Paper Title: Smart New Architecture for Cloud-Scale Storage

Paper Abstract: Modern applications including real-time analytics, AI/ML, IoT, AR/VR, cybersecurity, genomics, and video and image processing present new challenges for storage system architects. These new workloads require a combination of capacity, performance, and scalability that current storage architectures simply can’t deliver. The solution is a new generation of storage architectures enabled by new technologies including persistent memory, QLC flash, and NVMe-based fabrics. A new hardware architecture also requires rethinking the software that turns that hardware into a storage system using storage software in containers to manage simple NVMe-oF JBOFs at exabyte scale. These new architectures can provide the scale, performance, and cost, cloud operators demand while also simplifying and automating system management. This session will explore the challenges a new cloud-scale system must address, and one of these new architectures as an example.

Paper Author: Asaf Levy, Chief Architect, VAST Data

Author Bio: Asaf Levy is Chief Architect at VAST Data, a developer of large-scale all-flash file and object storage systems. He is responsible for requirements, analysis, architecture, design, and implementation of enterprise storage software solutions. He has led software development teams worldwide, and holds 11 patents in the storage area. He has over 12 years experience in software development, including management positions at Primary Data and IBM. He earned a BS degree in software engineering at the Ben-Gurion University of the Negev (Israel).