<div dir="ltr"><div dir="ltr">On Fri, Dec 4, 2020, at 12:50 AM Hal Murray via devel <<a href="mailto:devel@ntpsec.org">devel@ntpsec.org</a>> wrote:<br></div><div class="gmail_quote"><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><br>
That should lead to better (earlier) time stamps.  It will bypass the <br>
interrupt response time and the coalesce delays.<br>
<br>
As I understand it, the catch is that the clock out near the network is not <br>
directly connected to the CPU clock so the time stamps from the hardware need <br>
to be translated to system time.<br>
<br>
I'm looking for a HOWTO type recipe for setting things up.<br></blockquote><div><br></div>I found a question [1] that is tangential and led me to a<br>piece of documentation [2] and a PTP(ish) code sample [3]<br>that looks to be closer. It also looks like it might be<br>used in the ntpd/ntp_packetstamp.c code.<div><br></div><div>I didn't look very hard though.</div>





<div><br></div><div>[1] <a href="https://networkengineering.stackexchange.com/questions/23369/how-to-check-if-a-nic-supports-hardware-timestamps">https://networkengineering.stackexchange.com/questions/23369/how-to-check-if-a-nic-supports-hardware-timestamps</a></div><div>[2] <a href="https://www.kernel.org/doc/Documentation/networking/timestamping.txt">https://www.kernel.org/doc/Documentation/networking/timestamping.txt</a></div><div>[3] <a href="https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/tools/testing/selftests/net/timestamping.c">https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/tools/testing/selftests/net/timestamping.c</a></div></div></div>