Ian Bird, Ying Chen, Bryan Hess, Andy Kowalski, Chip Watson

Jefferson Lab has implemented a scalable, distributed, high performance mass storage system - JASMine.  The system is entirely implemented in Java, provides access to robotic tape storage and includes disk cache and stage manager components.  The disk manager subsystem may be used independently to manage stand-alone disk pools.  The system includes a scheduler to provide policy-based access to the storage systems.  Security is provided by pluggable authentication modules and is implemented at the network socket level.  The tape and disk cache systems have well defined interfaces in order to provide integration with grid-based services.  The system is in production and being used to archive 1 TB per day from the experiments, and currently moves over 2 TB per day total.  This paper will describe the architecture of JASMine; discuss the rationale for building the system, and present a transparent 3^rd party file replication service to move data to collaborating institutes using JASMine, XML, and servlet technology interfacing to grid-based file transfer mechanisms.