<br><font size=2 face="sans-serif">Hal,</font>
<p><font size=2 face="sans-serif">I think you're right. The language currently
in the spec implies that for intermediate packets PayloadLength is ignored
on receive, but I don't think it anywhere explicitly reconfirms that, as
a reserved field, it should be set to 0 on transmit.</font>
<p><font size=2 face="sans-serif">My take is that, as a result, on that
field it wouldn't be as straightforward to use the technique we used elsewhere
-- have nonzero in a previously-reserved field turn on some new optional
function.</font>
<p><font size=2 face="sans-serif">But I don't think there's any other effect
of that spec looseness. And using that field for such a purpose, only on
intermediate packets, strikes me as pretty unlikely.</font>
<p><font size=2 face="sans-serif"><br>
Greg Pfister<br>
IBM Distinguished Engineer, Member IBM Academy of Technology<br>
IBM Systems & Technology Group, Server Technology & Architecture<br>
(512) 838-8338 | IBM tieline 678-8338 | FAX (512) 838-3418<br>
Sic Crustulum Frangitur</font>
<p>
<p><font size=2><tt>Hal Rosenstock <halr@voltaire.com> wrote on 08/30/2005
07:50:31 AM:<br>
<br>
> Hi Greg,<br>
> <br>
> In addition to the question about whether the first packet Payload<br>
> Length only includes valid bytes in Transferred Data or all bytes
in all<br>
> Transferred Data in all sent segments in the case of a<br>
> multipacket/segment send, there is also a question about the Payload<br>
> Length in middle segments/packets. It looks to me like there is just
a<br>
> comment about the Payload Length being valid in first (optional) and<br>
> last (mandatory) segments/packets. So that means it is ignored on<br>
> receive but does it need to be set to 0 on transmit ? It seems possibly<br>
> different from a reserved field in those cases by language in the
spec<br>
> but I'm not sure whether this is the case or not.<br>
> <br>
> Thanks.<br>
> <br>
> -- Hal<br>
> <br>
</tt></font>