Threads don't scale, processes do - Fibers

[Robert Jacques]

On Wed, 27 Aug 2008 12:49:50 -0400, Oliver Dathe <o.dathe at gmx.de> wrote:

> 3.) Fibers could announce blocking calls to S, so it may transfer them  
> to a specific set of Threads which are created only for the purpose of  
> getting blocked. This is to avoid impact on the fibers in 1.) and 2.)

This sounds synergistic with thin-locks. Although locking code would have  
to be moved into the thread class to allow polymorphism on how the lock's  
aquired. i.e. Thead.getThis.lock(heavy_lock)

> If someone knows of similar attempts please let me know.

I'd recommend reading about JCSP (and it's C# and C++ brethren) and occam  
/ occam-pi (see: http://www.cs.kent.ac.uk/projects/ofa/kroc/ ).