[DB Seminar] Spring 2018: Joy Arulraj
For the first time since Von Neumann’s architecture of the 1940s, device manufacturers have created a new non-volatile memory (NVM) technology that can serve as both system memory and storage. NVM supports low-latency byte-addressable reads and writes similar to volatile memory, but all writes to it are persistent like a solid-state disk. The advent of NVM invalidates decades of design decisions that are deeply embedded in today’s database systems. These systems are unable to take full advantage of NVM because their internal architectures are predicated on the assumption that memory is volatile. With NVM, many of the components of today’s database systems are unnecessary and will degrade the performance and availability of data-intensive applications.
In this talk, I will present our research on understanding the implications of NVM for database systems. Specifically, I will discuss my work on Peloton, the first database system that is designed from the ground up for NVM. I will first present write-behind logging, a novel NVM-centric protocol that improves the performance and availability of the database system by an order-of-magnitude compared to the ubiquitous write-ahead logging protocol. Write-behind logging. I will then present the BzTree, an NVM-centric index data structure that illustrates how to simplify programming on NVM. Together, these projects demonstrate that the impact of NVM spans across multiple layers of the database system.