CN108021441A - A kind of resources of virtual machine collocation method and device based on cloud computing - Google Patents
A kind of resources of virtual machine collocation method and device based on cloud computing Download PDFInfo
- Publication number
- CN108021441A CN108021441A CN201610958169.7A CN201610958169A CN108021441A CN 108021441 A CN108021441 A CN 108021441A CN 201610958169 A CN201610958169 A CN 201610958169A CN 108021441 A CN108021441 A CN 108021441A
- Authority
- CN
- China
- Prior art keywords
- baseline
- virtual machine
- load
- value
- cpu
- 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.)
- Pending
Links
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
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5061—Partitioning or combining of resources
- G06F9/5077—Logical partitioning of resources; Management or configuration of virtualized resources
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Debugging And Monitoring (AREA)
Abstract
The present invention provides a kind of resources of virtual machine collocation method and device based on cloud computing.This method includes:Obtain use frequency, cpu load baseline and the memory load baseline of each process of each virtual machine;Use frequency to each process carries out cluster analysis, obtains process behaviour in service cluster analysis result;Cluster analysis is carried out respectively to cpu load baseline and memory load baseline, obtains cpu load baseline classification results and memory load baseline classification results;The cpu resource Configuration Values and memory source Configuration Values of each virtual machine are obtained according to cluster analysis result;Resource distribution is carried out to each virtual machine according to the cpu resource Configuration Values of each virtual machine and memory source Configuration Values.The embodiment of the present invention analyzes the resource load situation of inhomogeneity virtual machine according to cluster analysis result, and batch configuration is carried out to virtual machine, is calculated without repeating prediction, reduces the calculating process in resources of virtual machine configuration process, save computing resource.
Description
Technical field
The present invention relates to field of computer technology, and in particular to a kind of resources of virtual machine collocation method based on cloud computing and
Device.
Background technology
In recent years virtual machine and virtualization technology climax have been started in computer application field.Virtualization technology is exactly that design is empty
Intend the technology assembly of computer.Virtualization technology can expand the capacity of hardware, simplify the re-configuration process of software.For example,
The virtualization technology of CPU can list CPU simulation multi -CPUs it is parallel, it is allowed to 1 platform runs multiple operating systems at the same time, and should
It can be run and be independent of each other in mutually independent space with program, so as to significantly improve the work efficiency of computer.
In existing resources of virtual machine collocation method, the two kinds of predictions of resource load sequence periodicity and aperiodicity have been used
Model, carries out analysis calculating to historic load sequence, predicts the loading condition of next stage.Detailed process is:First determine whether void
Whether the resource consumption sequence of plan machine is periodically;Then selection cycle model or aperiodicity model, to historical data into
Row calculates, to predict the resource consumption situation of next stage;Finally carry out error correction calculating.
Every virtual machine is required in the prior art to repeat whether detection resource load sequence occurs periodically, and individually
Calculating is predicted, calculating is cumbersome, and computing resource consumption is big.
The content of the invention
The embodiment of the present invention provides a kind of resources of virtual machine collocation method and device based on cloud computing, existing for solving
Resources of virtual machine collocation method in calculate the problem of consumption of cumbersome, computing resource is big.
An embodiment of the present invention provides a kind of resources of virtual machine collocation method based on cloud computing, including:
Obtain use frequency, cpu load baseline and the memory load baseline of each process of each virtual machine;
Cluster analysis is carried out to the use frequency of each process, obtains process behaviour in service cluster analysis result, and
Cluster analysis carried out respectively to the cpu load baseline and memory load baseline, obtain cpu load baseline classification results and
Memory loads baseline classification results;
Baseline point is loaded according to the process behaviour in service cluster analysis result, cpu load baseline classification results and memory
Class result obtains the cpu resource Configuration Values and memory source Configuration Values of each virtual machine;
Each virtual machine is carried out according to the cpu resource Configuration Values of each virtual machine and memory source Configuration Values
Resource distribution.
Alternatively, cluster analysis is carried out to the use frequency of each process, including:
Hyperspace, the number of each dimension of each hyperspace are established respectively to each process of each virtual machine
It is worth for the use frequency of each process corresponding with virtual machine, establishes the vector model of hyperspace;
Cluster analysis is carried out to each vector in vector model using preset algorithm.
Alternatively, cluster analysis is carried out respectively to the cpu load baseline and memory load baseline, including:
The cpu load baseline and memory load baseline are fitted respectively, respectively to daily synchronization
Cpu load value and memory load value are averaged;
Cluster analysis is carried out to the cpu load baseline after fitting and memory load baseline respectively using preset algorithm.
