Video application-oriented virtualization resource management method and device

Abstract

Embodiments of the present invention provide a video application-oriented virtualization resource management method and device, wherein the method includes: after registering the server, for each resource block required to run a video application, according to the resource configuration information, from Select a server that meets the conditions for establishing a resource block from multiple servers, and establish an association relationship between the resource block and the selected server, where the server carries the physical infrastructure required to run video applications; select from all resource blocks A resource block corresponding to the physical infrastructure required for running the video application; deploying the video application to a server associated with the selected resource block, and running the video application on the server using the physical infrastructure corresponding to the selected resource block. This solution can abstract and virtualize the physical infrastructure required for running video applications carried by servers, and manage resources flexibly and dynamically at a finer granularity.

Description

technical field [0001] The invention relates to the technical field of the Internet, in particular to a video application-oriented virtualization resource management method and device. Background technique [0002] In the near future, video will become the mainstream carrier of information, representing the future of the Internet. It is estimated that by 2020 more than 80% of global Internet traffic will be video. Video applications themselves have much higher requirements for computing resources, storage resources, and network bandwidth than general Internet applications. The deployment of large-scale video applications will inevitably bring investment in hardware servers, switches and other infrastructure far beyond traditional Internet services. At the same time, the cost of operation and maintenance will also increase significantly. Therefore, it is very important to solve the problem of efficient resource management for large-scale video applications. [0003] The s...

AI Technical Summary

Problems solved by technology

Depending on the specific business form, the cost of video applications providing services for a single user is one to two orders of magnitude higher than that of ordinary Internet applications, requiring more refined resource control and scheduling capabilities, and the existing resource scheduling methods will hinder the development of video applications. resource optimization

[0007] 2) The above virtualization technology cannot abstractly manage all resources, such as GPU, ARM processor, PCI-E capture card, video compression chip and other video application infrastructure

Images