Filter of Files for Reliable Non-Volatile Memory Systems

Flash memory has been widely utilized in embedded systems and consumerelectronics, because of its low-power consumption, high-performance access, non-volatility, and shock resistance. A flash-memory device is different from a typical hard-disk device and requires a sophisticated management method to improve the reliable endurance and provide the efficient storage management. To improve the reliable endurance and provide the efficient storage management, the previous works have demonstrated that the identification of the frequently used data and the least recently used data is a key point.

In this paper, we will propose a hotness filter of files to calculate how the files are accessed (i.e., reads and writes) intensively. The proposed filter is designed specifically to distinguish between hot and cold files by considering the characteristics of file systems. In the experiments, we have implemented the hotness filter in a real Android system (e.g., Asus Nexus 7) and demonstrated that the proposed filter can correctly identify hot and cold files without significant overhead.