lkml.org 
[lkml]   [2021]   [Nov]   [10]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
    /
    Date
    From
    SubjectRe: [PATCH v2 6/7] net: dsa: b53: Add logic for TX timestamping
    On Wed, Nov 10, 2021 at 03:05:45PM +0200, Vladimir Oltean wrote:

    > So it is true that ptp4l is single threaded and always polls
    > synchronously for the reception of a TX timestamp on the error queue
    > before proceeding to do anything else. But writing a kernel driver to
    > the specification of a single user space program is questionable.

    There are a number of HW devices on the market that only support one
    outstanding Tx time stamp. The implementation of ptp4l follows this
    limitation because a) it allows ptp4l to "just work" with most HW, and
    b) there is as yet no practical advantage to asynchronous Tx time
    stamping.

    The premise of (b) might change if you had a GM serving hundreds or
    thousands of unicast clients, for example.

    In any case, I agree that the driver should enable the capabilities of
    the HW and not impose artificial limitations.

    Thanks,
    Richard

    \
     
     \ /
      Last update: 2021-11-10 16:10    [W:2.632 / U:0.024 seconds]
    ©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site