Group communication is one of the main paradigms for implementing replication middleware. The high run-time costs of group communication may constitute a major performance bottleneck for modern enterprise applications. In this paper we investigate the applicability of message packing, a technique originally proposed by Friedman and Van Renesse in 1997 for improving the performance of group communication, to modern hardware and group communication toolkits. Most importantly, we extend this technique with a policy for varying the packing degree automatically, based on dynamic estimates of the optimal packing degree. The resulting system is adaptive in that it allows exploiting message packing efficiently in a dynamic and potentially unknown run-time environment. Several case studies are analyzed.

SUMMARYWe propose a service replication framework for unreliable networks. The service exhibits the same consistency guarantees about the order of execution of operation requests as its non-replicated implementation. Such guarantees are preserved in spite of server replica failure or network failure (either between server replicas or between a client and a server replica), and irrespective of when the failure occurs. Moreover, the service guarantees that in the case when a client sends an 'update' request multiple times, there is no risk that the request be executed multiple times. No hypotheses about the timing retransmission policy of clients are made, e.g. the very same request might even arrive at different server replicas simultaneously. All of these features make the proposed framework particularly suitable for interaction between remote programs, a scenario that is gaining increasing importance. We discuss a prototype implementation of our replication framework based on Tomcat, a very popular Java-based Web server. The prototype comes into two flavors: replication of HTTP client session data and replication of a counter accessed as a Web service.

This paper outlines the expected research contribution of my Ph.D. thesis in the area of middleware for dependability. Dependability is a long-standing desirable property for today's network-based service applications but requirements of dependable systems are often conflicting in many ways, especially when dealing with performance related aspects. I describe a novel approach called translucent replication to address the conflicts between dependability and performance. The proposed solution is a software architecture with two key aspects: (i) enhanced intra-layer and cross-layer interaction, for flexibility and extensibility of the application/middleware infrastructure; and (ii) a semantic knowledge repository that enables smart middleware behavior, providing adaptation by matching application dependability needs, specific to data being replicated, and the system working conditions. Exploiting translucent replication, application designers can explore operating regions (instead of single points) in the dependability design-space, and dynamically investigate sets of solutions for the conflicts between dependability and performance. After presenting the general model, a realization of translucent replication within the context of a JMS solution is evaluated, to demonstrate the validity of this approach.

No abstract