Does the example work under native threads for Java Linux? Green threads
don't (AFAIK) have anything to do with kernel threads, and so are not
limited by any thread limits in the kernel or pthreads library. The
kernel will simply see all the threads as a single process. There may
be limits to the number of green threads, but this would be in the
implementation of green threads in the JDK, and a JDK developer would have
answer that because I don't know much about the green threads implementation.
And so the chronicles report that Patrick W. O'Neill spake thusly unto the masses:
>
> I don't *NEED* to, I realize there are better ways to compute Fibonacci,
> if computing Fibonacci was all I cared about. I just *WANT* to because I
> am benchmarking some multithreaded implementations, Java included, and
> Fibonacci, although a contrived example, gives a good indication of thread
> overhead because there is very little computation involved in each thread.
>
> Could a possible cause be the max threads limit on the machine being
> reached? I have a similar problem with P-Threads, however not until a
> much higher instance of Fib than 6.
>
> - Pat
>
--
¤--------------------------------------------------------------------¤
| Aaron Gaudio mailto:[EMAIL PROTECTED] |
| http://www.rit.edu/~adg1653/ |
¤--------------------------------------------------------------------¤
| "The fool finds ignorance all around him. |
| The wise man finds ignorance within." |
¤--------------------------------------------------------------------¤
Use of any of my email addresses is subject to the terms found at
http://www.rit.edu/~adg1653/email.shtml. By using any of my addresses, you
agree to be bound by the terms therein.
