WO2020222347A1 - 가상 머신 배치 방법 및 이를 구현하는 가상 머신 배치 장치 - Google Patents
가상 머신 배치 방법 및 이를 구현하는 가상 머신 배치 장치 Download PDFInfo
- Publication number
- WO2020222347A1 WO2020222347A1 PCT/KR2019/006072 KR2019006072W WO2020222347A1 WO 2020222347 A1 WO2020222347 A1 WO 2020222347A1 KR 2019006072 W KR2019006072 W KR 2019006072W WO 2020222347 A1 WO2020222347 A1 WO 2020222347A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- virtual machine
- physical server
- virtual
- workload
- arrangement
- Prior art date
Links
Images
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
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
- G06F9/505—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals considering the load
-
- 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]
- G06F9/5083—Techniques for rebalancing the load in a distributed system
- G06F9/5088—Techniques for rebalancing the load in a distributed system involving task migration
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2209/00—Indexing scheme relating to G06F9/00
- G06F2209/50—Indexing scheme relating to G06F9/50
- G06F2209/5019—Workload prediction
Definitions
- the present invention relates to a virtual machine arrangement method and a virtual machine arrangement apparatus implementing the same, wherein in order to efficiently operate a first physical server and a second physical server in which a plurality of virtual machines are respectively disposed, a plurality of the virtual machines Is to be disposed on the first physical server and the second physical server.
- the data center which accounts for about 2% of the world's electricity use, is a high-density energy-intensive building that uses the most electricity among single buildings, but it is showing inefficient operation by sticking to conservative operation that prioritizes stability.
- a virtual machine In a virtualization environment in which physical resources (Physical Machine, PM, physical server) are composed of logical resources (Virtual Machine, VM, virtual machine), a running virtual machine can be moved to another physical machine, which is called live migration.
- This is an essential management method for managing an efficient data center.
- migrating there are also disadvantages such as the risk of data loss and a large portion of resources.
- the object of the present invention is to provide a virtual machine arrangement method and a virtual machine arrangement apparatus implementing the same, which can stably manage data by reducing the number of migrations.
- a virtual machine arrangement method includes a physical server in which a virtual machine is installed-the physical server includes a first physical server and a second physical server.
- the first physical server stored in the storage unit
- virtual machine workload information which is information related to the virtual machine workload, which is the load of the physical server imposed by the virtual machine, is calculated based on information related to the operation of the second physical server and a predetermined workload calculation method.
- step Calculating initial predicted virtual load information, which is information related to an initial predicted virtual load associated with a load of a physical server predicted by the virtual machine for a first predetermined period based on the virtual machine workload; Calculating search arrangement information, which is information related to a search arrangement, which is arrangement of the virtual machines on the first physical server and the second physical server by a predetermined search arrangement calculation method; And placing the virtual machine on the first physical server and the second physical server based on the selected search arrangement, wherein the predetermined search arrangement calculation method comprises: based on the initial predicted virtual load information It may be a method of calculating the search arrangement of the virtual machine when the objective function value is minimized.
- the objective function may include a first objective function that is a function related to an amount of change in the workload of the physical server calculated by the initial predicted virtual load during the first predetermined period.
- the objective function may include a second objective function that is a function related to a difference between workloads of a physical server calculated by the initial predicted virtual load during the first predetermined period.
- the objective function may include a third objective function that is a function related to the number of times the virtual machine is batch-moved on the first physical server and the second physical server in order for the virtual machine to be deployed in the search batch. have.
- the objective function is a first objective function that is a function related to a change amount of a workload of a physical server calculated by the initial predicted virtual load during the first predetermined period, and during the first predetermined period, the initial
- the second objective function which is a function related to the difference between the workloads of the physical server calculated by the predicted virtual load, and the virtual machine on the first physical server and the second physical server in order to deploy the virtual machine in the search arrangement
- a third objective function that is a function related to the number of times the batch is moved may be provided.
- the search arrangement includes the first physical server and the second physical server in which the value of the second objective function and the value of the third objective function are minimized while the value of the first objective function is minimum.
- a first search configuration which is an arrangement of virtual machines, a first physical server and a second physical server in which values of the first objective function and the values of the third objective function are minimized while the value of the second objective function is minimum.
- the first physical server and the second in which the values of the first objective function and the values of the second objective function are minimized when the values of the second search arrangement and the third objective function, which are the arrangement of the virtual machines on the image, are minimized.
- a third discovery arrangement which is an arrangement of the virtual machines on a physical server, may be provided.
- the predetermined method of calculating the workload may be a method of calculating the virtual machine workload information based only on the degree of operation of the CPU.
- the predetermined search arrangement calculation method may be a method in which the arrangement of the virtual machine in which the workload of an arbitrary physical server is equal to or higher than an arbitrary reference is excluded as the search arrangement.
- selection predicted virtual load information which is information related to the selected predicted virtual load associated with the predicted load of the physical server
- It may further include determining whether the selection prediction virtual load information is normally calculated based on the actual virtual workload information, which is information related to the actual workload of the virtual machine, according to a predetermined inspection method.
- the predetermined inspection method may be a method of determining that the selection prediction virtual load is incorrectly calculated when the actual workload of the virtual machine is different from the corresponding selection prediction virtual load by a predetermined value or more.
- a virtual machine arrangement apparatus includes a physical server on which a virtual machine is installed, wherein the physical server includes a first physical server and a second physical server.
