• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39B no.7
• /
• pp.425-432
• /
• 2014

This paper proposes a wear-leveling algorithm that exploits the properties of SSD memories with multi-channel and multi-way architecture. When a write request arrives, the proposed algorithm classifies the stored data in DRAM buffer into hot or cold according to logical address access frequency, and performs data allocation to reduce deviation of block erase counts. It lowers the chance of increasing erase count by allocating cold data to blocks which have high erase count. Effectiveness of the proposed algorithm is verified by executing various applications on a multi-channel, multi-way SSD simulator. Experimental results show that differences in erase count among blocks is reduced by an average of 9.3%, and total erase count decreases by 4.6%, when compared to previous wear-leveling algorithm.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.12 no.3
• /
• pp.121-130
• /
• 2017

NAND flash memory has advantages of non-volatility, little power consumption and fast access time. However, it suffers from inability that does not provide to update-in-place and the erase cycle is limited. Moreover, the unit of read/write operation is a page and the unit of erase operation is a block. Therefore, erase operation is slower than other operations. The AGC, the proposed garbage collection policy focuses on not only garbage collection time reduction for real-time guarantee but also wear-leveling for a flash memory lifetime. In order to achieve above goals, we define three garbage collection operating modes: Fast Mode, Smart Mode, and Wear-leveling Mode. The proposed policy decides the garbage collection mode depending on system CPU usage rate. Fast Mode selects the dirtiest block as victim block to minimize the erase operation time. However, Smart Mode selects the victim block by reflecting the invalid page number and block erase count to minimizing the erase operation time and deviation of block erase count. Wear-leveling Mode operates similar to Smart Mode and it makes groups and relocates the pages which has the similar update time. We implemented the proposed policy and measured the performance compare with the existing policies. Simulation results show that the proposed policy performs better than Cost-benefit policy with the 55% reduction in the operation time. Also, it performs better than Greedy policy with the 87% reduction in the deviation of erase count. Most of all, the proposed policy works adaptively according to the CPU usage rate, and guarantees the real-time performance of the system.

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.06b
• /
• pp.321-326
• /
• 2007

최근 휴대전화 디지털 카메라, 랜 스위치, 디지털 셋톱박스, 휴대용 MP3 플레이어, 노트북용 PC 카드, 내장 기기의 펌웨어 등 플래시 메모리의 활용이 증가하고 있다. 하지만 기존 저장 장치와 달리 플래시 메모리는 특정 블록에 쓰기 연산을 하기 전에 해당 블록은 미리 소거(erase-before-write)되어 있어야 하는 제약이 있으며, 각 블록은 소거될 수 있는 횟수가 제한적이다. 이런 단점들은 플래시 메모리가 대용량화됨에 따라 중요한 문제로 대두되고 있다. 이런 각 블록에 대한 소거 횟수의 제한을 해결하기 위하여 소거 횟수 평준화 기법(wear-leveling) 기법이 필수적이다. 본 논문에서는 블록의 소거 횟수의 한계를 극복하기 위한 새로운 소거 횟수 평준화 기법으로 전체 블록에 대한 소거 횟수 레벨을 두어 소거 횟수 평준화를 이루는 KM-평준화(KM-leveling)를 제안한다. KM-평준화는 소거 횟수 평준화를 위한 전체 블록의 계산 비용을 최소화하고 블록에 대한 소거 레벨을 두어 적은 공간을 사용하는 효율적인 기법이다. 본 논문은 M값 범위 이내에 각 블록의 소거 횟수들이 존재하도록 보장하는 KM-평준화를 제안한다.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.6
• /
• pp.139-144
• /
• 2019

For recent decades, Non-volatile Memory (NVM) technologies have been drawing a high attention both in industry and academia due to its high density and short latency comparable to that of DRAM. However, NVM devices has write endurance problem and thus the current data structures that have been built around DRAM-specific features including unlimited program cycles is inadequate for NVM, reducing the device lifetime significantly. In this paper, we revisit a red-black tree extensively adopted for data indexing across a wide range of applications, and make it to better fit for NVM. Specifically, we observe that the conventional red-black tree wears out the specific location of memory because of its rebalancing operation to ensure fast access time over a whole dataset. However, this rebalancing operation frequently updates the long-lived nodes, which leads to the skewed wear out across the NVM cells. To resolve this problem, we present a new swapping wear-leveling red-black tree that periodically moves data in the worn-out node into the young node. The performance study with real-world traces demonstrates the proposed red-black tree reduces the standard deviation of the write count across nodes by up to 12.5%.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.07a
• /
• pp.787-789
• /
• 2005

