Towards a Globalised Data Access

Chapter
Part of the The Frontiers Collection book series (FRONTCOLL)

Abstract

In this chapter we address various solutions to initiate a smooth transition from a high performance storage model composed by several nodes in different distant sites to a model where the nodes cooperate to give a unique file system-like coherent view of their content. This task, historically considered very problematic, has to be considered from several points of view, functional and not, in order to be able to deploy a production-quality system, where the functionalities are effectively usable, and the data access performance is as close as possible to the one reachable by the used hardware. This can be considered as the major challenge in such systems, even because the general expectations about performance and robustness are very high, and very often they are compared to distributed file systems, whose evolution over time has been quite promising, but not to the point of being able to fully satisfy the requirements of large scale computing. To reach this objective, among other items, a design must face the difficulties dealing with the network latency, which varies of more than two orders of magnitude between local network access and Wide Area Network access.

Keywords

Data Access Wide Area Network Distribute File System Data Chunk Read Request 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

References

  1. 1.
    ALICE: Technical Design Report of the Computing. June 2005. ISBN 92-9083-247-9. http://aliceinfo.cern.ch/Collaboration/Documents/TDR/Computing.html
  2. 2.
    Anderson, T.E., Dahlin, M., Neefe, J.M., Patterson, D.A., Rosselli, D.S., Wang, R.Y.: Serverless Network File Systems. ACM Trans. Comput. Syst. 1, (1996)Google Scholar
  3. 3.
    Ballintijn, M., Brun, R., Rademakers, F., Roland, G.: Distributed Parallel Analysis Framework with PROOF. http://root.cern.ch/twiki/bin/view/ROOT/PROOF
  4. 4.
    Bar-Noy, A., Ho, C.-T.: Broadcasting Multiple Messages in the Multiport Model. IEEE Trans. Parallel Distr. Syst., Sept, 1988Google Scholar
  5. 5.
    Bar-Noy, A., Freund, A., (Seffi) Naor, J.: On-line Load Balancing in a Hierarchical Server Topology. In: Proceedings of the 7th Annual European Symposium on Algorithms, 1999Google Scholar
  6. 6.
    Betev, L., Carminati, F., Furano, F., Grigoras, C., Saiz, P.: The ALICE computing model: an overview. Third International Conference ”Distributed Computing and Grid-technologies in Science and Education”, GRID2008, http://grid2008.jinr.ru/
  7. 7.
    Dorigo, A., Elmer, P., Furano, F., Hanushevsky, A.: Xrootd - A highly scalable architecture for data access. WSEAS Trans. Comput., Apr. (2005)Google Scholar
  8. 8.
    Dorigo, A., Elmer, P., Furano, F., Hanushevsky, A.: XROOTD/TXNetFile: a highly scalable architecture for data access in the ROOT environment. Proceedings of the 4th WSEAS international Conference on Telecommunications and informatics (Prague, Czech Republic, March 13 - 15, 2005). Husak, M., Mastorakis, N. (eds.) World Scientific and Engineering Academy and Society (WSEAS), Stevens Point, Wisconsin, 1-6Google Scholar
  9. 9.
    Feichtinger, D., Peters, A.J.: Authorization of Data Access in Distributed Storage Systems. The 6th IEEE/ACM International Workshop on Grid Computing, 2005. http://ieeexplore.ieee.org/iel5/10354/32950/01542739.pdf?arnumber=1542739
  10. 10.
    Furano, F., Hanushevsky, A.: Data access performance through parallelization and vectored access. Some results. CHEP07: Computing for High Energy Physics. J. Phys. Conf. 119 119 (2008) 072016 (9pp)Google Scholar
  11. 11.
    Furano, F., Hanushevsky, A.: Managing commitments in a Multi Agent System using Passive Bids. iat, 2005 IEEE/WIC/ACM International Conference on Intelligent Agent Technology (IAT’05), pp. 698-701, 2005Google Scholar
  12. 12.
    Garcia, F., Calderon, A., Carretero, J., Perez, J.M., Fernandez, J.: A Parallel and Fault Tolerant File System based on NFS Servers” Euro-PDP’03, IEEE Computer Society, 2003Google Scholar
  13. 13.
    Ghemawat, S., Gobioff, H., Leung, S.-T.: The Google file system. In: Proceedings of the nineteenth ACM symposium on Operating systems principles, Oct, ACM press, 2003Google Scholar
  14. 14.
    Hanushevsky, A., Weeks, B.: Designing high performance data access systems: invited talk abstract. In: Proceedings of the 5th international Workshop on Software and Performance (Palma, Illes Balears, Spain, July 12 - 14, 2005). WOSP ’05. ACM, New York, NY, 267-267. DOI= http://doi.acm.org/10.1145/1071021.1071053
  15. 15.
    Hanushevsky, A.: Are SE architectures ready for LHC? In: Proceedings of ACAT 2008: XII International Workshop on Advanced Computing and Analysis Techniques in Physics Research. http://acat2008.cern.ch/
  16. 16.
    Howard, J.H. et al.: Scale and performance in a distributed file system. ACM Trans. Comput. Syst. 6 (1988)Google Scholar
  17. 17.
    Lustre: a scalable, secure, robust, highly-available cluster file system. It is designed, developed and maintained by Sun Microsystems, Inc. http://www.lustre.org/
  18. 18.
    Patterson, R.H., Gibson, G.A., Ginting, E., Stodolsky, D., Zelenka, J.: Informed prefetching and caching. In: Proceedings of the 15th ACM Symposium on Operating Systems Principles, 1995Google Scholar
  19. 19.
    Ripeanu, M., Foster, I., Iamnitchi, A.: Mapping the Gnutella Network: Properties of Large-Scale Peer-to-Peer Systems and Implications for System Design. IEEE Internet Comput. J. 1(Jan-Feb), Springer-Verlag (2002)Google Scholar
  20. 20.
    ROOT: An Object-Oriented Data Analysis Framework http://root.cern.ch
  21. 21.
    The babar collaboration home page. http://www.slac.stanford.edu/BFROOT
  22. 22.
    The IEEE Computer Society’s Storage System Standards Working Group. http://ssswg.org/
  23. 23.
  24. 24.
    Waterhouse, S.R., Doolin, D.M., Kan, G., Faybishenko, Y.: Distributed Search in P2P Networks. IEEE Internet Comput. J. 6 (2002)Google Scholar
  25. 25.
    Whitney, V.: Comparing Different File Systems’ NFS Performance. A cluster File System and a couple of NAS Servers thrown in. The sixth SCICOMP Meeting, SCICOMP 6 (Univ. of Berkeley), IBM System Scientific Computing User Group, http://pdsf.nersc.gov/talks/talks.html, 2002
  26. 26.
    XRootd explained. Computing seminar at CERN, http://indico.cern.ch/conferenceDisplay.py?confId=38458

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  1. 1.CERNGenevaSwitzerland
  2. 2.SLACStanfordUSA

Personalised recommendations