Alternatively, loaded according to the process behaviour in service cluster analysis result, cpu load baseline classification results and memory
Baseline classification results obtain the cpu resource Configuration Values and memory source Configuration Values of each virtual machine, including:
According to the process behaviour in service cluster analysis result, the cpu load multiple value and memory negative each classified are obtained
Carry multiple value;
The cpu load value at each moment each classified in the cpu load baseline cluster analysis result is calculated respectively
Average value, calculates the memory load value at each moment each classified in the memory load baseline cluster analysis result respectively
Average value, obtains the cpu load recommended value each classified and memory load recommended value;
According to the cpu load recommended value each classified, memory load recommended value, cpu load multiple value and memory negative
Multiple value is carried, calculates the cpu resource Configuration Values and memory source Configuration Values of the virtual machine of corresponding classification.
Alternatively, the use frequency to each process, the cpu load baseline and memory load baseline carry out
Cluster analysis use hadoop distributed treatment frames.
An embodiment of the present invention provides a kind of resources of virtual machine configuration device based on cloud computing, including:
Data capture unit, use frequency, cpu load baseline and the memory of each process for obtaining each virtual machine
Load baseline;
Process behaviour in service cluster analysis result acquiring unit, for being clustered to the use frequency of each process
Analysis, obtains process behaviour in service cluster analysis result;
Baseline classification results acquiring unit is loaded, for the cpu load baseline and memory load baseline difference
Cluster analysis is carried out, obtains cpu load baseline classification results and memory load baseline classification results;
Resource distribution value acquiring unit, for according to the process behaviour in service cluster analysis result, cpu load baseline point
Class result and memory load baseline classification results obtain cpu resource Configuration Values and the memory source configuration of each virtual machine
Value;
Resource configuration unit, according to the cpu resource Configuration Values of each virtual machine and memory source Configuration Values to described
Each virtual machine carries out resource distribution;
Wherein, the cpu load value engraved when the cpu load baseline is each, when the memory load baseline is each
The memory load value engraved.
Alternatively, the process behaviour in service cluster analysis result acquiring unit includes:
Vector model establishes module, each for establishing hyperspace respectively to each process of each virtual machine
The numerical value of each dimension of hyperspace is the use frequency of each process corresponding with virtual machine, establishes the vector of hyperspace
Model;
First Cluster Analysis module, for carrying out cluster analysis to each vector in vector model using preset algorithm.
Alternatively, the load baseline classification results acquiring unit includes:
Fitting module, for being fitted respectively to the cpu load baseline and memory load baseline, respectively to every
The cpu load value and memory load value of its synchronization are averaged;
Second Cluster Analysis module, for being loaded respectively to the cpu load baseline after fitting and memory using preset algorithm
Baseline carries out cluster analysis.
Alternatively, the resource distribution value acquiring unit includes:
Multiple value acquisition module is loaded, for according to the process behaviour in service cluster analysis result, obtaining each classification
Cpu load multiple value and memory load multiple value;
Recommended value acquisition module is loaded, is each classified for calculating respectively in the cpu load baseline cluster analysis result
Each moment cpu load value average value, calculate each classify in memory load baseline cluster analysis result respectively
Each moment memory load value average value, obtain the cpu load recommended value each classified and memory load recommended value;
Resource distribution value acquisition module, for being suggested according to the cpu load recommended value each classified, memory load
Value, cpu load multiple value and memory load multiple value, calculate the cpu resource Configuration Values and memory of the virtual machine of corresponding classification
Resource distribution value.
Alternatively, the use frequency to each process, the cpu load baseline and memory load baseline carry out
Cluster analysis use hadoop distributed treatment frames.
Resources of virtual machine collocation method and device provided in an embodiment of the present invention based on cloud computing, according to virtual machine into
Journey behaviour in service, cpu load baseline and memory load baseline carry out cluster analysis to more virtual machines, according to cluster analysis result
The resource load situation of inhomogeneity virtual machine is analyzed, batch configuration is carried out to virtual machine, calculates, reduces without repeating prediction
Calculating process in resources of virtual machine configuration process, saves computing resource, greatly improves the resource utilization of system, make cloud
The advantage of calculating is really sufficiently embodied.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is attached drawing needed in technology description to be briefly described, it should be apparent that, drawings in the following description are the present invention
Some embodiments, for those of ordinary skill in the art, without creative efforts, can also basis
These attached drawings obtain other attached drawings.
Fig. 1 is the resources of virtual machine collocation method flow diagram based on cloud computing of one embodiment of the invention;
Fig. 2 is the flow diagram that cluster analysis is carried out using frequency to each process of one embodiment of the invention;
Fig. 3 is the flow diagram that cluster analysis is carried out to load baseline of one embodiment of the invention;
Fig. 4 is the flow diagram of the computing resource Configuration Values of one embodiment of the invention;
Fig. 5 is the structure diagram of the resources of virtual machine configuration device based on cloud computing of one embodiment of the invention;
Fig. 6 is the logic diagram of the electronic equipment of one embodiment of the invention.
Embodiment
To make the purpose, technical scheme and advantage of the embodiment of the present invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, clear, complete description is carried out to the technical solution in the embodiment of the present invention, it is clear that described embodiment is
Part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
All other embodiments obtained without creative efforts, belong to the scope of protection of the invention.
