Hi Carolyn,

Fair enough.

But HW timestamping on the ring buffer is a cool feature. Silicon and
design time was put into implementing it,
so it is a shame that it is not easy to use. Finding and deleting the
#undef in the source code is likely to
be beyond the capabilities of many non-technical users.

I would suggest that as a minimum, a comment is added to the source
explaining why
IGB_PER_PKT_TIMESTAMP was undefined (and quantifying the performance penalty
of defining it in. A note in the documentation would also be nice.

Cheers,
   Amnon




>>>
> Thanks Amnon, yes that should help.  Let me know if it does not.  We do not 
> define this by default because there can be a performance hit that non-time 
> sync'ers may not want to deal with.
>
> Thanks,
>
> Carolyn
>
> Carolyn Wyborny
> Linux Development
> LAN Access Division
> Intel Corporation
>
>
>

------------------------------------------------------------------------------
Get a FREE DOWNLOAD! and learn more about uberSVN rich system, 
user administration capabilities and model configuration. Take 
the hassle out of deploying and managing Subversion and the 
tools developers use with it. http://p.sf.net/sfu/wandisco-d2d-2
_______________________________________________
E1000-devel mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/e1000-devel
To learn more about Intel® Ethernet, visit 
http://communities.intel.com/community/wired

Reply via email to