Re: [Qemu-devel] [RFC] dataplane: IOThreads and writing dataplane-capable code

[Stefan Hajnoczi]

On Thu, May 08, 2014 at 03:10:48PM +0200, Paolo Bonzini wrote:
> Il 08/05/2014 15:08, Kevin Wolf ha scritto:
> >Am 08.05.2014 um 12:16 hat Stefan Hajnoczi geschrieben:
> >>Side note: The main loop and IOThread are both event loops but their code is
> >>not shared completely.  Sometimes it is useful to remember that although 
> >>they
> >>are conceptually similar they are currently not interchangeable.
> >
> >We need to be careful with the terminology. The choice made here, that
> >the main loop thread is not an IOThread, is somewhat unfortunate,
> >because traditionally, the "I/O thread" has been what the main loop
> >thread is called (in contrast to vcpu threads).
> 
> Note that the main loop thread could definitely be an IOThread,
> since it has an AioContext and the IOThread is just a QOM veneer for
> AioContext.  It's just not done yet.

Yes, it's definitely a goal to unify the event loop implementations in
QEMU.  The main loop is more than just an AioContext, it's a glib event
loop.  The AioContext is a custom event loop that can be added to a glib
event loop (as a GSource) but also supports BHs and high-resolution
timers.

Stefan