- a virtual machine placement apparatus for implementing a virtual machine placement method which is a method of arranging a plurality of virtual machines on the first physical server and the second physical server, comprising: a processing unit; And a storage unit storing a program for performing the virtual machine arrangement method, wherein the virtual machine matching method includes an operation of the first physical server and the second physical server stored in the storage unit and the processing unit Calculating virtual machine workload information, which is information related to a virtual machine workload, which is a load of a physical server imposed by the virtual machine, based on the related information;
- the processing unit is information related to the first predicted virtual load associated with the predicted physical server load imposed by the virtual machine for a first predetermined period from the time when the virtual machine workload is calculated based on the virtual machine workload.
- Calculating initial predicted virtual load information Calculating, by the processing unit, search arrangement information, which is information related to search arrangement, which is arrangement of the virtual machines on the first physical server and the second physical server by a predetermined search arrangement calculation method; And arranging the virtual machine on the first physical server and the second physical server based on the search arrangement selected by the processing unit, wherein the predetermined search arrangement calculation method includes: It may be a method of calculating a search arrangement of the virtual machine when an objective function value is minimized based on the initial predicted virtual load information based on virtual load information.
- the virtual machine arrangement method and the virtual machine arrangement apparatus implementing the same according to the present invention can minimize data loss.
- data centers can be managed stably.
- FIG. 1 is a conceptual diagram of an apparatus for arranging a virtual machine according to an embodiment of the present invention and a diagram showing a relationship between the apparatus for arranging a virtual machine and a plurality of physical servers
- FIG. 2 is a flowchart of a virtual machine arrangement method according to an embodiment of the present invention
- FIG. 3 is a graph for explaining an effect achieved by arranging a virtual machine in consideration of a first objective function in a method of arranging a virtual machine according to an embodiment of the present invention
- FIG. 4 is a graph for explaining an effect achieved by arranging a virtual machine in consideration of a second objective function in a method of arranging a virtual machine according to an embodiment of the present invention
- FIG. 5 is a graph for explaining a method of calculating a prediction error among a virtual machine arrangement method according to an embodiment of the present invention
- a virtual machine arrangement method includes a physical server in which a virtual machine is installed-the physical server includes a first physical server and a second physical server.
- the first physical server stored in the storage unit
- virtual machine workload information which is information related to the virtual machine workload, which is the load of the physical server imposed by the virtual machine, is calculated based on information related to the operation of the second physical server and a predetermined workload calculation method.
- step Calculating initial predicted virtual load information, which is information related to an initial predicted virtual load associated with a load of a physical server predicted by the virtual machine for a first predetermined period based on the virtual machine workload; Calculating search arrangement information, which is information related to a search arrangement, which is arrangement of the virtual machines on the first physical server and the second physical server by a predetermined search arrangement calculation method; And placing the virtual machine on the first physical server and the second physical server based on the selected search arrangement, wherein the predetermined search arrangement calculation method comprises: based on the initial predicted virtual load information It may be a method of calculating the search arrangement of the virtual machine when the objective function value is minimized.
- a virtual machine arrangement apparatus includes a physical server on which a virtual machine is installed, wherein the physical server includes a first physical server and a second physical server.
- a virtual machine placement apparatus for implementing a virtual machine placement method which is a method of arranging a plurality of virtual machines on the first physical server and the second physical server, comprising: a processing unit; And a storage unit storing a program for performing the virtual machine arrangement method, wherein the virtual machine matching method includes an operation of the first physical server and the second physical server stored in the storage unit and the processing unit Calculating virtual machine workload information, which is information related to a virtual machine workload, which is a load of a physical server imposed by the virtual machine, based on the related information;
- the processing unit is information related to the first predicted virtual load associated with the predicted physical server load imposed by the virtual machine for a first predetermined period from the time when the virtual machine workload is calculated based on the virtual machine workload.
- Calculating initial predicted virtual load information Calculating, by the processing unit, search arrangement information, which is information related to search arrangement, which is arrangement of the virtual machines on the first physical server and the second physical server by a predetermined search arrangement calculation method; And arranging the virtual machine on the first physical server and the second physical server based on the search arrangement selected by the processing unit, wherein the predetermined search arrangement calculation method includes: It may be a method of calculating a search arrangement of the virtual machine when an objective function value is minimized based on the initial predicted virtual load information based on virtual load information.
- FIG. 1 is a conceptual diagram of a virtual machine arrangement apparatus 10 according to an embodiment of the present invention and a diagram showing a relationship between the virtual machine arrangement apparatus 10 and a plurality of physical servers.
- the virtual machine arrangement apparatus 10 includes a processing unit 11 for processing predetermined information, a storage unit 12 for storing predetermined information, a receiving unit 13 for receiving predetermined information, and A transmitter 14 for transmitting predetermined information may be provided.
- the virtual machine arrangement device 10 displays an input unit 15 for transmitting predetermined information to the receiving unit 13 by inputs from the outside and a search arrangement to be described later to transmit the search arrangement to the user.
- the medium may further include a display unit 16.
- the processing unit 11 may perform an operation such as processing all information necessary to implement the virtual machine matching method based on predetermined information.
- the processing unit 11 may refer to a central processing unit.
- the present invention is not limited thereto, and the processor 11 may include all devices or components capable of performing an operation required to implement the virtual machine arrangement method.
- the storage unit 12 may store information (data) necessary for implementing the virtual machine arrangement method.
- a program for performing the virtual machine arrangement method may be stored in the storage unit 12.
- the storage unit 12 may be a hard disk as an auxiliary memory device.
- the storage unit 12 may include all elements capable of storing information necessary for implementing the virtual machine arrangement method.
- the storage unit 12 may be a database.
