Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Kernel virtual machine scheduling policy-based implementation method

A technology of kernel virtual machine and scheduling strategy, applied in software simulation/interpretation/simulation, resource allocation, multi-program device, etc., can solve the problem of increasing virtual machine switching overhead, defects of kernel virtual machine scheduling strategy, and increasing the number of KVM process switching and other issues, to achieve the effect of shortening time, good use value and application prospect, and improving dispatching efficiency

Inactive Publication Date: 2013-11-13
SHANGHAI JUNESH INFORMATION TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] 3. Defects of the existing scheduling strategy of the kernel virtual machine
In this case, not only the higher-priority business in the KVM virtual machine cannot run, but also leads to the switching of the KVM process. This switch that should not have also increased the number of KVM process switching, thereby increasing the virtual machine switching overhead

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Kernel virtual machine scheduling policy-based implementation method
  • Kernel virtual machine scheduling policy-based implementation method
  • Kernel virtual machine scheduling policy-based implementation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] The present invention according to figure 1 In the shown deployment mode, one or more kernel virtual machines are run simultaneously on a single physical host, and then all kernel virtual machines and common Linux processes are uniformly scheduled by the improved Linux scheduler of the present invention, and the kernel virtual machine process adopts Special scheduling queues and scheduling strategies enable each kernel virtual machine to use system resources more efficiently, reduce the number of virtual machine switching, reduce the switching overhead of virtual machines, and thus improve the overall performance of the kernel virtual machine.

[0030] figure 2 Shown is the overall scheduling flow chart of the system. When the kernel virtual machine is created as a Linux process, it is identified as a virtual machine process and added to the under queue of the virtual machine ready queue. Since the priority of the virtual machine ready queue is higher than that of ord...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a kernel virtual machine scheduling policy-based implementation method. The method comprises two major steps of: 1, dividing Linux processes into a common process, a virtual machine process and a real-time process, making the priority of the virtual machine process between those of the common process and the real-time process, and providing a special scheduling algorithm for the virtual machine process; and 2, dividing virtual machines into a compute-intensive virtual machine and an I / O-intensive virtual machine according to demands of services in the virtual machines, and dynamically adjusting resources of each virtual machine to make the virtual machines better adaptive to the demands of the services in a client operating system. Due to the method, a kernel virtual machine has the priority to be scheduled during the scheduling process, each virtual machine can be fairly treated among a plurality of virtual machines, the resources of the virtual machines can be dynamically adjusted according to the service demands in the virtual machines, and the scheduling requirement of the kernel virtual machine is perfectly met. The method has a practical value and a wide application prospect in the technical field of computer virtual machine schedulers.

Description

(1) Technical field [0001] The present invention mainly relates to an implementation method based on a Kernel-based Virtual Machine (KVM) scheduling strategy, which realizes the coordination of resource competition between the Kernel-based Virtual Machine and the system process in the Linux environment, so that the Kernel-based Virtual Machine can To achieve better performance; in a multi-virtual machine environment, the virtual machines can use system resources more efficiently, and each virtual machine can achieve self-adaptive adjustment. In addition, the scheduling policy based on the kernel virtual machine reduces the switching overhead of the kernel virtual machine by reducing the number of virtual machine switching. The invention belongs to the technical field of a computer virtual machine scheduler. (2) Background technology [0002] 1. Virtualization technology [0003] Virtualization technology appeared in the 1960s and 1970s and was mainly applied to mainframes....

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06F9/50G06F9/455
Inventor 丁涛郝沁汾张冰董翰飞
Owner SHANGHAI JUNESH INFORMATION TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products