최근 이동성이 중요한 요소로 차지하는 기기들이 등장하면서 플래시 메모리가 각광을 받고 있다. 플래시 메모리의 소형화, 대용량화, 저전력화, 비휘발성, 고속화 그리고 충격에 강한 장점으로 인하여 많은 응용에서 디스크를 대체할 것으로 예상된다. 하지만 이런 플래시 메모리는 데이터를 기록하기 전에 해당 블록이 미리 소거가 되어야 하는 제약 조건을 가지고 있으며 각 블록들의 최대 소거 횟수가 제한되어 있다는 한계가 있다. 이때 소거 연산이 특정 블록에 집중되어 특정 블록의 수명이 단축되는 문제점을 해결하기 위하여 블록에 대한 소거 횟수 평준화 기법(wear-leveling)이 필요하다. 기존에 제안된 소거 횟수 평준화 기법은 각 블록의 소거 횟수를 유지해야하는 비용이 필요로 하거나 플래시 메모리가 대용량일 경우에는 블록 영역을 이동시키는데 비용이 발생하는 문제가 있다. 본 논문에서는 플래시 메모리의 소거 횟수 평준화를 위하여 해당 블록의 소거 횟수에 대한 정보의 유지의 부담을 줄이고 플래시 메모리의 대용량화 및 디스크 대체 시에 효율적인 소거 횟수 평준화 기법을 제안하고, 실험을 통하여 성능의 우수함을 보인다.

• Journal of the Semiconductor & Display Technology
• /
• v.6 no.2 s.19
• /
• pp.5-10
• /
• 2007

According to the advantageous features of flash memory, its exploitation and application in mobile and ubiquitous related devices as well as voluminous storage devices is being increased rapidly. The inherent properties that are determined by configuration of flash memory unit might restrict the promising expansion in its utilization. In this paper, we study policies based on threshold values, instead of using global search, in order to satisfy our objective that is to decrease the necessary processing cost or penalty for recycling of flash memory space at the same time minimizing the potential degradation of performance. The proposed cleaning methods create partitions of candidate memory regions, to be reclaimed as free, by utilizing global or dynamic threshold values. The impact of the proposed policies is evaluated through a number of experiments, the composition of the optimal configuration featuring the methods is tested through experiments as well.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2016.01a
• /
• pp.5-7
• /
• 2016

본 논문에서는 블록 생성 번호를 활용한 동적 마모도 평준화 기법을 제안한다. 지금까지 제안된 동적 마모도 평준화 기법들은 콜드 블록을 판별하기 위해 경과 시간을 사용하고 있다. 하지만 저장장치의 데이터 접근은 일정한 시간 간격으로 이루어지는 것이 아니기 때문에 이와 같은 경과 시간을 사용하는 방식은 데이터에 대한 블록 접근 정보가 왜곡될 수 있는 단점이 있다. 이러한 단점을 해결하기 위해, 본 논문에서 제안하는 기법은 블록을 할당할 때 블록 순차 번호를 테이블에 저장하고 이를 이용하여 블록의 접근 빈도를 판별한다. 실험에서 제한하는 기법은 기존의 CB, CAT 기법과 비교하여 최대 11% 수명이 향상됨을 확인하였다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.6
• /
• pp.761-767
• /
• 2010

In the case of NAND flash memory, a whole block needs to be erased for update operations because update-in- place operations are not supported in NAND flash memory. Blocks of NAND flash memory have the limited erasure cycles, so frequently updated data (hot data) easily makes blocks worn out. As the result, the capacity of NAND flash memory will be reduced by hot data. In this paper, we propose a wear-leveling algorithm by discriminating hot and cold data based on the update patterns of data. When we applied this scheme to NAND flash memory, we confirmed that the erase counts of blocks became more uniform by mapping hot data to a block with a low erase count and cold data to block with a high erase count.

• The KIPS Transactions:PartA
• /
• v.14A no.1 s.105
• /
• pp.39-46
• /
• 2007

Recently flash memory is widely accepted as a storage devise of embedded systems for portability and performance reasons. Flash memory has many distinguishing features compared to legacy magnetic disks. Especially, a file system for flash memory usually assumes the form of log-structured file system and it employs garbage collector accordingly. Since the garbage collector can greatly affect the performance of file system, it should be designed carefully considering flash memory features. In this paper, we suggest a new garbage collector for existing JFFS2 (Journaling Flash File System II) file system. By extensive performance evaluation, we show that the proposed garbage collector achieves improved performance in terms of flash memory consumption rate, increased flash memory life time, and improved wear-leveling.

• Proceedings of the Korean Information Science Society Conference
• /
• 2010.06a
• /
• pp.267-268
• /
• 2010