A Replication Software Architecture(RSA) for Supporting Irregular Applications on Wide-Area Distributed Computing Environments

In the distributed computing environment, many large-scale scientific applications are irregular applications which perform their computation and I/O on an irregularly discretized mesh. However, most of the previous work in the area of irregular applications focuses mainly on the local environments. In distributed computing environments, since many remotely located scientists should share the data to produce useful results, providing a consistent data replication mechanism to minimize the remote data access time is a critical issue in achieving high-performance bandwidth. We have developed a replication software architecture(RSA) that enables the geographically distributed scientists to easily replicate irregular computations with minimum overheads, while safely sharing large-scale data sets to produce useful results. Since RSA uses database support to store the data-related and computational-related metadata, it can easily be ported to any computing environments. In this paper, we describe the design and implementation of RSA for irregular applications and present performance results on Linux clusters.