On Thu, 18 Dec 2014, Udo van den Heuvel wrote: > > If the airspy sends 20 million samples per second to the host and each > > sample is 2 bytes, then the host would have to receive 40 MB/s of data > > from the airspy. As I mentioned before, the usbmon trace showed that > > the actual transfer rate was about 24 MB/s. > > That is weird or an issue or what? It is an issue, because you wanted to get 40 MB/s but you only got 24 MB/s. To put it another way, you expected to receive 10 million samples per second but you only received about 6 million samples per second. > > 40 MB/s is a little beyond the limit of what most EHCI host controllers > > are able to handle, although an xHCI host controller ought to be able > > to do it. > > The device is usb2. In theory, USB-2 can transfer up to 52 MB/s (that is, 13312000 samples per second). In practice, most EHCI hardware can't do more than about 32 MB/s (that is, about 8 million samples per second). xHCI hardware can come closer to the 52 MB/s limit when connected to a USB-2 device. Alan Stern -- To unsubscribe from this list: send the line "unsubscribe linux-usb" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
