Storage and File System Design Research

People | Publications | Tech Reports | Theses | Internal

We use experimentation and analysis to understand how systems interact, how the world is changing, and how file systems and storage systems should evolve.

Current work includes:

Our previous work (papers below) has aimed to answer the following questions [abstracts hyperlinked]:

This research is part of the SYRAH group.

People

Current

Alumni

  • Kiran-Kumar Muniswamy-Reddy. PhD 2010, Foundations for Provenance-Aware Systems
    (Now at Amazon).
  • Lex Stein. PhD 2007, Adaptive Parallel Computation for Heterogeneous Processors
    (Now at Microsoft Research Asia).
  • Daniel J. Ellard. PhD 2004, Trace-Based Analyses and Optimizations for Network Storage Servers
    (Now at Network Appliance, Advanced Technology Group).
  • Kostas Magoutis. PhD 2003, Exploiting Direct-Access Networking in Network Attached Storage Systems
    (Now at IBM Research, TJ Watson).
  • Keith A. Smith. PhD 2000, Workload-Specific File System Benchmarks
    (Now at Network Appliance, Advanced Technology Group).
  • Salimah Addetia. ME 2002, Caching in DAFS
    (Now at Network Appliance).

Publications

    • Lex Stein, David Holland, Margo Seltzer, and Zheng Zhang. 
      Can a file system virtualize processors? (PDF)
      In Proceedings of the 1st EuroSys Workshop on Virtualization for HPC,
      Lisbon, Portugal, March 2007.

    • Lex Stein.
      Stupid file systems are better. (PDFHTML)
      In Proceedings of the 10th ACM Workshop on Hot Topics in Operating Systems (HotOS-X),
      Santa Fe, New Mexico, May 2005

    • Jonathan Ledlie, Chaki Ng, David A. Holland, Kiran-Kumar Muniswamy-Reddy, Uri Braun, and Margo Seltzer. 
      Provenance-Aware Sensor Data Storage. (PDF
      In Proceedings of NetDB 2005, Tokyo, Japan, April 2005.

    • Michael Mesnier, Eno Thereska, Daniel Ellard, Gregory R. Ganger and Margo Seltzer. 
      File classification in self-* storage systems. (PDFPostscript
      Carnegie Mellon University Technical Report CMU-PDL-04-101, January 2004. 
      Proceedings of the International Conference on Autonomic Computing (ICAC-04).

    • Daniel Ellard and Margo Seltzer. 
      New NFS Tracing Tools and Techniques for System Analysis (PDFPostscript
      Appears in Proceedings of the 17th Large Installation System Administration Conference (LISA'03), pages 73-85, San Diego, CA. October 2003. (note that the page numbers in the on-line version are not identical to the printed proceedings)

    • Daniel Ellard and Margo Seltzer. 
      NFS Tricks and Benchmarking Traps (PDFHTML
      Appears in Proceedings of the 2003 USENIX Annual Technical Conference, FREENIX Track, pages 101-114, San Antonio, Texas. June 2003.

      • Source code for the changes described in the paper.

      • Slides from the presentation (PDFHTML).

      • Errata: there is a typo in Figure 8 of the published paper. The caption should read ``... scsi1 runs 60-70% faster for all tests when cursors are enabled.ide1 is only 50% faster for the 2-stride test...'' This on-line version of the paper is correct.

    • Kostas Magoutis, Salimah Addetia, Alexandra Fedorova, Margo I. Seltzer. 
      Making the Most out of Direct Access Network-Attached Storage, (PDF)
      In Proceedings of Second USENIX Conference on File and Storage Technologies (FAST'03), San Francisco, CA, March 31-April 2, 2003.

    • Daniel Ellard, Jonathan Ledlie, Pia Malkani and Margo Seltzer. 
      Passive NFS Tracing of Email and Research Workloads (PDFHTML
      Appears in Proceedings of the Second USENIX File and Storage Technologies Conference (FAST'03), pages 203-216, San Francisco, California. March, 2003.

      • Slides from the presentation (PDFHTML).

    • Lex Stein, Michael J. Tucker, and Margo I. Seltzer. 
      Building a Reliable Mutable File System on Peer-to-peer Storage, (Postscript)
      In Proceedings of the International Workshop on Reliable Peer-to-peer Distributed Systems, Osaka, Japan, October, 2002.

    • Kostas Magoutis, Salimah Addetia, Alexandra Fedorova, Margo I. Seltzer, Jeffrey S. Chase, Andrew J. Gallatin, Richard Kisley, Rajiv G. Wickremesinghe, Eran Gabber. 
      Structure and Performance of the Direct Access File System, (PDF)
      In Proceedings of 2002 USENIX Annual Technical Conference, Monterey, CA, June 9-14, 2002.

    • Kostas Magoutis. 
      Design and Implementation of a Direct Access File System (DAFS) Kernel Server for FreeBSD (PostscriptPDF),
      Appears in Proceedings of USENIX BSDCon 2002 Conference, San Franscisco, CA, February 11-14, 2002.

    • Kostas Magoutis. 
      The Optimistic Direct Access File System: Design and Network Interface Support (PostscriptPDF)
      Appears in Proceedings of Workshop on Novel Uses of System Area Networks (Held in conjunction with HPCA-8), Cambridge, MA, February 2, 2002.

Technical Reports

Theses

  • Lex Stein. 
    Adaptive Parallel Computation for Heterogeneous Processors (Abstract), 
    A dissertation presented by Lex Stein to the School of Engineering and Applied Sciences in partial fulfillment of the requirements for the Doctor of Philosophy in the subject of Computer Science, Harvard University, Cambridge, MA, May, 2007

  • Daniel J. Ellard. 
    Trace-Based Analyses and Optimizations for Network Storage Servers (Abstract), 
    A dissertation presented by Daniel J. Ellard to The School of Engineering and Applied Sciences in partial fulfillment of the requirements for the Doctor of Philosophy in the subject of Computer Science, Harvard University, Cambridge, MA, May, 2004

  • Kostas Magoutis. 
    Exploiting Direct-Access Networking in Network Attached Storage Systems (Abstract), 
    A dissertation presented by Kostas Magoutis to The School of Engineering and Applied Sciences in partial fulfillment of the requirements for the Doctor of Philosophy in the subject of Computer Science, Harvard University, Cambridge, MA, May, 2003

  • Keith Arnold Smith. 
    Workload-Specific File System Benchmarks (Abstract), 
    A dissertation presented by Keith Arnold Smith to The School of Engineering and Applied Sciences in partial fulfillment of the requirements for the Doctor of Philosophy in the subject of Computer Science, Harvard University, Cambridge, MA, January, 2001

  • Salimah Addetia. 
    CacheDAFS: User Level Client-side Caching for the Direct Access File System (DAFS) (Abstract), 
    A thesis presented by Salimah Addetia to The School of Engineering and Applied Sciences in partial fulfillment of the requirements for the Master of Engineering in the subject of Computer Science, Harvard University, Cambridge, MA, 2001