"Linux2.6内核在嵌入式应用上的突破" 勘误

网上广泛流传的文章“Linux2.6内核在嵌入式应用上的突破”（原文地址：http://industry.ccidnet.com/art/321/20060919/903963_1.html， 作者：yong）其中有这样一个测试结果：
“

图1和图2显示了2.4.1内核和2.6内核在平均情况下和最坏情况下任务的响应时间。数据 来自通过一台PⅢ 1.0GHz处理器采集的310万个样本。测试使用的是带有超过5个中断的LynuxWorks的实时测试设备。系统处在由持续地磁盘数据传送、网络通 信、控制台输入、图像处理和一个定时卡组成的高负载下运行。

图1 平均响应时间

”

用这个测试结果无非就是要证明linux 2.6内核比2.4内核在实时性方面有质的进步。但是稍微仔细一点，就可以看出最坏响应时间和平均响应时间居然是一样的。 我和同事又在网上搜了一圈，同事S找到了这个结果的原始出处：
http://www.linuxdevices.com/news/NS6292137578.html
LynuxWorks' BlueCat Linux 5.0, based on a 2.6-series Linux kernel, is now available for public beta testing, with a projected final release date set for November. LynuxWorks claims this to be the first public availability of embedded Linux based on the new kernel, and touts the system's improved realtime responsiveness.

Several dozen test releases are typical prior to the first stable release of a new Linux kernel, which is currently available as "2.6.0-test4." The final release of BlueCat 5.0 may follow quite closely after the first fully stable 2.6 release, projected for October.

The following two graphs provide a comparison between the average and worst-case interrupt and task response times for Linux kernel 2.4.1 (based on BlueCat 4.1) and Linux kernel 2.6 Beta (based on BlueCat 5.0 beta). The data represent 3.1 million samples, on a 1GHz Pentium III processor. The measurements were made using LynuxWorks' real-time tests with five or more interrupting devices. The system was under a heavy load consisting of continuous disk transfers (tar/sync), network traffic (ping flood), console input, graphics activity, and a timer card.





可见，《Linux2.6内核在嵌入式应用上的突破》这篇文章的作者正是采用了这个测试结果加到他的文章里，但是很不幸，抄错了一个图。
而且这篇文章的作者还犯了一个错误，就是这个结果是在2.6内核的beta上的测试结果，而不是2.6 release版的结果。