Subj : Re: recursive mutexes
To   : comp.programming.threads
From : Markus Elfring
Date : Thu May 19 2005 10:48 pm

> I've yet to see one generally usable. But I understand that such a generally usable
> lock-free method cannot exist.

Software libraries exist that can be used for basic data structures in key parts of an
application to increase concurrent/parallel execution.
The set of usable choices will grow for specific processor and operating systems in the
(near) future.


> My measurements are not that sophisticated, I simply measure the net effect
> by timing the elapsed clock ticks after doing some million iterations in a loop.
> I have also overlooked same papers on this to see its complexity and
> weighted their limitations and their advantages. In the end I came to the conclusion
> that it's not suitable for general use, too complicated, too costly in terms of
execution
> and too limited in their use. I concluded that it wasn't worth to invest more time on
this.

Example:
Did you read the thesis "Efficient and Practical Non-Blocking Data Structures"
(http://www.cs.chalmers.se/~phs/phd.pdf, 1414 KB) by Håkan Sundell?
This paper contains an analysis on scalability for more than a 2 CPU hardware that you can
test your approach on.

A few other developers are working on implementations for non-blocking synchronization
that will make it possible to adjust the views and opinions that this topic seems to be
"voodoo magic".

Regards,
Markus

.