10th Parallel Data Storage Workshop

held in conjunction with SC15

monday, November 16, 2015
Austin, TX
Hilton Salon g

Workshop Chairs:

Sandia National Laboratories

Virginia Tech

General Chair:


abstract / agenda / cfp / WIP session

full proceedings of the 10th pdsw are now online in the

ACm digital library


Peta­ and exascale computing infrastructures make unprecedented demands on storage capacity, performance, concurrency, reliability, availability, and manageability. This one­day workshop focuses on the data storage and management problems and emerging solutions found in peta­ and exascale scientific computing environments, with special attention to issues in which community collaboration can be crucial for problem identification, workload capture, solution interoperability, standards with community buy­in, and shared tools.

Addressing storage media ranging from tape, HDD, and SSD, to emerging storage devices like NVRAM, the workshop seeks contributions on relevant topics, including but not limited to:

  • performance and benchmarking
  • failure tolerance problems and solutions
  • APIs for high performance features
  • parallel file systems
  • high bandwidth storage architectures
  • support for high velocity or complex data
  • metadata intensive workloads
  • autonomics for HPC storage
  • virtualization for storage systems
  • archival storage advances
  • resource management innovations
  • incorporation of emerging storage technologies
  • workload study from production systems, and
  • programmability of storage systems


8:55am - 9:00am Welcome & Introduction
9:00am – 10:00am Keynote SpeakerDr. Ken Anderson, Akonia Holographics, LLC
10:00am - 10:30am Morning Break
10:30am – 12:00pm SESSION 1: Scaling Up
Chair: John Bent, EMC
Papers: 25 min + 5 min questions
  DeltaFS: Exascale File Systems Scale Better Without Dedicated Servers
*Qing Zheng (Carnegie Mellon University)
Kai Ren (Carnegie Mellon University)
Garth Gibson (Carnegie Mellon University)
Bradley W. Settlemyer (Los Alamos National Laboratory)
Gary Grider (Los Alamos National Laboratory)
Paper | Slides
  Taming the Cloud Object Storage with MOS
*Ali Anwar (Virginia Tech/Compuer Science)
Yue Cheng (Virginia Tech/Computer Science)
Aayush Gupta (IBM Research Almaden)
Ali R. Butt (Virginia Tech/Computer Science)
Paper | Slides
  Experiences in Using OS-level Virtualization for Block I/O
*Dan Huang (University of Central Florida)
Jun Wang (University of Central Florida)
Qing Liu (Oak Ridge National Lab)
Jiangling Yin (University of Central Florida)
Xuhong Zhang (University of Central Florida)
Xunchao Chen (University of Central Florida)
Paper | Slides
12:00pm - 1:30pm Lunch (not provided)
1:30pm – 3:00pm SESSION 2: Potpourri
Chair: Kathryn Mohror, Lawrence Livermore National Laboratory
  BAD Check: Bulk Asynchronous Distributed Checkpointing and IO
*John Bent (EMC), Brad Settlemyer (LANL)
Haiyun Bao (EMC)
Sorin Faibish (EMC), Jeremy Sauer (LANL)
Jingwang Zhang (EMC)
Paper | Slides
  Tackling the Reproducibility Problem in Storage Systems Research with Declarative Experiment Specifications
*Ivo Jimenez (UC Santa Cruz)
Carlos Maltzahn (UC Santa Cruz)
Jay Lofstead (SNL), Kathryn Mohror (LLNL)
Adam Moody (LLNL)
Remzi Arpaci-Dusseau (UW Madison)
Andrea Arpaci-Dusseau (UW Madison)
Paper | Slides
  Comparative I/O Workload Characterization of Two Leadership Class Storage Clusters
*Raghul Gunasekaran (ORNL)
Sarp Oral (ORNL)
Jason Hill (ORNL)
Ross Miller (ORNL)
Feiyi Wang (ORNL)
Dustin Leverman (ORNL)
Paper | Slides
3:00pm – 3:30pm Afternoon Break
3:30pm – 5:00pm SESSION 3: Characterization
Chair: Rob Latham, Argonne National Laboratory
  Heavy-tailed Distribution of Parallel I/O System Response Time
*Bin Dong (Computational Research Division, Lawrence Berkeley
   National Laboratory)
Surendra Byna (Computational Research Division, Lawrence
    Berkeley National Laboratory)
Kesheng Wu (Computational Research Division, Lawrence
    Berkeley National Laboratory)
Paper | Slides
  Pattern-driven Parallel I/O Tuning
*Babak Behzad (University of Illinois at Urbana-Champaign)
Suren Byna (Lawrence Berkeley National Laboratory)
Prabhat (Lawrence Berkeley National Laboratory)
Marc Snir (University of Illinois at Urbana-Champaign,
   Argonne National Laboratory)
Paper | Slides
  Automatic and Transparent I/O Optimization With Storage Integrated Application Runtime Support
*Noah Watkins (UC Santa Cruz)
Zhihao Jia (Stanford University)
Galen Shipman (LANL)
Carlos Maltzahn (UC Santa Cruz)
Alex Aiken (Stanford University)
Pat McCormick (LANL)
Paper | Slides
Chair: Dean Hildebrand, IBM
  Sirocco: A Storage System Design for Exascale
*Matthew L. Curry, Sandia National Laboratories
Geoff Danielson, Hewlett Packard Enterprise
H. Lee Ward, Sandia National Laboratories
Anthony Skjellum, Dept of Computer Science and Software
   Engineering, Auburn University
Jay Lofstead, Sandia National Laboratories
Abstract | Slides
  General I/O Characteristics of HPC Applications on Multiple Peta-scale Supercomputers
*Huong Luu, Marianne Winslett University of Illinois at
   Urbana - Champaign
William Gropp, Marianne Winslett University of Illinois at
   Urbana - Champaign
Abstract | Slides
  Rapid Replication of Multi-Petabyte File Systems
*Justin Sybrandt, Grove City College, NERSC
Jason Hick, NERSC
Abstract | Slides
  SADedupe: Skew-Aware Inline Deduplication for Distributed Storage
*Binqi Zhang, The University of Sydney, Sydney, Australia
Bing Bing Zhou, The University of Sydney, Sydney, Australia
Chen Wang, CSIRO, Sydney, Australia
Dong Yuan, The University of Sydney, Sydney, Australia
Albert Y. Zomaya, The University of Sydney, Sydney, Australia
Abstract | Slides
  MarFS - A Scalable Near-Posix Metadata File System with Cloud
Based Object Backend

