Method and device for reading metadata, and computer readable storage medium

Abstract

The invention discloses a method and a device for reading metadata, and a computer readable storage medium. The method includes transmitting access requests to a metadata server when the access requests for reading the metadata are first access requests corresponding to the metadata; receiving the metadata fed by the metadata server; caching the metadata in local spaces. The method, the device and the computer readable storage medium have the advantages that the corresponding metadata are cached in the local spaces when the access requests are the first access requests, accordingly, the metadata can be directly read from the local spaces when accessed at another time, and the frequencies of interaction between clients and the metadata server can be lowered to a great extent when each single metadata need to be repeatedly accessed; the metadata cached in the local spaces are directly read, accordingly, the metadata acquisition time can be saved, and the access request efficiency can be improved; the method does not depend on the metadata server to a certain extent, and accordingly the metadata acquisition reliability can be improved.

Description

technical field [0001] The present invention relates to the technical field of metadata, in particular to a metadata reading method, device and computer-readable storage medium. Background technique [0002] The data in the file system is divided into common data and metadata. Ordinary data refers to the actual data contained in ordinary files, while metadata refers to data used to describe the characteristics of files, such as access rights, file owners, and distribution information of file data blocks. In a distributed storage system, operations such as reading and writing small files need to obtain the metadata of the file from the metadata server, and then obtain the corresponding actual data of the file according to the metadata of the file. [0003] In the prior art, when the client receives a request for metadata access, it sends the request to the metadata server, and the metadata server finds the metadata corresponding to the request according to the request, and s...

AI Technical Summary

Problems solved by technology

[0004] With the rapid development of the Internet, there are more and more application scenarios for distributed storage systems, but with the storage of massive files in distributed storage systems, the interaction between clients and metadata servers is becoming more and more frequent

If the above access method is followed, the number of accesses to the metadata server by the client will be very large, even tens of millions of times, resulting in excessive pressure on the metadata server and slow system response

Images