Re: io pipe refactoring

On Thu, 2003-01-09 at 13:33, Henrik Nordstrom wrote:
> Like it, except for the small detail that some effort should perhaps be
> put into filtering of the pipe use not trigger a comm loop for events
> already processed.
>
> I fully agree that the mechanism whereby a subsytem can signal a async
> event which needs to be polled from the comm loop separate from
> filedescriptors indeed is a core component. Also allows for better
> abstraction on different architectures (pipes is just one of many
> alternatives for such signal).

Yep :}.

Ok, I'll apply this shortly, and we can improve from there.
Rob

-- 
GPG key available at: <http://users.bigpond.net.au/robertc/keys.txt>.