• Title/Summary/Keyword: iFLASH

Search Result 227, Processing Time 0.025 seconds

An Empirical Study on Linux I/O stack for the Lifetime of SSD Perspective (SSD 수명 관점에서 리눅스 I/O 스택에 대한 실험적 분석)

  • Jeong, Nam Ki;Han, Tae Hee
    • Journal of the Institute of Electronics and Information Engineers
    • /
    • v.52 no.9
    • /
    • pp.54-62
    • /
    • 2015
  • Although NAND flash-based SSD (Solid-State Drive) provides superior performance in comparison to HDD (Hard Disk Drive), it has a major drawback in write endurance. As a result, the lifetime of SSD is determined by the workload and thus it becomes a big challenge in current technology trend of such as the shifting from SLC (Single Level Cell) to MLC (Multi Level cell) and even TLC (Triple Level Cell). Most previous studies have dealt with wear-leveling or improving SSD lifetime regarding hardware architecture. In this paper, we propose the optimal configuration of host I/O stack focusing on file system, I/O scheduler, and link power management using JEDEC enterprise workloads in terms of WAF (Write Amplification Factor) which represents the efficiency perspective of SSD life time especially for host write processing into flash memory. Experimental analysis shows that the optimum configuration of I/O stack for the perspective of SSD lifetime is MinPower-Dead-XFS which prolongs the lifetime of SSD approximately 2.6 times in comparison with MaxPower-Cfq-Ext4, the best performance combination. Though the performance was reduced by 13%, this contributions demonstrates a considerable aspect of SSD lifetime in relation to I/O stack optimization.

Shadow Recovery for Column-based Databases (컬럼-기반 데이터베이스를 위한 그림자 복구)

  • Byun, Si-Woo
    • Journal of the Korea Academia-Industrial cooperation Society
    • /
    • v.16 no.4
    • /
    • pp.2784-2790
    • /
    • 2015
  • The column-oriented database storage is a very advanced model for large-volume data transactions because of its superior I/O performance. Traditional data storages exploit row-oriented storage where the attributes of a record are placed contiguously in hard disk for fast write operations. However, for search-mostly data warehouse systems, column-oriented storage has become a more proper model because of its superior read performance. Recently, solid state drive using flash memory is largely recognized as the preferred storage media for high-speed data analysis systems. In this research, we propose a new transaction recovery scheme for a column-oriented database environment which is based on a flash media file system. We improved traditional shadow paging schemes by reusing old data pages which are supposed to be invalidated in the course of writing a new data page in the flash file system environment. In order to reuse these data pages, we exploit reused shadow list structure in our column-oriented shadow recovery(CoSR) scheme. CoSR scheme minimizes the additional storage overhead for keeping shadow pages and minimizes the I/O performance degradation caused by column data compression of traditional recovery schemes. Based on the results of the performance evaluation, we conclude that CoSR outperforms the traditional schemes by 17%.

Mounting Time Reduction and Clean Policy using Content-Based Block Management for NAND Flash File System (NAND 플래시 파일 시스템을 위한 내용기반 블록관리기법을 이용한 마운트 시간 감소와 지움 정책)

  • Cho, Wan-Hee;Lee, Dong-Hwan;Kim, Deok-Hwan
    • Journal of the Institute of Electronics Engineers of Korea SD
    • /
    • v.46 no.3
    • /
    • pp.41-50
    • /
    • 2009
  • The flash memory has many advantages such as low power consumption, strong shock resistance, fast I/O and non-volatility. And it is increasingly used in the mobile storage device. Many researchers are studying the YAFFS, NAND flash file system, which is widely used in the embedded device. However, the existing YAFFS has two problems. First, it takes long time to mount the YAFFS file system because it scans whole spare areas in all pages. Second, the cleaning policy of the YAFFS does not consider the wear-leveling so that it cannot guarantee the duration of data completely. In order to solve these problems, this paper proposes a new content-based YAFFS that consists of a mounting time reduction technique and a content-cleaning policy by using content-based block management. The proposed method only scans partial spare areas of some special pages and provides the block swapping which enables the wear-leveling of data blocks. We performed experiments to compare the performance of the proposed method with those of the JFFS2 system and YAFFS system. Experimental results show that the proposed method reduces the average mounting time by 82.2% comparing with JFFS2 and 42.9% comparing with YAFFS. Besides, it increases the life time of the flash memory by 35% comparing with the existing YAFFS whereas no overheat is added.

