CN107391229B - Cluster filling method and device based on vmware virtualization - Google Patents

Cluster filling method and device based on vmware virtualization Download PDF

Info

Publication number
CN107391229B
CN107391229B CN201710619482.2A CN201710619482A CN107391229B CN 107391229 B CN107391229 B CN 107391229B CN 201710619482 A CN201710619482 A CN 201710619482A CN 107391229 B CN107391229 B CN 107391229B
Authority
CN
China
Prior art keywords
host
priority
cluster
load
highest priority
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201710619482.2A
Other languages
Chinese (zh)
Other versions
CN107391229A (en
Inventor
陈鸽
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhengzhou Yunhai Information Technology Co Ltd
Original Assignee
Zhengzhou Yunhai Information Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Zhengzhou Yunhai Information Technology Co Ltd filed Critical Zhengzhou Yunhai Information Technology Co Ltd
Priority to CN201710619482.2A priority Critical patent/CN107391229B/en
Publication of CN107391229A publication Critical patent/CN107391229A/en
Application granted granted Critical
Publication of CN107391229B publication Critical patent/CN107391229B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/44Arrangements for executing specific programs
    • G06F9/455Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
    • G06F9/45533Hypervisors; Virtual machine monitors
    • G06F9/45558Hypervisor-specific management and integration aspects
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46Multiprogramming arrangements
    • G06F9/50Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5005Allocation of resources, e.g. of the central processing unit [CPU] to service a request
    • G06F9/5027Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
    • G06F9/5038Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals considering the execution order of a plurality of tasks, e.g. taking priority or time dependency constraints into consideration
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46Multiprogramming arrangements
    • G06F9/50Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5083Techniques for rebalancing the load in a distributed system
    • G06F9/5088Techniques for rebalancing the load in a distributed system involving task migration
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/44Arrangements for executing specific programs
    • G06F9/455Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
    • G06F9/45533Hypervisors; Virtual machine monitors
    • G06F9/45558Hypervisor-specific management and integration aspects
    • G06F2009/4557Distribution of virtual machine instances; Migration and load balancing

Landscapes

  • Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computer And Data Communications (AREA)
  • Debugging And Monitoring (AREA)

Abstract

The document discloses a cluster filling method and device based on vmware virtualization, and relates to the technical field of cloud computing data centers. A method disclosed herein, comprising: determining the priority of each host participating in a cluster filling strategy under a cluster, wherein the priority of the host is inversely proportional to the real-time load state of the host; and migrating the virtual machine on the host with the lowest priority to the host with the highest priority according to a preset cluster filling strategy until the load of the host with the highest priority reaches the upper line, migrating the rest virtual machines on the host with the lowest priority to the host with the second highest priority until the load of the host with the second highest priority reaches the upper line, and so on until all the virtual machines finish migrating.

