CONTACT   |   QUICK LINKS   |   SITEMAP     search
 
Computer Sciences
image aboutBSC computational earth life computer applications marenostrum image
Computer Sciences
Storage Systems
Home > Computer Sciences > Storage Systems pdf print
 
 
Related links

XtreemOS

Universidad Politécnica de Madrid

Universidad de Murcia

XtreemFS

SCALUS

Iolanes
 

Storage systems

stroke

OVERVIEW

LogoStorage for large installations (i.e. large clusters or the Grid) is one of the key issues in current computing, as far as performance and usability are concerned. On the one hand, the size of data grows constantly and large systems have to be ready to store this huge amount of data. On the other hand, the access to this data has to be efficient. In addition, storage systems should offer easy mechanisms to store/retrieve/manage this data. None of these issues has found a satisfactory solution in today systems and thus BSC-CNS works towards better solutions to these key issues.

OBJECTIVES

  • Study how applications use storage. Most of the research done on file systems are based on assumptions about the use of storage studied at least a decade ago. We work on updating this information and either show how the behavior has changed or prove that these older studies are still valid for today applications.
  • Find mechanisms to make storage more efficient for applications. In order to make storage more efficient, we study what scalability problems appear in large installations and propose solutions mainly based on the autonomic storage, parallel data access, and the proper use of heterogeneity concepts.
  • Find better ways to express the needs applications have when run on large installations. Current large systems normally lack mechanisms and/or interfaces for applications to use data effectively. For instance, a basic mechanism such as producer/consumer I/O is not easy or efficient in Grid systems. The semantics for the file naming in Grid systems, which should be a basic issue, it is also quite underdeveloped. In this group we address these, and other similar, semantic problems.


PROJECTS/AREAS

The team structures its research activities around two areas:
  • Grid I/O:In this project we work on mechanism that will simplify the access to data in grid system, as well as making these accesses much more efficient.
  • Scalable file systems: In this project we study the problems found in cluster file systems when running on large cluster installation with thousands of clients.

In addition to these two areas, BSC-CNS has the mission of cooperating with other institutions. For this reason, the team does research in other areas in collaboration with other institutions:

  • DualFS is a new generation journal file system where metadata is only kept in the log and it is not replicated in the data device. This work is done in cooperation with the Universidad de Murcia (http://ditec.um.es/~piernas/dualfs/).
  • MAPFS-Grid is an upgrade of MAPFS, which is a parallel file system, to the grid environment. This work adds autonomic capabilities to MAPFS that allows it to take adequate decisions to a Grid environment. This work is done in cooperation with the Univesidad Politécnica de Madrid.
  • Disk scheduling. In this project we propose to investigate the relationship between the disk scheduling, the segments in the disk cache, and host memory caches to improve the performance of disk accesses allowing a tight cooperation between these three levels. This work is done in cooperation with the Universidad de Murcia.



PEOPLE
arrowARTIAGA AMOUROUX, ERNEST , RESEARCHER
arrowCORTES ROSELLO, ANTONIO , STORAGE SYSTEMS GROUP MANAGER
arrowDHEENA, KOUSIK , STUDENT
arrowGIRALT, JACOBO , RESEARCHER
arrowGONZALEZ DE BENITO, JUAN , RESEARCHER
arrowMAKATOS, THANOS , RESEARCHER
arrowMARTI FRAIZ, JONATHAN , RESEARCHER
arrowMIRANDA, ALBERTO , RESIDENT STUDENT
arrowNOU CASTELL, RAMON , RESEARCHER
arrowWIBERG, JAN , RESEARCHER


PUBLICATIONS AND COMMUNICATIONS


Publications

Journals

Alberto Sánchez, María S. Pérez, Jesús Montes, Toni Cortes. A high performance suite of data services for grids. Future Generation Computer Systems, Volume 26, issue 4 , April 2010.