Column-aware Transaction Management Scheme for Column-Oriented Databases (컬럼-지향 데이터베이스를 위한 컬럼-인지 트랜잭션 관리 기법)

  • Byun, Si-Woo
    • Journal of Internet Computing and Services
    • /
    • v.15 no.4
    • /
    • pp.125-133
    • /
    • 2014
  • The column-oriented database storage is a very advanced model for large-volume data analysis systems because of its superior I/O performance. Traditional data storages exploit row-oriented storage where the attributes of a record are placed contiguously in hard disk for fast write operations. However, for search-mostly datawarehouse systems, column-oriented storage has become a more proper model because of its superior read performance. Recently, solid state drive using MLC flash memory is largely recognized as the preferred storage media for high-speed data analysis systems. The features of non-volatility, low power consumption, and fast access time for read operations are sufficient grounds to support flash memory as major storage components of modern database servers. However, we need to improve traditional transaction management scheme due to the relatively slow characteristics of column compression and flash operation as compared to RAM memory. In this research, we propose a new scheme called Column-aware Multi-Version Locking (CaMVL) scheme for efficient transaction processing. CaMVL improves transaction performance by using compression lock and multi version reads for efficiently handling slow flash write/erase operation in lock management process. We also propose a simulation model to show the performance of CaMVL. Based on the results of the performance evaluation, we conclude that CaMVL scheme outperforms the traditional scheme.

Infrared Rainfall Estimates Using the Probability Matching Method Applied to Coincident SSM/I and GMS-5 Data

  • Oh, Hyun-Jong;Sohn, Byung-Ju;Chung, Hyo-Sang
    • Proceedings of the KSRS Conference
    • /
    • 1999.11a
    • /
    • pp.117-121
    • /
    • 1999
  • Relations between GMS-5 infrared brightness temperature with SSM/I retrieved rain rate are determined by a probability matching method similar to Atlas et al. and Crosson et al. For this study, coincident data sets of the GMS-5 infrared measurements and SSM/I data during two summer seasons of 1997 and 1998 are constructed. The cumulative density functions (CDFs) of infrared brightness temperature and rain rate are matched at pairs of two variables which give the same percentile contribution. The method was applied for estimating rain rate on 31 July 1998, examining heavy rainfall estimation of a flash flood event over Mt. Jiri. Results were compared with surface gauge observations run by Korean Meteorological Administration. It was noted that the method produced reasonably good quality of rain estimate, however, there was large area giving false rain due to the anvil type clouds surrounding deep convective clouds. Extensive validation against surface rain observation is currently under investigation.

  • PDF

A Study on Multimedia File System for Flash Memory (플래시 메모리를 위한 멀티미디어 파일 시스템의 구조 설계)

  • Yang, Hak-Mo;Han, Ryong-Cheol;Ryu, Yeon-Seung
    • Proceedings of the Korea Information Processing Society Conference
    • /
    • 2005.05a
    • /
    • pp.1687-1690
    • /
    • 2005
  • 플래시 메모리는 비휘발성 메모리로서 데이터 접근 속도가 빠르고 전력 소비가 적으며 가볍고 충격에 강한 특징을 가지고 있다. 최근 플래시 메모리의 가격이 저렴해지고 용량은 커져가고 있기 때문에 대용량의 멀티미디어 파일의 저장 장치로서 플래시 메모리의 사용이 증가할 것으로 보인다. 본 논문에서는 플래시 메모리를 위한 멀티미디어 파일 시스템의 구조 설계를 기술한다. 주요 특징으로는 i-node 를 데이터 블록과 분리된 i-node 영역에 로그 방식으로 기록하고, 삭제 연산이 잦은 i-node 영역을 이동할 수 있게 하여 마모도 평준화를 고려하였다. 파일의 데이터 블록은 멀티미디어 응용 프로그램의 특징을 고려하여 인덱스화된 이중 연결 리스트 구조로 관리한다.

