> > Well, I think I'm getting closer to finding what's causing the > > Solaris strangeness; for one, it appears that sometimes the LWP > > or Reader gets stuck, and so WasteTime() gets called an awful > > lot. A side effect seems to be the creation of several hundred > > threads. :) > > Wow -- there is some *strange* shit going on over there. Have you taken > a look at the solaris implementation of all the Thread/Mutex/Semaphore > stuff? Yeah, I have. With the difference of everything that says 'linux' saying 'solaris' instead, minor differences in spacing, and the fact that the solaris bit does pthread_mutexattr_settype(&attr, PTHREAD_MUTEX_ERRORCHECK); if under Sol 2.7, the two sources are identical. I'm gonna try disabling the errorcheck mutexen, but I ain't hopeful that it'll do much good.