LUG 2014 Presentations

OpenSFS_EOFS_theme-banner_finalSlideware PDFs provided by the authors. Videos thanks to InsideHPC.

Day 1 – April 8
Sessions 1 and 2 OpenSFS Community [Video] and EOFS Update [Video]
Galen Shipman, OpenSFS and Hugo Falter, EOFS
Session 3 Lustre Releases – Christopher Morrone, OpenSFS  [Video]
Session 4 Lustre Client Performance Comparison and Tuning
John Fragalla, Xyratex  [Video]
Session 5 Moving Lustre Forward – What We’ve Learned and What’s Coming
Brent Gorda, Intel [Video]
Session 6 Lustre Client IO Performance Improvements
Andrew Usleton, Intel  [Video]
Session 7 Xyratex Update (Lustre acquisition, futures, etc.)
Michael Connolly, Xyratex  [Video]
Session 8 Lustre 2.5 Performance Evaluation: Performance Improvements with Large I/O Patches, Metadata Improvements, and Metadata Scaling with DNE
Hitoshi Sato, TITECH and Shuichi Ihara, DDN  [Video]
Session 9 Lustre Future Features
Andreas Dilger, Intel  [Video]
Session 10 Lustre Feature Details:
Mike Pershin [Video]; Jinshan Xiong [Video]; and John Hammond [Video]; Intel
Session 11 OpenSFS, Lustre, and HSM: an update from Cray
Cory Spitz and Jason Goodman, Cray  [Video]
Session 12 “Quotas for Projects”: A Proposed New Feature
Shuichi Ihara, DDN  [Video]
Session 13 Dynamic LNET Config
Amir Shehata, Intel  [Video]
Session 14 LLNL – Production Plans and Best Practices
Marc Stearman, Lawrence Livermore National Laboratory  [Video]
Day 2 – April 9
Session 15 Presenting the First Lustre Annual Report: State of the Lustre Community
Meghan McClelland, OpenSFS  [Video]
Session 16 PLFS and Lustre Performance Comparison
Brett Kettering, Los Alamos National Laboratory  [Video]
Session 17 Running Native Lustre Client inside Xeon Phi
Dmitry Eremin and Zhiqi Tao, Intel  [Video]
Session 18 Integrating Array Management into Lustre
Roger Ronald and Kevin Moran, System Fabric Works  [Video]
Session 19 Metadata Benchmarks and MD Performance Metrics
Sorin Faibish, EMC   [Video]
Session 20 Practical Applications of Lustre/ZFS Hybrid Systems
Josh Judd, Warp Mechanics  [Video]
Session 21 Collective I/O for Exascale I/O Intensive Applications
Sai Narasimhamurthy, Xyratex   [Video]
Session 22 SSD Provisioning for Exascale Storage Systems: When, Where and How much?
Devesh Tiwari, Oak Ridge National Laboratory   [Video]
Session 23 Exascale Computing Vision
Eric Barton, Intel  [Video]
Session 24 An efficient distributed burst buffer system for Lustre
Bradley Settlemyer, Oak Ridge National Laboratory  [Video]
Session 25 Lustre for the Real World: Experiences with Lustre Beyond Standard HPC Applications
Robert Triendl, DDN   [Video]
Session 26 Panel: 2020 HPC Platform Architectures and their Impact on Storage
Panelists: Al Geist, Oak Ridge National Laboratory, Rob Ross, MCS, ANL, Lee Ward, Sandia National Laboratory, Terri Quinn, Lawrence Livermore National Laboratory
Moderator: Steve Simms, Indiana University  [Video]
Session 27 Lustre File System Acceleration Using Server or Storage-Side Caching: Basic Approachs and Application Use Cases
James Coomer, DDN  [Video]
Day 3 – April 10
Session 28 Run Hadoop Map Reduce Jobs on Lustre
Zhiqi Tao, Intel   [Video]
Session 29 Progress Report on Efficient Integration of Lustre and Hadoop/YARN
Weikuan Yu, Auburn University and Omkar Kulkarni, Intel  [Video]
Session 30 OpenSFS Benchmarking Working Group Filesystem Monitoring Task Effort
Andrew Uselton. Intel  [Video]
Session 31 Fine-grained File System Monitoring with Lustre Jobstat
Patrick Fitzhenry, DDN and Daniel Rodwell, Australian National University  [Video]
Session 32 Lustre Log Analyzer: A Community-centric Effort to Improve Lustre Log Analysis
Kalpak Shah, DDN  [Video]