Cache management method based on region heat degree

Abstract

The invention discloses a cache management method based on the region heat degree. By screening data blocks, only the hotspot data blocks are cached, replacement operation conducted after a cache is fully written is reduced, and therefore the cache hit rate is increased, and the service life of SSD is prolonged. The method specifically includes the steps of firstly, establishing a harsh table and a binary tree, conducting initialization, and recording disk region numbers, heat degree values corresponding to all disk regions, points of two subregions pointing leftwards and rightwards, and the heat degree values of the subregions; secondly, renewing information of the hash table and the binary tree for the reading and writing request of each time according to the sizes of disk regions and addresses corresponding to the reading and writing request data blocks; thirdly, screening out the data blocks to which a user frequently has access according to the region heat degree values, and writing data in the data blocks into the cache. By means of the cache management method of conducting screening and then conducting writing, the cache hit rate can be increased, the replacement operation of cache data is reduced, and the service life of solid state disk caches is prolonged.

Description

technical field [0001] The invention belongs to the technical field of computer information storage, and more specifically relates to a cache management method based on regional heat. Background technique [0002] Mechanical operations such as seeking and positioning when reading and writing data on the disk generate rotational delay, making the response speed of the disk much slower than that of the memory, thus causing a performance bottleneck of the entire storage system. In order to improve the storage speed of the system, a layer of high-speed access data cache device is added between the disk and the memory; the function of the cache in the disk storage system is to accelerate the disk access speed by storing frequently accessed hot data in the disk, then These hot data can be read directly from the cache, which shortens the data response time and improves the performance of the entire disk storage system. However, cache devices capable of high-speed data access are ge...

AI Technical Summary

Problems solved by technology

[0003] In order to improve the cache hit rate and prolong the service life of SSD, the traditional cache replacement algorithm mainly considers the time locality of access and hot data, and the statistical method of hot data is mainly based on the access volume of each block in a unit cycle, these methods are not suitable for direct Applied to SSD-based disk cache; first, SSD as a second-level cache has weaker temporal locality compared to first-level cache (memory); second, a large number of studies have shown that caching hot data and access frequency-based replacement (FBR) algorithms It is better than algorithms based on time locality such as LRU; however, the statistics of hot data are generally based on the access frequency of disk blocks, which requires a heat calculation process, which may cause hot data between or cold Frequent replacement of hot data will not only affect performance, but also cause a large number of writes to SSD, shortening the service life of SSD

Images