- the receiver 13 may receive predetermined information transmitted from a physical server.
- the receiving unit 13 may receive predetermined information related to the operation of the physical machine from a corresponding physical machine.
- the constant transmission unit 14 may transmit predetermined information to the physical server.
- the transmission unit 14 may transmit the control signal calculated by the processing unit 11 to the physical server.
- the virtual machine placement apparatus 10 may transmit a control signal to each physical server so that a virtual machine running on an arbitrary physical server is migrated to another physical server.
- the input unit 15 may be a keyboard.
- the type of the input unit 15 is not limited thereto, and may be variously modified at a level that is obvious to a person skilled in the art.
- the display unit 16 may be a display.
- the present invention is not limited thereto, and the type of the display unit 16 may be variously modified at a level that is obvious to a person skilled in the art.
- Components in the virtual machine placement apparatus 10 may be wired and/or wirelessly connected to each other.
- the virtual machine placement device 10 may be connected to each of the physical servers by wire and/or wirelessly.
- the physical server may mean a hardware platform on which a virtual machine can be executed.
- the physical machine may be a conventional desktop, server computer, laptop computer or mobile phone.
- the present invention is not limited thereto, and the physical machine may be a concept including all means by which a virtual machine can be executed.
- the virtual machine arrangement apparatus 10 according to an embodiment of the present invention is described based on controlling and managing the first physical server 20, the second physical server 30, and the third physical server 40, Accordingly, the present invention is not limited thereto, and the number of physical servers managed and controlled by the virtual machine arranging apparatus 10 can be variously modified at a level that is obvious to a person skilled in the art.
- the physical server is composed of a first physical server 20, a second physical server 30, and a third physical server 40, and on the first physical server 20, a virtual
- the machine 21, the bth virtual machine 22, and the cth virtual machine 23 may be running, and the dth virtual machine 31 and the eth virtual machine 32 on the second physical server 30 ) May be running, and the fth virtual machine 41 and the gth virtual machine 42 may be running on the third physical server 40.
- FIG. 2 is a flowchart of a method of arranging a virtual machine according to an embodiment of the present invention.
- a method for arranging a virtual machine is a physical server in which a virtual machine is installed, and the physical server includes a first physical server and a second physical server.
- the first physical server stored in the storage unit
- virtual machine workload information which is information related to the virtual machine workload, which is the load of the physical server imposed by the virtual machine, is calculated based on information related to the operation of the second physical server and a predetermined workload calculation method.
- Step (S10) related to the first predicted virtual load associated with the predicted physical server load imposed by the virtual machine for a first predetermined period from the time when the virtual machine workload is calculated based on the virtual machine workload
- the virtual machine arrangement method may further include a step (S40) of displaying a plurality of search arrangements calculated by the predetermined search arrangement calculation method by the display unit.
- the virtual machine arrangement method includes a step (S50) of inputting a selected search arrangement, which is one search arrangement among the search arrangements displayed by the display unit, by the input unit, and transferring information related to the selected search arrangement to the processing unit. It may contain more.
- the virtual machine placement method is information related to a selected predicted virtual load associated with a predicted load of the physical server when the virtual machine is disposed in the first physical server and the second physical server according to the selected search placement.
- a step (S70) of determining whether the selection prediction virtual load information is normally calculated based on the selection prediction virtual load information and the actual virtual workload information, which is information related to the actual workload of the virtual machine, according to a predetermined inspection method. Can include.
- information related to the operation of the first physical server, information related to the operation of the second physical server, and information related to the operation of the third physical server may be stored.
- information related to the operation of the first physical server, the second physical server, and the third physical server may be stored in the storage unit in a time series.
- the receiving unit may receive information related to each operation from the first physical server, the second physical server, and the third physical server.
- the information related to the operation may be information related to the operation rate of the configurations of the physical server.
- the processing unit is a virtual machine, which is information related to a virtual machine workload, which is a load of a physical server imposed by the virtual machine by a predetermined workload calculation method based on information related to operation of each physical server stored in the storage unit.
- Machine workload information can be calculated (S10).
- the virtual machine workload may mean a resource load of a corresponding physical server.
- the predetermined workload calculation method may be a method of calculating the virtual machine workload as a load imposed on a central processing unit (CPU) of the physical server when the virtual machine is operated on the physical server.
- CPU central processing unit
- the virtual machine workload information may be calculated based only on the degree of operation of the CPU.
- this may mean that one virtual machine cannot be implemented on two physical servers.
- the meaning of the workload of a physical machine means that when a plurality of virtual machines are run on one physical server, the sum of the workloads of each virtual machine is the physical server workload.
- the processing unit is information related to the first predicted virtual load that is associated with the predicted physical server load imposed by the virtual machine for a first predetermined period from the time when the virtual machine workload information is calculated based on the virtual machine workload information.
- Initial predicted virtual load information may be calculated (S20).
- the reason for calculating the deployment of virtual machines is that when migration is performed based on overload at a specific point in time, it is not possible to increase the number of migrations and to stabilize the overall physical server. It may be to solve this.
- the first predetermined period may be 3 months.
- the present invention is not limited thereto, and the predetermined first period may be variously modified at a level that is obvious to a person skilled in the art.
- the processing unit may perform the above-described prediction-related operation using an algorithm such as a multiple regression model, ARIMA analysis, or Deep Learning based on the virtual machine workload information.
- an algorithm such as a multiple regression model, ARIMA analysis, or Deep Learning based on the virtual machine workload information.
