Dynamic Self-Adapting Software Architecture for Replica Management in Grids

Single data replica management strategy can not meet the complexity and diverseness in data grid. This paper proposes a dynamic self-adapting replica management architecture (DSA-RM) driven by software architecture (SA). In DSA-RM, architecture descriptions are shared by the whole grid environment as a system kernel to schedule various replica management components that are adapted to various application and VO in data grid. By the abstraction of DSA-RM, the paper describes the formal definitions of replica management components and discusses the dynamic self-adapting regulation of component evolution and multiplication in dynamic environment. By these regulations, the DSA-RM’s framework and algorithms of multiplication are designed. Experimental results show that the DSA-RM can effectively promote the performance of grid system. Finally, the project of applying the DSA-RM on Shanghai medical data grid is introduced.