Automatic cluster server selection method

Abstract

The invention relates to an automatic cluster server selection method, which comprehensively considers factors such as server load, resource requirements of applications, current application distribution and mutual exclusiveness between the applications to finally select an optimal proxy server. According to the invention, multi-dimensional resource load balance is conveniently considered in loadassessment, so that the load conditions of each server can be assessed accurately; in the aspect of estimating the resource demand of the application, historical data is used for estimating the resource demand of the application, so that the method has certain predictability and relatively high accuracy; in the aspect of application distribution, all the current applications are accurately counted, so that the optimal running positions of the applications are mastered on the whole from a server cluster; and in the aspect of the mutual exclusiveness of the applications, the mutual exclusion applications which may generate resource competition are analyzed according to the resource use conditions of all the applications, so that the mutual exclusion applications are prevented from running inthe same server, and the resource requirements of the applications are met to the maximum extent.

Description

technical field [0001] The invention relates to the technical field of cloud computing virtualization, in particular to a method for automatically selecting a cluster server. Background technique [0002] As a key technology of cloud computing, virtualization technology generally includes: resource virtualization and application virtualization. Through the virtualization platform, functions such as dynamic deployment, expansion, migration, and backup of applications can be managed more conveniently. Users need different resources and computing capabilities to run different applications. The cloud computing platform can deploy resources and computing capabilities according to user needs. Various IT resources, such as software, hardware, operating systems, storage, and networks, can be virtualized. All of them are virtualized into a resource pool and managed in a unified manner, so as to improve resource utilization and ensure that user resource needs are met to the greatest e...

AI Technical Summary

Problems solved by technology

Only relying on the above single method, its implementation is simple, the application scenarios are limited, it is difficult to meet the scenarios of multiple applications and multiple concurrent users, and it does not consider resource competition among multiple applications, and it cannot satisfy the dynamic deployment of applications by application server clusters and resource scheduling requirements

Images