Re: [8023-CMSG] Proposed Upper Layer Compatibility Objective
Gary,
One difficulty is the ambiguity of the words "degrade the operation" (any
other words in the same position with the same general meaning will have the
same problem).
We are going to have to have a working definition that provides guidance.
Two extreme interpretations might help explain the problem.
1. I, XYZ, interpreted "degrade the operation" to mean that there is no
measurable decrease in performance of the protocol, even if operating at a
lowest priority.
2. I, ABC, interpreted "degrade the operation" to mean that as long as we
can turn off CM and run like we do today, we have met the objective, no
matter how well or how poorly any specific upper layer protocol operates
with CM.
XYZ and ABC can both raise their hands supporting the objective. But, when
the work begins, and decisions are made, both can simultaneously cry foul.
It might be the case that before we can get our arms around this, we need
specific and detailed information and analysis about what can go wrong (e.g.
PAUSE working at odds with TCP/IP) and why. It is difficult to know what is
acceptable and what is not acceptable when we don't know precisely what what
is.
jonathan
-----Original Message-----
From: owner-stds-802-3-cm@LISTSERV.IEEE.ORG
[mailto:owner-stds-802-3-cm@LISTSERV.IEEE.ORG]On Behalf Of McAlpine, Gary L
Sent: Wednesday, May 12, 2004 1:45 PM
To: STDS-802-3-CM@LISTSERV.IEEE.ORG
Subject: [8023-CMSG] Proposed Upper Layer Compatibility Objective
My A.R. from last meeting (thank you Ben).
Here's a first shot at a Upper Layer Compatibility objective:
The objective is:
"To define 802.3 congestion control support that, at a minimum, will do
nothing to degrade the operation of existing upper layer protocols and
flow/congestion control mechanisms, but has the explicit goal of
facilitating the improved operation of some existing and emerging protocols,
over 802.3 full-duplex link technology."
If we can narrow the scope and still make it meaningful, I'm all for it.
I have attached RFC3168 (on ECN) as a reference. It contains a very good
overview of congestion control at the TCP and IP layers. I would also
consider this and DiffServ as examples of existing ULPs we would want to do
our part to improve the operation of. IMO, what we can do at the 802.3 level
to better support these will also provide the support we need for improved
operation of some emerging protocols such as iSCSI and RDMA.
Gary <<rfc3168.txt>>