[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [RRG] Are we solving the wrong problem?
Mark,
right, but i think that what is missing in all these proposals
[like HIP, SHIM6, etc] is to understand the interaction with
congestion control, which may be critical if they get deployed.
Absolutely. The stable load-balancing properties come out of using
multiple links simultaneously in such a way that congestion on one
path causes more bytes to be sent the other way. But crucially it
must not move all the traffic the other way, or the system is
unstable and can oscillate backwards and forwards between the
multiple paths.
So far I fully agree, even don't I cannot claim really understanding
the issue. [Kelly & Voice is very next on my reading list; Bob B.
commended it too, in addition to Marcelo.]
This is the reason why I think you can solve the problem at L4
without changing the apps (or at the application layer, but only if
you change the apps), but I don't think you get the same properties
if you solve the problem below layer 4.
Here I do not agree, due to a) signalling efficiency, b) mobility, c)
path sharing within the network, and I guess a couple of other things
I just don't remember this early moment.
I still think that we should reconsider the sublayering or location
of functionality within layers 3/4, and rethink where to put
congestion control. For congestion control, we should apparently
separate flow-related functions (at transport) and path-related
functions (at end-to-end), where path-related functions are shared by
all flows going over the same path. [Consider also John Day's view
in his new book, where he basically claims that logically layers 3
and 4 form just one single layer, and some of the layering we've done
is just architecturally wrong due to us not understanding this.]
--Pekka
--
to unsubscribe send a message to rrg-request@psg.com with the
word 'unsubscribe' in a single line as the message text body.
archive: <http://psg.com/lists/rrg/> & ftp://psg.com/pub/lists/rrg