CN104699520B - A kind of power-economizing method based on virtual machine (vm) migration scheduling - Google Patents
A kind of power-economizing method based on virtual machine (vm) migration scheduling Download PDFInfo
- Publication number
- CN104699520B CN104699520B CN201310646427.4A CN201310646427A CN104699520B CN 104699520 B CN104699520 B CN 104699520B CN 201310646427 A CN201310646427 A CN 201310646427A CN 104699520 B CN104699520 B CN 104699520B
- Authority
- CN
- China
- Prior art keywords
- virtual machine
- task
- facility
- energy consumption
- machine facility
- 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
Links
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A kind of power-economizing method based on virtual machine (vm) migration scheduling, includes the following steps：Step 101, the service feature of virtual machine facility is analyzed, obtains business classification benchmark；Classified benchmark according to the business, the grade scale of the virtual machine facility is set；Task analysis is carried out to the virtual machine facility, obtains classification of task benchmark；Step 102, according to the grade scale and the classification of task benchmark, energy consumption strategy is worked out；Step 103, the energy consumption strategy is set in the virtual machine facility, realizes that the virtual machine (vm) migration is dispatched energy saving according to the energy consumption strategy.By the present invention, the active migration of virtual machine is realized, virtual generator terminal energy consumption is reduced, has achieveed the purpose that energy-saving and emission-reduction, realize the equilibrium of load, optimize the performance of virtual machine.
Description
Technical field
The present invention relates to virtual machine (vm) migration scheduling technical field, more particularly, to it is a kind of based on virtual machine (vm) migration scheduling
Power-economizing method.
Background technology
Virtualization refers to that computer components are run on the basis of virtually rather than on the basis of real.Virtualization technology can
To expand the capacity of hardware, simplify the re-configuration process of software.The virtualization technology of CPU can cause single CPU of server
It is parallel to simulate multi -CPU, it is allowed to which a platform runs multiple operating systems at the same time, and application program can be mutually independent
Run and be independent of each other in space, so as to significantly improve the work efficiency of computer.It is then virtualization that virtual machine migration technology, which is,
Provide easily method.
In the prior art in the technological means of generally use because a large amount of virtual machine (vm) migrations trigger clustering collision problem, it is necessary to
Realize load balancing, resource is obtained fair and reasonable application；But asking for server end passive migration is still suffered from the prior art
Topic, does not reduce server end energy consumption, the method for the virtual machine (vm) migration for the active not optimized.
The content of the invention
It is an object of the invention to design a kind of power-economizing method based on virtual machine (vm) migration scheduling, solve the above problems.
To achieve these goals, the technical solution adopted by the present invention is as follows：
A kind of power-economizing method based on virtual machine (vm) migration scheduling, includes the following steps：
Step 101, the service feature of virtual machine facility is analyzed, obtains business classification benchmark；According to the business
Classification benchmark, sets the grade scale of the virtual machine facility；Task analysis is carried out to the virtual machine facility, obtains task point
Class benchmark；
Step 102, according to the grade scale and the classification of task benchmark, energy consumption strategy is worked out；
Step 103, the energy consumption strategy is set in the virtual machine facility, the void is realized according to the energy consumption strategy
Plan machine migration scheduling it is energy saving.
Preferably, in the step 101, it is close that the service feature includes I/O intensive degree, CPU intensive degree and memory
Collection degree.
Preferably, in the step 101, the task analysis is included to operating in the virtual machine on the virtual machine facility
Take disk and virtual machine takes the analysis of Internet resources.
Preferably, in the step 102, the energy consumption strategy specifically includes the scheduling strategy and pipe of the virtual machine facility
Reason strategy.
Preferably, the scheduling strategy is that the virtual machine operated on the virtual machine facility is taken disk and to operation
Task of Internet resources are taken in the virtual machine of the virtual machine facility carries out migration scheduling.
Preferably, the management strategy is to be shut down to the virtual machine facility of blank state or sleep management.
