Publish-subscribe tree maintenance over a DHT

Content-based publish-subscribe middleware is emerging as a promising answer to the demands of modern highly dynamic distributed computing by providing the necessary decoupling and flexibility. The majority of currently available systems implement event dispatching on top of an overlay network with a tree topology. However, they fail to provide any mechanism to maintain it in the presence of failures, thus hampering their applicability in dynamic scenarios. In this paper, we present a novel approach to reconfiguring the overlay topology by exploiting a distributed hash table. Our algorithm supports arbitrary tree topologies and deals very well with the dynamicity of network scenarios by limiting the impact of reconfigurations induced by topology changes. These results are confirmed by simulations, which validate the applicability of our approach in reconfigurable publish-subscribe middleware. Beyond publish-subscribe, the algorithm is applicable in a wide range of contexts and provides a general way to maintain an overlay network with a controlled topology in dynamic environments.

[1]  Alfonso Fuggetta,et al.  The JEDI Event-Based Infrastructure and Its Application to the Development of the OPSS WFMS , 2001, IEEE Trans. Software Eng..

[2]  David Mazières,et al.  Kademlia: A Peer-to-Peer Information System Based on the XOR Metric , 2002, IPTPS.

[3]  Mark Handley,et al.  A scalable content-addressable network , 2001, SIGCOMM '01.

[4]  Ben Y. Zhao,et al.  Bayeux: an architecture for scalable and fault-tolerant wide-area data dissemination , 2001, NOSSDAV '01.

[5]  David S. Rosenblum,et al.  Design and evaluation of a wide-area event notification service , 2001, TOCS.

[6]  Antony I. T. Rowstron,et al.  Pastry: Scalable, Decentralized Object Location, and Routing for Large-Scale Peer-to-Peer Systems , 2001, Middleware.

[7]  Paolo Costa,et al.  Epidemic algorithms for reliable content-based publish-subscribe: an evaluation , 2004, 24th International Conference on Distributed Computing Systems, 2004. Proceedings..

[8]  Kirk L. Johnson,et al.  Overcast: reliable multicasting with on overlay network , 2000, OSDI.

[9]  Amy L. Murphy,et al.  Efficient content-based event dispatching in the presence of topological reconfiguration , 2003, 23rd International Conference on Distributed Computing Systems, 2003. Proceedings..

[10]  Robbert van Renesse,et al.  Willow: DHT, Aggregation, and Publish/Subscribe in One Protocol , 2004, IPTPS.

[11]  David R. Karger,et al.  Chord: A scalable peer-to-peer lookup service for internet applications , 2001, SIGCOMM '01.

[12]  Amy L. Murphy,et al.  Minimizing the reconfiguration overhead in content-based publish-subscribe , 2004, SAC '04.

[13]  Ben Y. Zhao,et al.  Tapestry: a resilient global-scale overlay for service deployment , 2004, IEEE Journal on Selected Areas in Communications.

[14]  Miguel Castro,et al.  Scribe: a large-scale and decentralized application-level multicast infrastructure , 2002, IEEE J. Sel. Areas Commun..

[15]  Peter R. Pietzuch,et al.  Hermes: a distributed event-based middleware architecture , 2002, Proceedings 22nd International Conference on Distributed Computing Systems Workshops.