Scalability of Multicast based Synchronization Methods

Bettina Schnor, Stefan Petri, M. Becker


Consistent maintenance of distributed data is important in application areas like groupware and jor runtime support for parallel computing. We examine the performance of different multicast based methods for maintaining the consistency of distributed data depending on the network topology and concurrency. Our prototype software implements ordered, reliable multicasts on top of the unreliable IP broad-or multicast with three different methods (Master-Slave, Token Exchange on Demand, Totem Single Ring). This paper shows measurement results for the esciency and scalability of the three methods in different topologies. The measurements conJirm earlier analytical results. Totem behaves well in large networks with many concurrent senders. The overhead of Token on Demand and of the Master-Slave algorithm is almost the same. Also we could notjnd an indication for the often-read opinion that the Master-Slave approach scales worse because of the central bottleneck.

Original languageEnglish
Title of host publicationProceedings. 24th EUROMICRO Conference (Cat. No.98EX204)
Number of pages7
Publication date01.01.1998
ISBN (Print)0-8186-8646-4
Publication statusPublished - 01.01.1998
Externally publishedYes
Event24th EUROMICRO Conference, EURMIC 1998
- Vasteras, Sweden
Duration: 25.08.199827.08.1998
Conference number: 133935


Dive into the research topics of 'Scalability of Multicast based Synchronization Methods'. Together they form a unique fingerprint.

Cite this