Paper Title: Painlessly Realizing Transparent Compression over Disaggregated Infrastructure

Paper Abstract: This proposed talk will discuss how Cloud infrastructure could conveniently realize application-agnostic infrastructure-level data compression. Modern Cloud infrastructure is built upon the principle of compute/storage disaggregation, which improves the system reliability and storage utilization efficiency at the cost of higher network traffic. Although data compression is an obvious option to reduce both network traffic and storage cost, very few (if any) Cloud today supports application-agnostic data compression, which is partly due to the challenge of post-compression data management in the disaggregated environment. To address this challenge without compromising data security, the (almost) only option is to decouple the tasks of “compressing data” and “managing compressed data” across the disaggregated architecture. This proposed talk will discuss such design methodology and present different strategies of implementing this design methodology. This talk will further discuss how the storage industry could innovate the design and implementation of SSDs to facilitate the implementation of infrastructure-level transparent data compression in future Cloud.

Paper Author: Tong Zhang, Chief Scientist, ScaleFlux

Author Bio: Tong Zhang is currently a Professor in the Electrical, Computer and Systems Engineering Department at Rensselaer Polytechnic Institute (RPI), NY. In 2002, he received the Ph.D. degree in electrical engineering from the University of Minnesota and joined the faculty of RPI. He has graduated 19 PhD students, and authored/co-authored over 160 papers, with over 5,000 citations and h-index of 40. In 2014, he co-founded ScaleFlux to spearhead the commercialization of computational storage drives, and currently serves as its Chief Scientist. He is an IEEE Fellow.