Resource scheduling method and resource scheduling device

Abstract

The invention provides a resource scheduling method and a resource scheduling device. The resource scheduling method comprises steps that state information of a resource node is acquired; according to the state information, the state parameter value of the resource value is calculated; when the state parameter value is smaller than a first preset threshold value, whether the to-be-allocated CPU resource of the resource node is smaller than a preset CPU demand quantity is determined; when yes, the excess allocation proportion of the to-be-allocated CPU resource is calculated; according to the excess allocation proportion, the CPU resource is scheduled for the resource node. Dynamic management of a resource pool is realized, and limitations on conventional fixed proportional allocation of a whole resource cluster are broken, and by aiming at the different load conditions of the different resource nodes, the scheduling and the management of the resources are realized dynamically and telescopically.

Description

technical field [0001] The present application relates to the technical field of cloud computing, and in particular to a resource scheduling method and a resource scheduling device. Background technique [0002] Cloud computing is the growth, usage, and delivery model of Internet-based related services, usually involving the provision of dynamically scalable and often virtualized resources over the Internet. Cloud computing distributes calculations on a large number of distributed computers instead of local computers or remote servers, so that users or enterprises can access cloud computing data centers through computers, notebooks, mobile phones, etc., so that resources can be switched to On-demand applications access computers and storage systems as needed. [0003] At present, the industry generally uses Openstack, Mesos and other open source software to manage cloud computing resources. According to the pre-configured rules, resource configuration is realized by setting...

AI Technical Summary

Problems solved by technology

[0004] However, the above-mentioned management method of setting the overshoot ratio is not flexible. Once the overshoot ratio is set, it is difficult to change it according to the actual operation requirements of the system, which will easily lead to resource fragmentation and waste a lot of resources.

At the same time, in the process of resource scheduling, according to the above management method, some machine resources are prone to be overloaded, and the utilization rate of other machines is too low, resulting in local resource conflicts or waste.

Images