Lustre User Group 2014

This is a stub page to facilitate contribution of information and presentations.

LUG 2014 was held in Miami, Florida, from April 8-10, 2014.

OpenSFS, in collaboration with EOFS, is proud to host the 12th annual Lustre User Group (LUG) conference. LUG continues to be the primary venue for discussion and seminars on the Lustre® parallel file system and other open source file system technologies. The event will include more than 50 sessions and panels, where attendees have the opportunity to:

· Hear from the world's leading developers, administrators, solution providers, and users of Lustre

· Be an active participant in industry dialogue on best practices and emerging technologies

· Explore upcoming developments of the Lustre file system

· Immerse in the strong Lustre community, working collaboratively to further the development of Lustre

As one of the many benefits of being a member of OpenSFS - the organization that drives HPC open source file system community efforts - OpenSFS is pleased to offer one complimentary pass to each current member entity of OpenSFS. Details are coming soon with the opening of the LUG 2014 registration site.

The venue for LUG 2014 is the Miami Marriott Biscayne Bay, located right on Biscayne Bay and just minutes from South Beach and other famous Miami attractions. Please visit the LUG 2013 web page to view the agenda and caliber of presentations of past LUG events. With the ongoing growth and outstanding progress of Lustre, the 2014 event promises to be exciting and informative.

LUG 2014 Agenda

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 10.1	Lustre Data-on-MDT/Small File I/O Mike Pershin, Intel Video
Session 10.2	Lustre Layout Enhancement John Hammond, Intel Video
Session 10.3	Lustre File Level Replication Jinshan Xiong, Intel Video
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	The First Lustre Annual 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 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