The IP over ATM Mailing List Archive by date

Cell Relay Retreat>List Archive>month:1995-Sep> msg00015



[Date Prev][Date Next][Thread Prev][Thread Next]  
  [Date Index][Thread Index][Author Index][Subject Index]

Alternate Encapsulations/Signals for IP on AAL5

  • From: kalyanaraman shivkumar <shivkuma@cis.ohio-state.edu>
  • Date: Fri, 8 Sep 1995 11:54:22 -0500 (EDT)
  • CC: ip-atm@hplms2.hpl.hp.com, shivkuma@cis.ohio-state.edu (kalyanaraman shivkumar)

Jon,

> 2/ TCP on IP on AAL5 on an ABR service
> 
> we'd like an explicit congestion bit (even if ATT don';t let us get
> the explicit rate,they'll still pass the congestion signal back sooner
> than packet loss in traditional TCP congestion detection) signal from
> AAL up thu IP....
> 

Right, but the bit will be insufficient ... 

Coming from the TM WG, we (Raj Jain's group) see that the explicit rate 
indication can change potentially at every RM cell (send as well as receive).
Hence, if the TCP/IP stream doesnt adapt reasonably, source congestion will 
be more serious than network congestion. 

By the same token, the source might underload the network even if it has the 
load to offer if it does not change its sending rate to match the current ACR
(available cell rate). 

-Shiv

-- 
Shivkumar Kalyanaraman  (shivkuma@cis.ohio-state.edu)
	http://www.cis.ohio-state.edu/~shivkuma
Office phone : (614)-292-7043 (or 292-7036)	Home phone : (614)-299-8634