[prev in list] [next in list] [prev in thread] [next in thread] 

List:       linux-atm
Subject:    Re: measuring the CTD
From:       Alfonso Gonzalez <e0192388 () brookes ! ac ! uk>
Date:       1997-10-24 20:36:55
[Download RAW message or body]

Jose Rezende wrote:
> I've got numbers as such 290 usec for the RTT when using a PCR of 50000 >cps. this \
> value increases when I use a smaller PCR (700 usec for 2000 pcr). Is it normal this \
> behavior? I expected that it would remain unchanged as soon as I respect the \
> max_pcr, that is, my cells would not be reshaped.

Hmmm (as Werner would say ;-)), I am not quite sure about this, but it
may be related to the SDU size used by AAL5. That's why I am so
interested about that matter.

What it may happen, is that the data being sent to the socket is
buffered until the SDU size is reached, and then encapsulated and sended
to the NIC. This may explain why you measure higher times when your cell
rate is lower. Simply it takes longer to fill up an SDU.

Could this be a sensible explanation?

Bye.

Alfonso.

-- 

--------------------------------------------------------------
"Copy from one, it's plagiarism; Copy from two, it's reseach"
--------------------------------------------------------------

Alfonso Gonzalez 
Msc. High Speed Networks & Distributed Systems
Oxford Brookes University


[prev in list] [next in list] [prev in thread] [next in thread]