Fig. 1 is the flow diagram of the resources of virtual machine collocation method based on cloud computing of one embodiment of the invention.Such as
Shown in Fig. 1, the method for the embodiment includes:
S11:Obtain use frequency, cpu load baseline and the memory load baseline of each process of each virtual machine;
It should be noted that the cpu load value that the cpu load baseline engraves when being each, the memory loads baseline
For it is each when the memory load value that engraves.
S12:Cluster analysis is carried out to the use frequency of each process, obtains process behaviour in service cluster analysis knot
Fruit;
It should be noted that step S12 classifies more virtual machines according to the use frequency of process.
S13:Cluster analysis is carried out respectively to the cpu load baseline and memory load baseline, obtains cpu load base
Line classification results and memory load baseline classification results;
It should be noted that step S13 classifies more virtual machines according to cpu load baseline;Loaded according to memory
Baseline classifies more virtual machines.
It will be appreciated that the embodiment of the present invention is the use frequency of each process to getting, cpu load baseline and interior
Deposit load baseline and carry out cluster analysis respectively, step S12 and step S13 do not have the precedence relationship in sequential.
S14:Base is loaded according to the process behaviour in service cluster analysis result, cpu load baseline classification results and memory
Line classification results obtain the cpu resource Configuration Values and memory source Configuration Values of each virtual machine;
It should be noted that existing resources of virtual machine collocation method needs every virtual machine weight and is individually predicted
Calculate, calculate cumbersome;And the embodiment of the present invention first classifies more virtual machines, the resource distribution per class virtual machine is obtained
Value, carries out batch configuration to every class virtual machine, saves computing resource.
S15:According to the cpu resource Configuration Values of each virtual machine and memory source Configuration Values to each virtual machine
Carry out resource distribution.
Resources of virtual machine collocation method provided in an embodiment of the present invention based on cloud computing, uses according to the process of virtual machine
Situation, cpu load baseline and memory load baseline carry out cluster analysis to more virtual machines, according to cluster analysis result analysis not
The resource load situation of similar virtual machine, batch configuration is carried out to virtual machine, is calculated without repeating prediction, is reduced virtual
Calculating process during machine resource distribution, saves computing resource, greatly improves the resource utilization of system, makes cloud computing
Advantage is really sufficiently embodied.
In a kind of optional embodiment of the embodiment of the present invention, similar with the method in Fig. 1, step S12 includes:
Hyperspace, the number of each dimension of each hyperspace are established respectively to each process of each virtual machine
It is worth for the use frequency of each process corresponding with virtual machine, establishes the vector model of hyperspace;
Cluster analysis is carried out to each vector in vector model using preset algorithm.
It should be noted that the embodiment of the present invention establishes a N-dimensional space according to the number of processes N of every virtual machine, and
And make the numerical value in each dimension in N-dimensional space corresponding using frequency with each process, and then obtain the vectorial mould in N-dimensional space
Type (such as the critical processes of virtual machine are A, B, C, and the use frequency of process A, B, C are respectively 0,10,5, then by the virtual machine into
Journey is converted into the vector (0,10,5) of 3-dimensional spatially using frequency).
The preset algorithm of the embodiment of the present invention can be Kmeans algorithms, or other algorithms, the present invention to this not
It is restricted.Specifically illustrated by taking Kmeans algorithms as an example.
Further, as shown in Fig. 2, step S12 includes:
S121:Hyperspace, each dimension of each hyperspace are established respectively to each process of each virtual machine
The numerical value of degree is the use frequency of each process corresponding with virtual machine, establishes the vector model of hyperspace;S122:According to pre-
If cluster centre number K, it is automatic to choose that otherness larger K is vectorial to be used as cluster centre;
S123:The Euclidean distance that each vector in hyperspace arrives each cluster centre is calculated, and each vector is distributed
To in the class where shortest cluster centre;
S124:K cluster centre and renewal iterations are recalculated using averaging method;
S125:Judge new cluster centre and last cluster centre distance whether be less than or equal to default threshold value or
Whether person's iterations, which reaches default iteration, is terminated number, if so, then performing step S13;Step is performed conversely, then returning
S123。
Further, step S13 includes:
The cpu load baseline and memory load baseline are fitted respectively, respectively to daily synchronization
Cpu load value and memory load value are averaged;
Cluster analysis is carried out to the cpu load baseline after fitting and memory load baseline respectively using preset algorithm.
