PROJECT TITLE :
Clustered page clustered page-level mapping for flash memory-based storage devices
Recent consumer devices such as smartphones, sensible TVs and tablet PCs adopt NAND flash memory as storage device due to its advantages of little size, reliability, low power consumption, and high performance. The distinctive characteristics of NAND flash memory need a further software layer, called flash translation layer (FTL), between traditional file systems and flash memory. So as to scale back the garbage collection value, FTLs usually strive to separate cold and warm knowledge. Previous hot and cold separation techniques monitor the storage access patterns among storage device, or exploit file system hints from host system. This paper proposes a novel clustered page-level mapping, called CPM, which can separate hot and cold data efficiently by allocating different flash memory block teams to completely different logical address regions. CPM will reduce the FTL map loading overhead during garbage assortment and it will not need any high-cost monitoring overhead or host hint. This paper also proposes a K-associative version of CPM, called K-CPM, which permits totally different logical address regions to share a physical block group so as to achieve high block utilizations. Experimental results show that CPM improves the storage I/O performance by concerning 54percent compared with a previous page-level mapping FTL, and K-CPM further improves the performance by about 19.fourpercent compared with CPM1.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here