Dong-Joo Park

A log buffer-based flash translation layer using fully-associative sector translation

Flash memory is being rapidly deployed as data storage for mobile devices such as PDAs, MP3 players, mobile phones, and digital cameras, mainly because of its low electronic power, nonvolatile storage, high performance, physical stability, and portability. One disadvantage of flash memory is that prewritten data cannot be dynamically overwritten. Before overwriting prewritten data, a time-consuming erase operation on the used blocks must precede, which significantly degrades the overall write performance of flash memory. In order to solve this “erase-before-write” problem, the flash memory controller can be integrated with a software module, called “flash translation layer (FTL).” Among many FTL schemes available, the log block buffer scheme is considered to be optimum. With this scheme, a small number of log blocks, a kind of write buffer, can improve the performance of write operations by reducing the number of erase operations. However, this scheme can suffer from low space utilization of log blocks. In this paper, we show that there is much room for performance improvement in the log buffer block scheme, and propose an enhanced log block buffer scheme, called FAST (full associative sector translation). Our FAST scheme improves the space utilization of log blocks using fully-associative sector translations for the log block sectors. We also show empirically that our FAST scheme outperforms the pure log block buffer scheme.

System software for flash memory: a survey

Recently, flash memory is widely adopted in embedded applications since it has several strong points: non-volatility, fast access speed, shock resistance, and low power consumption. However, due to its hardware characteristic, namely “erase before write”, it requires a software layer called FTL (Flash Translation Layer). This paper surveys the state-of-the-art FTL software for flash memory. This paper also describes problem definitions, several algorithms proposed to solve them, and related research issues. In addition, this paper provides performance results based on our implementation of each of FTL algorithms

FAST: an efficient flash translation layer for flash memory

Flash memory is used at high speed as storage of personal information utilities, ubiquitous computing environments, mobile phones, electronic goods, etc. This is because flash memory has the characteristics of low electronic power, non-volatile storage, high performance, physical stability, portability, and so on. However, differently from hard disks, it has a weak point that overwrites on already written block of flash memory is impossible to be done. In order to make it possible, an erase operation on the written block should be performed before the overwrite, which lowers the performance of flash memory highly. In order to solve this problem, the flash memory controller maintains a system software module called the flash translation layer(FTL). In this paper, we propose an enhanced log block buffer FTL scheme, FAST(Fully Associative Sector Translation), which improves the page usability of each log block by fully associating sectors to be written by overwrites to the entire log blocks. We also show that our FAST scheme outperforms the previous log block buffer scheme.

LSTAFF: system software for large block flash memory

Recently, flash memory is widely used in embedded applications since it has strong points: non-volatility, fast access speed, shock resistance, and low power consumption. However, due to its hardware characteristics, it requires a software layer called FTL (flash translation layer). We present a new FTL algorithm called LSTAFF (Large STAFF). LSTAFF is designed for large block flash memory. That is, LSTAFF is adjusted to flash memory with pages which are larger than operating system data sector sizes. We provide performance results based on our implementation of LSTAFF and previous FTL algorithms using a flash simulator.

Crash recovery in FAST FTL

NAND flash memory is one of the non-volatile memories and has been replacing hard disk in various storage markets from mobile devices, PC/Laptop computers, even to enterprise servers. However, flash memory does not allow in-place-update, and thus a block should be erased before overwriting the existing data in it. In order to overcome the performance problem from this intrinsic deficiency, flash storage devices are equipped with the software module, called FTL (Flash Translation Layer). Meanwhile, flash storage devices are subject to failure and thus should be able to recover metadata (including address mapping information) as well as data from the crash. In general, the FTL layer is responsible for the crash recovery. In this paper, we propose a novel crash recovery scheme for FAST, a hybrid address mapping FTL. It writes periodically newly generated address mapping information in a log structured way, but it exploits the characteristics of FAST FTL that the log blocks in a log area are used in a round-robin way, thus providing two advantages over the existing FTL recovery schemes. One is the low overhead in performing logging during normal operations in FTL. The other is the fast recovery time.

