Resource discovery in Grid systems based on the Distributed Hash Table

Resource discovery is one of the key functionalities of the Grid systems, since it is used by a variety of different services. The main goal of every resource discovery system is to collect the data about all the Grid resources and to serve those data to all the users and applications that are interested in them. The usage of the resource discovery service is simple: we provide it a search query as an input and it returns us the list of locations of all the resources which satisfy all the conditions provided by the query. This work presents a distributed system that is used for resource discovery in Grid systems. The system is based on structured peer-to-peer technologies; more precisely, on the Distributed Hash Table. It enables us to search for the Grid resources using exact-match queries as well as range queries. The support for range queries is very important in Grid systems since those queries are the most frequently used. The weakness of the majority of structured peer-to-peer resource discovery systems is the inefficient implementation of the support for range queries. In our system, on the other hand, the amount of network traffic that is generated during the resolution of range queries is the same as with exact-match queries. Additionally, the support for multi-attribute queries (i.e., the queries that contain multiple search conditions) is also more efficient since the amount of network traffic when resolving multi-attribute queries is also lower than with the other resource-discovery systems. Due to both the properties mentioned above and due to the better resilience to node failures, our system has better scalability than the rest of the resource-discovery systems that are based on a structured peer-to-peer system. As a consequence, its performance in large Grid systems is better than the other systems