On 10/30/07, <b class="gmail_sendername">Roland Dreier</b> <<a href="mailto:rdreier@cisco.com">rdreier@cisco.com</a>> wrote:<div><span class="gmail_quote"></span><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
So with that said:<br><br> > 1) the long time and endless threads related to the SA caching thing<br> > need to be there. Sean - I saw that you prepare a session, correct?<br> > will you presenting few possible designs?
<br><br>This is the perfect type of thing to try and settle.</blockquote><div><br>
I agree. Sean - I don't see how a two years old open issue can be
settled down in 30m, I would say we need between 45m and upto two hours
for that.<br>
</div><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;"> > 2) as for IPoIB stateless offload - with Eli and Liran not planned to<br> > be there. Dror - do you intend to actually present the actual ipoib /
<br> > core / drivers related design and implementation?<br><br>Given that there really hasn't even been an attempt to discuss this on<br>the mailing list, I'm not convinced it's worth trying to rush through
<br>explaining it. I didn't think the patches were particularly hard to<br>understand.</blockquote><div><br>
I think it would be good to have Dror explaining exactly what the HW
knows to do (the Sonoma slides were very short in details). Things I
think we want to discuss are: <br>
(A) why to put a SW only optimization (LRO) in Infiniband/networking driver (IPoIB)<br>
(B) the IB ICRC based checksum offload patch which you called "silent data corruption enhancement"<br>
etc<br>
<br>
Dror - I don't see how 30m would be enough, I would say 45m and upto an hour<br>
</div><br><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;"> > 4) IPoIB connected mode UC support - Roland, can work on this start<br> > once the no-SRQ design/code is agreed and committed to a branch at
<br> > your git?<br><br>Is there a spec for attaching UC QPs to SRQs? Other than that I think<br>it's just a matter of someone caring enough to start working on it.</blockquote><div><br>
Here's the thing: with the SRQ/UC spec and implementation status being
unclear, once the no-SRQ code is in some repository, we can start code
a no-SRQ/UC implementation. As for open issues, pls see <br>
<a href="http://lists.openfabrics.org/pipermail/general/2007-July/thread.html#37644">http://lists.openfabrics.org/pipermail/general/2007-July/thread.html#37644</a>
where in the second message on the thread MST states "The largest bit
of work would be<span style="font-family: monospace;"> </span>to add
connection liveness detection code to active side." and then a whole
discussion starts. If you tend to or just agree with Michael, can be
helpful if we discuss how to do that. </div><br><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;"> > 5) IB 4K MTU - in IPoIB and elsewhere in the IB stack, same here,
<br> > Roland, do you think a short session is needed<br><br>No -- I don't know of any issues that need face-to-face discussion.</blockquote><div><br>
OK <br>
</div><br><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;"> > 6) the netdev network batching RFCs - Krishna, Shirley, will someone<br> > from IBM can prepare a session to educate us on the matter and the
<br> > status?<br><br>Why do we need to spend face-to-face time on this?</blockquote><div><br>
I thought that face-to-face meeting can include education,
specifically when it is on interesting materials like this, which are
about to effect the ipoib driver.<br>
<br>
Or.<br>
</div><br></div><br>