  • PDF

A Hetero-Mirroring Scheme to Improve I/O Performance of High-Speed Hybrid Storage (고속 하이브리드 저장장치의 입출력 성능개선을 위한 헤테로-미러링 기법)

  • Byun, Si-Woo
    • Journal of the Korea Academia-Industrial cooperation Society
    • /
    • v.11 no.12
    • /
    • pp.4997-5006
    • /
    • 2010
  • A flash-memory-based SSDs(Solid State Disks) are one of the best media to support portable and desktop computers' storage devices. Their features include non-volatility, low power consumption, and fast access time for read operations, which are sufficient to present flash memories as major database storage components for desktop and server computers. However, we need to improve traditional storage management schemes based on HDD(Hard Disk Drive) and RAID(Redundant array of independent disks) due to the relatively slow or freezing characteristics of write operations of SSDs, as compared to fast read operations. In order to achieve this goal, we propose a new storage management scheme called Hetero-Mirroring based on traditional HDD mirroring scheme. Hetero-Mirroring-based scheme improves RAID-1 operation performance by balancing write-workloads and delaying write operations to avoid SSD freezing. Our test results show that our scheme significantly reduces the write operation overheads and freezing overheads, and improves the performance of traditional SSD-RAID-1 scheme by 18 percent, and the response time of the scheme by 38 percent.

Redundant Storage Device in Communication System (교환 시스템에서의 이중화 저장장치)

  • 노승환
    • The Journal of Korean Institute of Communications and Information Sciences
    • /
    • v.29 no.4B
    • /
    • pp.403-410
    • /
    • 2004
  • In general communication system is composed of processor subsystems, I/O processor subsystems and data storage device subsystems those are classified as their functions. In order to improve the data reliability, all subsystems are redundant. Storage device keeps the operational information such as system related information and charging information, and such informations must be stored in non-volatile memory. Flash memory and battery backup memory are commonly used as the non-volatile storage devices. But such kind of memories are expensive per unit capacity and data can't be restored when lost while not being backed up. In this paper we develop a redundant storage device to store a lot of data safely and reliably in communication system. The device consists of micro-controller, FPGA and hard disk It provides many functions those are rebuilding, automatic remapping, host service and remote host service. Also it is designed to provide host service while rebuilding is being done in order not to interrupt the communication services. The developed device can be used instead of expensive storage device like flash memory in various communication systems.

Friction Weldability of Grey Cast Iron - by the Concept of Friction Weld Heat Input Parameter - (회주철의 마찰용접 특성에 관한 연구 - 입열량 이론식을 중심으로 -)

  • Jeong, Ho-Shin;Bang, Kook-Soo
    • Journal of Welding and Joining
    • /
    • v.32 no.3
    • /
    • pp.95-101
    • /
    • 2014
  • Joining of grey cast iron by fusion welding has much difficulties for its extremely low ductility and low toughness because of the flake form of the graphite. And the brittle microstructure, i.e. ledeburite may be formed during fusion welding by its rapid cooling rates. By these kinds of welding problem, preheat and post heat treatment temperature must be increased to avoid weld crack or welding problems. In order to avoid these fusion welding problem, friction welding of cast iron was carried out for improving joint soundness, establishing friction welding variables. There is no factor for evaluating friction weldability in continuous drive type friction welding. In this point of view, this study proposed the parameters for calculating friction weld heat input. The results obtained are as follows ; 1. There was a close relationship between tensile strength and flash appearance of friction welded joint. 2. Tensile strength was decreased and flash was severely oxidized as increasing frictional heating time. 3. As increased forging pressure $P_2$, flash had a large crack and tensile strength was decreased. 4. As powdered graphite by rotational frictional force induced flat surface and hindered plastic flow of metal, tensile strength of welded joint was decreased. 5. Heat input for continuous drive type friction welding could be calculated by the factors of $P_1$, $P_2$ and upset distance(${\delta}$).

Formation of Mesoporous Membrane by Reverse Thermally induced Phase Separation (RTIPS) Process Using Flash Freezing (Mesoporous 막 제조를 위한 급냉법에 의한 역 열유도상전이공정)

  • Yeom, Choongkyun;Kim, Jiwon;Park, Heeyoung;Park, Seong Eun;Lee, Kee Yoon;Lee, Kew-Ho
    • Membrane Journal
    • /
    • v.31 no.1
    • /
    • pp.67-79
    • /
    • 2021
  • Mesoporous polystyrene (PS) and polyethersulfone (PES) membranes have been fabricated by reverse-thermally induced phase separation (RTIPS) process, using flash freezing. The mesoporous pores can be created by the nano-scaled phase separation induced by the formation and growth of solvent crystals in the dope solution in RTIPS process. RTIPS process has been characterized through analysis on the enthalpy change in the solvent of the dope solution, the morphology of the membrane fabricated with different polymer content, and the pore size distribution and its standard deviation of pore size of the membrane with polymer content via DSC, SEM, and BET, respectively. It is found that the kinetic aspect of the dope solution, i.e., the crystallization of solvent is a crucial factor to determine the structure of membrane fabricated in RTIPS rather than the thermodynamic aspect of the dope solution.