Further, as shown in figure 3, step S13 includes:
S131:The cpu load baseline and memory load baseline are fitted respectively, respectively to daily with for the moment
The cpu load value and memory load value at quarter are averaged;
S132:According to default cluster centre number K, the cpu load after K larger fitting of otherness is chosen automatically respectively
Baseline and memory load baseline as cluster centre;
S133:Cpu load baseline and memory after digital simulation load baseline to the distance of respective cluster centre, and will be every
A cpu load baseline and memory load baseline is assigned in the class where shortest cluster centre;
S134:K cluster centre and renewal iterations are recalculated using averaging method;
S135:Judge new cluster centre and last cluster centre distance whether be less than or equal to default threshold value or
Whether person's iterations, which reaches default iteration, is terminated number, if so, then performing step S14;Step is performed if it is not, then returning
S133。
The distance between load baseline is calculated using the following formula:
Dρ(X, Y)=1- ρ (X, Y)
Wherein, X, Y represent two baselines to be calculated, and m represents that one shares m time point, and x (i) is represented on baseline X
The value at i-th of time point,Representing the average value of baseline X, y (i) represented the value at baseline X upper i-th of time point,Represent
Represent the average value of baseline Y, ρ (X, Y) represents the related coefficient of baseline X, Y, Dρ(X, Y) represents the distance of baseline X, Y, X, Y's
Related coefficient is higher, then ρ (X, Y) closer 1, therefore distance Dρ(X, Y) is just smaller.
Further, as shown in figure 4, step S14 includes:
S141:According to the process behaviour in service cluster analysis result, the cpu load multiple value each classified and interior is obtained
Deposit load multiple value;
It should be noted that load multiple value is the experience determined according to the packet situation of process behaviour in service cluster analysis
Value.The effect of load multiple value is to be multiplied by multiple in CPU/ memories load recommended value to reach fine setting control.If user belongs to out
Hair personnel, then can set greatly a bit by multiple, meet the needs of user is to machine performance;If user is normal office personnel,
Multiple can be set a little bit smaller.
S142:The cpu load at each moment each classified in the cpu load baseline cluster analysis result is calculated respectively
The average value of value, calculates the memory load at each moment each classified in the memory load baseline cluster analysis result respectively
The average value of value, obtains the cpu load recommended value each classified and memory load recommended value;
It should be noted that the average value for loading the cpu load value that recommended value is each moment that basis is each classified is true
Fixed.
S143:According to the cpu load recommended value each classified, memory load recommended value, cpu load multiple value and interior
Load multiple value is deposited, calculates the cpu resource Configuration Values and memory source Configuration Values of the virtual machine of corresponding classification.
For example, process behaviour in service cluster analysis result is P1, P2, P3 ... Pk;Cpu load baseline cluster analysis
As a result it is C1, C2, C3;Memory load baseline cluster analysis result is M1, M2, M3, M4.Because cpu load baseline cluster result
For C1, C1 is load baseline, includes the cpu load amount engraved when each.The load capacity at C1 load baseline all moment is asked
Average value AC1, as the classification cpu load recommended value.Show that cpu load recommended value AC1, AC2, AC3 and memory load are suggested
Value AM1, AM2, AM3, AM4.It is P1, P2, P3 ... Pk according to process behaviour in service cluster analysis result, show that the CPU of P1 is born
Load multiple value is P1a, and memory load multiple value be P1b, then the CPU resources of virtual machine Configuration Values of P1 classification the inside are P1a × be somebody's turn to do
Cpu load recommended value in C groups where virtual machine, memory source Configuration Values are memory load of the P1b × virtual machine in M groups
Recommended value.If a virtual machine is assigned to P1, C3, and M2 classification the inside.According to the scheme of configuration, the cpu resource of the virtual machine
Configuration Values are P1a × AC3, and memory source Configuration Values are P1b × AM2.
Further, the use frequency to each process, the cpu load baseline and the memory load baseline into
Capable cluster analysis uses hadoop distributed treatment frames.
It should be noted that due to the scale of cloud computing center cluster, a large amount of load datas can be produced.Of the invention real
In the process of cluster analysis for applying example, hadoop distributed treatment frames are employed, preset algorithm is applied in distributed treatment frame
Parallelization is realized on frame, improves the efficiency of algorithm.
Fig. 5 is the structure diagram of the resources of virtual machine configuration device based on cloud computing of one embodiment of the invention.Such as
Shown in Fig. 5, the resources of virtual machine configuration device based on cloud computing of the embodiment of the present invention makes including data capture unit 51, process
With situation cluster analysis result acquiring unit 52, load baseline classification results acquiring unit 53, resource distribution value acquiring unit 54
With resource configuration unit 55, specifically:
Data capture unit 51, the use frequency of each process for obtaining each virtual machine, cpu load baseline and interior
Deposit load baseline;
Process behaviour in service cluster analysis result acquiring unit 52, for gathering to the use frequency of each process
Alanysis, obtains process behaviour in service cluster analysis result;
Baseline classification results acquiring unit 53 is loaded, for the cpu load baseline and memory load baseline point
Cluster analysis is not carried out, obtains cpu load baseline classification results and memory load baseline classification results;
Resource distribution value acquiring unit 54, for according to the process behaviour in service cluster analysis result, cpu load baseline
Classification results and memory load baseline classification results obtain cpu resource Configuration Values and the memory source configuration of each virtual machine
Value;
Resource configuration unit 55, according to the cpu resource Configuration Values of each virtual machine and memory source Configuration Values to institute
State each virtual machine and carry out resource distribution;
Wherein, the cpu load value engraved when the cpu load baseline is each, when the memory load baseline is each
The memory load value engraved.
