Storage systems


LogoStorage is the new challenge in large-scale computing systems. On the one hand, machines in 2020 are expected to break the exaflop barrier (Exascale). This new computational performance should be in pace with a similar increase in the storage capacity and performance, otherwise bottlenecks will appear and Exascale benefits will not show up. On the other hand, the exponential growth of available data is leading to what has been called the big-data problem. In this area, many new challenges have appeared such as accessing the data in an efficient way or enabling the sharing of this data while guaranteeing the control on the usage to the owner of the data. The storage-system group at BSC-CNS is actively participating in the research of new abstractions and middleware that will address the afore-mentioned problems.

  • Research new storage abstractions to organize and store data better suited for Exascale and big-data challenges.
  • Implement production-quality middleware solutions based on the proposed new abstractions to mitigate the Exascale and big-data problems.
  • Evaluate the potential of virtualization to improve both efficiency and usability of storage systems.
Research Lines: 

The team structures its research activities around three research lines:

  • Big data (Sharing, usability, and performance): This research line focuses on a new abstraction (self-contained objects) that will simplify the task of sharing large amounts of data among many players (in a secure, efficient, and controlled way).
  • High-performance IO (Exascale): Storage is becoming key in HPC systems, and especially when we have exascale systems into mind. This research line investigates several paths to improve the performance of storage systems at both data and metadata levels.
  • File system virtualization (Usability and performance): Virtualization, in its widest meaning, is starting to be used in the word of high-performance storage. This research line experiments on taking advantage of file-system virtualization to make storage systems more performant and/or usable.




Cortes T. EOFS Exascale IO workgroup status. 11th HLRS/hww Workshop on Scalable Global Parallel File Systems - Total Cost of Dataship. 2012 .
Pessolani P, Cortes T, Gonnet S, Tinetti FG. Sistema de Virtualización con Recursos Distribuidos. Workshop de Investigadores en Ciencias de la Computación. 2012 .
González-Férez P, Piernas J, Cortes T. DADS: Dynamic and Automatic Disk Scheduling. 27th Symposium On Applied Computing. 2012 .
Miranda A, Cortes T. Analyzing Long-Term Access Locality to Find Ways to Improve Distributed Storage Systems. 20th Euromicro International Conference on Parallel, Distributed and Network-Based Computing. 2012 .
Queralt A, Teniente E. Verification and Validation of UML Conceptual Schemas with OCL Constraints. ACM Transactions on Software Engineering and Methodology. 2012 ;21:13.
Juiz C, Kounev S, Gilly K, Brosig F, Nou R. Resilience Assessment and Evaluation of Computing Systems. In: Wolter K, Avritzer A, Vieira M, van Moorsel A Dagstuhl Seminar 10292. Dagstuhl Seminar 10292. Springer-Verlag Berlin Heidelberg; 2012.
Sánchez A, Montes J, Pérez MS, Cortes T. An Autonomic Framework for Enhancing the Quality of Data Grid Services. Future Generation Computer Systems. 2012 ;28(7):1005--1016.