CN110196756A - A kind of virtual machine mode transfer method for supporting energy optimization - Google Patents
A kind of virtual machine mode transfer method for supporting energy optimization Download PDFInfo
- Publication number
- CN110196756A CN110196756A CN201910466889.5A CN201910466889A CN110196756A CN 110196756 A CN110196756 A CN 110196756A CN 201910466889 A CN201910466889 A CN 201910466889A CN 110196756 A CN110196756 A CN 110196756A
- Authority
- CN
- China
- Prior art keywords
- virtual machine
- heat pattern
- mode
- cold
- server
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 25
- 238000012546 transfer Methods 0.000 title claims abstract description 13
- 238000005457 optimization Methods 0.000 title claims abstract description 12
- 230000000977 initiatory effect Effects 0.000 claims abstract description 4
- 101100311460 Schizosaccharomyces pombe (strain 972 / ATCC 24843) sum2 gene Proteins 0.000 claims description 14
- 238000013508 migration Methods 0.000 claims description 3
- 230000005012 migration Effects 0.000 claims description 3
- 238000005265 energy consumption Methods 0.000 abstract description 27
- 230000000694 effects Effects 0.000 abstract description 4
- 238000005516 engineering process Methods 0.000 description 2
- 238000010187 selection method Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
- G06F9/45558—Hypervisor-specific management and integration aspects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
- G06F9/45558—Hypervisor-specific management and integration aspects
- G06F2009/4557—Distribution of virtual machine instances; Migration and load balancing
-
- 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
Abstract
The present invention proposes a kind of virtual machine mode transfer method for supporting energy optimization, comprising: initiation parameter；Judge whether the quantity m of heat pattern adjustment is greater than 0, carries out the mode shifts of virtual machine；Dispose current virtual machine system；To every server resource surplus, it is ranked up from big to small；Sum1 carries out mode shifts, updates each set of modes compared with the quantity of heat pattern virtual machine for needing suspend mode；Dispose current virtual machine system；To every server resource surplus, it is ranked up again from big to small；Sum2 carries out mode shifts, updates each set of modes compared with the quantity for the cold mode virtual machine for needing to wake up；Entire server is selected to be in the cold mode virtual machine in sleep state, or virtual machine problem under cold mode in the server of operation, it is very big to the energy consumption of system, the present invention is on the basis of not only supporting performance guarantee but also meeting the reliability of virtual machine, the power saving in virtual machine mode transfer process is inquired into, good effect has been reached.
Description
Technical field
The invention belongs to field of cloud calculation, and in particular to a kind of virtual machine mode transfer method for supporting energy optimization.
Background technique
With the fast development of Internet technology, cloud computing technology is widely applied, people to cloud service performance and
Reliability requirement is higher and higher.But simultaneously excessively concern service performance and system reliability make the resource utilization of system it is low,
Energy consumption waste is serious.Therefore, how the efficient and rational various resources using in system scope, guarantee cloud system reliability, property
The lower system energy consumption that reduces of requirement is able to satisfy as a big critical issue.For this purpose, the present invention considers each mould from above-mentioned angle
The problem that diverts the aim of formula virtual machine, i.e. operation mode and heat pattern virtual machine concentrate on physical machine cluster few as far as possible, lead to
Closing free physical machine is crossed to reduce energy consumption；Cold mode virtual machine set is concentrated in another group of physical machine few as far as possible, is led to
Crossing collective's suspend mode reduces energy consumption.It executes under Performance And Reliability meet demand of the resource adjusting strategies to guarantee system above,
The energy consumption of system is reduced as far as possible.
