[M3devel] userthreads vs. pthreads performance?

[Dragiša Durić]

Fast glance shows there is no overhead in code? Just passthrough of
MUTEX field to pthread_mutex_lock()? And inefficiency comes from there?

On Sun, 2010-03-28 at 12:55 -0400, Tony Hosking wrote:
> Yes, we need to implement thin locks and biased locks.  These have
> minimal overhead for locks held mostly by just one thread.
-- 
Dragiša Durić <dragisha at m3w.org>