Exploiting virtual synchrony in distributed systems
SOSP '87 Proceedings of the eleventh ACM Symposium on Operating systems principles
ACM Transactions on Computer Systems (TOCS)
Time, clocks, and the ordering of events in a distributed system
Communications of the ACM
The JEDI Event-Based Infrastructure and Its Application to the Development of the OPSS WFMS
IEEE Transactions on Software Engineering
The many faces of publish/subscribe
ACM Computing Surveys (CSUR)
Shared-memory mutual exclusion: major research trends since 1986
Distributed Computing - Papers in celebration of the 20th anniversary of PODC
ICDCS '05 Proceedings of the 25th IEEE International Conference on Distributed Computing Systems
A Transparent Distributed Shared Memory for Clustered Symmetric Multiprocessors
The Journal of Supercomputing
On Quality-of-Service and Publish-Subscribe
ICDCSW '06 Proceedings of the 26th IEEE International ConferenceWorkshops on Distributed Computing Systems
Self-organizing broker topologies for publish/subscribe systems
Proceedings of the 2007 ACM symposium on Applied computing
Tight RMR lower bounds for mutual exclusion and other problems
STOC '08 Proceedings of the fortieth annual ACM symposium on Theory of computing
A Taxonomy of QoS-Aware, Adaptive Event-Dissemination Middleware
IEEE Internet Computing
Decentralized message ordering for publish/subscribe systems
Proceedings of the ACM/IFIP/USENIX 2006 International Conference on Middleware
A practical single-register wait-free mutual exclusion algorithm on asynchronous networks
Euro-Par'06 Proceedings of the 12th international conference on Parallel Processing
| Hi-index | 0.00 |
Publish/Subscribe middlewares are commonly used for providing asynchronous primitives for group communication. Traditionally, they do not offer quality of service guarantees regarding causal and total ordering of events delivered to client applications. However, the need for ordering can be found in many distributed multimedia applications, such as collaborative whiteboards, multiplayer games, chat systems, and others. Current solutions to ordering, such as the vector clock approach or a central sequencer, generate either a high network traffic overhead or a central point of failure. This work presents an architecture, based on distributed shared memory, for event ordering in topic-based publish/subscribe systems. Tests conducted with a reference implementation show that the network traffic generated can be three orders of magnitude lower than a vector based solution.