Application And Improvement In Wear Leveling To Improve The Life Of The SSD

Currently, what is the hot word in the storage world? The answer is SSD (Solid State Drive). All the friends in the Storage as know that memory data storage will change from transitional mechanical drive to solid state drive in the future. From the original capacity20MB to now many TB capacities, the SSD development and evolution marvelously changed. There are many new products created every year, and in the future, after the PCIE solid state drive application, the read and write speed performance will be reached the geometric growth. An SSD (solid-state drive) is a nonvolatile storage device that stores persistent data on solid-state flash memory. Solid-state drives actually aren’t hard drives in the traditional sense of the term, as there are no moving parts involved. An SSD, on the other hand, has an array of semiconductor memory organized as a disk drive, using integrated circuits (ICs) as NAND flash rather than magnetic media. Development and adoption of SSDs has been driven by a rapidly expanding need for higher read/write (I/O) performance. SSDs have much lower random access and read access latency than HDDs, making them a huge advantage for both heavy read and random workloads. That lower latency is the direct result of the ability of flash SSD to read data directly and immediately from a specific NAND flash memory. But if a particular block was programmed and erased repeatedly without writing to any other blocks, that block would wear out before all the other blocks. Thereby prematurely ending the life of the SSD. For this reason, SSD controllers use a technique called wear leveling to distribute writes as evenly as possible across all the NAND flash blocks in the SSD. In a perfect scenario, this would enable every block to be written to its maximum life so the all SSD blocks will fail at the same time that making the SSD reached the maximum used cycles. But unfortunately, in the perfect processing, there are many instability factors, including we are often read and write data called hot data and rarely read/write data call cold data, which all of these will lead to the NAND blocks P/E cycles severity imbalance of the SSD NAND memory flash. These will prompt us to find a key and effective algorithm to resolved or relax the problem. So the wear leveling algorithm is provided in this condition to optimize and improve NAND flash P/E cycles counts. But of course, the wear leveling algorithm corresponding bring some unnecessary performance loss of write amplification, so in this thesis, provide the innovative dual pool algorithm to balance the optimize performance and performance loss, making our SSD to reach a relative maximum used life but the performance relative unapparent drop.