Virtual central processing unit (CPU) scheduling method capable of supporting software real-time application

Abstract

The invention discloses a virtual CPU (VCPU) scheduling method capable of supporting software real-time application in a multinuclear virtual environment, which uses a virtual machine real-time engine module and a VCPU operation queue real-time scheduling module. The virtual machine real-time engine module consists of a real-time automatic sensing analysis sub-module and a real-time manual configuration sub-module, wherein the real-time automatic sensing analysis sub-module judges the real-time performance of the virtual machine according to the acquired data on the operation conditions of the virtual machine; and the real-time manual configuration sub-module completes manual setting for meeting the real-time requirements of specific virtual machines. The VCPU operation queue real-time scheduling module consists of a CPU operation queue state analysis sub-module, a VCPU operation queue real-time policy sub-module and a VCPU operation queue optimization sub-module, wherein the CPU operation queue state analysis sub-module acquires the binding information of a VCPU operation queue according to a real-time state; the VCPU operation queue real-time policy sub-module performs VCPU operation queue regulation according to a given policy; and the VCPU operation queue optimization sub-module responses for performing the optimization operation of the VCPU operation queue.

Description

technical field [0001] The invention relates to the technical field of virtualization under a multi-core hardware platform in computer science, in particular to a method for supporting virtual machine soft real-time applications. Background technique [0002] Virtualization is a computer system abstraction technology that manages computer resources through the virtual machine logic layer on the physical platform and provides virtual resources to the client layer running on it. The client operating system can access resources through standard interfaces, but the interfaces do not directly communicate with physical resources; instead, the virtualization layer manages real resources, so that a limited number of resources can be reused among multiple clients. The virtualization layer that runs directly on the hardware platform is usually called a virtual machine monitor (Virtual Machine Monitor, VMM or hypervisor), which is responsible for maintaining the abstraction while ensur...

AI Technical Summary

Problems solved by technology

Although soft real-time applications do not require too much CPU computing resources, they require frequent data transmission and interaction with users

Images