Window Scale option -- what about null windows ?

[Christian Huitema <[e-mail]>]

Bob,

One of the problems with the current window scale options is that it is
based on an old concept -- the idea that the max send window has to be
somehow configured to match the number of receive buffers available at the
peer.  This leads to design choices, such as annoucing scaling options
during the SYN exchange.

I contend that, if we implement congestion control, we don't actually need
a send window.  In fact, the send window is trying to protect the sender
against a very specific form of congestion, when the receiver rather than
the network is the bottleneck.  If this is the case, overflowing the
receive buffers will trigger a packet loss, and the congestion window will
shrink. The congestion window is automatically discovered, and permanently
updated. It is not artificially limited to 64K. It can lead to very
efficient implementations.

Can we propose a specific "window scaling" option that, instead of
negotiating an actual window scale, would merely establish an infinite
send window ?

-- 
Christian Huitema
----------
See you at INET'98, Geneva 21-24,July 98 http://www.isoc.org/inet98/