2002-08-23 16:02:39

by Dan Kegel

[permalink] [raw]
Subject: Re: aio-core why not using SuS? [Re: [rfc] aio-core for 2.5.29 (Re:async-io API registration for 2.5.29)]

John Gardiner Myers wrote:
>
> Dan Kegel wrote:
>
> >You can actually consider posix AIO using sigtimedwait() to pick up completion
> >notices to fit the definition of completion port if you squint a bit.
> >
> Except that signal queues are far too short to be useful for c10k. It's
> also not possible to allocate a queue (signal number) in a thread safe
> manner.
>
> Posix AIO is a horrid interface. Ben has done much better.

You're quite right. Still, posix AIO with sigtimedwait() might be enough
prior art to invalidate Microsoft's patent on completion ports.

- Dan