Roland,
These are all excellent perspectives, I hope others will respond with
their view points.
Certainly repeating what we have heard already is not a good use of
anyone's time or money but I'm under the impression that we will have
made some progress toward what we want to work on next as a result of
PathForward Phase 2, input from Tom Tucker and others on OpenIB iWARP
integration and the HSIR meeting in NYC tomorrow.
With respect to "release" of OpenIB rel 1.0, did Doug Ledford
effectively do that a week or two ago?
I think those of us ( including me) who originally thought OpenIB was
actually going be an organization that released and supported code
(like RedHat, say) had got it wrong. Now I believe that when a Linux
distribution, an IB company or a Tier One OEM decides that is a
version of the code that they will support, then that is a "release".
OpenIB may be best utilized to try to achieve some consistency in
timeframe and content amongst those who wish to "release and support"
the code???
Bill.
At 09:39 AM 12/12/2005, Roland Dreier wrote:
Bill> I think, subject to others input, it'll be focused on
Bill> wrapping up rel 1.0 of OpenIB, discussing what the
Bill> developers are going to focus on next and validating the
Bill> strategy for RDMA over Ethernet integration at the verbs
Bill> level to lay the foundation for one, consistent RDMA
Bill> structure in Linux, if possible.
I'm not sure I see the point in dragging everyone together in early
February. With the holidays coming, realistically we only have maybe
5 weeks to prepare a conference agenda, and I don't see that as being
enough time to set up a productive meeting.
In particular:
* wrapping up rel 1.0 -- the release process for a "1.0" release has
not even started. About all we could hope to accomplish would be
to pick a release manager and tell that person to go start driving
a release, and I don't see that as a good use of face-to-face
time. It would be much better to pick someone to drive the release
and then give the release manager time to start putting the release
together before getting together, so that we have some idea of what
the real issues that need to be hashed out in person are.
* iWARP integration -- again, not enough discussion has taken place
in advance. Until the community has a chance to really study the
proposed changes and figure out what the real difficult issues that
need to be sorted out in person are, again it's a waste of time to
meet in person.
* discuss developers next steps -- perhaps I'm pessimistic but I
think we'll just get the same talks we've already seen twice before
at Sonoma and IDF.
Sonoma is a short trip for me but given the number of people that will
have to come from the East coast and Israel, I think we should think
hard about whether this conference is the best use of our time.
- R.
_______________________________________________
openib-promoters mailing list
[EMAIL PROTECTED]
http://openib.org/mailman/listinfo/openib-promoters
Bill Boas [EMAIL PROTECTED]
ICCD LLNL, B-453, R-2018 Wk: 925-422-4110
7000 East Ave, L-555 Cell: 925-337-2224
Livermore, CA 94551 Pgr: 877-203-2248
_______________________________________________
openib-general mailing list
[email protected]
http://openib.org/mailman/listinfo/openib-general
To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
