Re: something to experiment with: LIFO and accept()

Alan Cox (
Wed, 9 Apr 1997 23:37:47 +0100 (BST)

> It's my suspicion that if accept() woke up the last process to
> block on it then there'd be a performance improvement for servers
> Seems like a good idea, only two things concern me:
> 1) What if anything do the "standards" say about this?

POSIX 1003.1g draft 6.4 says nothing, and makes no 'fairness' guarantee.

> 2) There could be the possibility of starvation under some
> corener cases, this needs to be investigated.

That is the hard part of a wake_one semantic. We must wake_one who will
always complete or wake another