WO2012117453A1 - 計算機システム、および、計算機システムにおける仮想計算機の最適配置方法 - Google Patents
計算機システム、および、計算機システムにおける仮想計算機の最適配置方法 Download PDFInfo
- Publication number
- WO2012117453A1 WO2012117453A1 PCT/JP2011/001271 JP2011001271W WO2012117453A1 WO 2012117453 A1 WO2012117453 A1 WO 2012117453A1 JP 2011001271 W JP2011001271 W JP 2011001271W WO 2012117453 A1 WO2012117453 A1 WO 2012117453A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- computer
- physical
- virtual
- virtual machine
- scheduled
- 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
-
- 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
- G06F9/44—Arrangements for executing specific programs
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
- G06F9/45558—Hypervisor-specific management and integration aspects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
- G06F9/45558—Hypervisor-specific management and integration aspects
- G06F2009/4557—Distribution of virtual machine instances; Migration and load balancing
Definitions
- the present invention relates to a computer system, and more particularly to a computer system suitable for optimally arranging virtual machines on a physical server existing in the computer system. Furthermore, the present invention relates to a method for optimizing the placement of virtual machines in a virtual machine system.
- a computer resource with a single physical server plurality of virtual machines that is utilized in (VM V irtual M achine), virtualization technology servers are known.
- the virtual computer is a physical server and operates as a virtual server, so that a plurality of users can effectively use the resources of the physical server (physical computer).
- a plurality of virtual computers are optimally arranged on a plurality of physical computers.
- a plurality of virtual machines may be distributed to a plurality of physical computers so that the load is leveled between a plurality of physical computers on which the virtual machines are operating, respectively.
- optimal placement processing of virtual machines is desired, such as by putting as many virtual machines as possible to the same physical machine.
- Virtual machine placement is reconfigured among multiple physical computers for optimal placement processing of virtual machines.
- the virtual machines are migrated between a plurality of physical machines.
- the management server (management computer) of the computer system releases the computer resource of the migration source physical computer from the virtual computer and allocates the computer resource of the migration destination computer to the virtual computer.
- a management computer calculates an optimal combination of a virtual computer and a physical computer, and based on the calculation result, the virtual computer A system is disclosed in which a virtual machine is migrated between a plurality of physical computers to adjust the load balance among the plurality of physical computers, each of which is deployed, even when the virtual computer is in operation.
- the conventional system disclosed by the above-mentioned publications considers the optimal load of a plurality of virtual machines with respect to a plurality of physical computers in consideration of the past load information of the virtual machines and the predicted load information of the virtual machines in the future. Although it was determined, it was not intended to realize the optimal arrangement of virtual machines taking into account the case where the number of virtual machines is changed.
- the optimal arrangement state of the virtual machines is adversely affected when a new virtual machine starts to operate on the physical computer.
- the management computer has to redo the optimal placement processing of the virtual computer when the new virtual computer is operated on the physical computer.
- an object of the present invention is to provide a computer system in which a load in processing for optimally arranging a plurality of virtual computers on a plurality of physical computers is reduced.
- Another object of the present invention is to provide a computer system in which even when a new virtual computer starts to run on a physical computer, the optimum arrangement state of the running virtual computer is not impaired.
- Still another object of the present invention is to provide a method for optimizing the placement of virtual machines in a computer system.
- the present invention obtains a planned load of a virtual machine scheduled to be operated from schedule information for operating a virtual machine in a computer system, and the actual load of the scheduled load and the virtual machine in operation.
- the execution subject of the virtual computer in which the computer related to the operation schedule is arranged is determined from the load before the operation start time of the virtual computer scheduled to operate in the computer system.
- the present invention it is possible to provide a computer system in which a load in a process of optimally arranging a plurality of virtual computers on a plurality of physical computers is reduced. Furthermore, according to the present invention, it is possible to provide a computer system in which even when a new virtual computer starts to operate on a physical computer, the optimum arrangement state of the operating virtual computer is not impaired. Furthermore, according to the present invention, it is possible to provide a method for optimizing the arrangement of virtual machines in the above-described computer system.
