Fri, 19-Nov-2021 / 1:00pm / TBA
In large-scale data storage systems, erasure codes are employed to store data in a redundant fashion to protect against data loss. In this setting, a set of k data blocks to be stored is encoded using an [n, k] code to generate n blocks that are then stored on distinct storage devices. In contrast to how redundancy is configured in current systems, we show that the failure rates of devices vary significantly over time. Dynamically tuning the redundancy to match the observed failure rates provides more than 15% cost and energy savings (translating to a savings of millions of dollars). However, traditional codes suffer from prohibitively high resource overheads in changing the code parameters on already encoded data.
In this talk, we: 1. Introduce the concept of redundancy tuning and its benefits using real-world production data from large-scale cluster storage systems, 2. Present a new theoretical framework to formalize the notion of “code conversion”—the process of converting data encoded using an [n, k] code into data encoded using a code with different parameters [n’, k’], while maintaining desired decodability properties, 3. Introduce “convertible codes”, a new class of codes that enable resource-efficient conversion, 4. Prove tight bounds on resource requirements of convertible codes and present optimal explicit constructions.
Rashmi Vinayak is an assistant professor in the Computer Science department at Carnegie Mellon University. Rashmi is a recipient of NSF CAREER Award 2020-25, Tata Institute of Fundamental Research Memorial Lecture Award 2020, Facebook Distributed Systems Research Award 2019, Google Faculty Research Award 2018, and Facebook Communications and Networking Research Award 2017. Her work has received USENIX NSDI 2021 Community (Best Paper) Award, UC Berkeley Eli Jury Dissertation Award 2016, and IEEE Data Storage Best Paper and Best Student Paper Awards for 2011⁄2012. During her Ph.D. studies, Rashmi was a recipient of Facebook Fellowship 2012-13, the Microsoft Research PhD Fellowship 2013-15, and the Google Anita Borg Memorial Scholarship 2015-16. Rashmi received her Ph.D. from UC Berkeley in 2016, and was a postdoctoral scholar at UC Berkeley’s AMPLab/RISELab from 2016-17. Webpage: http://www.cs.cmu.edu/~rvinayak/
Packard Building
Electrical Engineering Department
350 Jane Stanford Way
Stanford, CA 94305-9515