Preferably, in the step 103, the energy saving specific method for realizing the virtual machine (vm) migration scheduling is：
If the task quantity operated on the virtual machine in the virtual machine facility is more than or equal to 8, according to
Task immigration in the virtual machine facility of the operation task quantity more than or equal to 8 is less than 8 by energy consumption strategy to task quantity
On virtual machine in a virtual machine facility；
When if the task quantity operated on the virtual machine in the virtual machine facility is less than 8 and be more than 3 hours,
The task in the virtual machine facility is not handled according to the energy consumption strategy；
If the task quantity operated on the virtual machine in the virtual machine facility is less than or equal to 3, according to
Energy consumption strategy by task quantity less than or equal to the task in the virtual machine facility of 3 focus on one or several it is described virtual
On machine.
Compared with prior art, the present invention have the advantages that：
By the present invention, the active migration of virtual machine is realized, virtual generator terminal energy consumption is reduced, has reached energy-saving and emission-reduction
Purpose, realizes the equilibrium of load, optimizes the performance of virtual machine.
Brief description of the drawings
The flow diagram for showing a kind of power-economizing method based on virtual machine (vm) migration scheduling of the invention exemplary Fig. 1.
Embodiment
For the technical solution for being better understood from technical problem solved by the invention, being provided, below in conjunction with attached drawing and
Embodiment, the present invention will be described in further detail.Specific embodiment described herein only to explain the present invention reality
Apply, but be not intended to limit the present invention.
A kind of power-economizing method based on virtual machine (vm) migration scheduling as shown in Figure 1, includes the following steps：
Step 101, the service feature of virtual machine facility is analyzed, obtains business classification benchmark；The business is special
Sign includes I/O intensive degree, CPU intensive degree and memory-intensive degree；According to business classification benchmark, set described virtual
The grade scale of machine equipment；Task analysis is carried out to the virtual machine facility, obtains classification of task benchmark；The task analysis bag
Include and the analysis of disk is taken and to operating in the virtual of the virtual machine facility to the virtual machine for operating in the virtual machine facility
Machine takes the analysis of Internet resources；
Analyze, be combined using business classification benchmark and grade scale, first to industry for the service feature of virtual machine facility
Business feature includes I/O intensive type, CPU and memory-intensive etc. and is analyzed, and the business obtained according to analysis classifies benchmark to formulate
The grade scale of respective virtual machine equipment, then meets the classification of virtual machine facility according to grade scale to match；Thus
The classification of virtual machine facility can be made to be combined well with service feature, and have very strong specific aim；
For task analysis, the task of first analysis operation on a virtual machine is to virtual machine facility utilization level, according to these
Characteristic formulates classification of task benchmark, then these tasks of similar operation on a virtual machine is classified, according to demand
Concrete condition is divided, and can be tentatively divided into primary, intermediate and advanced；A other can have more fine-grained division；So draw
It is point easy and effective, but the analysis to service feature has shortcoming in terms of accuracy and fineness；
Step 102, according to the grade scale and the classification of task benchmark, energy consumption strategy is worked out；The energy consumption strategy
Specifically include the scheduling strategy of the virtual machine facility and the management strategy of the virtual machine facility；The scheduling strategy is to appoint
Business carries out migration scheduling with the virtual machine facility；The management strategy be shut down to the virtual machine facility of blank state or
Sleep management；
According to the status information for running task and virtual machine facility on a virtual machine, with reference to grade scale and classification of task
Benchmark, formulates optimal energy consumption strategy, and energy consumption strategy includes the scheduling strategy and management strategy to virtual machine facility；Such as daytime
The task of operation on a virtual machine is busy, and the load of some virtual machine facilities is very high, can will load very high virtual machine facility and move
Move on on the virtual machine facility of relative free, make load balancing achieve the purpose that to reduce server energy consumption.Compared to daytime, night
The task of operation on a virtual machine is less, scattered virtual machine and task can be concentrated, thus can be the free time
Virtual machine facility is closed or down conversion process, achievees the purpose that to reduce virtual machine facility energy consumption.
