Page-level buffer improvement method based on classification strategy

Abstract

The invention discloses a page-level buffer improvement method based on a classification strategy. The method comprises a request type distinguishing module, a hot data page storage area module, a cold data page storage area module and a continuous data page storage area module. The method comprises the following steps: firstly, dividing a hot data page cache into the hot data page storage area module, the cold data page storage area module and the continuous data page storage area module, and separately using the modules to load data pages of a request with frequent accesses, the data pages of a request with lower access frequency and the data pages of the request with high spatial locality; secondly, arriving at the continuous data page storage area module by prefetching multiple continuous data pages; and finally, when the data page cache is full, preferably replacing least recently used (LRU) clean pages in the cold data page storage area module, and if the cold data page storage area module does not have dirty pages, replacing the dirty pages. Compared with a page-level LRU algorithm, by adopting the page-level buffer improvement method disclosed by the invention, the responseperformance to continuous loads can be improved, and the read and write overheads of flash memories can be effectively reduced.

Description

technical field [0001] The invention belongs to the technical field of solid-state hard disk algorithm design, and discloses a page-level buffer improvement method based on a classification strategy. Background technique [0002] The buffer replacement algorithm is one of the important means to improve the performance of the storage system. Currently, buffer replacement algorithms are widely used in file systems, databases, and other storage systems. However, the traditional buffer replacement algorithm is mainly aimed at improving the buffer hit rate, and it is designed for mechanical hard disks, and the asymmetry of the read and write operation costs of flash memory makes the traditional buffer replacement algorithm unable to adapt well to solid-state disks. . [0003] Currently, existing buffer replacement algorithms for solid-state disks mainly classify data pages for the uncertainty of flash memory read and write costs. When replacing data pages, try to minimize the ...

AI Technical Summary

Problems solved by technology

However, the above two classic buffer replacement algorithms do not take into account the degree of hot and cold data pages in the buffer, that is, the buffer is not divided into hot data page cache and cold data page cache, and the data is classified and stored; moreover, the page Both LRU and CFLRU do not take into account the spatial locality of data access, and the prefetching strategy can be used to improve the processing capacity of requests with high spatial locality.

Images