Summary of the invention
In order to achieve the above objectives, a kind of virtual machine mode transfer method for supporting energy optimization of the present invention, specifically
Include: the virtual machine mode transfer method for supporting energy consumption guarantee, the heat pattern suspend mode selection method for supporting energy consumption guarantee, support energy
Consume the cold mode wakeup selection method ensured.Cloud service system will generate basic energy consumption and dynamic energy consumption once opening.When being
When system is in standby, basic energy consumption can be only generated；When system executes task, basic energy consumption can be both consumed, can also be consumed
Dynamic energy consumption；In order to reduce energy consumption, need further to consider the problem that diverts the aim of each mode virtual machine.It is hot when needing to reduce
When mode virtual machine quantity, need to switch the virtual machine of heat pattern arrives cold mode, and the present invention considers to select as far as possible in switching
It selects energy consumption and reduces more scheme, using the heat pattern suspend mode selection algorithm for supporting energy consumption guarantee；It is empty when needing to increase heat pattern
When quasi- machine quantity, need to switch the virtual machine of cold mode arrives heat pattern, and the present invention considers in switching, as far as possible selection energy consumption
Increase lesser scheme, so using the cold mode wakeup selection algorithm for supporting energy consumption guarantee.
A kind of virtual machine mode transfer method for supporting energy optimization, specifically comprises the following steps:
Step 1: initiation parameter, b indicate the quantity of virtual machine in a physical machine；
Step 2: judging whether the quantity m of heat pattern adjustment is greater than 0, carry out the mode shifts of virtual machine；
Step 2.1: if the quantity m of heat pattern adjustment is greater than 0, going to step 2.2；If the quantity m of heat pattern adjustment is less than
0, go to step 2.3；
Step 2.2: if the quantity m of heat pattern adjustment is less than or equal to the summation a of cold mode quantity on non-sleep server,
M therein cold mode virtual machines are selected to switch to heat pattern；If the quantity m of heat pattern adjustment is greater than cold mould on non-sleep server
Cold mode virtual machine on the server of not suspend mode is then converted to heat pattern, and wakes up a physics by the summation a of formula quantity
The cold mode virtual machine of remaining m-a platform is converted to heat pattern by machine；
Step 2.3: reducing the quantity of heat pattern, and judge the summation and heat pattern of cold mode in remaining non-sleep physical machine
Whether the quantity of reduction is greater than the quantity in a physical machine on virtual machine；
Step 2.3.1: if a-m > b, virtual machine (vm) migration on server being gone out, and server of sleeping updates each mould
Formula set；
Step 2.3.2: if a-m≤b, m platform heat pattern virtual machine is converted to according to heat pattern suspend mode selection algorithm cold
Mode, renewal model set；
Step 3: deployment current virtual machine system, the quantity of physical machine are f, the heat pattern quantity M of suspend mode, i-th clothes
Be engaged in device resource residual amount Rcpu[i]；
Step 4: to every server resource surplus Rcpu[i] is ranked up to obtain R ' from big to smallcpu, obtain residue
The quantity of heat pattern is sum1 on stock number maximum service device；
Step 5: if sum1 is more than or equal to the quantity M for needing the heat pattern virtual machine of suspend mode, M heat pattern being transferred to cold
Set of modes updates each set of modes；If as quantity M of the sum1 less than the heat pattern virtual machine for needing suspend mode, by sum1
Heat pattern is transferred to cold set of modes, and updates each set of modes；
Step 6: deployment current virtual machine system, the cold mode quantity to be waken up are N；
Step 7: to every server resource surplus Rcpu[i] is ranked up to obtain R ' from big to small againcpu, arrive surplus
The quantity of heat pattern is sum2 on remaining stock number maximum service device；
Step 8: in R 'cpuCold mode quantity sum2 therein is found in the virtual machine set of [i] reference numeral server,
If sum2 is more than or equal to the quantity N for needing the cold mode virtual machine waken up, N number of cold mode is transferred to heat pattern set, is updated
Set of modes；If sum2 quantity is less than the quantity N for needing the cold mode virtual machine waken up, sum2 cold modes are transferred to hot-die
Formula set, and update each set of modes.
Advantageous effects:
The present invention uses a kind of virtual machine mode transfer method for supporting energy optimization, in order to solve system reliability deficiency
When, virtual machine selects entire server to be in the cold mode virtual machine in sleep state still from cold mode shifts to heat pattern
Virtual machine problem under cold mode, very big to the energy consumption of system in the server of operation, and the present invention is both supporting performance guarantee
Meet the power saving inquired on the basis of the reliability of virtual machine in virtual machine mode transfer process again, reaches good section
It can effect.
Detailed description of the invention
Fig. 1 is a kind of virtual machine mode transfer method flow chart for supporting energy optimization of the embodiment of the present invention；
Fig. 2 is the method for the present invention and the other methods energy consumption effect contrast figure of the embodiment of the present invention.
