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

[Paolo Bonzini]

Il 08/05/2014 13:56, Stefan Hajnoczi ha scritto:
> > > Is dataplane the only user for this now?
> Yes, and neither dataplane (x-data-plane=on) nor IOThread (-object
> iothread,id=<name>) are finalized.
>
> There was a discussion about -object and QOM on the mailing list a
> while back.  We reached the conclusion that -object shouldn't be a
> supported command-line interface, it should be used for testing,
> development, etc.  So an -iothread option still needs to be added.

Actually I think that wasn't the conclusion.

"-object" is a supported command-line interface; we also support 
hotplug/unplug nowadays for it, and the implementation makes QMP 
entirely typesafe unlike netdev_add and device_add.  We're using it for 
iothreads and virtio-rng backends, and we'll add memory backends in 2.1.

However, the agreement was that "QMP methods" are the preferred 
interface to work with objects.  Properties and qom-get/qom-set are not 
the way to build a command-line interface.

Paolo