Re: [Qemu-devel] Performance issues with -usb

[Lonnie Mendez]

On Mon, 2006-07-24 at 13:06 +0400, Brad Campbell wrote:
> G'day all,
> 
> Just a diary note or similar.
> 
> I've been playing with skype under win2k under qemu with -kernel-kqemu and 
> the alsa audio driver.
> 
> 1st. The user-net driver appears to be a problem for skype but the tap driver 
> works nicely.
> 
> 2nd. I was having awful problems with the audio. The app was reporting 
> failures of either the dac or 
> adc apparently randomly and when it did work it was rather intermittent.
> 
> I noticed that with -usb -usbdevice tablet that qemu sits at about 20% cpu 
> usage (on this machine 
> which is a Pentium-M 1.2G which idles at 600Mhz) whereas without -usb qemu 
> idles completely.
> 
> In addition to this, without -usb.. skype works almost perfectly. There is 
> the occasional audio 
> glitch (as you would expect) but it does everything it is supposed to do 
> quite nicely.
> 
> I'm using all the latest gear. A 2.6.18-rc2 host kernel, Latest Qemu CVS and 
> the -pre9 kernel 
> accelerator. Win2k SP4 as a guest with either 256 or 384M of ram depending on 
> my mood :)
> 
> I'm going to have a dig around in the USB stuff when I get the chance, but 
> it's more of a fyi and 
> for google that I post it here.

   Perhaps tweaking the value of ep_bInterval for the tablet's status
change endpoint would help?  The endpoint descriptor for the tablet
currently has this at 3 milliseconds.  The hid mouse reports a 10
millisecond polling interval.

excerpt from qemu_tablet_config_descriptor in hw/usb-hid.c:

        /* one endpoint (status change endpoint) */
        0x07,       /*  u8  ep_bLength; */
        0x05,       /*  u8  ep_bDescriptorType; Endpoint */
        0x81,       /*  u8  ep_bEndpointAddress; IN Endpoint 1 */
        0x03,       /*  u8  ep_bmAttributes; Interrupt */
        0x08, 0x00, /*  u16 ep_wMaxPacketSize; */
        0x03,       /*  u8  ep_bInterval; (255ms -- usb 2.0 spec) */