• KIISE Transactions on Computing Practices
• /
• v.21 no.2
• /
• pp.126-131
• /
• 2015

As flash-based storage systems have been actively employed in large-scale servers and data centers, reliability has become an indispensable element. One promising technique for enhancing reliability is static wear-leveling, which distributes erase operations evenly among blocks so that the lifespan of storage systems can be prolonged. However, increasing the capacity makes the processing overhead of this technique non-trivial, mainly due to searching for blocks whose erase count would be minimum (or maximum) among all blocks. To reduce this overhead, we introduce a new randomized block selection method in static wear-leveling. Specifically, without exhaustive search, it chooses n blocks randomly and selects the maximal/minimal erased blocks among the chosen set. Our experimental results revealed that, when n is 2, the wear-leveling effects can be obtained, while for n beyond 4, the effect is close to that obtained from traditional static wear-leveling. For quantitative evaluation of the processing overhead, the scheme was actually implemented on an FPGA board, and overhead reduction of more than 3 times was observed. This implies that the proposed scheme performs as effectively as the traditional static wear-leveling while reducing overhead.

• Annual Conference of KIPS
• /
• 2012.11a
• /
• pp.24-26
• /
• 2012

데이터 저장장치로 널리 사용되고 있는 플래시 메모리의 블록들은 소거 횟수가 제한되어 있어서 특정 블록에 소거 동작이 집중되지 않도록 마모 균등화 기능을 제공해야 한다. 저장 장치의 데이터들은 주기적으로 갱신이 자주 되는 hot데이터와 갱신이 거의 일어나지 않는 cold 데이터로 구성된다. 이런 두 가지 타입의 데이터로 인해 발생하는 소거 횟수에 대한 편차를 줄이기 위하여 정적 마모 균등화 기법을 사용하는데 데이터 이동에 따른 추가적인 소거 동작이 발생하게 된다. 본 논문에서는 데이터 이동 결정을 위한 임계값을 제어하여 플래시 메모리 내의 전체 블록들의 평균 소거 횟수가 크지 않을 때는 마모 균등화 작업을 자주 발생하지 않게 하고, 평균 소거 횟수가 소거 허용 한계치에 점차 근접하면 설정된 임계값으로 동작하도록 하여 정적 마모 평준화에 의해 추가되는 소거 횟수를 효율적으로 감소시키는 방법을 제안한다.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.12 no.3
• /
• pp.185-192
• /
• 2017

Due to the characteristics of low power, high durability and high density, NAND flash memory is being heavily used in various type of devices such as USB, SD card, smart phone and SSD. On the other hand, because of another characteristic of flash cell with the limited number of program/erase cycles, NAND flash memory has a short lifetime compared to other storage devices. To overcome the lifetime problem, many researches related to the wear leveling have been conducted. This paper presents a method called a TCB (Tracking Cold Blocks) using more reinforced constraint conditions when classifying cold blocks than previous works. TCB presented in this paper keeps a MCT (Migrated Cold block Table) to manage the enhanced classification process of cold blocks, with which unnecessary migrations of pages can be reduced much more. Through the experiments, we show that TCB reduces the overhead of wear leveling by about 30% and increases the lifetime up to about 60% compared to BET and BST.