Specific embodiment
Invention is described further with specific implementation example with reference to the accompanying drawing, a kind of virtual machine for supporting energy optimization
Mode shifts method, specifically comprises the following steps:
Step 1: initiation parameter, b indicate the quantity of virtual machine in a physical machine；
Step 2: judging whether the quantity m of heat pattern adjustment is greater than 0, carry out the mode shifts of virtual machine；
Step 2.1: if the quantity m of heat pattern adjustment is greater than 0, going to step 2.2；If the quantity m of heat pattern adjustment is less than
0, go to step 2.3
Step 2.2: if the quantity m of heat pattern adjustment is less than or equal to the summation a of cold mode quantity on non-sleep server,
M therein cold mode virtual machines are selected to switch to heat pattern；If the quantity m of heat pattern adjustment is greater than cold mould on non-sleep server
Cold mode virtual machine on the server of not suspend mode is then converted to heat pattern, and wakes up a physics by the summation a of formula quantity
The cold mode virtual machine of remaining m-a platform is converted to heat pattern by machine；
Step 2.3: reducing the quantity of heat pattern, and judge the summation and heat pattern of cold mode in remaining non-sleep physical machine
Whether the quantity of reduction is greater than the quantity in a physical machine on virtual machine；
Step 2.3.1: if a-m > b, virtual machine (vm) migration on server being gone out, and server of sleeping updates each mould
Formula set；
Step 2.3.2: if a-m≤b, m platform heat pattern virtual machine is converted to according to heat pattern suspend mode selection algorithm cold
Mode, renewal model set；
Step 3: deployment current virtual machine system, the quantity of physical machine are f, the heat pattern quantity M of suspend mode, i-th clothes
Be engaged in device resource residual amount Rcpu[i]；
Step 4: to every server resource surplus Rcpu[i] is ranked up to obtain R ' from big to smallcpu, obtain residue
The quantity of heat pattern is sum1 on stock number maximum service device；
Step 5: if sum1 is more than or equal to the quantity M for needing the heat pattern virtual machine of suspend mode, M heat pattern being transferred to cold
Set of modes updates each set of modes；If as quantity M of the sum1 less than the heat pattern virtual machine for needing suspend mode, by sum1
Heat pattern is transferred to cold set of modes, and updates each set of modes；
Step 6: deployment current virtual machine system, the cold mode quantity to be waken up are N；
Step 7: to every server resource surplus Rcpu[i] is ranked up to obtain R ' from big to small againcpu, arrive surplus
The quantity of heat pattern is sum2 on remaining stock number maximum service device；
Step 8: in R 'cpuCold mode quantity sum2 therein is found in the virtual machine set of [i] reference numeral server,
If sum2 is more than or equal to the quantity N for needing the cold mode virtual machine waken up, N number of cold mode is transferred to heat pattern set, is updated
Set of modes；If sum2 quantity is less than the quantity N for needing the cold mode virtual machine waken up, sum2 cold modes are transferred to hot-die
Formula set, and update each set of modes.
As shown in Figure 2, the work virtual machine average energy consumption under this paper method of adjustment is much smaller than the energy consumption of contrast method once,
Because this paper dynamic optimization method contains the mode shifts strategy based on energy consumption guarantee, cold mode one has been concentrated on as far as possible
In physical machine, and all virtual machines of contrast method one are in working condition that not account for power saving energy consumption most；To analogy
Method only considered a kind of backup mode (cold mode), in a dormant state, energy consumption also compares cold mode second is that traditional backup method
It is smaller.It is calculated, executes energy consumption caused by strategy proposed in this paper compared to contrast method two and averagely save 3.16%；Phase
Than averagely saving 4.15% in contrast method one.
Power consumption when experiment measures server zero load is 0.1096；Power consumption when server is standby is 0.1106；When suspend mode
Power consumption be 0.0095；Power consumption when shutdown is 0.0095；So the energy consumption generated under server shutdown and dormant state is far small
In server zero load and standby mode.
