Solid state disk wear balancing method for distributed storage system

Abstract

The invention relates to a solid state disk wear balancing method for a distributed storage system, which comprises the following steps of: step 1, collecting storage media, recording weight information of a current storage cluster as an initial weight, and grouping the media according to fault domains to ensure that the storage media in different fault domains are distributed in different groups;and step 2, recording weight information of the current storage medium, generating a wear degree e of the storage medium according to a writing amount m, a bad block number b, a reading error retry rate r and an official writing life L of the current storage medium in SMART information of the storage medium, and then judging measures taken by the storage cluster according to a distribution situation of the wear degree e between 01. According to the invention, the performance of the storage cluster in a non-idle state is ensured, and the stability and controllability of the storage cluster arealso ensured.

Description

technical field [0001] The invention relates to the field of computing storage, in particular to a wear leveling method of a solid-state hard disk in a distributed storage system. Background technique [0002] With the development of technologies such as hosts, disks, and networks, the methods and structures of data storage are constantly changing, from local storage to network storage, from stand-alone storage to distributed storage, which also brings some The problem is that in large-scale production applications, the scale of distributed storage storage clusters becomes very large, which brings huge challenges to the management of enterprises and individuals. The amount of reads and writes of the distributed storage of the enterprise is very large. Naturally, extremely high requirements are placed on the reliability and consistency of the physical storage devices on it. With the improvement of network performance and the improvement of user requirements for data throughp...

AI Technical Summary

Problems solved by technology

With the improvement of network performance and the improvement of user requirements for data throughput, more and more cloud storage systems use solid-state drives to store files, which improves the file read and write speed and shortens the response time. Due to its storage characteristics, the hard disk has a limit on the total write volume. If the total write volume exceeds the official limit, the stability of the solid state drive will decrease significantly, and the number of bad blocks will increase.

Under the protection of the wear and tear mechanism of the current distributed storage system, after each SSD enters the storage cluster for a period of time, its wear and tear will converge to that of other devices in the storage cluster. It is impossible to know which solid-state drives will have problems, and this uncontrollability makes maintenance costs higher

Images