Lightweight Causal Cluster Consistency

Report, 2005

Within an effort for providing a layered architecture of services supporting multi-peer collaborative applications, this paper proposes a new type of consistency management aimed for applications where a large number of processes share a large set of replicated objects. Many such applications, like peer-to-peer collaborative environments for training or entertaining purposes, platforms for distributed monitoring and tuning of networks, rely on a fast propagation of updates on objects, however they also require a notion of consistent state update. To cope with these requirements and also ensure scalability, we propose the cluster consistency model. In the proposed model a dynamic set of processes, called coordinators, may concurrently propose updates to a subset of objects which form a cluster. Updates are applied in some order of interest by the coordinators of the cluster. Moreover, any interested process can receive update messages referring to replicated objects, with an option for the updates to be delivered unordered or in the same order as to the coordinators. We also propose a two-layered architecture for providing cluster consistency. This is a general architecture that can be applied on top of the standard Internet communication layers and can offer a modular, layered set of services to the applications that need them. Further, we present a fault-tolerant protocol implementing causal cluster consistency with predictable reliability, running on top of decentralised probabilistic protocols supporting group communication. Our experimental study, conducted by programming and evaluating the two-layered architecture as protocols executing on top of standard Internet transport services, shows that the approach scales well, imposes an even load on the system, and provides high-probability reliability guarantees.