On (Thu) Mar 11 2010 [23:45:51], Marcelo Tosatti wrote:
> Wake up iothread when buffers are consumed.
>
> Signed-off-by: Marcelo Tosatti <mtosatti@xxxxxxxxxx>
>
> Index: qemu-ioworker/hw/virtio-serial-bus.c
> ===================================================================
> --- qemu-ioworker.orig/hw/virtio-serial-bus.c
> +++ qemu-ioworker/hw/virtio-serial-bus.c
> @@ -331,6 +331,7 @@ static void handle_output(VirtIODevice *
>
> static void handle_input(VirtIODevice *vdev, VirtQueue *vq)
> {
> + qemu_notify_event(main_io_worker);
> }
ACK, the host lets us know buffers are consumed and new buffers have
been added to the pool so that we can start sending more data.
Before this patch my tests took 16m18s to run.
After this patch my tests take 1m17s to run.
Both tests done with just one buffer made available in the virtio-queues.
Amit
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
