[e2e] High Packet Loss and TCP

[Jonathan Stone]

>Take an idealization of TCP, additive increase-multiplicative decrease. 
>Numerous papers have shown that the relationship between loss probability
>"p" and average window size "W" is 
>        (W^2)*p = k
>
>where k is some constant between 1.5 and 2 (the "square root p formula").
>At loss rates above 10% (p > 0.1), the average window size drops down to 3 
>or below. Any loss of packet then, in a real implementation of TCP results 
>in (multiple) timeouts with high probability (you do not have a large enough 
>window to get triple duplicate acks). 

Oh, sure.  Standard TCP is bad at 10% loss. All I'm saying is that
modelling and (somewhat ad-hoc) observation agree that somewhere
around 30% loss, TCP (Tahoe/New-Tahoe) goes from very bad,
to even worse.