Subj : Re: Windows Suspend/ResumeThread API equivalent for Linux or POSIX?
To   : comp.programming.threads
From : Chris Thomasson
Date : Wed May 11 2005 07:25 pm

> I don't really understand what Chris' is doing here because I'm not
> familiar with this "hazard-pointers" (although I already heard of
> this term and I know that it has to do with lock-free algorithms);

Here is a paper describing the original SMR algorithm:

http://www.research.ibm.com/people/m/michael/ieeetpds-2004.pdf


> but I implemented a lock-free stack some time ago on Win32/x86.

Yes, I believe it used SEH to handle the problems with freeing it's nodes?




> And I vaguely suppose that this suspension is done in case of a
> collision between two threads which isn't impossible, but usually
> very unlikely (at least with my stack).

For this tweaked version of SMR I need to suspend the threads in order to 
get a snapshot of there current context, at least on windows.




> So isn't it possible that
> this suspension statistically needs a very small amount of compu-
> tation-time because it is done very rare ?

Yes. About every five seconds for read-mostly collections.

.