Resource scheduling method and device

Abstract

The invention discloses a resource scheduling method and device. The method comprises the following steps: a server judges a self virtual machine state according to load information; when judging that the self virtual machine state is a high-load state, the server generates virtual machine emigration information according to the self load information and sends the virtual machine emigration information to at least one another server; the another server receives the virtual machine emigration information, calculates virtual machine immigration parameters according to the self load information when judging that the self virtual machine state is a low-load state according to the self load information, and sends the virtual machine immigration parameters to the server; the server receives the virtual machine immigration parameters sent by at least one another server and selects an another server corresponding to the maximum virtual machine immigration parameter as a target server; the server emigrates a virtual machine to the target server according to the virtual machine emigration information. By means of the technical scheme provided by the invention, the resource scheduling flexibility and timeliness are improved.

Description

technical field [0001] The invention relates to computer application technology, in particular to a resource scheduling method and device. Background technique [0002] With the development and maturity of related technologies in the field of cloud computing, more and more cloud computing solutions have been practically applied and promoted. Server virtualization is one of the key technologies of cloud computing, and using server virtualization can achieve higher device utilization. At present, the resource scheduling method of traditional server virtualization relies on the management center. Each server periodically reports its own load information to the management center or the management center collects the load information of each server, and then the management center analyzes the load of all servers. information, and make a virtual machine migration plan. [0003] However, the traditional resource scheduling method has the following problems: 1. Due to the overall ...

AI Technical Summary

Problems solved by technology

[0003] However, the traditional resource scheduling method has the following problems: 1. Due to the overall monitoring and scheduling of resources by the management center, when the management center has a shortage of computing resources or fails to collect load information in time, it is easy to cause resource scheduling to be untimely

2. When the scale of the cloud computing system is expanded, resource scheduling is likely to be inflexible

3. Since the load information of the server must be reported to the management center, the cost of data transmission is increased

[0004] To sum up, the traditional resource scheduling method uses the management center to centrally monitor and schedule resources globally, which has the problems of over-reliance on the management center, high cost of load information collection, and insufficient scheduling

Images