The IP over ATM Mailing List Archive by date

[manfredi@engr05.comsys.rockwell.com (Albert E. Manfredi)]

> From:	jh@lohi.dat.tele.fi    27-MAR-1996 04:15
> To:	murray@pa.dec.com

[ ... ]

>    You don't have to take the store-and-forward delay all the time, 
>    just when there is another packet already using the outgoing VC.
> 
>    You can forward the first packet cell at a time.  If a second packet 
>    arrives, you buffer it until the first packet ends. 
> 
> this sounds dangerous to me.  if you have a slow speed source, do you
> really want to start sending its cells out before the whole packet is in
> the buffer and thus potentially create a head-of-the-line blocking
> problem?

Agreed. And now, we ask ourselves, what was the point of the small cells 
anymore? Haven't we just reasoned away la raison d'etre of ATM? We've 
introduced significant jitter and buffer delays equivalent to those found 
in standard IP routers.

Bert
manfredi@engr05.comsys.rockwell.com