Description

Cluster filling method and device based on vmware virtualization
Technical Field
The invention relates to the technical field of cloud computing data centers, in particular to a realization scheme of a cluster filling strategy based on vmware virtualization.
Background
In the cloud computing era, as the application field of cloud services is wider and wider, the scale of a server cluster based on a virtualization technology is larger and larger, which provides a new challenge for resource scheduling of the cluster. In large-scale virtualized clusters, the number and load of virtual machines may change frequently with usage requirements, static resource allocation may result in wasted or insufficient resources, and dynamic resource adjustment through manual intervention may have significant successors. Therefore, the resources need to be adjusted according to the requirements by using a dynamic resource scheduling mode, and finally, the goals of energy-saving integration or load balancing and the like are achieved.
Disclosure of Invention
The invention provides a vmware virtualization-based cluster filling method and a vmware virtualization-based cluster filling device, which can solve the problem that cluster resources cannot be dynamically allocated.
Disclosed herein is a vmware virtualization-based cluster filling method, which comprises the following steps:
determining the priority of each host participating in a cluster filling strategy under a cluster, wherein the priority of the host is inversely proportional to the real-time load state of the host;
and migrating the virtual machine on the host with the lowest priority to the host with the highest priority according to a preset cluster filling strategy until the load of the host with the highest priority reaches the upper line, migrating the rest virtual machines on the host with the lowest priority to the host with the second highest priority until the load of the host with the second highest priority reaches the upper line, and so on until all the virtual machines finish migrating.
Optionally, in the above method, the priority of the host is further inversely proportional to the total number of times of virtual machine migration on the host.
Optionally, in the foregoing method, the cluster filling policy includes:
and migrating the virtual machines on the host with the lowest priority to the host with the highest priority according to the maximum migration number of the single virtual machines until the load of the host with the highest priority reaches the online state, and migrating the virtual machines to the host with the second highest priority.
Optionally, in the foregoing method, the cluster filling policy further includes:
after the migration of the virtual machine on the host with the lowest priority is completed, the load of the host with the highest priority still does not reach the online state, and then the virtual machine on the host with the second lowest priority is migrated to the host with the highest priority until the load of the host with the highest priority reaches the online state.
Optionally, in the foregoing method, the determining the priority of each host participating in the cluster fill policy under the cluster includes:
and when the load state of each host under the cluster is monitored according to a preset period, determining the priority of each host under the cluster, which participates in the cluster filling strategy.
Also disclosed herein is a vmware virtualization-based cluster population device, comprising:
the system comprises a priority determining unit, a priority determining unit and a control unit, wherein the priority determining unit determines the priority of each host participating in a cluster filling strategy under a cluster, and the priority of the host is inversely proportional to the real-time load state of the host;
and the virtual machine migration unit migrates the virtual machines on the hosts with the lowest priority to the hosts with the highest priority according to a preset cluster filling strategy until the load of the hosts with the highest priority reaches the online state, migrates the remaining virtual machines on the hosts with the lowest priority to the hosts with the second highest priority until the load of the hosts with the second highest priority reaches the online state, and so on until all the virtual machines finish migration.
Optionally, in the above apparatus, the priority of the host is further inversely proportional to the total number of times of virtual machine migration on the host.
Optionally, in the foregoing apparatus, the cluster filling policy includes:
and migrating the virtual machines on the host with the lowest priority to the host with the highest priority according to the maximum migration number of the single virtual machines until the load of the host with the highest priority reaches the online state, and migrating the virtual machines to the host with the second highest priority.
Optionally, in the above apparatus, the cluster filling policy further includes:
after the migration of the virtual machine on the host with the lowest priority is completed, the load of the host with the highest priority still does not reach the online state, and then the virtual machine on the host with the second lowest priority is migrated to the host with the highest priority until the load of the host with the highest priority reaches the online state.
Optionally, in the above apparatus, the determining, by the priority determining unit, the priority of each host participating in the cluster full policy under the cluster includes:
and when the load state of each host under the cluster is monitored according to a preset period, determining the priority of each host under the cluster, which participates in the cluster filling strategy.
According to the technical scheme, the resource use condition of the cluster is monitored in real time, the whole load state of the current cluster can be automatically judged according to the monitoring data, corresponding resource adjustment decisions are made according to different load states, and the decisions are executed, so that the filling operation of the host under the VMware cluster is reasonably and simply finished, and the loss caused by the error easiness of computer hardware and software is reduced.
Drawings
FIG. 1 is a flow chart of a cluster filling method based on vmware virtualization in the embodiment of the present invention;
fig. 2 is a schematic diagram of a cluster filling policy in the embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be described in further detail with reference to specific embodiments. It should be noted that the embodiments and features of the embodiments of the present application may be arbitrarily combined with each other without conflict.
The inventor of the application provides that the resource use condition of each host under the cluster can be monitored in real time, and the load state of the cluster can be judged quickly and accurately by utilizing an algorithm for automatically judging the integral load state of the cluster according to the resource monitoring result of the cluster. The judgment result is used as the basis of resource scheduling control, for example, the resource use condition result can be used as the input of a scheduling algorithm, the virtual machine is dynamically migrated to a certain host, the aims of energy conservation and load balancing are finally achieved, and a large amount of time for repeated calculation can be saved.
Based on the above thought, the present embodiment provides a cluster filling method based on vmware virtualization, as shown in fig. 1, including the following operations:
step 100, determining the priority of each host participating in a cluster filling strategy under a cluster, wherein the priority of the host is inversely proportional to the real-time load state of the host;
in this context, the trigger condition for determining the priority of each host participating in the cluster filling policy under the cluster may be real-time or periodic.
