An improved DHT-based Grid Information services architecture

Fundamental problems that confront traditional centralized Grid information services are low query efficiency and single points of failure. This paper presents an improved DHT-based Grid information services architecture, that resolves these problems well. The architecture assigns each resource node and information server an m-bit identifier by hashing attribute values. Every node makes connection with successor information server according to their identifiers to organize Virtual Organization(VO). Resource query is highly efficient with locating identifier. Information servers are fully decentralized, solving single points of failure. Range query is a difficult problem in DHT but an indispensable part in Grid information services. We improve our architecture with tree data structure and Path Caching Schemes to support range query. Results from theory analysis and simulations show that DHT-based architecture is highly efficient, robust, load balanced and scalable.