Step 103, the energy consumption strategy is set in the virtual machine facility, the void is realized according to the energy consumption strategy
Plan machine migration scheduling it is energy saving；Realize that the energy saving specific method that the virtual machine (vm) migration is dispatched is：
If the task quantity operated on the virtual machine in the virtual machine facility is more than or equal to 8, according to
Task immigration in the virtual machine facility of the operation task quantity more than or equal to 8 is less than 8 by energy consumption strategy to task quantity
On virtual machine in a virtual machine facility；
If the task quantity operated on the virtual machine in the virtual machine facility is less than or equal to 3, according to
Energy consumption strategy by task quantity less than or equal to the task in the virtual machine facility of 3 focus on one or several it is described virtual
On machine.By the present invention, the active migration of virtual machine is realized, virtual generator terminal energy consumption is reduced, has reached the mesh of energy-saving and emission-reduction
, the equilibrium of load is realized, optimizes the performance of virtual machine, it can therefore be seen that holding by some energy optimization strategies
Row can reduce energy consumption.The formulation of energy consumption strategy at the same time, the establishment to virtual machine at the beginning is instructed, according to the business of user
Feature selecting creates virtual machine on different virtual machine facilities.
The present invention is described in detail above by specific and preferred embodiment, but those skilled in the art should be bright
In vain, the invention is not limited in embodiment described above, all any modifications within the basic principle of the present invention, made, group
Conjunction and equivalent substitution etc., are all contained within protection scope of the present invention.
Claims (1)
1. a kind of power-economizing method based on virtual machine (vm) migration scheduling, it is characterised in that include the following steps：
Step 101, the service feature of virtual machine facility is analyzed, obtains business classification benchmark；Classified according to the business
Benchmark, sets the grade scale of the virtual machine facility；Task analysis is carried out to the virtual machine facility, obtains classification of task base
It is accurate；
Step 102, according to the grade scale and the classification of task benchmark, energy consumption strategy is worked out；
Step 103, the energy consumption strategy is set in the virtual machine facility, the virtual machine is realized according to the energy consumption strategy
Migration scheduling it is energy saving；
In the step 101, the service feature includes I O dense degrees, CPU intensive degree and memory-intensive degree；
In the step 101, the task analysis include to operate in the virtual machine on the virtual machine facility take disk and
Virtual machine takes the analysis of Internet resources；
In the step 102, the energy consumption strategy specifically includes the scheduling strategy and management strategy of the virtual machine facility；It is described
Scheduling strategy is that the virtual machine operated on the virtual machine facility is taken disk and to operating in the virtual machine facility
The task that virtual machine takes Internet resources carries out migration scheduling；The management strategy is the virtual machine facility to blank state
Shut down or sleep management；
In the step 103, the energy saving specific method for realizing the virtual machine (vm) migration scheduling is：If operate in the virtual machine
When task quantity on virtual machine in equipment is more than or equal to 8, then operation task quantity is more than according to the energy consumption strategy
It is virtual in the virtual machine facility of the task immigration in the virtual machine facility to task quantity less than 8 equal to 8
On machine；If the task quantity operated on the virtual machine in the virtual machine facility is less than 8 and is more than 3, according to institute
Energy consumption strategy is stated not handle the task in the virtual machine facility；If operate on the virtual machine in the virtual machine facility
When task quantity is less than or equal to 3, then task quantity is less than or equal to the virtual machine facility of 3 according to the energy consumption strategy
In task focus on one or several virtual machines.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310646427.4A CN104699520B (en) | 2013-12-04 | 2013-12-04 | A kind of power-economizing method based on virtual machine (vm) migration scheduling |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310646427.4A CN104699520B (en) | 2013-12-04 | 2013-12-04 | A kind of power-economizing method based on virtual machine (vm) migration scheduling |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104699520A CN104699520A (en) | 2015-06-10 |
| CN104699520B true CN104699520B (en) | 2018-05-01 |
Family
ID=53346686
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310646427.4A Active CN104699520B (en) | 2013-12-04 | 2013-12-04 | A kind of power-economizing method based on virtual machine (vm) migration scheduling |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104699520B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106201691A (en) * | 2016-07-11 | 2016-12-07 | 浪潮(北京)电子信息产业有限公司 | The dispatching method of a kind of network I/O intensive task and device |
