XROOTD/TXNetFile: a highly scalable architecture for data access in the ROOT environment

Abstract

When dealing with the concurrent access from a multitude of clients to petabyte-scale data repositories, high performance, fault tolerance, robustness, and scalability are four very important issues. This paper describes the choices and the work done to address the high demand data access needs of modern physics experiments, such as the BaBar experiment at SLAC, and of any other field in which a reliable data access is a primary issue. For this purpose a highly scalable architecture has been designed and deployed which allows thousands of batch jobs and interactive sessions to effectively access the data repositories with as few fails as possible.