Felix Hupfeld, Björn Kolbeck, Jan Stender, Mikael Högqvist, Toni Cortes, Jonathan Martí and Jesús Malo . FaTLease: scalable fault-tolerant lease negotiation with Paxos. Cluster Computing, Volume 12, number 2, pp. 175–188, June 2009.

Felix Hupfeld, Toni Cortes, Björn Kolbeck, Jan Stender, Erich Focht, Matthias Hess, Jesus Malo, Jonathan Marti, Eugenio Cesario . The XtreemFS architecture—a case for object-based file systems in Grids. CONCURRENCY AND COMPUTATION: PRACTICE AND EXPERIENCE, Vol 20, No. 17, December 2008.

Alberto Sánchez, María S. Pérez, Pierre Gueant, Jesús Montes, Pilar Herrero and Toni Cortes. Improving GridFTP transfers by means of a multiagent parallel file system. Multiagent and Grid Systems - An International Journal, Vol 3, No. 4, , December 2007.

J. Piernas, T. Cortes, J. M. García. The Design of New Journaling File Systems: The DualFS Case. IEEE TRANSACTION ON COMPUTERS, Vol. 52, num. 2, February 2007.

J. Piernas, T. Cortes, J. M. Garcia. Traditional File Systems versus DualFS: a Performance Comparison Approach. IEICE Transactions on Information and Systems, Vol.E87-D No.7 p. 1703 - 1711, July 2004.

T. Cortes, J. Labarta. Taking Advantage of Heterogeneity in Disk Arrays. Journal on Parallel and Distributed Computing (JPDC), Volume 63, number 4, pp. 448-464, April 2003.

Book chapters

T. Cortes, J. Labarta, S. Girona. Design Issues of a Cooperative Cache with no Coherence Problems. High Performance mass Storage and Parallel I/O: Technologies and Applications, Editors: Hai Jin, Toni Cortes, and Rajkumar Buyya. Publisher: IEEE Press and Wiley. ISBN: 0-471-20809-4, January 2002.

T. Cortes. Software RAID and Parallel Filesystems. High Performance Cluster Computing: Architectures and Systems, Editor: Rajkumar Buyya. Publisher: Prentice Hall. ISBN: 0-13-013784-7, January 1999.

International Conferences

Ramón Nou, Jacobo Girarlt, Julita Corbalan, Enric Tejedor, J. Oriol Fitó, Josep M. Pérez, Toni Cortes. XtreemOS Application Execution Management: A scalable approach. 11th ACM/IEEE International Conference on Grid Computing (Grid 2010), Brussels, Belgium , October 2010.

Pilar Gonález-Férez, Juan Piernas, and Toni Cortes. Simultaneous Evaluation of Multiple I/O Strategies. 22nd International Symposium on Computer Architecture and High Performance Computing, Petrópolis, Brazil , October 2010.

Alvaro Martínez, Santiago Prieto, Noé Gallego, Ramon Nou, Jacobo Giralt, Toni Cortes. XtreemOS-MD: Grid computing from mobile devices. Mobilware 2010, Chicago, USA, June 2010.

J. L. Gonzalez, Toni Cortes, Jaime Delgado-Meraz, Ana Piedad Rubio. HRaidTools: An on-line Suite of Simulation Tools for Heterogeneous RAID systems. Third International Conference on Simulation Tools and Techniques (SIMUTools 2010), Malaga, Spain, March 2010.

Ernest Artiaga and Toni Cortes. Using File System Virtualization to Avoid Metadata Bottlenecks. Design, Automation and Test in Europe (DATE 2010), Dresden, Germany, March 2010.

José Luis González and Toni Cortes. Distributing Orthogonal Redundancy on Adaptive Disk Arrays. International Conference on Grid computing, high-performAnce and Distributed Applications (GADA'08), Monterrey, Mexico, November 2008.

Pilar Gonález-Férez, Juan Piernas, and Toni Cortes. Evaluating the Effectiveness of REDCAP to Recover the Locality Missed by Today’s Linux Systems. 16th Annual Meeting of the IEEE International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems (MASCOTS) (poster), Baltimore, MD, September 2008.

