Stochastic modeling of large-scale solid-state storage systems: Analysis, design tradeoffs and optimization
Refereed conference paper presented and published in conference proceedings


Times Cited
Altmetrics Information
.

Other information
AbstractSolid state drives (SSDs) have seen wide deployment in mobiles, desktops, and data centers due to their high I/O performance and low energy consumption. As SSDs write data out-of-place, garbage collection (GC) is required to erase and reclaim space with invalid data. However, GC poses additional writes that hinder the I/O performance, while SSD blocks can only endure a finite number of erasures. Thus, there is a performance-durability tradeoff on the design space of GC. To characterize the optimal tradeoff, this paper formulates an analytical model that explores the full optimal design space of any GC algorithm. We first present a stochastic Markov chain model that captures the I/O dynamics of large-scale SSDs, and adapt the mean-field approach to derive the asymptotic steady-state performance. We further prove the model convergence and generalize the model for all types of workload. Inspired by this model, we propose a randomized greedy algorithm (RGA) that can operate along the optimal tradeoff curve with a tunable parameter. Using trace-driven simulation on DiskSim with SSD addons, we demonstrate how RGA can be parameterized to realize the performance-durability tradeoff. Copyright © 2013 ACM.
All Author(s) ListLi Y., Lee P.P.C., Lui J.C.S.
Name of Conference2013 ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems, SIGMETRICS 2013
Start Date of Conference17/06/2013
End Date of Conference21/06/2013
Place of ConferencePittsburgh, PA
Country/Region of ConferenceUnited States of America
Detailed descriptionorganized by ACM\n\nTo ORKTS: ACM Sigmetrics is considered as a top tier conference by the external visiting committee in the Faculty of Engineeri
Year2013
Month7
Day22
Volume Number41
Issue Number1 SPEC. ISS.
Pages179 - 190
ISBN9781450319003
ISSN0163-5999
LanguagesEnglish-United Kingdom
KeywordsCleaning cost, Garbage collection, Mean field analysis, Solid-state drives, Stochastic modeling, Wear-leveling

Last updated on 2020-12-09 at 00:49