- FIG. 1 is a hardware configuration diagram of a computer system according to Embodiment 1.
- FIG. 3 is an example of a physical computer configuration table according to the first embodiment.
- 3 is an example of an information table of a virtual machine according to the first embodiment.
- 4 is an example of a reservation information table according to the first embodiment.
- 3 is a flowchart of optimal placement processing of an operation-scheduled virtual computer according to the first embodiment.
- 2 is an arrangement score table of the first embodiment.
- 3 is a flowchart of an arrangement determination process for an operation scheduled virtual machine according to the first embodiment.
- 10 is a physical computer configuration table, a VM information table, and a reservation information table according to the second embodiment.
- 12 is a flowchart of optimal placement processing of a virtual machine according to a second embodiment.
- FIG. 10 is a flowchart of an optimal arrangement plan creation process for a virtual machine that is operating and a virtual machine that is scheduled to operate according to the second embodiment.
- FIG. 10 illustrates a physical computer configuration table, a VM information table, and a reservation information table according to the third embodiment.
- FIG. 10 is a flowchart of an optimal arrangement process for an operation scheduled virtual machine according to a third embodiment.
- the resource management program is a management table related to a state in which it is not necessary to consider the end time of an operating virtual machine when determining the placement of a virtual machine to be operated, and a physical computer information table (FIG. 13 ( A)), a VM information table (FIG. 13B), and a reservation information table (FIG. 13C).
- FIG. 1 shows hardware blocks of the computer system.
- the computer system includes a plurality of physical computers 0130, 0140,..., A management server 0100 that manages the placement of virtual computers between physical computers, and a network 0120 that connects the plurality of physical computers and the management server. ing.
- the resource management server 0100 includes a CPU 0101, a memory 0102, a network interface card (shown as NIC) 0109, an input I / F 0103, an output I / F 0105, and an HDD I / F 0107.
- NIC network interface card
- the input I / F 0103 of the resource management server 0100 is connected to an input device such as a mouse or a keyboard 0104, and accepts an operation from a user of the resource management server 0100.
- the output I / F 0105 is connected to an output device such as a display 0106, and performs screen output to the user.
- a printer (not shown) can be connected as long as it is an output device.
- the HDD I / F 0107 is connected to the HDD 0108, which is an external storage, and stores various programs, various data tables processed by the CPU 0101, and the like.
- the NIC 0109 is connected to the network 0120 and is connected to other physical computers 0130 and 0140.
- a resource management program 0110 is installed in the memory 0102.
- the resource management program 0110 may be stored in the HDD 0108 and loaded into the memory 0102 in response to a request from the CPU 0101.
- the resource management program 0110 includes a reservation acceptance process 0111, a virtual machine placement calculation process 0112, a virtual machine migration process 0113, a measurement process 0114 for calculating the load of an operating virtual machine, and a virtual machine that has been scheduled to be operated as a virtual machine Deployment processing 0115 that makes it available to users on a timely basis, and load information and configuration information of virtual machines and hypervisors operating on the physical computers 0130 and 0140 are collected and managed from the physical computers 0130 and 0140 and hypervisors 0135 and 0145 Management processing 0116 is executed.
- Each of these processes is achieved by one or a combination of flowcharts described later, or one or more steps of these flowcharts.
- the memory 0102 stores a physical computer information table (TBL) 0200 that stores information on the total resource amount that can be allocated from the physical computer to the virtual computers 0136 and 0146 by the hypervisors 0135 and 0145.
- TBL physical computer information table
- the total resource amount is collected from the physical computers 0130 and 0140 by the resource management program 0110.
