Please use this identifier to cite or link to this item: http://scholarbank.nus.edu.sg/handle/10635/139718
Title: AN OPTIMIZED WEAR LEVELING ALGORITHM FOR NVM CACHE WITH WRITE ENDURANCE PROBLEM
Authors: BAO NING
Keywords: NVM, disk cache, write endurance, wear leveling, algorithm
Issue Date: 14-Dec-2017
Citation: BAO NING (2017-12-14). AN OPTIMIZED WEAR LEVELING ALGORITHM FOR NVM CACHE WITH WRITE ENDURANCE PROBLEM. ScholarBank@NUS Repository.
Abstract: The NVM technologies are developing rapidly. Intel Optane have been selling to public since late 2017, which are attractive replacements for SSDs as disk cache. However, most NVM technologies have limited write endurance which means that too many writes to a single cell results in failing permanently. To increase the lifespan of NVM disk cache, wear leveling techniques try to balance the write traffic among different units on the device. To have a better wear performance, it is crucial to utilize information about data temperature that measures the future update frequency. However, the existing wear leveling algorithms fail to utilize such information contained in caching algorithm. We propose a novel algorithm called CacheWL that highly integrates the caching algorithm mechanisms into wear leveling to get a better performance. We conducted a series of trace-driven experiments and CacheWL increased the standard deviation by 14.1% compared with a representative traditional wear leveling algorithm.
URI: http://scholarbank.nus.edu.sg/handle/10635/139718
Appears in Collections:Master's Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
BAON.pdf785.46 kBAdobe PDF

OPEN

NoneView/Download

Page view(s)

52
checked on Nov 15, 2018

Download(s)

116
checked on Nov 15, 2018

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.