On Tue, 7 Jun 2011, Sarah Sharp wrote: > > > Also, what about USB 3.0 devices, where multiple max packets can be > > > burst at one time? The devices that set bMaxBurst are required to set > > > the max packet size to a fixed value. I think USB 3.0 isochronous > > > devices can do bursts, but I would have to check. > > > > Yes, bursting might complicate the issue. Still, drivers should be > > able to tell the scheduling code how much of the potential bandwidth > > they actually intend to use. > > Yes, and the endpoints that benefit most from bursting (bulk endpoints) > won't count against the bus bandwidth. The transfers will just be fit > in as necessary. For SuperSpeed periodic endpoints, the wBytePerInterval field in the endpoint companion descriptor could be adjusted. However I'm not aware of any bandwidth-limited SuperSpeed applications that could benefit from this... The most interesting case is high-speed high-bandwidth isochronous endpoints (i.e., bits 11-12 are set in the wMaxPacketSize field). The bus protocol requires that each packet except the last have size equal to the maxpacket value. This means that all you could do is reduce the multiplicity count, which is a rather awkward restriction -- changing bits 0-10 would break multi-transaction transfers. The facility could have some limited use for non-high-bandwidth isochronous endpoints (which includes all full-speed endpoints). > > > I'm more interested in making sure that the drivers that use a different > > > polling interval than advertised in the endpoint descriptors are able to > > > change the xHCI interval. > > > > Why would a driver want to use a different interval? Generally > > speaking, with isochronous transfers you _can't_ reasonably change the > > interval. With interrupt transfers you can, but the only effect is to > > decrease latency -- why wouldn't the latency in the descriptor be > > adequate? It turns out that this isn't quite right either. 5.6.4 in the USB-2.0 spec says: "However, an isochronous endpoint must be prepared to handle poll rates faster than the one specified." So it is valid to use periods smaller than the descriptor says (although again, I can't think of any occasions where you would want to). On the other hand, it's not valid to use periods that are longer. 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
