Jean Tourrilhes wrote:
>
> Hi,
>
> I've got a questions for the USB gurus... What is the minimum
> or typical round trip time of a USB bulk transfer ?
> (BTW, I'm not on the list...)
>
> Let's take an example...
> My driver has 2 bulk pipes, in and out. The transfer is
> assumed to be a single TD (typical 24 bytes) in both ways.
> The timeline looks like :
> t1 : USB device has data, start pushing it to host via 'in'
> t2 : USB driver receives data via 'in'
> t3 : USB driver has data, start pushing it to device via 'out'
> t4 : USB device finished receiving data via 'out'
> What I want to know is tusb = (t2-t1)+(t4-t3).
>
t2-t1: min.: 16 us for 24*8 bit at 12Mbit/s plus int processing ...
max.: 1ms or more depends on the traffic on the USB
t4-t3: also min 16 us, max 1ms or more
The typical times depends on the HCI type.
- Roman
> The reason : the IrDA protocol mandate what is the minimum
> time between Rx and Tx on the medium, tmin. This time tmin is
> negociated over the medium, and can vary from 10us to 10ms. I am
> mandated to ensure that (t4-t1) > tmin. The driver can control pretty
> accurately (t3-t2), and I can udelay() in the driver if needed.
> Currently, I ensure that (t3-t2) > tmin. However, I strongly
> suspect that tusb is in the order of 1ms for bulk transfer (due to the
> USB frame beeing 1ms period). In other words, it would be pointless
> for me to udelays() in the driver if tusb is larger than that...
>
> Thanks in advance...
>
> Jean
>
> _______________________________________________
> [EMAIL PROTECTED]
> To unsubscribe, use the last form field at:
> https://lists.sourceforge.net/lists/listinfo/linux-usb-devel
_______________________________________________
[EMAIL PROTECTED]
To unsubscribe, use the last form field at:
https://lists.sourceforge.net/lists/listinfo/linux-usb-devel
