文章基本信息

标题：Wear Leveling Revisited
本地全文：下载
作者：Taku Onodera ; Tetsuo Shibuya
期刊名称：LIPIcs : Leibniz International Proceedings in Informatics
电子版ISSN：1868-8969
出版年度：2020
卷号：181
页码：1-17
DOI：10.4230/LIPIcs.ISAAC.2020.65
出版社：Schloss Dagstuhl -- Leibniz-Zentrum fuer Informatik
摘要：Wear leveling - a technology designed to balance the write counts among memory cells regardless of the requested accesses - is vital in prolonging the lifetime of certain computer memory devices, especially the type of next-generation non-volatile memory, known as phase change memory (PCM). Although researchers have been working extensively on wear leveling, almost all existing studies mainly focus on the practical aspects and lack rigorous mathematical analyses. The lack of theory is particularly problematic for security-critical applications. We address this issue by revisiting wear leveling from a theoretical perspective. First, we completely determine the problem parameter regime for which Security Refresh - one of the most well-known existing wear leveling schemes for PCM - works effectively by providing a positive result and a matching negative result. In particular, Security Refresh is not competitive for the practically relevant regime of large-scale memory. Then, we propose a novel scheme that achieves better lifetime, time/space overhead, and wear-free space for the relevant regime not covered by Security Refresh. Unlike existing studies, we give rigorous theoretical lifetime analyses, which is necessary to assess and control the security risk.
关键词：Wear leveling; Randomized algorithm; Non-volatile memory