- the initial predicted virtual load may mean a workload of a virtual machine predicted for a first predetermined period from a time when the virtual machine workload information is calculated or for a first predetermined period from an arbitrary point in time.
- the processing unit may calculate (S30) search arrangement information, which is information related to a search arrangement, which is arrangement of the virtual machines on the first physical server and the second physical server by a predetermined search arrangement calculation method.
- the predetermined search arrangement calculation method may refer to a method of calculating a search arrangement of the virtual machine when an objective function value is minimized based on the initial predicted virtual load information.
- the predetermined search arrangement calculation method may be a method in which an arrangement of the virtual machine in which the workload of an arbitrary physical server is equal to or higher than a predetermined criterion (a, see FIGS. 3 and 4) is excluded as the search arrangement.
- the arbitrary criterion (a) may be 80%.
- the present invention is not limited thereto, and the arbitrary standard may be variously modified at a level that is obvious to a person skilled in the art.
- the objective function may include a first objective function, a second objective function, and a third objective function.
- the processing unit may calculate three non-dominant solutions in which each objective function value has a minimum value.
- FIG. 3 is a graph for explaining an effect achieved by arranging a virtual machine in consideration of a first objective function in a method of arranging a virtual machine according to an embodiment of the present invention.
- the objective function may include a first objective function that is a function related to a change amount of a workload of a physical server calculated by the initial predicted virtual load during the first predetermined period.
- FIG. 3(a) is a graph showing the workload of a first physical server, a second physical server, and a third physical server when the virtual machines are in a first batch
- FIG. 3(b) is a graph showing a second batch of virtual machines. In this case, it is a graph showing the workload of the first physical server, the second physical server, and the third physical server.
- the workload of each physical server can be calculated as the sum of the virtual machine workloads installed on each physical server.
- a virtual machine a, a virtual machine b, and a virtual machine c may be disposed on a first physical server, and a virtual machine d and a virtual machine e may be disposed on the second physical server.
- a virtual machine may be disposed, and the fth virtual machine and the gth virtual machine may be disposed on the third physical server.
- a virtual machine a when the virtual machines are in a second arrangement, a virtual machine a may be disposed on the first physical server, and a virtual machine b, a virtual machine d, and a virtual machine f are disposed on the second physical server.
- the c-th virtual machine, the e-th virtual machine, and the g-th virtual machine may be disposed on the third physical server.
- the processing unit can calculate the second batch as a more suitable batch than the first batch as the search batch.
- the change rate of the workload of the physical server is large, the workload of the physical server exceeds a certain standard for only a short period of time, and the virtual machine can be migrated (relocated).
- the first objective function may be a function for preventing this.
- FIG. 4 is a graph for explaining an effect achieved by arranging a virtual machine in consideration of a second objective function in a method of arranging a virtual machine according to an embodiment of the present invention.
- the objective function may include a second objective function that is a function related to a difference between workloads of a physical server calculated by the initial predicted virtual load during the first predetermined period.
- Fig. 4(a) is a graph showing the workload of the first physical server, the second physical server, and the third physical server when the virtual machines are in a third batch
- Fig. 4(b) is In this case, it is a graph showing the workload of the first physical server, the second physical server, and the third physical server.
- the processing unit can calculate the fourth batch as a more appropriate batch than the third batch as the search batch.
- the physical servers may be compared with each other based on the average value of the workload during the first predetermined period.
- the meaning of the second objective function may be to use the physical server evenly.
- the objective function may include a third objective function that is a function related to the number of times the virtual machine is batch-moved on the first physical server and the second physical server in order for the virtual machine to be deployed in the search batch.
- the third objective function may be related to the number of times the virtual machine moves between physical servers to be deployed from the current deployment of virtual machines to the search arrangement.
- the meaning of the third objective function may be to find an arrangement that minimizes the number of movements of the virtual machine.
- the search arrangement may mean arrangement of the virtual machines on physical machines in which each objective function is minimized.
- the objective function is a first objective function that is a function related to a change amount of a workload of a physical server calculated by the initial predicted virtual load during the first predetermined period, and the initial predicted virtual load during the first predetermined period
- the virtual machine is batch-moved on the first physical server and the second physical server in order to deploy the second objective function and the virtual machine in the search batch, which is a function related to the difference between the workloads of the physical server calculated by
- a third objective function which is a function related to the number of times, may be provided.
- the display unit may display search arrangements S40 transmitted from the processing unit.
- the processing unit may calculate first search arrangement information that is information related to the first search arrangement, second search arrangement information that is information related to the second search arrangement, and third search arrangement information that is information related to the third search arrangement, , It is possible to transmit information about this to the display unit.
- the values of the second objective function and the values of the third objective function are minimized while the value of the first objective function is the minimum (for example, the first physical server and the first 2 physical servers), the physical servers in which the values of the first objective function and the third objective function are minimized when the values of the first and third objective functions are minimized.
- the values of the first objective function and the second A third search arrangement may be provided, which is the arrangement of the virtual machines on the physical servers (for example, the first physical server and the second physical server) in which the value of the objective function is minimized.
- the display unit may display the first search arrangement, the second search arrangement, and the third search arrangement.
- the first search arrangement, the second search arrangement, and the third search arrangement are non-dominant solutions of objective functions and may mean independent solution methods.
- the operator may select one of the first search arrangement, the second search arrangement, and the third search arrangement through the input unit and input the selected search arrangement.
- the input unit may calculate information related to the selected search arrangement and transmit the information to the processing unit.
- FIG. 5 is a graph for explaining a method of calculating a prediction error among a virtual machine arrangement method according to an embodiment of the present invention.
