[Mono-devel-list] PATCH: reworked async IO for Socket

[Miguel de Icaza]

> >Miguel told me that the performance issue will appear when, say,
> >thousands of sockets have to be passed to/from kernel/user space.
> 
> And you believed him?  Why? ;-)
> 
> There has been plenty of work on this sort of thing - google
> for c10k.
> 
> The bottom line is that more modern interfaces like kqueue on
> *BSD and /dev/epoll make this problem (of the socket passing)
> go away.

I was explaining why async IO is used instead of poll/select.  The C10k
page is interesting nonetheless.

Epool, kqueue and async IO all share the same problem: they are barely
portable.

Miguel