For example, the resource usage of the cluster is monitored in real time through a wave cloud-cloud data center management platform, the resource usage of each host under the cluster is monitored in real time, the load state of each host under the cluster is automatically determined according to the monitoring data, when the load state of any one or more hosts changes, the virtual machines under the cluster are automatically adjusted according to the requirements, that is, the priority of each host participating in the cluster full-filling strategy under the cluster is determined according to the load state of each host.
Or, when the resource usage of each host under the cluster is monitored according to a preset period, the priority of each host participating in the cluster filling policy under the cluster can be determined.
In addition, when migration is performed according to the load state of the host under the cluster, the host which does not exceed the highest load host and has the smallest migration number of the virtual machines is preferentially selected, and dynamic adjustment of the virtual machines under the virtual machine cluster is performed. That is, the priority of the host may be inversely proportional to the total number of times of virtual machine migration on the host, in addition to being inversely proportional to the load state of the host, that is, the higher the load of the host, the lower the priority, the lower the load of the host, and the higher the priority. The higher the total number of virtual machine migration on the host is, the lower the priority is, and the smaller the total number of virtual machine migration on the host is, the higher the priority is.
The load state of the host referred to herein includes resource usage conditions such as CPU and memory load, which are not limited in particular.
Step 200: and migrating the virtual machine on the host with the lowest priority to the host with the highest priority according to a preset cluster filling strategy until the load of the host with the highest priority reaches the upper line, migrating the rest virtual machines on the host with the lowest priority to the host with the second highest priority until the load of the host with the second highest priority reaches the upper line, and so on until all the virtual machines finish migrating.
The following describes the implementation of the above step 200 in detail.
The principle of the cluster filling strategy is shown in fig. 2.
The process of presetting the cluster filling strategy is as follows:
firstly: a VMware virtualization environment must be provided, and the VMware environment must have two or more server host devices to which the same VMware server virtualization system is installed.
Then: and configuring a cluster filling strategy for the VMware virtualization platform.
A cluster is selected for which an application fill-up policy is to be applied.
Virtual machines are selected that need to be migratable with the fill policy applicable.
The number of virtual machines that are migrated from one host to another at a single time (i.e., the maximum number of virtual machines migrated at a single time) is selected.
Configuring a cluster filling strategy:
and migrating the virtual machines on the host with the lowest priority to the host with the highest priority according to the maximum migration number of the single virtual machines until the load of the host with the highest priority reaches the online state, and migrating the virtual machines to the host with the second highest priority.
It should be further noted that, in addition to the above cluster full policy, the virtual machine on the host with the lowest priority may be migrated, and the virtual machine on the host with the lowest priority may also be migrated to achieve the purpose of load balancing, where the cluster full policy further includes:
after the migration of the virtual machine on the host with the lowest priority is completed, the virtual machine on the host with the second lowest priority is migrated to the host with the highest priority in the hosts which do not reach the load online state until all the hosts participating in the cluster filling strategy reach the load balance. For example, after the migration of the virtual machine on the host with the lowest priority is completed, the host with the highest priority still does not reach the online state, and then the virtual machine on the host with the second lowest priority is migrated to the host with the highest priority until the host with the highest priority reaches the online state.
The process of executing the cluster filling strategy of the VMware virtualization platform is as follows:
and S1, acquiring all virtual machines applying the cluster filling strategy of the VMware virtualization platform.
And S2, acquiring all hosts applying the cluster filling strategy of the VMware virtualization platform.
And S3, arranging the optimal host filling sequence according to the load state of each host and the load conditions of all the virtual machines in sequence. Wherein the smaller the host load, the more priority the host fill.
And S4, according to the optimal host filling sequence and the maximum migration number of the single virtual machines, filling the virtual machines on the host with the lowest priority to the host with the highest priority until the host load is on line, and then continuing the migration of the host with the second priority until the migration is completed.
The embodiment also provides a vmware virtualization-based cluster filling device, which can implement the method and mainly includes the following two units.
The system comprises a priority determining unit, a priority determining unit and a control unit, wherein the priority determining unit determines the priority of each host participating in a cluster filling strategy under a cluster, and the priority of the host is inversely proportional to the real-time load state of the host;
and the virtual machine migration unit migrates the virtual machines on the hosts with the lowest priority to the hosts with the highest priority according to a preset cluster filling strategy until the load of the hosts with the highest priority reaches the online state, migrates the remaining virtual machines on the hosts with the lowest priority to the hosts with the second highest priority until the load of the hosts with the second highest priority reaches the online state, and so on until all the virtual machines finish migration.
Since the above-described vmware virtualization-based cluster filling method can be implemented by the above-described apparatus, the specific implementation of the apparatus, such as the cluster filling policy and the operations of virtual machine migration, can refer to the above-described related contents, and will not be described herein again.
It can be seen from the above embodiments that the technical solution of the present application has the following beneficial effects:
the resource scheduling mode is changed from the traditional physical machine granularity to the virtual machine granularity, as many virtual machine instances as possible can be simultaneously operated on a single physical machine, the effective utilization and skill target of physical resources can be realized, the system can accurately judge the resource load condition of the cluster in a short time, then the scheduling requirement can be completed by scheduling and controlling a plurality of virtual machines, and the utilization rate of physical resource equipment are improved.
It will be understood by those skilled in the art that all or part of the steps of the above methods may be implemented by instructing the relevant hardware through a program, and the program may be stored in a computer readable storage medium, such as a read-only memory, a magnetic or optical disk, and the like. Alternatively, all or part of the steps of the above embodiments may be implemented using one or more integrated circuits. Accordingly, each module/unit in the above embodiments may be implemented in the form of hardware, and may also be implemented in the form of a software functional module. The present application is not limited to any specific form of hardware or software combination.
The above description is only a preferred example of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (8)

