Browsing by Author "Debnath, Biplob"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    CFTL: A Convertible Flash Translation Layer with Consideration of Data Access Patterns
    (2009-09-14) Park, Dongchul; Debnath, Biplob; DuHung-Chang, David
    NAND flash memory-based storage devices are increasingly adopted as one of the main alternatives for magnetic disk drives. The flash translation layer (FTL) is a software/hardware interface inside NAND flash memory, which allows existing disk-based applications to use it without any significant modifications. Since FTL has a critical impact on the performance of NAND flash-based devices, a variety of FTL schemes have been proposed to improve their performance. However, existing FTLs perform well for either a read intensive workload or a write intensive workload, not for both of them due to their static address mapping schemes. To overcome this limitation, in this paper, we propose a novel FTL addressing scheme named Convertible Flash Translation Layer (CFTL, for short). CFTL is adaptive to data access patterns so that it can dynamically switch the mapping of a data block to either read-optimized or write-optimized mapping scheme in order to fully exploit the benefits of both schemes. By judiciously taking advantage of both schemes, CFTL resolves the intrinsic problems of the existing FTLs. In addition to this convertible scheme, we propose an efficient caching strategy so as to considerably improve the CFTL performance further with only a simple hint. Consequently, both of the convertible feature and caching strategy empower CFTL to achieve good read performance as well as good write performance. Our experimental evaluation with a variety of realistic workloads demonstrates that the proposed CFTL scheme outperforms other FTL schemes.
  • Thumbnail Image
    Item
    HotDataTrap: A Sampling-based Hot Data Identification Scheme for Flash Memory
    (2011-04-20) Park, Dongchul; Debnath, Biplob; NamJin, Young; DuHung-Chang, David; Kim, Youngkyun; Kim, Youngchul
    Hot data identification is an issue of paramount importance in flash-based storage devices since it has a great impact on their overall performance as well as retains a big potential to be applicable to many other fields. However, it has been least investigated. In this paper, we propose a novel on-line hot data identification scheme named HotDataTrap. The main idea is to maintain a working set of potential hot data items in a cache based on a sampling approach. This sampling scheme enables HotDataTrap to early discard some of the cold items so that it can reduce runtime overheads and a waste of memory spaces. Moreover, our two-level hierarchical hash indexing scheme helps HotDataTrap directly look up a requested item in the cache and save a memory space further by exploiting spatial localities. Both our sampling approach and hierarchical hash indexing scheme empower HotDataTrap to precisely and efficiently identify hot data even with a very limited memory space. Our extensive experiments with various realistic workloads demonstrate that our HotDataTrap outperforms the state-of-the-art scheme by an average of 335% and our two-level hash indexing scheme considerably improves further HotDataTrap performance up to 50.8%.