基于dht的数据网格副本定位研究-计算机软件与理论专业论文.docxVIP

AB AB STRACT More data·-intensive and high--performance applications are required in the modem scientific research and application areas．Because lacking of data sharing and cooperation，many information systems are difficult：to communicate with each other．Data Grid provides the services which contain access，storage，transformation and management of data files． Replica is the one of the most important key technique in data grid．They are able to reduce the delay of data transfer and improve the efficiency of data access and processing．The existence of replica Can also detract the access requirements of data on original node，balance the work load of nodes in grid and consequentially optimize the performance of the whole network．Besides，when some nodes are invalid，replica are also able to reduce the possibilities of data lost and enhance the stability．However, ensuring efficient and fast access to all replicas of a file is a challenging problem for ns now． Distributed hash table(DHT)scheme is the core technique to location resources in structured peer-to-peer systems．This thesis applies peer-to—peer resource location techniques to data grids and proposes DHTRL strategy,a DHT based data西d replica location approach．Through DHTRL，data grid is divided into three layers，TRIN layer, ‘RIDN layer；RSN layer．DHTRL uses DIM(dynamic index mapping)technology to organize TRIN nodes and storage replica catalog，DIM dynamically and evenly distribute all global replica catalog information on the all TRIN．Besides by using the Chord ring thinking，we maintain TRIN efficiently． In this paper,by data鲥d simulator OptorSim，we do some experiments to prove the correctness of DHTRL strategy．Analysis and experiments show that DHTRL call provide scalable and self-adaptive replica location service，which Can effectively support one or multiple replicas location and achieve good scalability,adaptability, robustness and】0ad balance． Graduate student：pengyang Li(tSomputer Software and Theory) Directed by