- the processing unit may rearrange the virtual machines on physical servers based on the selected search arrangement (S60).
- the resources of the physical machine can be evenly utilized without being biased to one physical machine.
- the processing unit select predicted virtual load information and the virtual machine, which are information related to the selected predicted virtual load associated with the predicted load of the physical server. It may be determined whether the selection predicted virtual load information is normally calculated based on the actual virtual workload information, which is information related to the actual workload of the users, according to a predetermined inspection method (S70).
- the selection prediction virtual load information may be the same as the initial prediction virtual load information described above.
- the present invention is not limited thereto, and the selected prediction virtual load information may not match the initial prediction virtual load information.
- the processor may calculate the selection predicted virtual load information by predicting the workload of the virtual machines for a predetermined period.
- the predetermined checking method may be a method of determining that the selected predicted virtual load is incorrectly calculated when the actual virtual workload differs from the corresponding selected predicted virtual load by a predetermined value or more.
- FIG. 5 illustrates a first workload X10 representing a selected predicted virtual load that is a predicted workload of a virtual machine a and a second workload X20 representing an actual workload of the a virtual machine. It can be a graph.
- the processing unit may determine that the workload of the virtual machine a is incorrectly predicted when the first workload and the second workload are different from each other by a predetermined workload (a predetermined value, X) or more.
- Re-predicted virtual load information which is information related to re-predicted virtual load related to the load of the physical server, may be calculated (S80).
- the processing unit may recalculate (S80) a search batch based on the re-prediction virtual load information by the above-described method of calculating a search batch, and based on this, the virtual machines may be re-arranged (S90). Can be operated on.
- the second predetermined period may be the same as or different from the first predetermined time.
- Such a method of arranging the virtual machine may be performed repeatedly and continuously.
- the operator may select one search arrangement from among a plurality of search arrangements, and the processing unit may relocate the virtual machines (S90) based on the selected search arrangement. .
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
Description
Claims (11)
- 가상 머신이 설치된 물리 서버 - 상기 물리 서버는 제1 물리 서버 및 제2 물리 서버를 구비함. -를 효율적으로 운용하기 위하여, 복 수의 상기 가상 머신을 상기 제1 물리 서버와 상기 제2 물리 서버 상에 배치하는 방법인 가상 머신 배치 방법에 있어서,저장부에 저장되어 있는 상기 제1 물리 서버와 상기 제2 물리 서버의 작동과 관련된 정보를 기초로 미리 정해진 워크 로드 산출 방법에 의해 상기 가상 머신에 의해 부과되는 물리 서버의 부하인 가상 머신 워크 로드와 관련된 정보인 가상 머신 워크 로드 정보가 산출되는 단계;상기 가상 머신 워크 로드를 기초로 미리 정해진 제1 기간 동안 상기 가상 머신에 의해 예측되는 물리 서버의 부하와 연관된 최초 예측 가상 로드와 관련된 정보인 최초 예측 가상 로드 정보가 산출되는 단계;미리 정해진 탐색 배치 산출 방법에 의해 상기 제1 물리 서버와 상기 제2 물리 서버 상의 상기 가상 머신의 배치인 탐색 배치와 관련된 정보인 탐색 배치 정보가 산출되는 단계; 및선택된 상기 탐색 배치를 기초로 상기 가상 머신이 상기 제1 물리 서버와 상기 제2 물리 서버 상에서 배치되는 단계;를 포함하고,상기 미리 정해진 탐색 배치 산출 방법은,상기 최초 예측 가상 로드 정보를 기초로 목적 함수 값이 최소화될 때의 상기 가상 머신의 탐색 배치가 산출되는 방법인,가상 머신 배치 방법.
- 제1항에 있어서,상기 목적 함수는,상기 미리 정해진 제1 기간 동안, 상기 최초 예측 가상 로드에 의해 산출되는 물리 서버의 워크 로드의 변화량과 관련된 함수인 제1 목적 함수를 구비하는,가상 머신 배치 방법.
- 제1항에 있어서,상기 목적 함수는,상기 미리 정해진 제1 기간 동안, 상기 최초 예측 가상 로드에 의해 산출되는 물리 서버의 워크 로드들 간의 차이와 관련된 함수인 제2 목적 함수를 구비하는,가상 머신 배치 방법.
- 제1항에 있어서,상기 목적 함수는,상기 가상 머신이 상기 탐색 배치로 배치되기 위해서 상기 제1 물리 서버와 상기 제2 물리 서버 상에서 상기 가상 머신이 배치 이동되는 횟수와 관련된 함수인 제3 목적 함수를 구비하는,가상 머신 배치 방법.
- 제1항에 있어서,상기 목적 함수는,상기 미리 정해진 제1 기간 동안, 상기 최초 예측 가상 로드에 의해 산출되는 물리 서버의 워크 로드의 변화량과 관련된 함수인 제1 목적 함수, 상기 미리 정해진 제1 기간 동안, 상기 최초 예측 가상 로드에 의해 산출되는 물리 서버의 워크 로드들 간의 차이와 관련된 함수인 제2 목적 함수 및 상기 가상 머신이 상기 탐색 배치로 배치되기 위해서 상기 제1 물리 서버와 상기 제2 물리 서버 상에서 상기 가상 머신이 배치 이동되는 횟수와 관련된 함수인 제3 목적 함수를 구비하는,가상 머신 배치 방법.
