The IP over ATM Mailing List Archive by date

Cell Relay Retreat>List Archive>month:1996-Mar> msg00200



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

SCSP and epidemic

  • From: Eric Mannie <mannie@helios.iihe.rtt.be>
  • Date: Wed, 27 Mar 1996 17:33:37 +0100
  • X400-Content-Type: P2-1984 (2)
  • X400-Mts-Identifier: [/PRMD=iihe/ADMD=rtt/C=be/;960327163337]
  • X400-Originator: mannie@helios.iihe.rtt.be
  • X400-Received: by mta sun1.iihe.ac.be in /PRMD=IIHE/ADMD=RTT/C=BE/; Relayed; Wed, 27 Mar 1996 16:52:59 +0100
  • X400-Received: by mta elem5 in /PRMD=IIHE/ADMD=RTT/C=BE/; Relayed; Wed, 27 Mar 1996 17:33:37 +0100
  • X400-Received: by /PRMD=iihe/ADMD=rtt/C=be/; Relayed; Wed, 27 Mar 1996 17:33:37 +0100
  • X400-Recipients: non-disclosure:;

Hello,

Does anybody know where it is possible to find information (paper,
report, ...) on the scalability of SCSP algorithm vs epidemic (counter+
feedback and anti-entropy as backup). Does anyone intends to make
simulations or has already simulation results ? By the way, I am looking
for scalability information on OSPF. If SCSP does not scale for large
environments (200 servers, 10000 clients), is that means that OSPF is not
suitable for the same kind of size. Or, could we say that the scalability
problem is different as the number of client registrations/deregistrations
is (much more) greater than the number of topology changes in OSPF or P-NNI.

Eric Mannie
Brussels University
mannie@helios.iihe.rtt.be