[e2e] congestion correlation?

[vern at aciri.org]

>   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?

This is discussed in my end-to-end packet dynamics paper:

	ftp://ftp.ee.lbl.gov/papers/vp-pkt-dyn-ton99.ps.gz

where the finding was that the two directions are generally either weakly
correlated or not correlated at all.

		Vern