- 제5항에 있어서,상기 탐색 배치는,상기 제1 목적 함수의 값이 최소인 상태에서 상기 제2 목적 함수의 값과 상기 제3 목적 함수의 값이 최소화되는 상기 제1 물리 서버와 상기 제2 물리 서버 상의 상기 가상 머신의 배치인 제1 탐색 배치,상기 제2 목적 함수의 값이 최소인 상태에서 상기 제1 목적 함수의 값과 상기 제3 목적 함수의 값이 최소화되는 제1 물리 서버와 상기 제2 물리 서버 상의 상기 가상 머신의 배치인 제2 탐색 배치 및상기 제3 목적 함수의 값이 최소인 상태에서 상기 제1 목적 함수의 값과 상기 제2 목적 함수의 값이 최소화되는 제1 물리 서버와 상기 제2 물리 서버 상의 상기 가상 머신의 배치인 제3 탐색 배치를 구비하는,가상 머신 배치 방법.
- 제6항에 있어서,상기 미리 정해진 워크 로드 산출 방법은,CPU의 가동 정도만을 기초로 상기 가상 머신 워크 로드 정보가 산출되는 방법인,가상 머신 배치 방법.
- 제7항에 있어서,상기 미리 정해진 탐색 배치 산출 방법은,임의의 물리 서버의 상기 워크 로드가 임의의 기준 이상이 되는 상기 가상 머신의 배치가 상기 탐색 배치로서 제외되는 방법인,가상 머신 배치 방법.
- 제1항에 있어서,선택된 상기 탐색 배치에 따라 상기 가상 머신이 상기 제1 물리 서버와 상기 제2 물리 서버에 배치되는 경우, 예측되는 물리 서버의 부하와 연관된 선택 예측 가상 로드와 관련된 정보인 선택 예측 가상 로드 정보와 가상 머신의 실제 워크 로드와 관련된 정보인 실제 가상 워크 로드 정보를 기초로 미리 정해진 점검 방법에 따라 상기 선택 예측 가상 로드 정보가 정상적으로 산출되었는지 여부를 판단하는 단계;를 더 포함하는,가상 머신 배치 방법.
- 제9항에 있어서,상기 미리 정해진 점검 방법은,상기 가상 머신의 실제 워크 로드가 대응되는 상기 선택 예측 가상 로드와 소정 값 이상 차이 날 경우 상기 선택 예측 가상 로드가 잘못 산출되었다고 판단하는 방법인,가상 머신 배치 방법.
- 가상 머신이 설치되는 물리 서버 - 상기 물리 서버는 제1 물리 서버 및 제2 물리 서버를 구비함. - 를 효율적으로 운용하기 위하여, 복 수의 상기 가상 머신을 상기 제1 물리 서버와 상기 제2 물리 서버 상에 배치하는 방법인 가상 머신 배치 방법을 구현하는 가상 머신 배치 장치에 있어서,처리부; 및상기 가상 머신 배치 방법을 수행하는 프로그램이 저장된 저장부;를 포함하고,상기 가상 머신 매치 방법은,상기 처리부가 상기 저장부에 저장되어 있는 상기 제1 물리 서버와 상기 제2 물리 서버의 작동과 관련된 정보를 기초로 미리 정해진 워크 로드 산출 방법에 의해 상기 가상 머신에 의해 부과되는 물리 서버의 부하인 가상 머신 워크 로드와 관련된 정보인 가상 머신 워크 로드 정보를 산출하는 단계;상기 처리부가 상기 가상 머신 워크 로드를 기초로 상기 가상 머신 워크 로드가 산출된 시점부터 미리 정해진 제1 기간 동안 상기 가상 머신에 의해 예측되는 물리 서버의 부하와 연관된 최초 예측 가상 로드와 관련된 정보인 최초 예측 가상 로드 정보를 산출하는 단계;상기 처리부가 미리 정해진 탐색 배치 산출 방법에 의해 상기 제1 물리 서버와 상기 제2 물리 서버 상의 상기 가상 머신의 배치인 탐색 배치와 관련된 정보인 탐색 배치 정보를 산출하는 단계; 및상기 처리부가 선택된 상기 탐색 배치를 기초로 상기 가상 머신을 상기 제1 물리 서버와 상기 제2 물리 서버 상에서 배치하는 단계;를 포함하고,상기 미리 정해진 탐색 배치 산출 방법은,상기 처리부가 상기 최초 예측 가상 로드 정보를 기초로 목적 함수 값이 최소화될 때의 상기 가상 머신의 탐색 배치를 산출하는 방법인,가상 머신 배치 장치.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US16/470,364 US11354163B2 (en) | 2019-04-29 | 2019-05-21 | Virtual machine placement method and virtual machine placement device implementing the same |
CN201980000794.2A CN112154416B (zh) | 2019-04-29 | 2019-05-21 | 虚拟机配置方法以及用于实施该方法的虚拟机配置装置 |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020190049976A KR102062157B1 (ko) | 2019-04-29 | 2019-04-29 | 가상 머신 배치 방법 및 이를 구현하는 가상 머신 배치 장치 |
KR10-2019-0049976 | 2019-04-29 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2020222347A1 true WO2020222347A1 (ko) | 2020-11-05 |
Family
ID=69155391
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/KR2019/006072 WO2020222347A1 (ko) | 2019-04-29 | 2019-05-21 | 가상 머신 배치 방법 및 이를 구현하는 가상 머신 배치 장치 |
Country Status (4)
Country | Link |
---|---|
US (1) | US11354163B2 (ko) |
KR (1) | KR102062157B1 (ko) |
CN (1) | CN112154416B (ko) |
WO (1) | WO2020222347A1 (ko) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR102403625B1 (ko) * | 2021-10-15 | 2022-05-30 | 오케스트로 주식회사 | 물리 서버 성능 저하를 고려하여 가상 머신 예측 관리를 구현한 가상 머신 배치 시스템 및 가상 머신 배치 방법 |
KR102403632B1 (ko) * | 2021-10-15 | 2022-05-30 | 오케스트로 주식회사 | 핫 스팟을 고려하여 가상 머신의 예측 마이그레이션을 구현한 가상 머신 배치 시스템 및 가상 머신 배치 방법 |
KR102381570B1 (ko) * | 2021-10-21 | 2022-04-01 | 오케스트로 주식회사 | 예측 불확실성이 반영된 배치 스케줄을 제공하는 가상 머신 배치 시스템 및 가상 머신 배치 방법 |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2011170787A (ja) * | 2010-02-22 | 2011-09-01 | Nippon Telegraph & Telephone West Corp | リソース割当装置、リソース割当方法、およびリソース割当制御プログラム |
KR20120023703A (ko) * | 2009-06-01 | 2012-03-13 | 후지쯔 가부시끼가이샤 | 서버 관리 프로그램을 기록한 컴퓨터 판독 가능한 기록 매체, 관리 서버, 가상 서버 배치 방법 |
