Redundant data processing method, device and system of raid system and medium

Abstract

The embodiment of the invention discloses a redundant data processing method, device and system of a raid system and a computer readable storage medium, and the method comprises the steps: when a disk in the raid system is damaged and an available hot spare disk does not exist, reconstructing redundant data of a fault disk according to data of a healthy disk in the raid system; the reconstructed redundant data are stored in a pre-established redundancy maintaining area; when it is detected that a newly-added disk exists in the raid system, redundant data in the redundancy keeping area is copied to the newly-added disk; in the using process, the time for data reconstruction after a new disk is added is greatly saved, the risk of data loss in the period from disk damage to new disk adding is further reduced, and the data safety of the raid system is greatly improved.

Description

technical field [0001] The present invention relates to the field of computer technology, and in particular, to a redundant data processing method, device, system and computer-readable storage medium of a raid system. Background technique [0002] In cloud computing data centers, the security of data storage is the core issue that users care about, and the raid of the storage system will provide corresponding guarantees for data security. However, the data security provided by raid is based on the number of redundant copies of data blocks. For example, raid6 provides security that can damage two data blocks at the same time without data loss, and raid5 provides security that can damage one data block at the same time without data loss. security. Because the more redundant disks, the larger the data write amplification, the smaller the effective space, and the worse the performance. Therefore, most raid systems use raid5 and other redundant data protection. If the redundant ...

AI Technical Summary

Problems solved by technology

Since the more redundant disks, the larger the data write amplification, the smaller the effective space, and the worse the performance. Therefore, most raid systems use only one redundant data protection such as raid5. If the data redundant block is damaged, this It is no longer possible to provide security guarantees at this time. If data corruption occurs at this time, all data in the entire stripe will be lost and cannot be recovered.

Therefore, the storage system generally provides multiple hot spare disks. When a disk is damaged, the hot spare disk needs to intervene immediately to reconstruct data. However, if there is no available hot spare disk when the disk is damaged, then insert Previously, any further disk corruptions would result in unrecoverable data corruption

Images