Linode更新8核心后的测试结果(Unixbench及编译速度)

[molinxx]

Benchmark Run: Tue Mar 19 2013 03:37:21 - 04:05:31
8 CPUs in system; running 8 parallel copies of tests

Dhrystone 2 using register variables 68946736.6 lps (10.0 s, 7 samples)
Double-Precision Whetstone 14379.4 MWIPS (9.3 s, 7 samples)
Execl Throughput 3942.2 lps (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 361703.9 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 101080.3 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 1259278.7 KBps (30.0 s, 2 samples)
Pipe Throughput 1750269.3 lps (10.0 s, 7 samples)
Pipe-based Context Switching 265448.1 lps (10.0 s, 7 samples)
Process Creation 7710.0 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 9105.4 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 1168.8 lpm (60.2 s, 2 samples)
System Call Overhead 2028309.7 lps (10.0 s, 7 samples)

System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 68946736.6 5908.0
Double-Precision Whetstone 55.0 14379.4 2614.4
Execl Throughput 43.0 3942.2 916.8
File Copy 1024 bufsize 2000 maxblocks 3960.0 361703.9 913.4
File Copy 256 bufsize 500 maxblocks 1655.0 101080.3 610.8
File Copy 4096 bufsize 8000 maxblocks 5800.0 1259278.7 2171.2
Pipe Throughput 12440.0 1750269.3 1407.0
Pipe-based Context Switching 4000.0 265448.1 663.6
Process Creation 126.0 7710.0 611.9
Shell Scripts (1 concurrent) 42.4 9105.4 2147.5
Shell Scripts (8 concurrent) 6.0 1168.8 1947.9
System Call Overhead 15000.0 2028309.7 1352.2
========
System Benchmarks Index Score 1397.4
===============
APACHE make -j8编译速度11m03s
以上测试使用Linode东京节点512Plan Debian 6

[tarsier]

已经更新cpu了？我那台还是l5520

[molinxx]

@tarsier L5520没错，换成8 share cores了。性能大大增强了~很给力~

[zhangxiao]

咋看出来更新了，我的那台貌似还是4core

[molinxx]

@zhangxiao 重启之后就能看到了

[zhangxiao]

@molinxx 好... 不过重启一次有点累啊 :-|

[iZr]

我也是8了。cpu是快了。线路呢？

[Ebola]

http://code.mglinski.com/X3ps/30zoh6Yf

[molinxx]

@iZr 线路没有什么改变，日本普遍是100M的端口，加州节点已经上升到300M端口了，伦敦现在是G口~