> C. Partridge, 'ACK Spacing for High Delay-Bandwidth Paths with Insufficient
> Buffering', IETF, draft-partridge-e2e-ackspacing-00.txt, July 1997.
The latest version should be draft-rfced-exp-partridge-01.txt.
> There really are two different "burstiness" definitions, I think.
> One is outlined above. That is, how many segments are sent in
> response to each ACK (a sort of "micro burstiness"). The other
> version would be a "macro burstiness", which is caused by ACKs
> arriving one right after another causing causing a large amount of
> data transmission (but, not at line rate). This is especially true
> on long-delay links. What you see during slow start is all the ACKs
> arriving at the beginning of the RTT, causing a macro burst of data
> packets, followed by a long idle period that we spend waiting for
> the ACKs. There is a nice paper that talks about these macro
> bursts....
I see what the "burst" is referred to here now. It is my English ): The
problem is about the total number of TCP segments for a connection in the
network at any time. And when TCP is in slow start, this number doubles for
every RTT. So Mukul's question is how the network responds to this large
number of segments. I have never considered this as a burst before...
Thanks for clearing the "burst" definition.
K. Poon.
[email protected]
This archive was generated by hypermail 2b29 : Fri Feb 25 2000 - 16:41:34 EST