Data writing method and device, and storage medium

Abstract

The invention relates to a data writing method and device, and a storage medium, and the method comprises the steps: obtaining to-be-written first data, and enabling a plurality of sub-data blocks inthe first data to be stored in a specified aggregation queue in a plurality of aggregation queues according to an aggregation strategy; performing data interception on a plurality of sub-data blocks in the current queue in each specified aggregation queue to obtain second data to be written; and writing the second data into a storage device. The data written into the storage device are distributedmore ideally in a multi-queue aggregation mode, and the time consumed for reading the storage device can be effectively shortened according to the data writing method in the embodiment of the invention.

Description

technical field [0001] The present disclosure relates to the field of computer storage, in particular to a data writing method and device, and a storage medium. Background technique [0002] Read and write performance is a key indicator of a solid state disk (SSD, Solid State Disk), and the SSD master is responsible for important tasks such as data management, performance discovery, and life maintenance. The read and write performances of different SSD controllers on the same NAND-flash memory or hardware environment are not the same or vary greatly, mainly due to the advantages and disadvantages of the read and write algorithms in them. [0003] In the existing writing algorithm, regardless of the length of the data block, the data blocks are aggregated sequentially in an aggregation queue (or called a flushing queue), which leads to an unsatisfactory distribution of data written into the memory. When reading the data in the NAND-flash memory, when a data block is distribu...

AI Technical Summary

Problems solved by technology

[0003] In the existing writing algorithm, regardless of the length of the data block, the data blocks are aggregated in order in an aggregation queue (or called the next brush queue), which leads to an unsatisfactory distribution of data written into the memory

When reading data in the NAND-flash memory, when a data block is distributed in multiple multi-plane pages (MP, muti-plane page), if the host reads the data block, it needs to issue multiple read commands, Consumes multiple trigger times, resulting in extended time to read data

Images