Claims (2)
1. a kind of virtual machine mode transfer method for supporting energy optimization, which is characterized in that specific step is as follows:
Step 1: initiation parameter, b indicate the quantity of virtual machine in a physical machine；
Step 2: judging whether the quantity m of heat pattern adjustment is greater than 0, carry out the mode shifts of virtual machine；
Step 3: the quantity of deployment current virtual machine system, physical machine is f, the heat pattern quantity M of suspend mode, i-th server
Resource residual amount Rcpu[i]；
Step 4: to every server resource surplus Rcpu[i] is ranked up to obtain R ' from big to smallcpu, obtain surplus resources
The quantity for measuring heat pattern on maximum service device is sum1；
Step 5: if sum1 is more than or equal to the quantity M for needing the heat pattern virtual machine of suspend mode, M heat pattern being transferred to cold mode
Set, updates each set of modes；If as quantity M of the sum1 less than the heat pattern virtual machine for needing suspend mode, by sum1 hot-die
Formula is transferred to cold set of modes, and updates each set of modes；
Step 6: deployment current virtual machine system, the cold mode quantity to be waken up are N；
Step 7: to every server resource surplus Rcpu[i] is ranked up to obtain R ' from big to small againcpu, to remaining money
The quantity that heat pattern on maximum service device is measured in source is sum2；
Step 8: in R 'cpuCold mode quantity sum2 therein is found in the virtual machine set of [i] reference numeral server, if
Sum2 is more than or equal to the quantity N for needing the cold mode virtual machine waken up, then N number of cold mode is transferred to heat pattern set, updates mould
Formula set；If sum2 quantity is less than the quantity N for needing the cold mode virtual machine waken up, sum2 cold modes are transferred to heat pattern
Set, and update each set of modes.
2. supporting the virtual machine mode transfer method of energy optimization according to claim 1, which is characterized in that the step 2,
Specifically comprise the following steps:
Step 2.1: if the quantity m of heat pattern adjustment is greater than 0, going to step 2.2；If the quantity m of heat pattern adjustment turns less than 0
To step 2.3；
Step 2.2: if the quantity m of heat pattern adjustment is less than or equal to the summation a of cold mode quantity on non-sleep server, selecting
M therein cold mode virtual machines switch to heat pattern；If the quantity m of heat pattern adjustment is greater than cold pattern count on non-sleep server
Cold mode virtual machine on the server of not suspend mode is then converted to heat pattern, and wakes up a physical machine by the summation a of amount,
The cold mode virtual machine of remaining m-a platform is converted into heat pattern；
Step 2.3: reducing the quantity of heat pattern, and judge that the summation of cold mode and heat pattern are reduced in remaining non-sleep physical machine
Quantity whether be greater than the quantity in a physical machine on virtual machine；
Step 2.3.1: if a-m > b, virtual machine (vm) migration on server being gone out, and server of sleeping updates each set of patterns
It closes；
Step 2.3.2: if a-m≤b, being converted to cold mode for m platform heat pattern virtual machine according to heat pattern suspend mode selection algorithm,
Renewal model set.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910466889.5A CN110196756B (en) | 2019-05-31 | 2019-05-31 | Virtual machine mode transfer method supporting energy consumption optimization |
| PCT/CN2019/090865 WO2020237726A1 (en) | 2019-05-31 | 2019-06-12 | Virtual machine mode transfer method for supporting energy consumption optimization |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910466889.5A CN110196756B (en) | 2019-05-31 | 2019-05-31 | Virtual machine mode transfer method supporting energy consumption optimization |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110196756A true CN110196756A (en) | 2019-09-03 |
| CN110196756B CN110196756B (en) | 2020-07-10 |
Family
ID=67753641
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910466889.5A Active CN110196756B (en) | 2019-05-31 | 2019-05-31 | Virtual machine mode transfer method supporting energy consumption optimization |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN110196756B (en) |
| WO (1) | WO2020237726A1 (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102446115A (en) * | 2012-01-09 | 2012-05-09 | 浙江大学 | Dynamic deployment method for virtual machines |
| CN106775933A (en) * | 2016-11-29 | 2017-05-31 | 深圳大学 | A kind of virtual machine on server cluster dynamically places optimization method and system |
