Re: [8023-CMTF] 802.3ar/D0.9 is available
Kevin,
Thanks for the timely response and clarification. I see
from the official stated objectives
I was mistaken.
I had incorrectly assumed (via informal discussions in
the past) that an objective was
to eliminate congestion-related frame drops. The
observations were that frame drops
on 802.3 were the primary (and possibly only) reason
for using FibreChannel and/or
Infiniband rather than 802.3 links. And, many of the
frame drops could be associated
with transient overload conditions.
I
happened to agree with this informal objective and believed it could be done,
without
undue complexity, if the scope was limited
to computer-room communications, where
the link distance (measured in time) is
less than an MTU.
From your email, I assume this is not an official
objective, and certainly not the
primary objective. While that will no doubt allow the
group to converge quickly,
I'm disappointed that (what I feel is) the most
valuable objective will not be met.
Since avoiding frame loss (via credits, busy-retry,
etc.) is a bit inconsistent with
Ethernet philosophies, this may not be the right area
to accomplish this objective.
Perhaps this is better done in other
arena, where more backplane designers are
present and/or available for
consultation.
Respectfully,
DVJ
From: Kevin Daines
[mailto:Kevin.Daines@wwp.com]
Sent: Tuesday, October 25, 2005 11:36
PM
To: David V James;
STDS-802-3-CM@listserv.ieee.org
Subject: RE: [8023-CMTF] 802.3ar/D0.9
is available
David,
Not sure what you mean by "primary objective".
Perhaps you didn't intend to use the "reserved word" objective. The following
are the (4) TF objectives:
1) Specify a mechanism to limit the rate of
transmitted data on an Ethernet link
2) Specify a mechanism to
support the communication of congestion information
3) Preserve the MAC/PLS
service interfaces
4) Minimize throughput reduction in non-congested
flows
The CMTF adopted a proposal to satisfy CMTF objective
#1.
Recently, proposals related to (backward)
congestion notification have been made in 802.1 (related to
#2).
Kevin Daines
Chair, P802.3ar TF
Kevin,
I would claim that the TF has still not provided any
promising
solutions for avoiding dropped frames in a
short-distance
(computer room) environment.
Thus, since it doesn't currently meet its primary
objective,
I would smile (rather than frown) at radical new
ideas that
have a chance of meeting the primary
objective.
DVJ
Asif,
As with any TF meeting pre-D1.0, presentations in
support of or related to the TF objectives are welcome and encouraged.
Post-D1.0, the TF naturally shifts its focus to perfecting the draft. During
that phase, radically new ideas are generally frowned
upon.
That said, the plans for the meeting
are
1) Review D0.9 and prepare D1.0. Since we have adopted
one proposal in support of one of our objectives, it is the first order of
business.
2) Entertain presentations, if any, in support of or
related to the TF objectives. I'll send my customary "Call for
presentations" e-mail shortly.
Kevin Daines
Chair, P802.3ar TF
Kevin,
Hello. Time to discuss about the plans for the plenary
meeting.
What are the plans? We would like to meet and discuss the draft and
get updates.
regards
asif
Congestion
Management TF members,
At the July
2005 IEEE 802 Plenary meeting in San Francisco, we (the P802.3ar
CMTF) passed the following motion:
"Adopt changes
to Clause 4, Annex 4A & Clause 30 described in barrass_1_0505.pdf as a
baseline proposal for 802.3ar/D1.0. The changes to Clause 4 will be made
after the
changes to Annex 4A have been solidified in 802.3ar TF
review."
In order to
jumpstart our progress on D1.0, Hugh Barrass and I have
prepared P802.3ar/D0.9 for CMTF preview. It may be found
here:
Please note
this draft has no official status. It is being made available for TF
preview, prior to the November meeting, in order to more efficiently
prepare P802.3ar/D1.0 and commence TF ballot after we meet in November.
Hope to see you in Vancouver.
Kevin
Daines
Chair,
P802.3ar CMTF