Distributed erasure code storage system data restoration method based on simulated annealing

Abstract

The invention discloses a distributed erasure code storage system data restoration method based on simulated annealing. The method comprises the following steps: constructing a distributed storage system; the monitoring node judging that the storage node has a fault; the monitoring node selecting a storage node as a repair node to repair the data and store the lost data; the repair node obtainingthe network transmission speed; the repair node obtaining the erasure code generation matrix, the failure node number and the current node number and obtaining a repair scheme through a search algorithm; the repair node constructing a data reading request according to the repair scheme and sending the data reading request to each storage node; each complete storage node reading corresponding element data and returns the element data to the repair node; the restoration node executing decoding operation to reconstruct the lost data; and the restoration node feeding back the metadata informationto the monitoring node and storing the data locally. The bandwidth occupation of data restoration of the CRS erasure codes is effectively reduced, the adverse influence of data restoration on the system is reduced, and the data restoration speed is increased.

Description

technical field [0001] The invention belongs to the field of distributed erasure code storage systems, and in particular relates to a method for restoring data in a distributed erasure code storage system based on simulated annealing. Background technique [0002] Distributed storage system has attracted widespread attention due to its good scalability and low cost. This system is composed of cheap storage servers interconnected through the network, and some data redundancy technologies are adopted to ensure data reliability. The traditional data redundancy technology in a distributed storage system is a copy strategy, but the copy strategy brings about a large storage overhead. For example, for a three-copy strategy, it will bring three times the storage overhead. The erasure code strategy is a relatively new type of data redundancy technology, which divides the original data into k blocks, and encodes these data blocks to obtain m check blocks, and finally places the data ...

AI Technical Summary

Problems solved by technology

However, these optimization methods cannot effectively reduce the amount of network transmission data during data repair

Images