Indeed, linuxthreads do end up calling sigsuspend() when they fail to
acquire a mutex within a given time, and will/might receive a signal when
the mutex becomes available again. So at this level, there is kernel
level synchronization going on.
I need to think some more, obviously (!! :), about whether this is
enough to ensure correct order scheduling of a threaded pipeline on an
MP machine.
--p
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/