Cache design method, device and computer equipment based on solid-state hard disk

Abstract

The present application relates to a solid-state disk-based cache design method, device, computer equipment, and storage medium, wherein the method includes: obtaining a solid-state disk-based cache design request; according to the solid-state disk-based cache design request, storing LBA data In the corresponding cache unit; when the LBA data is stored in the cache unit, record the physical location of the LBA data in the cache unit through the mapping table; when the subsequent host needs to read the LBA data, the cache directly queries the mapping The physical location of the corresponding LBA data recorded in the table; read the corresponding LBA data directly from the cache according to the query result. The present invention combines the global characteristics of the mapping table in the SSD, combines the design of the cache with the mapping table, uses the mapping table to record the physical position of the LBA data in the cache, and realizes reducing the search time complexity to the theoretical optimum, achieving an improvement The technical effect of caching search efficiency.

Description

technical field [0001] The invention relates to the technical field of solid-state hard disks, in particular to a cache design method, device, computer equipment and storage medium based on solid-state hard disks. Background technique [0002] At present, whether it is an enterprise-level solid-state drive (SSD) or a consumer-level SSD, it has high requirements on the bandwidth (Throughput) and latency (Latency) of read and write commands. Generally speaking, the SSD must be designed with a cache (RAM). The data of the command is first stored in the cache of the SSD, and after a certain amount of data is assembled, it is packaged and written into the flash memory (NAND), such as figure 1 As shown, this effectively utilizes the efficient random-access nature of cache and the write-by-physical-page nature of flash memory. [0003] Specifically, when a read command is sent to the SSD, the SSD needs to confirm whether the data required by the read command is in the cache, and i...

AI Technical Summary

Problems solved by technology

A key point in cache design is whether the search algorithm for judging whether the read command hits the cache is efficient. The existing mainstream search algorithms are mainly dedicated to optimizing the storage structure of the cache to reduce the search time, but the search time in this method is not as good as The size of the cache is proportional to a certain relationship and cannot achieve optimal performance

Images