Method for realizing data synchronization of main/standby metadata servers and apparatus thereof

Abstract

The invention discloses a method for realizing data synchronization of main/standby metadata servers and an apparatus thereof, and is used for solving the problems that data synchronization has to depend on third party equipment in the prior art and the data consistency among main/standby metadata servers cannot be guaranteed when the third party equipment breaks down. The method includes the steps: when a router receives a file operation request sent from a user every time, transferring the received file operation request to a main metadata server and storing the file storage position information which is returned according to the file operation request of the main meta server on the local; and when an acquire request sent from a standby metadata server is received, determining that the main metadata server operates abnormally and sending all the currently locally-stored file storage position information to the standby metadata server according to the acquire request. By means of the method, based on the reliability of the router, and having no requirement for extra increase of third party equipment, the problem for data loss between the main metadata server and the standby metadata server is solved.

Description

technical field [0001] The invention relates to the field of data storage, in particular to a method and a device for realizing data synchronization of active and standby meta-servers. Background technique [0002] In order to ensure the reliability of distributed metadata, a dual-machine hot backup method is usually used to achieve data synchronization through the heartbeat line. However, due to network reasons or the timeliness of data transmission, etc., it cannot be guaranteed that when the master server fails to provide services and the backup server takes over the service, all the data on the master server has been transferred to the backup server. . [0003] For example, when the master server receives the data sent by the user, it sends the data to the backup server, but it has not been sent to the backup server due to network reasons. At this time, the master server fails, and this part of the data will not be synchronized to the backup server in time. meta server...

AI Technical Summary

Problems solved by technology

[0005] The embodiment of the present invention provides a method and device for realizing the data synchronization of the master and backup meta servers, which is used to solve the problem in the prior art that the data synchronization must rely on third-party equipment, and when the third-party equipment fails, the master and backup meta-server cannot be guaranteed. The problem of data consistency between meta servers

Images