Further, process behaviour in service cluster analysis result acquiring unit 52 includes:
Vector model establishes module, each for establishing hyperspace respectively to each process of each virtual machine
The numerical value of each dimension of hyperspace is the use frequency of each process corresponding with virtual machine, establishes the vector of hyperspace
Model;
First Cluster Analysis module, for carrying out cluster analysis to each vector in vector model using preset algorithm.
Further, loading baseline classification results acquiring unit 53 includes:
Fitting module, for being fitted respectively to the cpu load baseline and memory load baseline, respectively to every
The cpu load value and memory load value of its synchronization are averaged;
Second Cluster Analysis module, for being loaded respectively to the cpu load baseline after fitting and memory using preset algorithm
Baseline carries out cluster analysis.
Further, resource distribution value acquiring unit 54 includes:
Multiple value acquisition module is loaded, for according to the process behaviour in service cluster analysis result, obtaining each classification
Cpu load multiple value and memory load multiple value;
Recommended value acquisition module is loaded, is each classified for calculating respectively in the cpu load baseline cluster analysis result
Each moment cpu load value average value, calculate each classify in memory load baseline cluster analysis result respectively
Each moment memory load value average value, obtain the cpu load recommended value each classified and memory load recommended value;
Resource distribution value acquisition module, for being suggested according to the cpu load recommended value each classified, memory load
Value, cpu load multiple value and memory load multiple value, calculate the cpu resource Configuration Values and memory of the virtual machine of corresponding classification
Resource distribution value.
Further, the use frequency to each process, the cpu load baseline and the memory load baseline into
Capable cluster analysis uses hadoop distributed treatment frames
The resources of virtual machine configuration device based on cloud computing of the embodiment of the present invention can be used for performing above method implementation
Example, its principle is similar with technique effect, and details are not described herein again.
The embodiment of the present invention additionally provides a kind of electronic equipment.
Referring to Fig. 6, electronic equipment includes:Processor 61;And
The memory 62 communicated to connect with processor 61;Wherein,
Memory 62 is stored with the programmed instruction that can be performed by processor 61, and processor 61 calls described program instruction can
Perform above-mentioned resource allocation method.
The embodiment of the present invention provides a kind of computer program product, and the computer program product includes being stored in non-transient
Computer program on computer-readable recording medium, the computer program include programmed instruction, when described program instructs quilt
When computer performs, the computer is set to perform above-mentioned method.
The embodiment of the present invention provides a kind of non-transient computer readable storage medium storing program for executing, the non-transient computer readable storage
Medium storing computer instructs, and the computer instruction makes the computer perform above-mentioned method.
Resources of virtual machine collocation method and device provided in an embodiment of the present invention based on cloud computing, according to virtual machine into
Journey behaviour in service, cpu load baseline and memory load baseline carry out cluster analysis to more virtual machines, according to cluster analysis result
The resource load situation of inhomogeneity virtual machine is analyzed, batch configuration is carried out to virtual machine, calculates, reduces without repeating prediction
Calculating process in resources of virtual machine configuration process, saves computing resource, greatly improves the resource utilization of system, make cloud
The advantage of calculating is really sufficiently embodied.
It should be understood by those skilled in the art that, the embodiment of the present invention can be provided as method, system or computer program
Product.Therefore, the present invention can use the reality in terms of complete hardware embodiment, complete software embodiment or combination software and hardware
Apply the form of example.Moreover, the present invention can use the computer for wherein including computer usable program code in one or more
The computer program production that usable storage medium is implemented on (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.)
The form of product.
The present invention be with reference to according to the method for the embodiment of the present invention, the flow of equipment (system) and computer program product
Figure and/or block diagram describe.It should be understood that it can be realized by computer program instructions every first-class in flowchart and/or the block diagram
The combination of flow and/or square frame in journey and/or square frame and flowchart and/or the block diagram.These computer programs can be provided
The processors of all-purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices is instructed to produce
A raw machine so that the instruction performed by computer or the processor of other programmable data processing devices, which produces, to be used in fact
The device for the function of being specified in present one flow of flow chart or one square frame of multiple flows and/or block diagram or multiple square frames.
It should be noted that term " comprising ", "comprising" or its any other variant are intended to the bag of nonexcludability
Contain, so that process, method, article or equipment including a series of elements not only include those key elements, but also including
Other elements that are not explicitly listed, or further include as elements inherent to such a process, method, article, or device.
In the absence of more restrictions, the key element limited by sentence "including a ...", it is not excluded that including the key element
Process, method, also there are other identical element in article or equipment.
