image placeholder

UCSB COMPUTER SCIENCE DEPARTMENT PRESENTS:

Wednesday, October 30, 2013
3:30 – 4:30 PM
Room 1132 Harold Frank Hall

HOST: Amr El Abbadi

SPEAKER: David Lomet
Principal Researcher, Microsoft Research

Title:

LLAMA: A Cache/Storage Subsystem for Modern Hardware (joint work with Justin Levandoski and Sudipta Sengupta)

Abstract:

LLAMA is a subsystem designed for new hardware environments that supports an API for page-oriented access methods, providing both cache and storage management. Caching (CL) and storage (SL) layers use a common mapping table that separates a page’s logical and physical location. CL supports data updates and management updates (e.g., for index re-organization) via latch-free compare-and-swap atomic state changes on its mapping table. SL uses the same mapping table to cope with page location changes produced by log structuring on every page flush. To demonstrate LLAMA’s suitability, we tailored our latch-free Bw-tree implementation to use LLAMA. The Bw-tree is a B-tree style index. Layered on LLAMA, it has higher performance and scalability using real workloads compared with BerkeleyDB’s B-tree, which is known for good performance.

Bio:

David Lomet (Ph.D from Penn) is a Principal Researcher and manager of the Database Group at Microsoft Research Redmond. Earlier, he was at Digital’s CRL, Wang Institute, and IBM Research. Lomet has over 100 papers on databases, indexing, concurrency, and recovery, including two SIGMOD “best papers”. He is one of the inventors of transactions. Lomet has served on SIGMOD, VLDB, and ICDE PCs, being co-chair of ICDE’2000 and VLDB’2006. He won SIGMOD’s Contributions Award for his service as Data Engineering Bulletin Editor-in-Chief since 1992. He has been editor of ACM TODS, VLDB Journal, and DAPD. He has served on the VLDB Endowment and ICDE Steering Committee, has been IEEE TCDE Chair and is a Fellow of AAAS, ACM, and IEEE.