Data reading method, data writing method, equipment and system

Abstract

The embodiment of the invention discloses a data reading method, a data writing method, equipment and a system, which are used for reducing competition of different threads for lock resources of a log buffer so as to improve the performance of a database. In the embodiment of the invention, the computer equipment comprises storage equipment and a plurality of nodes of a non-uniform memory access architecture (NUMA) system, each node is provided with a buffer area and a controller for controlling the buffer area, and the method comprises the following steps: acquiring a write request of target data; in response to the write request, determining a target page used for storing the target data in the storage device; determining a target buffer region corresponding to the target page from a plurality of buffer regions corresponding to the plurality of nodes; writing the target data into a page of the target buffer area by controlling a target controller of the target buffer area; and writing data of the page of the target buffer into a target page in the storage device.

Description

technical field [0001] The present application relates to the technical field of databases, in particular to a method for reading data, a method for writing data, a device and a system. Background technique [0002] In a database, it often involves reading data from or writing data to the database's disk. However, in some scenarios, the data in the disk will be read multiple times, or data will be written to the same page in the disk multiple times, so if you interact with the disk every time to read data or write data , will inevitably increase a large number of input / output I / O operations, which will increase I / O overhead and reduce the performance of the database. [0003] For this purpose, buffers are usually used for reading and writing data. That is, data is first read from disk into a buffer, and thereafter only the data is read from the buffer, not from disk. Alternatively, write data into the buffer first, and after the data in the buffer reaches a certain amount...

AI Technical Summary

Problems solved by technology

[0005] It can be seen that the lock resources of the buffer will be competed among the business threads, which will affect the performance of the database.

Images