ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술지 CLOCK-DNV: A Write Buffer Algorithm for Flash Storage Devices of Consumer Electronics
Cited 14 time in scopus Download 5 time Share share facebook twitter linkedin kakaostory
저자
강동현, 한세준, 김영창, 엄영익
발행일
201702
출처
IEEE Transactions on Consumer Electronics, v.63 no.1, pp.85-91
ISSN
0098-3063
출판사
IEEE
DOI
https://dx.doi.org/10.1109/TCE.2017.014700
협약과제
16MS2200, (ICBMS-총괄) ICBMS(IoT, 클라우드, 빅데이터, 모바일, 정보보호) 핵심 기술 개발 사업 총괄 및 엑사스케일급 클라우드 스토리지 기술 개발, 김영균
초록
Today, flash storage devices have become a standard storage in consumer electronics devices, such as smartphones, smart tablets, and smart TVs, due to their attractive features. Since flash storage helps to cut down on system response for customers, consumer devices based on the flash storage are gradually increasing. Unfortunately, the flash storage of consumer electronics devices suffers from random write requests because applications running on the consumer device simultaneously issue a lot of write operations to store their persistent data. This paper proposes a novel write buffer algorithm, called Clock with DRAM and NVM hybrid write buffer (CLOCK-DNV), that reshapes random write requests into sequential ones. In order to maximize the number of consecutive write requests, CLOCK-DNV takes the benefits of NVM media with the dirty page padding mechanism. For extensive evaluation, the proposed algorithm is implemented on a flash storage simulator, which is widely used for performance analysis, and is compared with two write buffer algorithms, FAB and CBM. The evaluation results clearly show that CLOCK-DNV maintains higher hit ratios than other write buffer algorithms. Moreover, CLOCK-DNV efficiently reduces the number of write requests issued to the underlying flash memory by up to 56% compared with the state-of-the-art algorithm, CBM, while extending the endurance of flash storage by up to 56%.
KSP 제안 키워드
ART algorithm, Consumer devices, Dirty page, Extensive evaluation, Flash Memory, Flash storage, Performance analysis, Random Write, Storage device, System response, Write buffer