Regional homogeneity hash load equalizing method of private cloud based on dynamic feedback

Abstract

The invention discloses a regional homogeneity hash load equalizing method of a private cloud based on dynamic feedback. The regional homogeneity hash load equalizing method comprises the following steps of enabling a service finding module and a health examination module in the private cloud to obtain a service providing end and a real-time load thereof, calculating the weight for continuing to provide services, and utilizing a regional homogeneity hash algorithm with weight to calculate a harsh route list, so as to provide services for the request of the client. The regional homogeneity hash load equalizing method has the advantages that the weight of the service providing end can be dynamically updated in real time, the property of load equalizing service is improved, and the load condition of each service providing end is equalized.

Description

technical field [0001] The invention relates to the field of communication technology, in particular to a dynamic feedback-based local consistency hash load balancing method. Background technique [0002] With the development of the Internet, the use of cloud computing has become more and more extensive. Cloud computing is the increase, use and delivery model of Internet-based related services, usually involving the provision of dynamically scalable and often virtualized resources through the Internet. [0003] In a general cloud platform that supports cloud computing, users can create their own cloud environment through the console, including various specific needs such as network, storage, and computing. Most cloud platforms also need to support certain specific environments, such as load balancing services, virtual private networks, and so on. [0004] Among the various technologies mentioned above, load balancing services are an indispensable part of various cloud compu...

AI Technical Summary

Problems solved by technology

First of all, the weight part of the existing load balancing algorithm is statically configured, and the weight of the service cannot be updated in time according to the existing load of the service provider, resulting in a service with a high real-time load rate for some reasons. The provider still receives most of the client requests because the initial weight is too high

Secondly, the existing load balancing algorithm generally adopts the consistent hash algorithm, which is not enough in balance, and its time complexity is also high, which has a certain impact on its performance.

Images