Toggle Main Menu Toggle Search

Open Access padlockePrints

A Non-Blocking Atomic-Multicast Service for Scalable In-memory Transaction Systems

Lookup NU author(s): Ryan Emerson, Dr Paul EzhilchelvanORCiD

Downloads


Abstract

Atomic Multicasting is central to managing replication. Our focus is on its deployment for enhancing scalability and performance of in-memory transactional systems where data replication is essential. When it is deployed as an external service, enhancement is demonstrably accomplished when no node within the service crashes. Since known atomic-multicast protocols block whenever a node is crashed or appears so, using them for service implementation risks the transaction system making no progress when blocking prevails. To eliminate this risk, our service simultaneously runs two protocols with distinct properties. The first one is the fastest when crashes are absent, but blocks until a crashed node is isolated. The second, newly-designed one never blocks but can fail to deliver messages with a probability that can be made vanishingly small in return for slower performance. The service uses slow protocol when the fast one is blocked and the switch-over is instantaneous. Extensive performance study confirms best crash-free performance, crash-uninterrupted service and no delivery failure in practical settings.


Publication metadata

Author(s): Emerson R, Ezhilchelvan P

Publication type: Report

Publication status: Published

Series Title: School of Computing Science Technical Report Series

Year: 2014

Pages: 8

Print publication date: 01/10/2014

Report Number: 1435

Institution: Newcastle University

Place Published: Newcastle upon Tyne

URL: http://www.cs.ncl.ac.uk/publications/trs/papers/1435.pdf


Share