| US20170161117A1 (en) * | 2015-12-07 | 2017-06-08 | Fujitsu Limited | Apparatus and method to determine a service to be scaled out based on a predicted virtual-machine load and service importance |
| US20190079789A1 (en) * | 2016-03-18 | 2019-03-14 | Telefonaktiebolaget Lm Ericsson (Publ) | Using nano-services to secure multi-tenant networking in datacenters |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10242054B2 (en) * | 2016-01-12 | 2019-03-26 | International Business Machines Corporation | Query plan management associated with a shared pool of configurable computing resources |
-
2019
- 2019-05-31 CN CN201910466889.5A patent/CN110196756B/en active Active
- 2019-06-12 WO PCT/CN2019/090865 patent/WO2020237726A1/en active Application Filing
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102446115A (en) * | 2012-01-09 | 2012-05-09 | 浙江大学 | Dynamic deployment method for virtual machines |
| US20170161117A1 (en) * | 2015-12-07 | 2017-06-08 | Fujitsu Limited | Apparatus and method to determine a service to be scaled out based on a predicted virtual-machine load and service importance |
| US20190079789A1 (en) * | 2016-03-18 | 2019-03-14 | Telefonaktiebolaget Lm Ericsson (Publ) | Using nano-services to secure multi-tenant networking in datacenters |
| CN106775933A (en) * | 2016-11-29 | 2017-05-31 | 深圳大学 | A kind of virtual machine on server cluster dynamically places optimization method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2020237726A1 (en) | 2020-12-03 |
| CN110196756B (en) | 2020-07-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Xie et al. | Minimizing energy consumption of real-time parallel applications using downward and upward approaches on heterogeneous systems | |
| CN102929720B (en) | A kind of energy-conservation job scheduling system | |
| CN108487994B (en) | A kind of micro- energy net composite energy storage system | |
| Wang et al. | An energy-efficient heterogeneous dual-core processor for Internet of Things | |
| CN105893148B (en) | A kind of accidental task low energy consumption dispatching method based on RM strategy | |
| CN102819460B (en) | Budget power guidance-based high-energy-efficiency GPU (Graphics Processing Unit) cluster system scheduling algorithm | |
| CN103823718B (en) | Resource allocation method oriented to green cloud computing | |
| CN104376412A (en) | High energy-consuming enterprise peak regulation control method used in new energy power generation mode | |
| CN108539743B (en) | Energy-efficient type distribution terminal | |
| CN103970256B (en) | Energy saving method and system based on memory compaction and CPU dynamic frequency modulation | |
| CN103023802B (en) | A kind of low energy consumption dispatching patcher towards web cluster and method | |
| CN101330211B (en) | Micro-electric network system capable of generating and using electricity using renewable energy resources comprehensively | |
| CN201966664U (en) | Solar power generating and supplying system | |
| Yuan et al. | Energy aware resource scheduling algorithm for data center using reinforcement learning | |
| CN110189056A (en) | A kind of method of electric power system dispatching, system and equipment | |
| CN104142850A (en) | Energy-saving scheduling method of data center | |
| CN110008515B (en) | Renewable energy data center management method and device | |
| CN110196756A (en) | A kind of virtual machine mode transfer method for supporting energy optimization | |
| CN102662759A (en) | Energy saving method based on CPU (central processing unit) load in cloud OS (operating system) | |
| Kant et al. | Enhancing data center sustainability through energy-adaptive computing | |
| CN110011351A (en) | A kind of efficiency control method based on constraint function | |
| CN115912436A (en) | Power grid dispatching operation optimization calculation method considering power demand response | |
| CN102521715B (en) | A kind of method and system controlling application system Resourse Distribute | |
| CN112561263B (en) | Resident user energy-saving control device and control strategy | |
| CN110061497B (en) | Flexible load prediction and control method based on active power distribution network |
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 | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20190903 Assignee: Shenyang Zhizhi Technology Co.,Ltd. Assignor: Northeastern University Contract record no.: X2023210000209 Denomination of invention: A Virtual Machine Mode Transfer Method Supporting Energy Consumption Optimization Granted publication date: 20200710 License type: Common License Record date: 20231127 |
|
| EE01 | Entry into force of recordation of patent licensing contract |