Abstract
Flash memory has been widely used as a storage device for consumer devices. Recently, applications using flash memory are becoming complex and diverse. One of obstacles to its wide use is the slow write performance of flash memory caused by its erase-before-write characteristic. To enhance the write performance, FTL (Flash Translation Layer) generally uses the flash log-buffer, where data is written by the out-of-place scheme. However, current log buffer-based FTL schemes show poor performance for random write requests due to the block thrashing problem and high block associativity. Recently, flash-aware buffer cache management schemes are proposed to solve the block thrashing problem. However, they cannot also eliminate the problem completely. In this paper, we propose a novel flashaware buffer cache replacement policy. The technique selects the victim page to be evicted from buffer cache considering the recent victim page sent to the flash log buffer. Our experimental results show that the proposed technique reduces the flash I/O execution time by up to 30%.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have