SPY-TEC+ : AN INTEGRATED INDEX STRUCTURE FOR k-NEAREST NEIGHBOR QUERIES WITH SEMANTIC PREDICATES IN MULTIMEDIA DATABASE

Recently, advanced multimedia applications, such as geographic information system, and content-based multimedia retrieval system, require the efficient processing of k-nearest neighbor queries over large collection of multimedia objects. These queries usually include the semantic information that is represented by text, as well as the visual information that is represented by a high-dimensional feature vector. Among the available techniques for processing such queries, the incremental nearest neighbor algorithm proposed by Hjaltason and Samet is known as the best choice. However, the R-tree used in their algorithm has no facility capable of partially pruning the candidate tuples that will turn out not to satisfy the semantic predicate. Also, the R-tree does not perform sufficiently well on high-dimensional data even though it provides good results on low or middle-dimensional data. These drawbacks may lead to a poor performance when processing the query. In this paper, we propose an integrated index structure, so-called SPY-TEC+, that provides an efficient method for indexing the visual and semantic feature at the same time using the SPY-TEC that was proposed for indexing high-dimensional data, and the signature file. We also propose an efficient incremental nearest neighbor algorithm for processing k-nearest neighbor queries with visual and semantic predicates on the SPY-TEC+. Finally, we show that the SPY-TEC+ enhances the performance of the SPY-TEC for processing k-nearest neighbor queries with visual and semantic predicates through various experiments.

An efficient incremental nearest neighbor algorithm for processing k -nearest neighbor queries with visal and semantic predicates in multimedia information retrieval system

Recently, advanced multimedia applications, such as geographic information system, and content-based image/video retrieval system, require the efficient processing of k-nearest neighbor queries with semantic predicates as well as visual predicates. In this paper, we propose an integrated index structure, so-called SPY-TEC+, that provides an efficient method for indexing visual and semantic feature information at the same time using the SPY-TEC and the signature file. We also propose an efficient incremental nearest neighbor algorithm for processing the k-nearest neighbor queries with visual and semantic predicates on the SPY-TEC+.

WPCB-Tree: A Novel Flash-Aware B-Tree Index Using a Write Pattern Converter

For the past few years, flash memory has been widely used because of its prominent advantages such as fast access speed, nonvolatility, high reliability, and low power consumption. However, flash memory still has several drawbacks that need to be overcome, e.g., the erase-before-write characteristic and a limited life cycle. Among these drawbacks, the erase-before-write characteristic causes the B-tree implementation on flash memory to be inefficient because it generates many erase operations. This study introduces a novel B-tree index structure using a write pattern converter (WPCB-tree) for flash memory. A WPCB-tree can minimize the risk of data loss and can improve the performance of the B-tree on flash memory. This WPCB-tree uses some blocks of flash memory as a buffer that temporarily stores all updated nodes. When the buffer is full, a buffer block is selected by a greedy algorithm, then the node pages in the block are converted into a sequential write pattern, and finally they are written into flash memory. In addition, in the case that all key values of a leaf node are continuously inserted, the WPCB-tree does not split the leaf node. As a result, this mechanism helps the WPCB-tree reduce the number of write operations on the flash memory. The experimental results show that the proposed B-tree variant on flash memory yields a better performance than that of other existing variants of the B-tree.

An Efficient Flash Translation Layer for Large Block NAND Flash Devices

Recently, flash memory is widely used as a non-volatile storage for embedded applications such as smart phones, MP3 players, digital cameras and so on. The software layer called flash translation layer (FTL) becomes more important since it is a key factor in the overall flash memory system performance. Many researchers have proposed FTL algorithms for small block flash memory in which the size of a physical page of flash memory is equivalent to the size of a data sector of the file system. However, major flash vendors have now produced large block flash memory in which the size of a physical page is larger than the file systems data sector size. Since large block flash memory has new features, designing FTL algorithms specialized to large block flash memory is a challenging issue. In this paper, we provide an efficient FTL named LSTAFF* for large block flash memory. LSTAFF* is designed to achieve better performance by using characteristics of large block flash memory and to provide safety by abiding by restrictions of large block flash memory. Experimental results show that LSTAFF* outperforms existing algorithms on a large block flash memory.

LSTAFF*: an efficient flash translation layer for large block flash memory

Recently, flash memory is widely used as a non-volatile storage for embedded applications such as cellular phones, mp3 players, digital cameras, and so on. The software layer called FTL (flash translation layer) becomes more important since it is a key factor in the overall flash memory system performance. Many researchers have proposed FTL algorithms for small block flash memory in which the size of a physical page of flash memory is same to the size of a data sector of the file system. However, major flash vendors have now produced large block flash memory in which the size of a physical page is larger than the file systems data sector size. Since large block flash memory has new features, designing FTL algorithms optimized for large block flash memory is a challenging one. In this paper, we provide an efficient FTL named LSTAFF* for large block flash memory. LSTAFF* is designed to achieve better performance by using characteristics of large block flash memory and to provide safety by abiding by restrictions of large block flash memory. Our experimental results show that LSTAFF* is an optimized FTL algorithm for large block flash memory.