Building Next-Generation Flash Storage Systems: From Data Centers to Wearables

February 27, 2017 - 11:15am to 12:15pm
Georgia Institute of Technology
Keller Hall 3-180
Jon Weissman

ABSTRACT: Flash-based storage (e.g., SSD) has been widely adopted in almost every kind of platform spanning all the way from wearables, to mobiles, to data center servers. Since their arrival more than a decade ago, Flash has been improved significantly in terms of latency, throughput and capacity. While storage hardware has evolved, the corresponding software stack is the main bottleneck not only for Flash but also for imminent storage media deemed to be significantly faster than Flash.

In this talk, I will demonstrate new approaches to designing flash-based storage systems to unleash the power of hardware devices while preserving the simplicity and guarantees of system abstractions. Specifically, I will present three systems (FlashBlox, FlashMap, and WearDrive) that enable applications leverage the power of Flash with little software overheads by challenging conventional wisdom on storage system design. They improve performance and energy-efficiency significantly for applications in large-scale data centers as well as in small smart devices such as wearables.

BIO: Jian Huang is a Ph.D. candidate in the School of Computer Science at Georgia Institute of Technology. His research interests lie in the areas of computer systems, including operating systems, systems architecture, systems reliability and security, and distributed systems. He enjoys building practical, reliable, secure and high-performance systems. Most of his recent work focuses on building memory and storage systems with new and emerging memory technologies such as flash memory, battery-backed DRAM and phase-change memory. His research contributions have been published at ASPLOS, FAST, USENIX ATC, ISCA, VLDB, SoCC, and IPDPS. His work WearDrive won the Best Paper Award at USENIX ATC in 2015 and attracted popular press coverage in more than eight countries. His work FlashMap won the IEEE Micro Top Picks Honorable Mention in 2016. Most of the technologies he has developed have had an impact on industrial and real-world systems, some of them are being transferred into products including those at Microsoft data centers.

More details about his research can be found at