JP2012159928A (ja) * | 2011-01-31 | 2012-08-23 | Internatl Business Mach Corp <Ibm> | 情報処理装置、情報処理システム、配置構成決定方法、プログラムおよび記録媒体 |
JP2014006739A (ja) * | 2012-06-25 | 2014-01-16 | Fujitsu Ltd | プログラム、管理サーバおよび仮想マシン移動制御方法 |
KR101867487B1 (ko) * | 2016-12-23 | 2018-07-18 | 경희대학교 산학협력단 | 클라우드 환경에서 퍼지기반의 마이그레이션 시스템 및 방법 |
Family Cites Families (25)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6868114B2 (en) * | 2001-01-18 | 2005-03-15 | The Titan Corporation | Interference suppression in a spread spectrum communications system using non-linear frequency domain excision |
AU2002255806A1 (en) * | 2001-03-20 | 2002-10-08 | Dealigence Inc. | Negotiating platform |
JP2007183883A (ja) * | 2006-01-10 | 2007-07-19 | Fujitsu Ltd | 資源計画作成プログラム、該プログラムを記録した記録媒体、資源計画作成装置、および資源計画作成方法 |
JP5412926B2 (ja) * | 2009-04-02 | 2014-02-12 | 日本電気株式会社 | 仮想マシン管理システム,仮想マシン配置設定方法及びそのプログラム |
US8694638B2 (en) * | 2009-06-29 | 2014-04-08 | Red Hat Israel | Selecting a host from a host cluster to run a virtual machine |
JP2011186701A (ja) * | 2010-03-08 | 2011-09-22 | Nec Corp | リソース割当装置、リソース割当方法、およびリソース割当プログラム |
JP5785050B2 (ja) * | 2011-10-27 | 2015-09-24 | 株式会社日立製作所 | 情報処理システム、その省電力制御方法、及び装置 |
US9116181B2 (en) * | 2011-12-29 | 2015-08-25 | Huawei Technologies Co., Ltd. | Method, apparatus, and system for virtual cluster integration |
US8862744B2 (en) * | 2012-02-14 | 2014-10-14 | Telefonaktiebolaget L M Ericsson (Publ) | Optimizing traffic load in a communications network |
US20140019964A1 (en) * | 2012-07-13 | 2014-01-16 | Douglas M. Neuse | System and method for automated assignment of virtual machines and physical machines to hosts using interval analysis |
SG10201907682RA (en) * | 2012-10-05 | 2019-10-30 | Mould Diane | System and method for providing patient-specific dosing as a function of mathematical models |
CN103822097B (zh) * | 2012-11-16 | 2016-11-16 | 国际商业机器公司 | 在流体输送管道中估计负压波的波速的方法及装置 |
US10318881B2 (en) * | 2013-06-28 | 2019-06-11 | D-Wave Systems Inc. | Systems and methods for quantum processing of data |
CN104461728B (zh) * | 2013-09-18 | 2019-06-14 | Sap欧洲公司 | 迁移事件调度管理的计算机系统、介质和方法 |
CN107428568A (zh) * | 2015-03-26 | 2017-12-01 | 皇家飞利浦有限公司 | 控制水的单向pH调节中电极的再生 |
JP2017228881A (ja) * | 2016-06-21 | 2017-12-28 | 富士通株式会社 | ネットワーク評価プログラム、ネットワーク評価方法、及び、ネットワーク評価装置 |
CN107562512B (zh) * | 2016-07-01 | 2020-06-26 | 华为技术有限公司 | 一种迁移虚拟机的方法、装置及系统 |
US10949492B2 (en) * | 2016-07-14 | 2021-03-16 | International Business Machines Corporation | Calculating a solution for an objective function based on two objective functions |
CN106598733A (zh) * | 2016-12-08 | 2017-04-26 | 南京航空航天大学 | 一种云计算能耗关键的三维度虚拟资源调度方法 |
US10636141B2 (en) * | 2017-02-09 | 2020-04-28 | Siemens Healthcare Gmbh | Adversarial and dual inverse deep learning networks for medical image analysis |
JP6568175B2 (ja) * | 2017-10-20 | 2019-08-28 | ヤフー株式会社 | 学習装置、生成装置、分類装置、学習方法、学習プログラム、および動作プログラム |
CN107967179B (zh) * | 2017-12-12 | 2021-08-06 | 山东省计算中心(国家超级计算济南中心) | 一种支持突发应急的云计算资源分配方法 |
CN108469983B (zh) * | 2018-04-02 | 2021-10-19 | 西南交通大学 | 一种云环境下的基于粒子群算法的虚拟机部署方法 |
JP7070051B2 (ja) * | 2018-04-27 | 2022-05-18 | 日本電信電話株式会社 | 計算装置、計算方法及びプログラム |
US20200019841A1 (en) * | 2018-07-12 | 2020-01-16 | Vmware, Inc. | Neural network model for predicting usage in a hyper-converged infrastructure |
-
2019
- 2019-04-29 KR KR1020190049976A patent/KR102062157B1/ko active IP Right Grant
