Tuning modern storage hierarchies

Abstract

Storage systems are becoming increasingly complex, with new devices on the market such as NVMe, new computing paradigms such as micro services, and new workloads such as self-driving cars. Each of these departures from the monolithic computing baseline introduce new opportunities for tuning the system to be lower latency, lower cost, or better to support tighter SLOs. In this talk, I will go over how SimBioSysLab is using a variety of statistical methods to define and solve the problems in tuning modern storage hierarchies, focusing on caching and workload characterization.

Bio:

Avani Wildani is an Assistant Professor in Mathematics/Computer Science and Neuroscience at Emory University. Prior to that, she was a Pioneer Postdoctoral Fellow in computational neuroscience at the Salk Institute for Biological Sciences. Her interests are centered around information storage and retrieval across different storage models, with application domains including access prediction, data deduplication, archival economics, power management, wireless mesh networks, auditory receptive field characterization, and pollution monitoring.

Join meeting in Sococo VH 102. Login: tuftscs.sococo.com

Join Zoom Meeting: https://tufts.zoom.us/j/98610939077

PASSWORD: see colloquium email

Dial by your location: +1 646 558 8656 US (New York)

Meeting ID: 986 1093 9077

Passcode: see colloquium email