Felix Hupfeld, Björn Kolbeck, Jan Stender, Mikael Högqvist, Toni Cortes, Jonathan Martí, Jesús Malo. FaTLease: Scalable Fault-Tolerant Lease Negotiation with Paxos. International Symposium on High-Performance Distributed Computing, Boston, MA, June 2008.

J.L. Gonzalez and Toni Cortes. An Adaptive Data Block Placement based on Deterministic Zones (AdaptiveZ). International Conference on Grid computing, high-performAnce and Distributed Applications (GADA'07), Vilamoura, Algarve, Portugal, November 2007.

Pilar González-Férez, Juan Piernas, and Toni Cortes. The RAM Enhanced Disk Cache Project (REDCAP). 24th IEEE Conference on Mass Storage Systems and Technologies (MSST07), San Diego, California, USA, September 2007.

Alberto Sánchez, Toni Cortes, Jesús Montes, Pierre Gueant and María S. Pérez. Lessons learnt from cluster computing: How they can be applied to grid environments. The 8th Hellenic European Research on Computer Mathematics & its Applications Conference, Athens Greece, , September 2007.

J. Martí, J. Malo, T. Cortes. Increasing Parallelism for Workflows in the Grid. Europar 2007, Rennes, France, , August 2007.

Eugenio Cesario, Toni Cortes, Erich Focht, Matthias Hess, Felix Hupfeld, Björn Kolbeck, Jesús Malo, Jonathan Martí, Jan Stender. XtreemFS - an object-based file system for large-scale federated IT infrastructures. LinuxTAG 2007, Berlin, Germany, , May 2007.

J. L. Gonzalez, T. Cortes. Evaluating the Effects of Upgrading Heterogeneous Disk Arrays. International Symposium on Performance Evaluation of Computer and Telecommunication Systems (SPECTS 2006), Calgary, Canada. (Best paper award) , August 2006.

F. Hidrobo and T. Cortes. Autonomic Storage System Based on Automatic Learning. International Conference on High-performance Computing (HiPC 2004), Bangalore, India, December 2004.

T. Olivares, T. Cortes, L. Orozco-Barbosa, F.J. Quiles, and A. Garrido. A Multithread NFS Client Architecture for Multimedia Cluster Generation. Parallel and Distributed Computing and Systems (PDCS 2003), Marina del Rey, USA, November 2003.

F. Hidrobo, T. Cortes. Towards an Automatic Storage System to Improve Parallel I/O. F. Hidrobo and T. CortesParallel and Distributed Computing and Systems (PDCS 2003), Marina del Rey, USA, November 2003.

T. Cortes, J. Labarta. A Case For Heterogeneous Disk Arrays. 1st IEEE International Conference on Cluster Computing (Cluster 2000), Chemnitz, Germany, November 2002.

J. Piernas, T. Cortes, J. M. Garcia. DualFS: a New Journaling File System without Meta-Data Duplication. 16th Annual ACM International Conference on Supercomputing, New York, June 2002.

T. Cortes, J. Labarta. Extending Heterogeneity to RAID level 5. USENIX Annual Technical Conference, Boston, MA, June 2001.

T. Cortes, J. Labarta. HRaid: a Flexible Storage-system Simulator. International Conference on Parallel and Distributed Processing Techniques and Applications (PDPTA'99), Las Vegas, Nev, June 1999.

T. Cortes and J. Labarta . Linear Aggressive Prefetching: A way to Increase the Performance of Cooperative Caches. International Parallel Processing Symposium (IPPS'99), San Juan, Puerto Rico, April 1999.

T. Cortes and J. Labarta. PAFS: a new Generation in Cooperative Caching. International Conference on Parallel and Distributed Processing Techniques and Applications (PDPTA'98), Las Vegas, Nev, July 1998.

T. Cortes, S. Girona and J. Labarta. Avoiding the Cache-coherence Problem in Parallel/Distribute File Systems. High Performance Computing and Networking (HPCN´97), Vienna, Austria, April 1997.

