Just out of curiosity -- where do you want to get the not publicly available L4 x86-assembly kernel from to actually being able to redo the measurements? It is intellectual property of a company and not downloadable anywhere.
I think I already have it. Otherwise, I'll make sure to contact you personally.
Furthermore, if you redo the measurements on different hardware and you read the "On mk construction" paper you should know that MKs (at least L4 MKs) are highly optimized for one particular architecture. Hence, even when having the kernel and running it on different hardware your numbers are bogus and do not state anything except that you get a set of more numbers...
Well, I was under imperssion that L4 is highly optimized for a processor (CPU), but not an PCI2ISA bridge or hard drive bandwidth. Am I missing something? Please let me know, so that I don't waste my time.
From that perspective it is nice to see your arguments for reproducibility of measurements and on the other that you completely ignore the fact that you have no setup to actually do it. So I'm curious what new findings you are going to have...
Well, it seems that you might just have to wait. I would be happy to post results before I tests, but sorry, I do have have these yet.
BTW, binaries were for 1.2 kernel, but I managed to roll back some changes from current CVS repository (surely with help of binaries+sources) and produced working 2.0 kernel. Thank you Jean.
Later.