Stuart J. Norcross

A Methodology for Developing and Deploying Distributed Applications

We describe a methodology for developing and deploying distributed Java applications using a reflective middleware system called RAFDA. We illustrate the methodology by describing how it has been used to develop a peer-to-peer infrastructure, and explain the benefits relative to other techniques. The strengths of the approach are that the application logic can be designed and implemented completely independently of distribution concerns, easing the development task, and that this gives great flexibility to alter distribution decisions late in the development cycle.

Stuart J. Norcross

This paper describes an infrastructure for the deployment and use of Web Services that are resilient to the failure of the nodes that host those services. The infrastructure presents a single interface that provides mechanisms for users to publish services and to find hosted services. The infrastructure supports the autonomic deployment of services and the brokerage of hosts on which services may be deployed. Once deployed, services are autonomically managed in a number of aspects including load balancing, availability, failure detection and recovery, and lifetime management. Services are published and deployed with associated metadata describing the service type. This same metadata may be used subsequently by interested parties to discover services. The infrastructure uses peer-to-peer (P2P) overlay technologies to abstract over the underlying network to deploy and locate instances of those services. It takes advantage of the P2P network to replicate directory services used to locate service instances (for using a service), Service Hosts (for deployment of services) and Autonomic Managers which manage the deployed services. The P2P overlay network is itself constructed using novel Web services-based middleware and a variation of the Chord P2P protocol, which is self-managing.

Unifying static and dynamic approaches to evolution through the compliant systems architecture

Support for evolution can be classified as static or dynamic. Static evolvability is principally concerned with structuring systems as separated abstractions. Dynamic evolvability is concerned with the means by which change is effected. Dynamic evolution provides the requisite flexibility for application evolution, however, the dynamic approach is not scalable in the absence of static measures to achieve separation of abstractions. This separation comes at a price in that issues of concern become trapped within static abstraction boundaries, thereby inhibiting dynamic evolution. The need for a unified approach has long been recognised but existing systems that attempt to address this need do so in an ad-hoc manner. The principal reason for this is that these approaches fail to resolve the incongruence in the underlying models. Our contention is that this disparity is incidental rather than fundamental to the problem. To this end, we propose an alternative model based on the compliant systems architecture (CSA), a structuring methodology for constructing software systems. The overriding benefit of this work is increased flexibility. Specifically our contribution is an instantiation of the CSA that supports unified static and dynamic evolution techniques. Our model is explored through a worked example in which we evolve an applications concurrency model.

Design, Implementation and Deployment of State Machines Using a Generative Approach

We describe an approach to designing and implementing a distributed system as a family of related finite state machines, generated from a single abstract model. Various artefacts are generated from each state machine, including diagrams, source-level protocol implementations and documentation. The state machine family formalises the interactions between the components of the distributed system, allowing increased confidence in correctness. Our methodology facilitates the application of state machines to problems for which they would not otherwise be suitable. We illustrate the technique with the example of a Byzantine-fault-tolerant commit protocol used in a distributed storage system, showing how an abstract model can be defined in terms of an abstract state space and various categories of state transitions. We describe how such an abstract model can be deployed in a concrete system, and propose a general methodology for developing systems in this style.