- the memory 0102 further includes a reservation information table 0300 that stores information related to a schedule for operating a virtual machine created based on an input from a user of the virtual machine, load information of the operating virtual machine, virtual information A VM information table 0400 that stores information on the physical computer on which the computer operates, a placement score table 0600 that stores priority information for determining which physical computer is to be the physical computer on which the virtual computer is to be placed, and the like Management table.
- a reservation information table 0300 that stores information related to a schedule for operating a virtual machine created based on an input from a user of the virtual machine, load information of the operating virtual machine, virtual information
- a VM information table 0400 that stores information on the physical computer on which the computer operates
- a placement score table 0600 that stores priority information for determining which physical computer is to be the physical computer on which the virtual computer is to be placed, and the like Management table.
- the resource management program 0100 performs read or write processing on these management tables in the course of resource management processing.
- the management table may be stored in the HDD 0108.
- the CPU 0101 reads the management table from the HDD 0108, loads it into the memory 0102, and stores the management table in the HDD 0108.
- the physical computers 0130 and 0140 have the same hardware configuration as that of the resource management server 0100.
- HDD I / Fs 0134 and 0144 for connecting to 0150 are provided.
- an input I / F (0103) and an output I / F (0105) may be provided.
- the identifier of the physical computer 0130 is P1
- the identifier of the physical computer 0140 is P2
- the third and subsequent physical computers are P3, P4,.
- Hypervisors 0135 and 0145 are loaded in the memory 0132 and 0142 of the physical computer, and one or a plurality of virtual machines 0136... 137, 0146. Management processing related to various virtual computers such as allocation of computer resources of physical computers to virtual computers is performed.
- the computer resource is, for example, one or more of a CPU, a memory, a hard disk drive, a NIC network bandwidth, a disk I / O, and the like included in the computer.
- Computer resources include not only hardware resources but also logical resources such as volumes, host groups, and pools.
- Each hypervisor 135, 145 is management software for allocating one or more virtual machines to each physical machine and deploying them. For example, a plurality of virtual machines including a virtual machine 0136 and a virtual machine 0137 are assigned to the physical machine P1: 0130. A plurality of virtual machines including a virtual machine 0146 and a virtual machine 0147 are allocated on the physical computer P2: 0140. In the virtual machine assignment management in the management table described above, the assignment target of the virtual machine may be a physical computer or a hypervisor.
- the resource management program 0110 of the resource management server 0100 exchanges information by communicating with the hypervisors 0135 and 0145 of the physical computers P1: 0130 and P2: 0140, and at any time load information of the virtual machine and load information of the hypervisor ( (Physical computer load information) can be acquired and the physical computer information table 0200 and the VM information table 0400 can be updated.
- load information of the virtual machine and load information of the hypervisor (Physical computer load information) can be acquired and the physical computer information table 0200 and the VM information table 0400 can be updated.
- the resource management server 0100 sets and updates the reservation information table 0300 based on the reservation information of the virtual machine input from the user who uses the virtual machine.
- the virtual machine 0136 and the virtual machine 0137 operate on the hypervisor 0135.
- the hypervisor 0135 divides the computer resources of the physical computer P1: 0130, for example, the CPU 0131 and the memory 0132 into each virtual computer of a plurality of virtual computers and assigns them.
- the hypervisor 0135 can also dynamically change the amount of computer resources allocated to each virtual computer.
- the hypervisor 0145 similarly acts on the virtual machine 0146 and the virtual machine 0147. Since the guest OS runs on one virtual machine, the virtual machine can use application software that runs on the guest OS.
- the shared storage 0150 connected to the physical computers P1: 0130 and P2: 0140 stores a disk image 0151 of the virtual computer.
- the virtual machine disk image is an image file stored in a virtual HDD given to the virtual machine.
- the shared storage 0150 sets a virtual HDD, and loads an operating system or application stored in the virtual HDD into the memory 0132 (0142) for execution.
- the VM disk image becomes a substance of the virtual HDD.
