Re: Clarification on behaviour of Iperf's -w option


On Thu, 2 Aug 2007, Marc Herbert wrote:

Also please note that, due to latency, the sender systematically sees a smaller TCP window than the one published to him by the receiver at the same time.

Sorry this is wrong. I was thinking of the maximum sequence number allowed.


At any given time the window values seen can be "different", not just smaller.


That's really the big problem with the current documentation: it makes the user believes she can set a complex and very dynamic protocol value.

My mistake above demonstrates this :-)



Other Mailing lists | Author Index | Date Index | Subject Index | Thread Index