[USRP-users] Effect of num_send_frames on TX latency

Michael West michael.west at ettus.com
Thu Jul 9 14:46:46 EDT 2015


Hi Dario,

There should be no need to change the num_send_frames as long as the
application can supply samples at the desired sample rate.  If additional
buffering is needed, it will only be compensating for the application's
inability to provide data consistently at that rate.  The major effects on
latency for the TX side will be the send_frame_size and the time taken by
the application before calling send().

Regards,
Michael

On Thu, Jul 9, 2015 at 10:47 AM, Dario Fertonani via USRP-users <
usrp-users at lists.ettus.com> wrote:

> Michael West clarified the effect of num_recv_frames on RX latency, which
> turns out to be an effect only on the peak RX latency allowed.
>
> Is the same true for num_send_frames and TX latency?
>
> Thanks,
> Dario
>
> _______________________________________________
> USRP-users mailing list
> USRP-users at lists.ettus.com
> http://lists.ettus.com/mailman/listinfo/usrp-users_lists.ettus.com
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.ettus.com/pipermail/usrp-users_lists.ettus.com/attachments/20150709/631f412f/attachment-0002.html>


More information about the USRP-users mailing list