Selection algorithms for replicated Web servers
ACM SIGMETRICS Performance Evaluation Review
Consistency in replicated continuous interactive media
CSCW '00 Proceedings of the 2000 ACM conference on Computer supported cooperative work
Time, clocks, and the ordering of events in a distributed system
Communications of the ACM
Replication Techniques in Distributed Systems
Replication Techniques in Distributed Systems
Introduction to Discrete Event Systems
Introduction to Discrete Event Systems
Evaluation of transport protocols for the session initiation protocol
IEEE Network: The Magazine of Global Internetworking
Inconsistency evaluation in a replicated IP-Based call control system
ISAS'06 Proceedings of the Third international conference on Service Availability
Journal of Systems and Software
Hi-index | 0.00 |
There has been a rapid growth of services based on session control. Session-based services comprise multimedia conferences, Internet telephone calls, instant messaging, and similar applications consisting of one or more media types such as audio and video. Deployment examples include session control services as part of the IP multimedia subsystem (IMS), in the third-generation mobile networks. High service dependability in session control systems is achieved by introducing redundancy, e.g., through reliable server pooling (RSerPool) or clustering. Namely, session control servers are multiplied in server sets. Performance of such replicated session control servers is quantified by transaction control time. Thus, reducing transaction control time enhances performance. Server selection policies (SSP) are crucial in achieving this goal. The maximum availability (MA) SSP is proposed to improve session control performance in scenarios with server and communication failures. Based on a status vector, MA aims at maximizing the probability of successful transaction with the current transmission, thereby minimizing the average number of attempted servers until success. MA is applicable in a broad range of IP-based systems and services, and it is independent of the fault-tolerant platform. A simple protocol extension is proposed in order to integrate MA into the RSerPool fault-tolerant architecture. In addition, an analytic model is derived based on certain system model assumptions. Analytic and simulation results show that transaction control time is considerably reduced with MA as opposed to when using traditional round robin.