Linux - KernelThis forum is for all discussion relating to the Linux kernel.
Welcome to LinuxQuestions.org, a friendly and active Linux Community.
You are currently viewing LQ as a guest. By joining our community you will have the ability to post topics, receive our newsletter, use the advanced search, subscribe to threads and access many other special features. Registration is quick, simple and absolutely free. Join our community today!
Note that registered members see fewer ads, and ContentLink is completely disabled once you log in.
I am trying to modify the redblack tree datastructure used in 2.6.24 and above kernels to some radix tree, for my university project. I dont have a proper guidance, and therefore stuck and dont know where to start. I dont know how to solve the dependencies if I change the datastructure. Anyone with suggestions??? please??
But this is the 'better' of the two - the other should be closed and merged into this.
Originally Posted by syg00
ISTR the last fella that something like that got very disillusioned with the whole kernel dev community. His latest effort is BFS - I'll let you track down what that means for yourselves ...
Con Kolivas, IIRQ. Good for a search, anyway...
How can I evaluate the new kernel performance with reference to the actual 2.6.32 kernel? any tools?
The OP is asking about tools to evaluate kernel performance. While I honestly have doubts whether that is what is required (or, maybe, all that is required) I'll have a go at it, anyway.
Define what constitutes performance. (memory usage, execution time, latency, power consumption, 'smooth' multitasking (however you measure that), task switching efficiency and processor utilisation in a queued task environment...)
Is it the case that certain applications are more important to you than others? The consideration on the desktop are probably quite different from the consideration running a LAMP stack, so you'd want to know if you have a restricted area of application.
Have a look at Phoronix. They have a test suite and look at what they do. I'm not suggesting that you copy them, but you can understand what they do and learn from them, and a subset of their test suite might be quite useful to you. Or not, potentially, depending on the answers to the previous questions.