I/O and Data Seminar Series: Revisiting Databases for Scale Up Data Management
Title of Presentation: “Revisiting Databases for Scale Up Data Management”
Presented by: Jay Lofstead, Sandia National Laboratory
Traditional relational databases were rejected for data management for scale up computing due to overhead issues. Instead, we have adopted custom file formats with minimal overhead. With the shifting technology landscape including data movement being the new bottleneck (rather than storage device latencies), revisiting how much databases, including newer NoSQL databases, can be useful in scale up computing. Data indexing to accelerate data selection and robust resilience mechanisms inherent in transactional systems offer features that are still attractive for scale up computing. This talk describes initial efforts investigating using these technologies for scale up computing.
Speaker’s Bio: Dr. Jay Lofstead is a Principal Member of Technical Staff at Sandia National Laboratories. His work focuses on infrastructure to support all varieties of simulation, scientific, and engineering workflows with a strong emphasis on IO, middleware, storage, transactions, operating system features to support workflows, containers, software engineering and reproducibility. He is co-founder of the IO-500 storage list. He also works extensively to support various student mentoring and diversity programs at several venues each year including outreach to both high school and college students. Jay graduated with a BS, MS, and PhD in Computer Science from Georgia Institute of Technology and was a recipient of a 2013 R&D 100 award for his work on the ADIOS IO library.