1. A cluster filling method based on vmware virtualization comprises the following steps:
determining the priority of each host participating in a cluster filling strategy under a cluster, wherein the priority of the host is inversely proportional to the real-time load state of the host;
selecting a host which does not exceed the highest load and has the smallest migration frequency sum of the virtual machines as a host with the highest priority according to a preset cluster filling strategy, migrating the virtual machine on the host with the lowest priority to the host with the highest priority until the load of the host with the highest priority reaches the upper line, migrating the rest virtual machines on the host with the lowest priority to the host with the second highest priority until the load of the host with the second highest priority reaches the upper line, and so on until all the virtual machines finish migrating; wherein the priority of the host is further inversely proportional to a total number of virtual machine migrations on the host.
2. The method of claim 1, wherein the cluster fill policy comprises:
and migrating the virtual machines on the host with the lowest priority to the host with the highest priority according to the maximum migration number of the single virtual machines until the load of the host with the highest priority reaches the online state, and migrating the virtual machines to the host with the second highest priority.
3. The method of claim 2, wherein the cluster fill policy further comprises:
after the migration of the virtual machine on the host with the lowest priority is completed, the load of the host with the highest priority still does not reach the online state, and then the virtual machine on the host with the second lowest priority is migrated to the host with the highest priority until the load of the host with the highest priority reaches the online state.
4. The method of claim 3, wherein the determining the priority of each host under the cluster that participates in the cluster fill policy comprises:
and when the load state of each host under the cluster is monitored according to a preset period, determining the priority of each host under the cluster, which participates in the cluster filling strategy.
5. A vmware virtualization based cluster population filling apparatus, comprising:
the system comprises a priority determining unit, a priority determining unit and a control unit, wherein the priority determining unit determines the priority of each host participating in a cluster filling strategy under a cluster, and the priority of the host is inversely proportional to the real-time load state of the host;
the virtual machine migration unit selects a host which does not exceed the highest load and has the smallest sum of the migration times of the virtual machines as a host with the highest priority according to a preset cluster filling strategy, migrates the virtual machines on the host with the lowest priority to the host with the highest priority until the load of the host with the highest priority reaches the upper line, migrates the remaining virtual machines on the host with the lowest priority to the host with the second highest priority until the load of the host with the second highest priority reaches the upper line, and so on until all the virtual machines finish migration; wherein the priority of the host is also inversely proportional to the total number of times of virtual machine migration on the host.
6. The apparatus of claim 5, wherein the cluster fill policy comprises:
and migrating the virtual machines on the host with the lowest priority to the host with the highest priority according to the maximum migration number of the single virtual machines until the load of the host with the highest priority reaches the online state, and migrating the virtual machines to the host with the second highest priority.
7. The apparatus of claim 6, wherein the cluster fill policy further comprises:
after the migration of the virtual machine on the host with the lowest priority is completed, the load of the host with the highest priority still does not reach the online state, and then the virtual machine on the host with the second lowest priority is migrated to the host with the highest priority until the load of the host with the highest priority reaches the online state.
8. The apparatus of claim 7, wherein the priority determining unit to determine the priority of each host participating in a cluster fill policy under the cluster comprises:
and when the load state of each host under the cluster is monitored according to a preset period, determining the priority of each host under the cluster, which participates in the cluster filling strategy.
CN201710619482.2A 2017-07-26 2017-07-26 Cluster filling method and device based on vmware virtualization Active CN107391229B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710619482.2A CN107391229B (en) 2017-07-26 2017-07-26 Cluster filling method and device based on vmware virtualization