| CN107861796B (en) * | 2017-11-30 | 2021-05-04 | 南京信息工程大学 | Virtual machine scheduling method supporting energy consumption optimization of cloud data center |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102117226A (en) * | 2011-03-18 | 2011-07-06 | 浪潮(北京)电子信息产业有限公司 | Resource dispatching system and resource dispatching method |
| CN102426475A (en) * | 2011-11-04 | 2012-04-25 | 中国联合网络通信集团有限公司 | Energy saving method, energy saving management server and system under desktop virtual environment |
| CN102571986A (en) * | 2012-02-27 | 2012-07-11 | 浙江大学 | Load balancing method based on vector mapping |
-
2013
- 2013-12-04 CN CN201310646427.4A patent/CN104699520B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102117226A (en) * | 2011-03-18 | 2011-07-06 | 浪潮(北京)电子信息产业有限公司 | Resource dispatching system and resource dispatching method |
| CN102426475A (en) * | 2011-11-04 | 2012-04-25 | 中国联合网络通信集团有限公司 | Energy saving method, energy saving management server and system under desktop virtual environment |
| CN102571986A (en) * | 2012-02-27 | 2012-07-11 | 浙江大学 | Load balancing method based on vector mapping |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104699520A (en) | 2015-06-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Hu et al. | A time-series based precopy approach for live migration of virtual machines | |
| WO2018099299A1 (en) | Graphic data processing method, device and system | |
| CN102981890B (en) | A kind of calculation task in Visualized data centre and virtual machine deployment method | |
| CN105260235A (en) | Method and device for scheduling resources on basis of application scenarios in cloud platform | |
| CN102360313B (en) | Performance acceleration method of heterogeneous multi-core computing platform on chip | |
| US10176014B2 (en) | System and method for multithreaded processing | |
| CN104102543A (en) | Load regulation method and load regulation device in cloud computing environment | |
| CN102981893B (en) | A kind of dispatching method of virtual machine and system | |
| CN102117226A (en) | Resource dispatching system and resource dispatching method | |
| Zidenberg et al. | Multiamdahl: How should i divide my heterogenous chip? | |
| CN103595780A (en) | Cloud computing resource scheduling method based on repeat removing | |
| CN104615480A (en) | Virtual processor scheduling method based on NUMA high-performance network processor loads | |
| CN103401939A (en) | Load balancing method adopting mixing scheduling strategy | |
| CN106293944A (en) | System and optimization method is accessed based on nonuniformity I/O under virtualization multi-core environment | |
| CN106339351A (en) | SGD (Stochastic Gradient Descent) algorithm optimization system and method | |
| CN103475538A (en) | Multi-interface-based self-adaptive cloud service test method | |
| CN105868004A (en) | Cloud computing based business system scheduling method and apparatus | |
| CN105373432A (en) | Cloud computing resource scheduling method based on virtual resource state prediction | |
| CN104182278A (en) | Method and device for judging busy degree of computer hardware resource | |
| Han et al. | Energy efficient VM scheduling for big data processing in cloud computing environments | |
| CN107807854A (en) | The method and rendering task processing method of a kind of Automatic dispatching Node station | |
| CN104699520B (en) | A kind of power-economizing method based on virtual machine (vm) migration scheduling | |
| CN105389196A (en) | Method for processing seismic data by utilizing virtualization technology | |
| CN104299170B (en) | Intermittent energy source mass data processing method | |
| CN105049499A (en) | Multi-cube mapping-based resource allocation method in network function virtualization |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| EXSB | Decision made by sipo to initiate substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 100176 201, 2nd floor, building 18, yard 1, Disheng North Street, Beijing Economic and Technological Development Zone, Daxing District, Beijing Patentee after: Great Wall Chaoyun (Beijing) Technology Co.,Ltd. Address before: 100176 201, 2nd floor, building 18, yard 1, Disheng North Street, Beijing Economic and Technological Development Zone, Daxing District, Beijing Patentee before: BEIJING TIANDI SUPERCLOUD Co.,Ltd. |
|
| CP01 | Change in the name or title of a patent holder | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: An energy saving method based on virtual machine migration scheduling Effective date of registration: 20210820 Granted publication date: 20180501 Pledgee: Beijing first financing Company limited by guarantee Pledgor: Great Wall Chaoyun (Beijing) Technology Co.,Ltd. Registration number: Y2021980008087 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PC01 | Cancellation of the registration of the contract for pledge of patent right |
Date of cancellation: 20230901 Granted publication date: 20180501 Pledgee: Beijing first financing Company limited by guarantee Pledgor: Great Wall Chaoyun (Beijing) Technology Co.,Ltd. Registration number: Y2021980008087 |
|
| PC01 | Cancellation of the registration of the contract for pledge of patent right |