On Tue, Mar 09, 2010 at 05:30:09PM +0200, Felipe Balbi wrote: > On Tue, Mar 09, 2010 at 07:22:42AM -0800, Greg KH wrote: > > Sure, I understand, but it seems like it is easier to fix the existing > > code for these minor things, than to write a whole new driver, right? > > > > If you do that, then the existing users will also benifit from those > > changes. > > and dig through the whole TTY code ?!? Waaay too many memcpy() like I > replied to Alan Stern :-s I _really_ doubt that memcpy is the slow path for a USB transfer. The line speeds of USB really would seem to not justify this at all. Have you benchmarked and run the perf tools on the tty layer that shows this inefficiency? Last I checked, we could run 10Gb line speeds with the tty layer involved on top of the network stack. And again, if the tty layer is a speed problem, well, let's fix it then. thanks, greg k-h -- 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
