James Carlson wrote:
Yes, of course there'd be "kernel involvement" if you had an implementation of async I/O. The original topic of discussion, though, was the implementation of a kernel interface to sockets.
I really should reread the original before mouthing off, shouldn't I :-) Mea culpa. In my defense, having an application-level implementation would shake out a good proportion of the issues needed to do a kernel-level variant of such a service. It'd be nice to do a proper ksocket interface first (for traditional, synchronous access) of course - unless that has snuck in while I wasn't watching. Cheers, Jeremy Harris _______________________________________________ networking-discuss mailing list [email protected]
