[e2e] congestion correlation?

[Andrew Odlyzko]

As Vern Paxson noted already, he has collected extensive evidence
that corrections are weak, if they exist at all.  This should not
be too surprising, since, among other things, "hot potato routing"
means that packets often traverse almost disjoint paths.  Futher,
even when they do travel over the same path, there is often
substantial asymmetry in the traffic load in the two directions.  This
is true even within the US. but very noticeable on trans-Atlantic
and trans-Pacific connections.  As an example, if you look at the
data for JANET, the British academic and research network (available
at <http://bill.ja.net/>) you will find the following ratio for
(traffic from the US to Britain) / (Britain to US traffic):

 month         ratio
--------        ----
March 97        1.26
March 98        1.98
March 99        2.05
March 00        3.27
March 01        2.70

(An increase in this ratio also held true for some other links in
the late 1990s, and I am watching with interest whether it will
reverse course and shrink, as the ratio for JANET may be doing.)

Capacities are generally completely symmetric.  This is true 
throughout the telecom world (except for newer technologies
at the edges, like DSL, cable modems, and satellite data), a
legacy of the voice telephony world.  (Frame Relay offers 
customers the option of asking for asymmetric PVCs, but this
is just how the capacity is sold, as the Frame links themselves
are symmetric.)  In my Globecom '99 paper I used this as an
argument against QoS:  Basically the reasoning was that with 
far less effort than is going into developing and deploying
QoS, one could develop a transport infrastructure that would
take advantage of the asymmetries in traffic patterns, which
tend to persist for extended periods of time, and that this
would provide at least as much of a gain in performance.

Andrew Odlyzko



        -----Original message-----
	From: Adam Wolisz <wolisz at ee.tu-berlin.de>
	To: Sam Liang <sliang at DSG.Stanford.EDU>, end2end-interest at postel.org
	Subject: Re: [e2e] congestion correlation?
	Date: Thu, 03 May 2001 10:37:57 +0200

	The answer is: NO
	For example in 1999 we have done measurements both ways
	between Berlin, Germany and Berkeley, CA:
	Losses in the direction; Berkeley=>Berlin
	have been much higher.
	We believe that there is much more content being
	transported from US to Europe than another way round.
	And the capacities are not asymmetric enough.
	(if at all).
	Btw: Does anybody know if there is at all an asymmetry
	of the resources between US and Europe?
	
	
	You could contact Dorgham Sisalem,
	sisalem at fokus.gmd.de
	for more details on this measurements, done in the
	context of his Ph.D Thesis on TCP friendly
	UDP traffic, available from
	ftp://ftp.fokus.gmd.de/pub/glone/sa.da/Sisa0010:TCP.pdf
	
	Adam Wolisz
	
	Sam Liang wrote:
	
	> Hello,
	>
	>   Is there any study done on whether there is any congestion correlation
	> on the two directions between two endpoints A and B?  Suppose A is sending
	> data to B.  When there is congestion and packet loss from A to B, do we
	> expect packet loss from B to A at the same time?
	>
	>   Thanks,
	>
	> Sam
	


************************************************************************
Andrew Odlyzko                                      amo at research.att.com
AT&T Labs - Research                                voice:  973-360-8410 
http://www.research.att.com/~amo                    fax:    973-360-8178
************************************************************************