Gary Grider, Los Alamos National Lab
Dave Montoya, Los Alamos National Lab
Hsing-bung Chen, Los Alamos National Lab
Brett Kettering, Los Alamos National Lab
Jeff Inman, Los Alamos National Lab
Chris DeJager, Los Alamos National Lab
Alfred Torrez, Los Alamos National Lab
*Kyle Lamb, Los Alamos National Lab
Chris Hoffman, Los Alamos National Lab
David Bonnie, Los Alamos National Lab
Ronald Croonenberg, Los Alamos National Lab
Matthew Broomfield, Los Alamos National Lab
Sean Leffler, Los Alamos National Lab
Parks Fields, Los Alamos National Lab
Jeff Kuehn, Los Alamos National Lab
John Bent, EMC Corporation
Abstract | Slides
  BBAlloc: Towards Allocation based Management of Burst Buffer Systems
*Sagar Thapaliya, University of Alabama at Birmingham
Purushotham Bangalore, University of Alabama at Birmingham
Jay Lofstead, Sandia National Laboratories
Kathryn Mohror, Lawrence Livermore National Laboratory
Adam Moody, Lawrence Livermore National Laboratory
Abstract | Slides
* = speaker



CALL FOR PAPERS POSTER - download, print, and hang one up at your office / department!

The Parallel Data Storage Workshop holds a peer reviewed competitive process for selecting short papers. Submit a not previously published short paper of up to 5 pages, not less than 10 point font and not including references, in a PDF file as instructed on the workshop web site. Submitted papers will be reviewed under the supervision of the workshop program committee. Submissions should indicate authors and affiliations. Final papers must not be longer than 5 pages (excluding references). Selected papers and associated talk slides will be made available on the workshop web site; the papers will also be published in the digital library of the IEEE or ACM.

Work-in-progress (WIP) Submissions

There will also be a WIP session at the workshop, where presenters give 5-minute brief talks on their on-going work, with fresh problems/solutions, but may not be mature or complete yet for paper submission. A 1-page abstract is required.


Please be aware that all attendees to the workshop, both speakers and participants, will have to pay the SC15 registration fee. Workshops are no longer included as part of the technical program registration. With a paid Technical Program registration, workshop fees are $50 for Members/Non-Members and $25 for Students. A workshop only fee is available for $200 for Members/Non-Members and $100 for Students.

To attend the workshop, please register through the Supercomputing '15 registration page. Registration opens in July.

program COMMITTEE:

Eric Barton, Intel, UK
John Bent, EMC, USA
Ali Butt (Chair), Virginia Tech, USA
Suren Byna, Lawrence Berkeley National Laboratory, USA
Philip Carns, Argonne National Laboratory, USA
Garth Gibson, CMU and Panasas, USA
Dean Hildebrand, IBM Research, USA
John Jenkins, Argonne National Laboratory, USA
Julian Kunkel, University of Hamburg, Germany
Robert Latham, Argonne National Laboratory, USA
Min Li, IBM Watson, USA
Jay Lofstead (Chair), Sandia National Laboratories, USA
Jeremy Logan, Oak Ridge National Laboratory, USA
Xiaosong Ma, Qatar Computing Research Institute, Qatar
Carlos Maltzahn, University of California, Santa Cruz, USA
Kathryn Mohror, Lawrence Livermore National Laboratory, USA
Robert Ross, Argonne National Laboratory, USA
Karsten Schwan, Georgia Tech, USA
Jin Xiong, ICT, Chinese Academy of Science, China


John Bent, EMC 
Evan J. Felix, Pacific Northwest National Laboratory 
Garth A. Gibson (chair), Carnegie Mellon University and Panasas Inc. 
Gary Grider, Los Alamos National Laboratory
Dean Hildebrand, IBM Research
Dries Kimpe, KCG, USA
Darrell Long, University of California, Santa Cruz 
Xiaosong Ma, Qatar Computing Research Institute, Qatar
Carlos Maltzahn, University of California, Santa Cruz
Robert Ross, Argonne National Laboratory
Philip C. Roth, Oak Ridge National Laboratory 
Karsten Schwan, Georgia Tech
John Shalf, National Energy Research Scientific Computing Center,
    Lawrence Berkeley National Laboratory 
Lee Ward, Sandia National Laboratories