Cargando…

Enabling data-intensive science with Tactical Storage Systems

Large scale scientific computing requires the ability to share and consume data and storage in complex ways across multiple systems. However, conventional systems constrain users to the fixed abstractions selected by the local system administrator. The result is that users must either move data manu...

Descripción completa

Detalles Bibliográficos
Autores principales: Thain, Douglas, Marquina, Miguel Angel
Lenguaje:eng
Publicado: 2006
Materias:
Acceso en línea:http://cds.cern.ch/record/977396
Descripción
Sumario:Large scale scientific computing requires the ability to share and consume data and storage in complex ways across multiple systems. However, conventional systems constrain users to the fixed abstractions selected by the local system administrator. The result is that users must either move data manually over the wide area or simply be satisfied with the resources of a single cluster. To remedy this situation, we introduce the concept of a tactical storage system (TSS) that allows users to create, reconfigure, and destroy distributed storage systems without special privileges or complex configuration. We have deployed a prototype TSS of 200 disks and 8 TB of storage at the University of Notre Dame and applied it to several problems in astrophysics, high energy physics, and bioinformatics. This talk will focus on novel system structures that support data-intensive science. About the speaker: Douglas Thain is an Assistant Professor of Computer Science and Engineering at the University of Notre Dame. He received a Ph.D. in Computer Science at the University of Wisconsin where he contributed to the Condor distributed computing project. His areas of research include distributed file systems, distributed computing, fault tolerance, and mobile computing.