T. Cortes, S. Girona and J. Labarta. PACA: A Cooperative File-system Cache for Parallel Machines. 2nd International Euro-Par Conference (Euro-Par'96), Lyon, France, August 1996.

National Conferences

Pilar Gonález-Férez, Juan Piernas, and Toni Cortes . The RAM Enhanced Disk Cache Project (REDCAP). XIX Jornadas de Paralelismo, Castellón,  Spain, September 2008.

Jesús Malo, Jonathan Martí, Toni Cortes. Replica management in GRID superscalar. XVIII Jornadas de Paralelismo, Zaragoza , September 2007.

Teresa Olivares, Toni Cortes, Luis Orozco, Francisco J. Quiles, Antonio Garrido . Un nuevo cliente NFS predictivo multihilo para la era multimedia. XIV Jornadas de Paralelismo, Leganés, Madrid , September 2003.

J. Piernas, T. Cortes, and J. M. Garcia. DualFS: Towards a New Journaling File System. Jornadas de Paralelismo, LLeida , September 2002.

T. Cortes, S. Girona and J. Labarta. PACA: A Cooperative File-system Cache. VII Jornadas de Paralelismo, Santiago de Compostela, Spain , September 1996.

Workshops

Jan Stender, Björn Kolbeck, Felix Hupfeld, Eugenio Cesario, Erich Focht, Matthias Hess, Jesús Malo, and Jonathan Martí. Striping without Sacrifices: Maintaining POSIX Semantics in a Parallel File System. 1st Workshop on Large Scale Computing Systems, Boston, MA, June 2008.

Felix Hupfeld, Toni Cortes, Björn Kolbeck, Erich Focht, Matthias Hess, Jesus Malo, Jonathan Marti, Jan Stender, Eugenio Cesario. XtreemFS: a case for object-based storage in Grid data management. 3rd VLDB Workshop on Data Management in Grids, Vienna, Austria , September 2007.

Jose Luis Gonzalez, Toni Cortes. Increasing the capacity of RAID5 by online gradual assimilation. International Workshop on Storage Network Architecture and Parallel I/Os, Antibes Juan-les-pins, France , September 2004.

F. Hidrobo, T. Cortes. Towards a Zero-Knowledge Model for Disk Drive. Autonomic Computing Workshop (AMS 2003), Seattle, WA , June 2003.

T. Cortes, S. Girona and J. Labarta . Design Issues of a Cooperative Cache with no Coherence Problems. 5th workshop on I/O in Parallel and Distributed Systems (IOPADS'97), San Jose, CA , November 1997.

Communications

Toni Cortes, Christine Morin, Yvon Jegu. Easing Application Execution in Grids with XtreemOS Operating System. OGF-28, Munich, Germany, March 2010.

A. Brinkmann and T. Cortes. Handling Heterogeneous Storage Devices in Clusters. IEEE Conference on Cluster Computing (Cluster 2007),, Austin, Texas (Tutorial), September 2007.

T. Cortes. Parallel I/O: Lessons learnt in the last 20 years. IEEE Conference on Cluster Computing (Cluster 2004), San Diego, California (Tutorial), September 2004.

J. Piernas, T. Cortes, J. M. Garcia. Traditional versus Next-Generation Journaling File Systems: a Performance Comparison Approach. 2nd Workshop on Hardware/Software Support for High performance Scientific and Engineering Computing (SHPSEC-03), New Orleans, Louisiana, September 2003.

T. Cortes. Autonomic Storage System based on Automatic Learning. Microsoft Research, Cambridge, UK, , February 2008.

T. Cortes. XtreemFS: a global file system targeted to data sharing among organizations. Universidad de Murcia, Murcia, , February 2008.

T. Cortes. Adapting RAID technology to large heterogeneous clusters. HeteroPar, Austin, Texas (Invited talk), September 2007.

 
  top
link_top
  Barcelona Supercomputing Center, 2010 - Legal Notice
 
link_top