Data access method and device, client and storage medium

Abstract

The invention relates to the field of distributed storage, and provides a data access method and device, a client and a storage medium. The method comprises the steps of: obtaining to-be-written data, wherein the to-be-written data comprises a plurality of target data blocks organized by erasure codes, each target data block needs to be written into each storage node, each storage node comprises old data written last time; sending a write request to each storage node, so that each storage node writes the corresponding target data block based on the respective received write request and feeds back a write response message to the client; and if the number of the target storage nodes feeding back the write response message of successful writing is greater than a preset number, sending deletion commands to the target storage nodes according to the number of the target storage nodes, so that the target storage nodes delete respective old data according to the respective received deletion commands. According to the method, the high consistency of data writing can be ensured, and the requirement of high performance can also be ensured.

Description

technical field [0001] The present invention relates to the field of distributed storage, in particular to a data access method, device, client and storage medium. Background technique [0002] Distributed storage systems have different requirements for data consistency according to different actual business needs. For example, data consistency usually includes various degrees of consistency such as strong consistency, weak consistency, and eventual consistency. Strong consistency means that the most recently written data can be read in any read. Weak consistency means that the data read when reading data can be the most recently written data or the data written before the last time. The final consistency Consistency is a special form of weak consistency, which means that in the absence of new updates, all read data is the last written value. [0003] In the prior art, methods such as 2PC (two-phase commit protocol, 2PC) and 3PC (three-phase commit protocol, 3PC) are usuall...

AI Technical Summary

Problems solved by technology

[0003] In the prior art, methods such as 2PC (two-phase commit protocol, 2PC) and 3PC (three-phase commit protocol, 3PC) are usually adopted in two phases to ensure strong data consistency. Although these methods can guarantee data Strong consistency, but it needs to sacrifice certain performance, so it has certain limitations when it is suitable for application scenarios that require high performance

Images