A protocol-independent technique for eliminating redundant network traffic
Proceedings of the conference on Applications, Technologies, Architectures, and Protocols for Computer Communication
Condor-G: A Computation Management Agent for Multi-Institutional Grids
Cluster Computing
The Anatomy of the Grid: Enabling Scalable Virtual Organizations
International Journal of High Performance Computing Applications
Packet caches on routers: the implications of universal redundant traffic elimination
Proceedings of the ACM SIGCOMM 2008 conference on Data communication
Network-aware scheduling for real-time execution support in data-intensive optical Grids
Future Generation Computer Systems
Hi-index | 0.00 |
In the last years we observed an explosive growth in the number and size of electronic data repositories, often organized and structured according to the emerging distributed computing paradigm referred to as the datagrid. Here, one of the most essential and critical components is the data management layer faced with the problem of moving extremely large datasets, shared among large end user communities, connected to the grid by means of a broad and heterogeneous variety of communication links/infrastructures, often very limited in their capacity/performance. In this scenario we proposed and developed a new service oriented abstraction implementing WAN optimization facilities, such as traffic Compression, and Protocol-Specific Acceleration, for Internet-based data grid environments, to minimize I/O and communication latencies incurred during data transfer operation on low performance/congested links. Such a solution demonstrated to efficiently and effectively scale low-performance datagrid sites beyond their traditional capabilities, by improving communication performance and minimizing its costs through consolidation.