Method and device for dynamic resource scheduling of virtualized cluster

A dynamic resource and virtualization technology, applied in the computer field, can solve problems such as inability to meet the resource requirements of high-priority virtual machines

Active Publication Date: 2017-12-22
HUAWEI TECH CO LTD
View PDF7 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention provides a method and device for dynamic resource scheduling of a virtualized cluster, which is used to solve the problem in the prior art that multiple high-priority virtual machines with the same priority are on the same physical server and cannot meet the requirements of high-priority virtual machines. The question of resource requirements

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
  • Method and device for dynamic resource scheduling of virtualized cluster
  • Method and device for dynamic resource scheduling of virtualized cluster
  • Method and device for dynamic resource scheduling of virtualized cluster

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 2

[0154] On the basis of Embodiment 1 of the management server of the present invention, optionally, the adjustment module 602 is specifically used for:

[0155] Use the following formula (1) to determine the load balance degree σ1 of the mth virtual group:

[0156]

[0157] Among them, N is the number of physical servers in the virtualization cluster; x i is the resource occupancy rate of the virtual machines belonging to the m-th virtual machine group on the physical server i, where m is less than K;

[0158] Determine whether σ1 is greater than the load balance threshold of the virtual group;

[0159] If so, perform virtual machine deployment adjustment on the mth virtual machine group;

[0160] Otherwise, repeat the above process for the m+1th virtual group.

[0161] The management server in this embodiment can be used to execute image 3 The implementation principles and technical effects of the technical solutions of the shown method embodiments are similar and wi...

Embodiment 3

[0163] On the basis of Embodiment 1 or Embodiment 2 of the management server of the present invention, optionally, the adjustment module 602 is specifically used for:

[0164] According to the resource occupancy rate of the virtual machines belonging to the nth virtual machine group on each physical server, it is determined that the virtual machine to be migrated needs to be migrated from the source physical server to the target physical server; wherein the virtual machine to be migrated is the virtual machine of the nth virtual machine group A virtual machine; wherein, n is less than K;

[0165] Determine whether the remaining resources of the target physical server are greater than the resources required by the virtual machine to be migrated;

[0166] If yes, then migrate the virtual machine to be migrated to the target physical server;

[0167] Otherwise, on the target physical server, the virtual machine belonging to the kth virtual machine group is migrated from the targ...

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 provides a method and device for dynamic resource scheduling of a virtualized cluster. A method for dynamic resource scheduling of a virtualized cluster, the virtualized cluster includes at least one management server and multiple physical servers, one or more virtual machines are deployed on the physical servers, and services run on the virtual machines, The method includes: the management server determines the service priority corresponding to each virtual group in the K virtual groups; the virtual group is a group of virtual machines running the same service; In the lowest order, virtual machine deployment adjustments are performed on the K virtual groups sequentially, so that the resources occupied by the virtual machines belonging to the same virtual group on each physical server are balanced.

Description

technical field [0001] The embodiments of the present invention relate to computer technology, and in particular to a method and device for Dynamic Resources Scheduling (DRS, Dynamic Resources Scheduling) of a virtualized cluster. Background technique [0002] In the virtualization technology, multiple virtual machines can be deployed on a single physical server by virtualizing the physical server, thereby effectively improving the resource occupancy rate of the physical server. Among them, a resource pool composed of multiple physical servers deployed with virtual machines is called a virtualization cluster. [0003] DRS is an important feature of virtual clusters; in the prior art, the methods for implementing DRS mainly include: the cluster management system regularly monitors the resource occupancy rate of each physical server; and migrates some virtual machines on physical servers with high resource occupancy To the physical server with low resource usage rate, realize...

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): G06F9/455G06F9/48
Inventor 何嘉莹刘力力
Owner HUAWEI 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
Try Eureka
PatSnap group products