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710619482.2A CN107391229B (en) 2017-07-26 2017-07-26 Cluster filling method and device based on vmware virtualization

Publications (2)

Publication Number Publication Date
CN107391229A CN107391229A (en) 2017-11-24
CN107391229B true CN107391229B (en) 2020-09-08

Family

ID=60342401

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710619482.2A Active CN107391229B (en) 2017-07-26 2017-07-26 Cluster filling method and device based on vmware virtualization

Country Status (1)

Country Link
CN (1) CN107391229B (en)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103810016A (en) * 2012-11-09 2014-05-21 北京华胜天成科技股份有限公司 Method and device for realizing virtual machine migration and cluster system
CN104407925A (en) * 2014-12-10 2015-03-11 中国电信集团系统集成有限责任公司 Dynamic resource distribution method
CN105893155A (en) * 2016-04-14 2016-08-24 广州杰赛科技股份有限公司 Virtual machine load balancing control method and device

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9317314B2 (en) * 2010-06-29 2016-04-19 Microsoft Techology Licensing, Llc Techniques for migrating a virtual machine using shared storage

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103810016A (en) * 2012-11-09 2014-05-21 北京华胜天成科技股份有限公司 Method and device for realizing virtual machine migration and cluster system
CN104407925A (en) * 2014-12-10 2015-03-11 中国电信集团系统集成有限责任公司 Dynamic resource distribution method
CN105893155A (en) * 2016-04-14 2016-08-24 广州杰赛科技股份有限公司 Virtual machine load balancing control method and device

Also Published As

Publication number Publication date
CN107391229A (en) 2017-11-24

Similar Documents

Publication Publication Date Title
EP3606008B1 (en) Method and device for realizing resource scheduling
AU2011299337B2 (en) Controlled automatic healing of data-center services
CN107222531B (en) Container cloud resource scheduling method
JP5584765B2 (en) Method and apparatus for data center automation
JP5332065B2 (en) Cluster configuration management method, management apparatus, and program
US20140245298A1 (en) Adaptive Task Scheduling of Hadoop in a Virtualized Environment
US10365943B2 (en) Virtual machine placement
US20140007093A1 (en) Hierarchical thresholds-based virtual machine configuration
CN104011685A (en) Resource management method of virtual machine system, virtual machine system, and apparatus
KR20130101693A (en) Method and apparatus for power management in virtualization system using different operation system
US20140196030A1 (en) Hierarchical thresholds-based virtual machine configuration
US20160196157A1 (en) Information processing system, management device, and method of controlling information processing system
CN104008018B (en) The online moving method of virtual machine under cloud computing environment
Sampaio et al. Towards high-available and energy-efficient virtual computing environments in the cloud
EP4248314A1 (en) Coordinated container scheduling for improved resource allocation in virtual computing environment
WO2015032201A1 (en) Virtual machine placing method and device
CN107220125A (en) A kind of cloud resource dispatching method and device
CN109960579B (en) Method and device for adjusting service container
CN113032102A (en) Resource rescheduling method, device, equipment and medium
KR20160104419A (en) Apparatus and method for autonomic scaling of monitoring function resource in software defined network
CN109739634A (en) A kind of atomic task execution method and device
Ramirez et al. Capacity-driven scaling schedules derivation for coordinated elasticity of containers and virtual machines
CN112559122A (en) Virtualization instance management and control method and system based on electric power special security and protection equipment
US10002173B1 (en) System and methods for dynamically adjusting between asynchronous and synchronous data replication policies in a networked virtualization environment
CN105208111A (en) Information processing method and physical machine

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant