Method for automatically balancing cloud platform resources

Abstract

The invention provides a method for automatically balancing cloud platform resources. The method comprises the following steps: starting inspection according to a preset rule; recording an inspectionlog; querying the resources with the triggered threshold early warning; judging whether over-allocation or down-allocation needs to be executed on the resource or not; wherein the over-allocation is to allocate corresponding shared resources to the resources, and the down-allocation is to return a part of the resources to a shared resource pool; and if so, executing overconfiguration or downconfiguration, thereby dynamically balancing the computing capability, the storage capability and the network flow capability of the cloud platform resources. Moreover, after the over-allocated resources complete the task, allocation reduction is carried out, and the over-allocated resources are returned to the shared resource pool. According to the method, the limitation of a manual processing mode inthe aspects of quantity and authority is avoided, the manual operation and maintenance cost is effectively saved, available resources of the cloud platform are mined to the maximum extent, and the operation stability of a cloud platform user is improved.

Description

technical field [0001] The invention relates to the technical field of data processing, in particular to a method for automatically balancing cloud platform resources. Background technique [0002] The cloud computing management platform (hereinafter referred to as "cloud platform") is deployed inside the data center, and is used to provide users with virtualized data center hardware capabilities, and provide users with a variety of resources and job options. The original intention of the design of the cloud platform is to allow users to use computing resources like water and electricity, obtain them on demand, and charge by volume. Therefore, truly elastic cloud computing will help users minimize the overall cost of ownership and use of computing resources. As for the definition of "elasticity", the traditional understanding includes integrating virtual resources, pooling their resources and using them on demand (that is, scheduling and balancing resources), but from the p...

AI Technical Summary

Problems solved by technology

[0007] As an ordinary user of the cloud platform, there is no right to analyze and view the scheduled jobs set by other users

And administrators may also be divided into different levels, resulting in the regular job information between administrators often cannot be shared, let alone comprehensive evaluation and analysis

[0008] The above situation will lead to: even when a virtualization resource is created, it is defined a relatively reasonable virtualization resource specification, including CPU quantity and type, memory size, cache type and size, network card type and quantity, other device card types and However, as subsequent services such as changes in the business traffic corresponding to virtualized resources, the operating environment of the resources will change, causing virtualized resources to fail to meet business needs

At the same time, there are often many virtualized resources in the cloud platform that are idle or run inefficiently, resulting in an unbalanced state of the overall computing capacity, resulting in corresponding economic losses

Images