An Efficient Grid Data Access with StoRM

Abstract

In production data Grids, high performance disk storage solutions using parallel file systems are becoming increasingly important to provide reliability and high speed I/O operations needed by High Energy Physics analysis farms. Today, Storage Area Network solutions are commonly deployed at Large Hadron Collider data centres, and parallel file systems such as GPFS and Lustre provide reliable, high speed native POSIX I/O operations in parallel fashion. In this paper, we describe StoRM, a Grid middleware component, implementing the standard Storage Resource Manager v2.2 interface. Its architecture fully exploits the potentiality offered by the underlying cluster file system. Indeed, it enables and encourages the use of the native POSIX file protocol (i.e. ``file://{''}) allowing managed Storage Element to improve job efficiency in data accessing. The job running on the worker node can perform a direct access to the Storage Element managed by StoRM as if it were a local disk, instead of transferring data from Storage Elements to the local disk.