Re: [Linuxptp-users] High path delay: i219 vs i210?

[Vladimir O. <ol...@gm...>]

On Fri, Mar 18, 2022 at 02:19:24PM +0200, Joseph Matan wrote:
> Hi,
> 
> I don't have an answer to your question, but I can share from my experience
> that I'm familiar with this. I even posted a similar question a year or so
> ago.
> I also tried to open a ticket in Intel Customer Service but nothing good
> came through.
> Maybe the e1000e developers community would have an idea (but I didn't try
> to ask there).
> 
> My problem with the i219 NIC was that with no traffic the path delay was
> around ~7 or 8 usec (as you mentioned), but in intervals of high load of
> traffic the path delay decreased significantly to something like 800 nsec
> (0.8 usec).
> These significant changes in the path delay between 8 usec to 0.8 usec
> caused me lots of accurecy troubles... (and I didn't use any switch between
> my master and slave).
> However, from the tests I was doing, the i210 doesn't suffer from this
> behaviour.
> Intel Customer Service didn't know to answer if this is a bug or perhaps a
> feature that can be switched off/on.
> 
> Hope it helped somehow...
> Joseph

Not sure if you've exhausted this option with Intel support, but this
sounds like the typical signature of what Energy Efficient Ethernet
would do to PTP.