In the specification of the present invention, numerous specific details are set forth.Although it is understood that the embodiment of the present invention can
To be put into practice in the case of these no details.In some instances, known method, structure and skill is not been shown in detail
Art, so as not to obscure the understanding of this description.Similarly, it will be appreciated that disclose in order to simplify the present invention and helps to understand respectively
One or more of a inventive aspect, in the description to the exemplary embodiment of the present invention above, each spy of the invention
Sign is grouped together into single embodiment, figure or descriptions thereof sometimes.However, should not be by the method solution of the disclosure
Release and be intended in reflection is following:I.e. the present invention for required protection requirement is than the feature that is expressly recited in each claim more
More features.More precisely, as the following claims reflect, inventive aspect is to be less than single reality disclosed above
Apply all features of example.Therefore, it then follows thus claims of embodiment are expressly incorporated in the embodiment,
Wherein each claim is in itself as separate embodiments of the invention.
Above example is merely to illustrate technical scheme, rather than its limitations;Although with reference to the foregoing embodiments
The present invention is described in detail, it will be understood by those of ordinary skill in the art that:It still can be to foregoing each implementation
Technical solution described in example is modified, or carries out equivalent substitution to which part technical characteristic;And these are changed or replace
Change, the essence of appropriate technical solution is departed from the spirit and scope of various embodiments of the present invention technical solution.
Claims (10)
- A kind of 1. resources of virtual machine collocation method based on cloud computing, it is characterised in that including:Obtain use frequency, cpu load baseline and the memory load baseline of each process of each virtual machine;Cluster analysis is carried out to the use frequency of each process, obtains process behaviour in service cluster analysis result, and to institute State cpu load baseline and memory load baseline carries out cluster analysis respectively, obtain cpu load baseline classification results and memory Load baseline classification results;Baseline classification knot is loaded according to the process behaviour in service cluster analysis result, cpu load baseline classification results and memory Fruit obtains the cpu resource Configuration Values and memory source Configuration Values of each virtual machine;Resource is carried out to each virtual machine according to the cpu resource Configuration Values of each virtual machine and memory source Configuration Values Configuration.
- 2. the resources of virtual machine collocation method according to claim 1 based on cloud computing, it is characterised in that to described each The use frequency of process carries out cluster analysis, including:Hyperspace is established respectively to each process of each virtual machine, the numerical value of each dimension of each hyperspace is The use frequency of each process corresponding with virtual machine, establishes the vector model of hyperspace;Cluster analysis is carried out to each vector in vector model using preset algorithm.
- 3. the resources of virtual machine collocation method according to claim 1 based on cloud computing, it is characterised in that to the CPU Load baseline and memory load baseline carry out cluster analysis respectively, including:The cpu load baseline and memory load baseline are fitted respectively, the CPU of daily synchronization is born respectively Load value and memory load value are averaged;Cluster analysis is carried out to the cpu load baseline after fitting and memory load baseline respectively using preset algorithm.
- 4. the resources of virtual machine collocation method according to claim 1 based on cloud computing, it is characterised in that according to it is described into Journey behaviour in service cluster analysis result, cpu load baseline classification results and memory load baseline classification results obtain described each The cpu resource Configuration Values and memory source Configuration Values of virtual machine, including:According to the process behaviour in service cluster analysis result, the cpu load multiple value each classified and memory load times are obtained Numerical value;Being averaged for the cpu load value at each moment each classified in the cpu load baseline cluster analysis result is calculated respectively Value, the memory load value for calculating each moment for each classifying in memory load baseline cluster analysis result respectively are averaged Value, obtains the cpu load recommended value each classified and memory load recommended value;According to the cpu load recommended value each classified, memory load recommended value, cpu load multiple value and memory load times Numerical value, calculates the cpu resource Configuration Values and memory source Configuration Values of the virtual machine of corresponding classification.
- 5. according to resources of virtual machine collocation method of the claim 1-4 any one of them based on cloud computing, it is characterised in that right The cluster analysis carried out using frequency, the cpu load baseline and the memory load baseline of each process is used Hadoop distributed treatment frames.
- A kind of 6. resources of virtual machine configuration device based on cloud computing, it is characterised in that including:Data capture unit, use frequency, cpu load baseline and the memory load of each process for obtaining each virtual machine Baseline;Process behaviour in service cluster analysis result acquiring unit, for carrying out cluster point to the use frequency of each process Analysis, obtains process behaviour in service cluster analysis result;Baseline classification results acquiring unit is loaded, for being carried out respectively to the cpu load baseline and memory load baseline Cluster analysis, obtains cpu load baseline classification results and memory load baseline classification results;Resource distribution value acquiring unit, for according to the process behaviour in service cluster analysis result, cpu load baseline classification knot Fruit and memory load baseline classification results obtain the cpu resource Configuration Values and memory source Configuration Values of each virtual machine;Resource configuration unit, according to the cpu resource Configuration Values of each virtual machine and memory source Configuration Values to described each Virtual machine carries out resource distribution;Wherein, the cpu load value engraved when the cpu load baseline is each, the memory load baseline engrave when being each Memory load value.
- 7. the resources of virtual machine configuration device according to claim 6 based on cloud computing, it is characterised in that the process makes Included with situation cluster analysis result acquiring unit:Vector model establishes module, for establishing hyperspace, each multidimensional respectively to each process of each virtual machine The numerical value of each dimension in space is the use frequency of each process corresponding with virtual machine, establishes the vectorial mould of hyperspace Type;First Cluster Analysis module, for carrying out cluster analysis to each vector in vector model using preset algorithm.