- the virtual machine can handle the VM disk image as a virtual HDD.
- the VM disk image corresponds to one file actually stored in the HDD when viewed from the hypervisor.
- One virtual machine requires one or more VM disk images.
- the virtual machine 0147 on the physical machine P2: 0140 uses one VM disk image 0151 stored in the HDD 0150.
- the VM disk image 0151 is controlled by the hypervisor. Since the VM disk image is stored in the shared HDD 0150 connected to both the physical computers P1: 0130 and P2: 0140, the management server 0100 loads the operating system and application software stored in the VM disk image. If the target physical computer is changed, the physical computer on which the virtual computer operates can be changed, that is, the virtual computer can be moved between a plurality of physical computers.
- the management server 0100 When the management server 0100 enables the virtual machine to operate on another physical machine, the physical machine that is the migration source of the virtual machine is loaded into the memory for the virtual machine, and data that is added, updated, or deleted as appropriate Is copied over the network to the physical computer to which the virtual machine is migrated.
- changing the physical computer on which the virtual machine operates means that the migration source physical computer copies the memory data used for the virtual machine to be migrated to the memory of the migration destination physical computer, and This is executed by the hypervisor performing an operation such as changing a VM disk image into which data is loaded.
- the migration of the virtual machine is started when the resource management server 0100 issues an instruction to migrate the virtual machine to the hypervisors 0135 and 0145 of the migration source / destination physical machine.
- the physical computers P1: 130 and P2: 140 are both connected to the shared HDD 150 in which the VM disk image is stored.
- the VM disk image can be copied via the network, and the VM disk image data can be copied. If the physical computer to be loaded can be changed, the HDD in which the VM disk image is stored need not be a shared HDD connected to both the physical computers P1: 130 and P2: 140, and the physical computers P1: 130, P2 : HDDs individually connected to 140.
- the resource management server 0100 obtains information from the physical computers P1: 0130 and P2: 0140, and the physical computer for migrating the virtual computers.
- the network for copying data and the like between P1: 0130 and P2: 0140 may be separated.
- FIG. 2 shows an example of the physical computer information table 0200.
- the physical computer information table 0200 stores all physical computers that can deploy virtual computers in the computer system, such as the physical computer P1: 0130 and the physical computer P2: 0140, and the total computer resource amount allocated to the virtual computers. ing. In the physical computer information table 0200, one row is assigned to one physical computer.
- the physical computer identifier column 0201 stores an identifier for identifying each physical computer P1: 0130, P2: 0140, and the like.
- the total memory capacity column 0202 stores the total computer resource amount that each physical computer can allocate to the virtual computer.
- the row 0211 indicates that the total memory capacity that can be allocated from the memory 0132 of the physical computer P1: 0130 to all virtual computers operating on the physical computer P1: 0130 is “6.0 GB”. Yes.
- the memory is illustrated as an example of the computer resource allocated to the virtual machine, but other resources allocated to the virtual machine such as the number of CPU clocks and disk I / O, or a combination thereof may be used instead of the memory.
- FIG. 3 shows an example of the VM information table 0400.
- the VM information table 0400 stores load information of virtual machines (0136, 0146, etc.) operating on the physical computer P1: 0130 and the physical computer P2: 140 that constitute the computer system.
- a load is a load that a virtual computer gives to a physical computer.
- one row is allocated to one virtual machine. It is not necessary to register information regarding virtual machines that are not operating in this table.
- the VM identifier column 0401 stores identifiers of virtual machines that operate on a plurality of physical computers constituting the computer system. As shown in FIG. 1, an identifier for identifying a virtual machine 0136 and a virtual machine 0146 running on the physical computer P1: 0130 and the physical computer P2: 140 is stored.
- the physical computer identifier column 0402 stores an identifier for identifying a physical computer to which a running virtual computer is deployed. This identifier is the same identifier as the identifier stored in the physical computer identifier column 0201 of the physical computer information table 0200.