- 2019-05-21 US US16/470,364 patent/US11354163B2/en active Active
- 2019-05-21 CN CN201980000794.2A patent/CN112154416B/zh active Active
- 2019-05-21 WO PCT/KR2019/006072 patent/WO2020222347A1/ko active Application Filing
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20120023703A (ko) * | 2009-06-01 | 2012-03-13 | 후지쯔 가부시끼가이샤 | 서버 관리 프로그램을 기록한 컴퓨터 판독 가능한 기록 매체, 관리 서버, 가상 서버 배치 방법 |
JP2011170787A (ja) * | 2010-02-22 | 2011-09-01 | Nippon Telegraph & Telephone West Corp | リソース割当装置、リソース割当方法、およびリソース割当制御プログラム |
JP2012159928A (ja) * | 2011-01-31 | 2012-08-23 | Internatl Business Mach Corp <Ibm> | 情報処理装置、情報処理システム、配置構成決定方法、プログラムおよび記録媒体 |
JP2014006739A (ja) * | 2012-06-25 | 2014-01-16 | Fujitsu Ltd | プログラム、管理サーバおよび仮想マシン移動制御方法 |
KR101867487B1 (ko) * | 2016-12-23 | 2018-07-18 | 경희대학교 산학협력단 | 클라우드 환경에서 퍼지기반의 마이그레이션 시스템 및 방법 |
Also Published As
Publication number | Publication date |
---|---|
CN112154416B (zh) | 2024-03-29 |
CN112154416A (zh) | 2020-12-29 |
KR102062157B1 (ko) | 2020-01-03 |
US11354163B2 (en) | 2022-06-07 |
US20220050716A1 (en) | 2022-02-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2015020471A1 (en) | Method and apparatus for distributing data in hybrid cloud environment | |
WO2020222347A1 (ko) | 가상 머신 배치 방법 및 이를 구현하는 가상 머신 배치 장치 | |
WO2018076868A1 (zh) | 一种数据同步方法、装置、系统、存储介质和服务器 | |
WO2021060609A1 (ko) | 복수의 엣지와 클라우드를 포함하는 분산 컴퓨팅 시스템 및 이의 적응적 지능 활용을 위한 모델 제공 방법 | |
WO2015008971A1 (en) | Mobile terminal and method of determining and displaying power efficiency of an application | |
WO2018076840A1 (zh) | 数据分享方法、装置、存储介质及服务器 | |
WO2015041436A1 (en) | Method of managing control right, client device therefor, and master device therefor | |
WO2018076812A1 (zh) | 数据请求的响应方法、装置、存储介质、服务器及系统 | |
WO2018076889A1 (zh) | 数据备份的方法、装置、系统、存储介质及服务器 | |
WO2018120681A1 (zh) | 数据同步方法、装置、系统、数据处理服务器和存储介质 | |
WO2019103280A1 (ko) | 클라우드 서비스를 제공하는 적어도 하나의 클라우드 서버의 컴퓨팅 자원들을 관리하는 전자 장치 및 방법 | |
WO2020153750A1 (ko) | 전자 장치에서 어플리케이션 목록 제공 방법 및 장치 | |
WO2018076433A1 (zh) | 多开应用程序方法、多开应用程序装置及终端 | |
WO2018076829A1 (zh) | 终端数据的处理方法、装置、系统、存储介质及服务器 | |
WO2020052247A1 (zh) | 网络资源批量加载方法、智能电视、存储介质及装置 | |
WO2018120680A1 (zh) | 虚拟磁盘备份系统、方法、装置、服务主机和存储介质 | |
WO2018076869A1 (zh) | 一种数据备份方法、装置、存储介质和电子设备 | |
WO2021070983A1 (ko) | Vr 훈련 시스템 및 방법 | |
WO2017206885A1 (zh) | 应用程序的关闭方法、装置、存储介质及电子设备 | |
WO2018076872A1 (zh) | 数据备份方法、装置、存储介质及服务器 | |
WO2017206867A1 (zh) | 一种传感器的关闭方法、装置、存储介质及电子设备 | |
WO2020218743A1 (en) | Method for controlling execution of application, electronic device and storage medium for the same | |
WO2020076056A1 (ko) | 트래픽 오프로딩을 제어하기 위한 장치 및 방법 | |
WO2016035979A1 (en) | Method and system for controlling operation of image forming apparatus by using wearable device | |
WO2021141441A1 (ko) | 스크래핑 기반 서비스 제공 방법 및 이를 수행하는 어플리케이션 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 19927415 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 19927415 Country of ref document: EP Kind code of ref document: A1 |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 19927415 Country of ref document: EP Kind code of ref document: A1 |
|
32PN | Ep: public notification in the ep bulletin as address of the adressee cannot be established |
Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205 DATED 22/04/2022) |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 19927415 Country of ref document: EP Kind code of ref document: A1 |