- 8. the resources of virtual machine configuration device according to claim 6 based on cloud computing, it is characterised in that the load base Line classification results acquiring unit includes:Fitting module, for being fitted respectively to the cpu load baseline and memory load baseline, respectively to same daily The cpu load value and memory load value at one moment are averaged;Second Cluster Analysis module, for loading baseline to the cpu load baseline after fitting and memory respectively using preset algorithm Carry out cluster analysis.
- 9. the resources of virtual machine configuration device according to claim 6 based on cloud computing, it is characterised in that the resource is matched somebody with somebody Putting value acquiring unit includes:Multiple value acquisition module is loaded, for according to the process behaviour in service cluster analysis result, obtaining the CPU each to classify Load multiple value and memory load multiple value;Load recommended value acquisition module, for calculate respectively each classify in the cpu load baseline cluster analysis result it is every The average value of the cpu load value at one moment, calculate respectively each classify in memory load baseline cluster analysis result it is every The average value of the memory load value at one moment, obtains the cpu load recommended value each classified and memory load recommended value;Resource distribution value acquisition module, for according to the cpu load recommended value each classified, memory load recommended value, CPU Multiple value and memory load multiple value are loaded, the cpu resource Configuration Values and memory source for calculating the virtual machine of corresponding classification are matched somebody with somebody Put value.
- 10. the resources of virtual machine configuration device according to claim 6 based on cloud computing, it is characterised in that to described each The cluster analysis carried out using frequency, the cpu load baseline and the memory load baseline of a process is using hadoop points Cloth handles frame.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610958169.7A CN108021441A (en) | 2016-11-03 | 2016-11-03 | A kind of resources of virtual machine collocation method and device based on cloud computing |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610958169.7A CN108021441A (en) | 2016-11-03 | 2016-11-03 | A kind of resources of virtual machine collocation method and device based on cloud computing |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108021441A true CN108021441A (en) | 2018-05-11 |
Family
ID=62083376
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610958169.7A Pending CN108021441A (en) | 2016-11-03 | 2016-11-03 | A kind of resources of virtual machine collocation method and device based on cloud computing |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108021441A (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109039831A (en) * | 2018-09-21 | 2018-12-18 | 浪潮电子信息产业股份有限公司 | A kind of load detection method and device |
CN109165083A (en) * | 2018-09-14 | 2019-01-08 | 郑州云海信息技术有限公司 | A kind of virtual machine configuration method and apparatus |
CN109271232A (en) * | 2018-07-03 | 2019-01-25 | 广东省城乡规划设计研究院 | A kind of cluster resource distribution method based on cloud computing platform |
CN109445936A (en) * | 2018-10-12 | 2019-03-08 | 深圳先进技术研究院 | A kind of cloud computing load clustering method, system and electronic equipment |
CN109800085A (en) * | 2018-12-24 | 2019-05-24 | 东软集团股份有限公司 | Detection method, device, storage medium and the electronic equipment of resource distribution |
CN111858070A (en) * | 2020-08-05 | 2020-10-30 | 中国工商银行股份有限公司 | Computing resource allocation method, device, equipment and storage medium |
WO2021082939A1 (en) * | 2019-10-31 | 2021-05-06 | 深圳前海微众银行股份有限公司 | Virtual machine tuning method and apparatus |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101788920A (en) * | 2010-02-05 | 2010-07-28 | 北京航空航天大学 | CPU virtualization method based on processor partitioning technology |
CN102546379A (en) * | 2010-12-27 | 2012-07-04 | 中国移动通信集团公司 | Virtualized resource scheduling method and system |
CN102854968A (en) * | 2012-05-04 | 2013-01-02 | 北京邮电大学 | Real-time energy consumption metering method of virtual machine |
CN102968344A (en) * | 2012-11-26 | 2013-03-13 | 北京航空航天大学 | Method for migration scheduling of multiple virtual machines |
CN103873569A (en) * | 2014-03-05 | 2014-06-18 | 兰雨晴 | Resource optimized deployment method based on IaaS (infrastructure as a service) cloud platform |
CN104065745A (en) * | 2014-07-07 | 2014-09-24 | 电子科技大学 | Cloud computing dynamic resource scheduling system and method |
CN104536803A (en) * | 2014-12-23 | 2015-04-22 | 西安电子科技大学 | Virtual machine scheduling method based on combination optimization |
-
2016
- 2016-11-03 CN CN201610958169.7A patent/CN108021441A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101788920A (en) * | 2010-02-05 | 2010-07-28 | 北京航空航天大学 | CPU virtualization method based on processor partitioning technology |
