<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
<HTML><HEAD>
<META HTTP-EQUIV="Content-Type" CONTENT="text/html; charset=us-ascii">
<TITLE>Message</TITLE>
<META content="MSHTML 6.00.2800.1458" name=GENERATOR></HEAD>
<BODY dir=ltr>
<DIV><SPAN class=125114105-09092004><FONT face=Arial size=2>There is an IETF
meeting in the beginning of November. I was wondering
whether</FONT></SPAN></DIV>
<DIV><SPAN class=125114105-09092004><FONT face=Arial size=2>it makes sense to
bring up the multicast aliasing issue there ? I believe that
without</FONT></SPAN></DIV>
<DIV><SPAN class=125114105-09092004><FONT face=Arial size=2>any patch to current
kernels, it'll be pretty hard to support multicast aliasing
which</FONT></SPAN></DIV>
<DIV><SPAN class=125114105-09092004><FONT face=Arial size=2>is different than
the Ethernet aliasing. There are two options I'd consider:</FONT></SPAN></DIV>
<DIV><SPAN class=125114105-09092004><FONT face=Arial size=2>1) OpenIB stack,
once merged into the kernel, will include the kernel patch to fix
it.</FONT></SPAN></DIV>
<DIV><SPAN class=125114105-09092004><FONT face=Arial size=2>
Existing (gen1) implementations will not be able to interoperate with it (for
multicast).</FONT></SPAN></DIV>
<DIV><SPAN class=125114105-09092004><FONT face=Arial size=2>2) Discuss with
IETF a change in the specification to accommodate similar
aliasing</FONT></SPAN></DIV>
<DIV><SPAN class=125114105-09092004><FONT face=Arial size=2>
to the one that is in Ethernet.</FONT> <FONT face=Arial size=2>It might be
too late, though.</FONT></SPAN></DIV>
<DIV><SPAN class=125114105-09092004><FONT face=Arial
size=2></FONT></SPAN> </DIV>
<DIV><SPAN class=125114105-09092004><FONT face=Arial size=2>I don't know too
deeply how is that supposed to work in other operating
systems.</FONT></SPAN></DIV>
<DIV><SPAN class=125114105-09092004><FONT face=Arial size=2>They may or may not
include flexible mechanisms to take care of longer MAC </FONT></SPAN></DIV>
<DIV><SPAN class=125114105-09092004><FONT face=Arial size=2>address for
multicast. However, if some of them also don't support it, then that
</FONT></SPAN></DIV>
<DIV><SPAN class=125114105-09092004><FONT face=Arial size=2>may be a valid
</FONT></SPAN><SPAN class=125114105-09092004><FONT face=Arial size=2>argument
for IETF too.</FONT></SPAN></DIV>
<DIV><SPAN class=125114105-09092004><FONT face=Arial
size=2></FONT></SPAN> </DIV>
<DIV><SPAN class=125114105-09092004><FONT face=Arial
size=2>Thanks</FONT></SPAN></DIV>
<DIV><SPAN class=125114105-09092004><FONT face=Arial
size=2>Dror</FONT></SPAN></DIV>
<DIV><SPAN class=125114105-09092004><FONT face=Arial
size=2></FONT></SPAN> </DIV></BODY></HTML>