0.86, 0.73; runlevel 3
------------------------------------------------------------------------
Benchmark Run: Sat Nov 07 2020 09:14:12 - 09:42:27
2 CPUs in system; running 1 parallel copy of tests
Dhrystone 2 using register variables 32313341.5 lps (10.0 s, 7 samples)
Double-Precision Whetstone 3920.2 MWIPS (9.8 s, 7 samples)
Execl Throughput 3210.0 lps (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 815882.4 KBps (30.2 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 237087.7 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 2098862.2 KBps (30.0 s, 2 samples)
Pipe Throughput 1557921.6 lps (10.0 s, 7 samples)
Pipe-based Context Switching 74007.9 lps (10.0 s, 7 samples)
Process Creation 12949.7 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 6337.6 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 1330.5 lpm (60.0 s, 2 samples)
System Call Overhead 3286567.9 lps (10.0 s, 7 samples)
System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 32313341.5 2768.9
Double-Precision Whetstone 55.0 3920.2 712.8
Execl Throughput 43.0 3210.0 746.5
File Copy 1024 bufsize 2000 maxblocks 3960.0 815882.4 2060.3
File Copy 256 bufsize 500 maxblocks 1655.0 237087.7 1432.6
File Copy 4096 bufsize 8000 maxblocks 5800.0 2098862.2 3618.7
Pipe Throughput 12440.0 1557921.6 1252.3
Pipe-based Context Switching 4000.0 74007.9 185.0
Process Creation 126.0 12949.7 1027.8
Shell Scripts (1 concurrent) 42.4 6337.6 1494.7
Shell Scripts (8 concurrent) 6.0 1330.5 2217.5
System Call Overhead 15000.0 3286567.9 2191.0
========
System Benchmarks Index Score 1316.9
------------------------------------------------------------------------
Benchmark Run: Sat Nov 07 2020 09:42:27 - 10:10:53
2 CPUs in system; running 2 parallel copies of tests
Dhrystone 2 using register variables 60836526.1 lps (10.0 s, 7 samples)
Double-Precision Whetstone 7830.6 MWIPS (9.9 s, 7 samples)
Execl Throughput 6089.6 lps (29.9 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 728198.2 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 195899.3 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 1867019.9 KBps (30.0 s, 2 samples)
Pipe Throughput 2820751.0 lps (10.0 s, 7 samples)
Pipe-based Context Switching 505530.3 lps (10.0 s, 7 samples)
Process Creation 18392.5 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 8729.9 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 1359.1 lpm (60.0 s, 2 samples)
System Call Overhead 3643952.0 lps (10.0 s, 7 samples)
System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 60836526.1 5213.1
Double-Precision Whetstone 55.0 7830.6 1423.7
Execl Throughput 43.0 6089.6 1416.2
File Copy 1024 bufsize 2000 maxblocks 3960.0 728198.2 1838.9
File Copy 256 bufsize 500 maxblocks 1655.0 195899.3 1183.7
File Copy 4096 bufsize 8000 maxblocks 5800.0 1867019.9 3219.0
Pipe Throughput 12440.0 2820751.0 2267.5
Pipe-based Context Switching 4000.0 505530.3 1263.8
Process Creation 126.0 18392.5 1459.7
Shell Scripts (1 concurrent) 42.4 8729.9 2058.9
Shell Scripts (8 concurrent) 6.0 1359.1 2265.1
System Call Overhead 15000.0 3643952.0 2429.3
========
System Benchmarks Index Score 1973.5
通常执行时间要20~30分钟左右 , 有点久😂~~
一般单核跑分1000+为优秀, 800+为一般, 500- 为差
速度测试软件可以参考这篇文章:speedtest-centos网络测速
网络路由追踪可以参考这篇文章:BestTrace路由追踪软件
CN2网络介绍可以查看这篇文章:中国电信CN2 GT、CN2 GIA、ChinaNet线路介绍