CN102546379A (en) * | 2010-12-27 | 2012-07-04 | 中国移动通信集团公司 | Virtualized resource scheduling method and system |
CN102854968A (en) * | 2012-05-04 | 2013-01-02 | 北京邮电大学 | Real-time energy consumption metering method of virtual machine |
CN102968344A (en) * | 2012-11-26 | 2013-03-13 | 北京航空航天大学 | Method for migration scheduling of multiple virtual machines |
CN103873569A (en) * | 2014-03-05 | 2014-06-18 | 兰雨晴 | Resource optimized deployment method based on IaaS (infrastructure as a service) cloud platform |
CN104065745A (en) * | 2014-07-07 | 2014-09-24 | 电子科技大学 | Cloud computing dynamic resource scheduling system and method |
CN104536803A (en) * | 2014-12-23 | 2015-04-22 | 西安电子科技大学 | Virtual machine scheduling method based on combination optimization |
Non-Patent Citations (3)
Title |
---|
曾五一 等: "《统计学》", 31 August 2012 * |
李梓萌 等: "基于基线分析的云计算资源自动分配技术", 《现代计算机》 * |
王成墨: "《MATLAB在遥感技术中的应用》", 30 September 2016 * |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109271232A (en) * | 2018-07-03 | 2019-01-25 | 广东省城乡规划设计研究院 | A kind of cluster resource distribution method based on cloud computing platform |
CN109271232B (en) * | 2018-07-03 | 2019-11-19 | 广东省城乡规划设计研究院 | A kind of cluster resource distribution method based on cloud computing platform |
CN109165083A (en) * | 2018-09-14 | 2019-01-08 | 郑州云海信息技术有限公司 | A kind of virtual machine configuration method and apparatus |
CN109039831A (en) * | 2018-09-21 | 2018-12-18 | 浪潮电子信息产业股份有限公司 | A kind of load detection method and device |
CN109445936A (en) * | 2018-10-12 | 2019-03-08 | 深圳先进技术研究院 | A kind of cloud computing load clustering method, system and electronic equipment |
CN109800085A (en) * | 2018-12-24 | 2019-05-24 | 东软集团股份有限公司 | Detection method, device, storage medium and the electronic equipment of resource distribution |
CN109800085B (en) * | 2018-12-24 | 2021-01-29 | 东软集团股份有限公司 | Resource configuration detection method and device, storage medium and electronic equipment |
WO2021082939A1 (en) * | 2019-10-31 | 2021-05-06 | 深圳前海微众银行股份有限公司 | Virtual machine tuning method and apparatus |
CN111858070A (en) * | 2020-08-05 | 2020-10-30 | 中国工商银行股份有限公司 | Computing resource allocation method, device, equipment and storage medium |
CN111858070B (en) * | 2020-08-05 | 2023-12-01 | 中国工商银行股份有限公司 | Computing resource allocation method, device, equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108021441A (en) | A kind of resources of virtual machine collocation method and device based on cloud computing | |
US11392843B2 (en) | Utilizing a machine learning model to predict a quantity of cloud resources to allocate to a customer | |
WO2021104096A1 (en) | Method and apparatus for task scheduling in container cloud environment, and server and storage apparatus | |
CN108829494A (en) | Container cloud platform intelligence method for optimizing resources based on load estimation | |
Jiang et al. | Distributed dynamic scheduling for cyber-physical production systems based on a multi-agent system | |
US20220414426A1 (en) | Neural Architecture Search Method and Apparatus, Device, and Medium | |
CN114138486B (en) | Method, system and medium for arranging containerized micro-services for cloud edge heterogeneous environment | |
WO2018036282A1 (en) | Task scheduling method, device and computer storage medium | |
CN111124689A (en) | Dynamic allocation method for container resources in cluster | |
CN106681826B (en) | Resource planning method, system and device for cluster computing architecture | |
CN107273197B (en) | Hadoop task scheduling method based on orthogonal experiment improved spectral clustering genetic algorithm | |
WO2016040699A1 (en) | Computing instance launch time | |
US11055139B2 (en) | Smart accelerator allocation and reclamation for deep learning jobs in a computing cluster | |
CN109918205A (en) | A kind of edge device dispatching method, system, device and computer storage medium | |
CN106326000A (en) | A method and a device for resource scheduling in a cloud computing system | |
CN108427602B (en) | Distributed computing task cooperative scheduling method and device | |
CN105740059B (en) | A kind of population dispatching method towards Divisible task | |
Li et al. | A novel multi-objective optimization scheme for rebalancing virtual machine placement | |
CN110347515A (en) | A kind of resource optimal distribution method of suitable edge calculations environment | |
CN106790332A (en) | A kind of resource regulating method, system and host node | |
CN112732444A (en) | Distributed machine learning-oriented data partitioning method | |
Hummaida et al. | Scalable virtual machine migration using reinforcement learning | |
CN115277692A (en) | Automatic operation and maintenance method, device and system for edge network computing terminal equipment | |
CN112000460A (en) | Service capacity expansion method based on improved Bayesian algorithm and related equipment | |
CN109960579A (en) | A kind of method and device of adjustment business container |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180511 |