Data storage method, management server and system

Abstract

The invention relates to a data storage method, a management server and a management system. The method comprises: combining all the devices for storing data into a data pool; and selecting m devices from all the devices in the data pool as a group by polling when data is required to be stored, and storing the data into the m devices in the selected group respectively, wherein m is a natural number which is more than 1 and less than the total number of all the devices. Various embodiments of the invention can solve the problems of increase of the load and instability of other nodes because a certain node is damaged when the prior clustering method is used for data storage, low utilization rate of each node and poor predictability in the prior data storage method, etc., realize high stability of the other nodes when the node is damaged, and improves the resource utilization rate and the predictability of the nodes.

Description

technical field [0001] The present invention relates to a data storage method, especially a method that can evenly load equipment, improve equipment resource utilization, and increase equipment stability; the invention also relates to a management server, especially a data storage management method. , a management server that evenly stores the load of the device, improves the utilization rate of the device resource, and increases the stability of the device; the invention also relates to a data storage system, which belongs to the field of communication technology. Background technique [0002] In the field of telecommunications, user data needs to be stored. For example, in the field of mobile communication, a large number of user registration information and service attributes are stored. In the prior art, user data is mainly stored in a cluster (hereinafter referred to as CLUSTER). The existing storage system is divided into several clusters. There are two or more devices...

AI Technical Summary

Problems solved by technology

[0014] The first object of the present invention is to provide a data storage method to solve the problem that when a node is damaged in the existing cluster mode for data storage, the load of other nodes is increased, instability and the utilization of each node in the existing data storage mode Low rate, poor predictability, etc., to achieve high stability of other nodes when a node is damaged, and improve resource utilization and predictability of nodes (storage devices)

[0015] The second object of the present invention is to provide a kind of management server, in order to solve the problem that existing storage equipment (as, BE) damage brings other equipment load increase, unstable and existing storage equipment resource utilization rate is not high problem, with Realize the high stability of each storage device and improve the utilization rate of each storage device at the same time

[0016] Another object of the present invention is to provide a data storage system, which is used to solve the problem that when a node is damaged in the existing group storage system for data storage, the load of other nodes increases, instability and the problem that each node in the existing data storage system The utilization rate of the storage system is not high, and the predictability of the loss is poor, so that the storage system still has high stability when a node is damaged, and the resource utilization rate and predictability of the entire system are improved.

Images