A Restoration Method for Distributed Data Storage System

Abstract

The present invention relates to a method for repairing a distributed data storage system, comprising the following steps: Step S1: providing a management node and a plurality of storage nodes; the storage nodes include a set of storage nodes for repairing damaged data blocks and for storing repaired data The storage node set for the required erasure code data; Step S2: The management node monitors and searches for damaged data blocks in the system. When the management node finds damaged data blocks, it uses the LeDiR algorithm to select the optimal storage node and authorizes the optimal storage node. The node performs data repair work; Step S3: the optimal storage node uses the erasure code algorithm to perform repair work; Step S4: After the optimal storage node completes data repair, it sends the data repair status to the management node. The invention relies on the management node to detect the damaged storage node and repairs it based on the erasure code algorithm. The repair process on different nodes can be performed concurrently, which improves the repair ability of the storage system and reduces the load of the management server.

Description

technical field [0001] The invention relates to the technical field of data restoration in a distributed data storage system, in particular to a method for repairing a distributed data storage system. Background technique [0002] With the popularization and development of the Internet, data plays an increasingly important role in human life, and people have higher requirements for data reliability and security. Gordon Moore, one of the founders of Intel, proposed Moore's Law, which reads: when the price remains constant, the number of transistors that can be accommodated on an integrated circuit will double every 18 months, and the performance will also be doubled. In 1998, Jim Gray, the winner of the Turing Award, published the famous "Moore's Law" in the storage industry: the amount of new information in the world every 18 months is equal to the sum of all the information in history. Data massification has become a trend. In order to facilitate the storage of large-scal...

AI Technical Summary

Problems solved by technology

[0008] The disadvantage of this technology is that: nodes need to store a large amount of data, and each storage node needs to store a copy of a file, and the storage redundancy is large, resulting in a large waste of storage resources

[0012] However, there is a problem with erasure codes when repairing damaged data nodes: repairing M1-sized data blocks requires a total of k×M1-sized data blocks to be downloaded from k different nodes through network connections, so repairing bandwidth is expensive

Although the repair algorithm based on router acceleration improves the repair efficiency, all repair management is still in charge of the management node, and the load of the management node is relatively large, which has certain requirements on the performance and function of the router.

Images