Method and device for organizing metadata of distributed file system

Abstract

The invention relates to the field of computers, and discloses a method for organizing metadata of a distributed file system, which comprises the following steps of: establishing a default file blockcombination index table according to the content of a file to be created and used for reflecting a mapping relation between a text block combination of the file to be created and all text blocks forming the text block combination; if the to-be-created file contains other existing files or existing text block combinations, the to-be-created file is created; if yes, replacing the reference of the existing file in the to-be-created file or each text block in the existing text block combination with the reference of the text block combination of the existing file or the existing text block combination, and updating a file block combination index table according to the reference; and generating and maintaining the to-be-created file according to the updated file block combination index table. According to the method, the change of the bottom text block structure does not need to be concerned, the organization mode is more convenient, the organization efficiency is higher, the utilization and organization of the text blocks are more reasonable, and the system resource utilization rate is higher.

Description

technical field [0001] This application relates to the field of computer technology, in particular to data organization technology. Background technique [0002] Computers manage and store data through the file system, and in the era of information explosion, the data that people can obtain increases exponentially. Simply by increasing the number of hard disks to expand the storage capacity of the computer file system, in terms of capacity, capacity growth rate, Data backup, data security and other aspects of performance are not satisfactory. [0003] The distributed file system can effectively solve the problem of data storage and management. [0004] Specifically, the distributed file system will be fixed at a certain file system at a certain location and extended to any number of locations / multiple file systems, and many nodes form a file system network. Each node can be distributed in different locations, and the communication and data transmission between nodes can be...

AI Technical Summary

Problems solved by technology

[0008] It can be seen that according to the existing distributed file system metadata organization technology, it is necessary to pay attention to the change of the underlying text block (Chunk) structure, the organization method is not convenient enough, the organization efficiency is not high, and the utilization and organization of the text block (Chunk) is not enough. Reasonable, so that the system resource utilization is not high

Images