- the row 0411 stores an identifier “P1” for identifying the physical computer P1: 0130 on which the virtual computer “VM1” operates.
- the load column 0403 stores the loads of active virtual machines collected from the hypervisors 0135 and 0145 by the measurement process 0114 by the resource management program 0110.
- the value stored in the load column 0403 is, for example, the maximum value of a plurality of pieces of load information collected by the resource management server 0110 from the hypervisors 0135 and 0145 in the past certain period.
- the row 0411 means that the maximum value of the memory consumption of the virtual machine “VM1” collected from the hypervisor 0135 by the resource management server 0100 is “2.0 GB”.
- the maximum value of the memory consumption of the virtual machine collected in the past certain period is illustrated, but the average value of the memory consumption or the standard deviation is added to the average value. It may be an added value. Alternatively, it may be a predicted value of the future load for a certain period from the present, which is predicted based on the load actually measured in the past certain period. Further, instead of the memory, other resources assigned to the virtual machine, such as the number of CPU clocks and disk I / O, or a combination thereof may be used.
- the value stored in the load column 0403 is an absolute value, but it may be a relative value between the computer resource amount of the physical computer and the collected virtual computer load. Note that the value stored in the load column 0403 does not need to be information of one load, but may be a set of a plurality of pieces of load information of virtual machines collected from the hypervisors 0135, 0136, etc. by the resource management server 0100 in the past fixed period. .
- FIG. 4 is an example of the reservation information table 0300.
- This table 0300 is for storing information relating to the operation schedule of the virtual machine.
- the reservation identifier column 0301 stores an identifier for identifying reservation information for operating a virtual machine in a certain period.
- the VM identifier column 0302 stores an identifier for identifying a virtual machine that operates the reservation. This identifier is the same as the identifier stored in the virtual machine identifier column 0401 of the VM information table 0400.
- the identifier stored in the VM identifier column 0401 of the VM information table 0400 is always present in the VM identifier column of the reservation information table 0300, the start time of the reservation information is before the current time, and the end time is after the current time. Is stored. If the disk image of the virtual machine identified by this identifier has already been created in the shared HDD 0150, the virtual machine identifier is stored.
- the resource management program 0110 stores an appropriate unique identifier and stores the virtual machine disk image when the virtual machine disk image is created. Let the identifier be the identifier of the virtual machine.
- the start time column 0304 stores the time when the reserved virtual machine starts operating and the resources are allocated from the physical computer, and the end time column 0305 ends the virtual computer and returns the resource to the physical computer. Stores the time.
- the reservation identifier “RSV1” in the row 0311 indicates that the virtual machine “VM1” is a reservation that operates from April 1, 2010 to September 1, 2010.
- the deployed physical computer column 0303 stores an identifier for identifying a physical computer that is mounted and operated when the virtual computer starts operation. This identifier is the same as the identifier stored in the physical computer identifier column 0201 of the physical computer information table 0200.
- the row 0311 indicates that when the virtual machine VM1 starts operation, the virtual machine VM1 operates on the physical computer P1: 0130 and computer resources can be allocated from the physical computer P1: 0130.
- the identifier in the deployment destination physical computer column 0303 can be changed as appropriate until the virtual computer starts operation.
- the physical computer on which the virtual computer operates does not have to be determined until the virtual computer starts operation. If it is not determined, “null” may be stored in the deployment destination physical computer column 0303 (line 0314). Since the virtual machine that has started operation can be migrated between a plurality of physical computers, after the virtual machine starts operation, the combination of the VM identifier column 0302 and the deployment destination physical computer column 0303 in the reservation information table 0400, and the VM The combination of the VM identifier column 0401 and the physical computer identifier column 0402 of the information table 0400 may be different.
- the scheduled load column 0306 the predicted value of the computer resource allocated from the physical computer to the virtual computer when the virtual computer is operated is stored.
- the value stored in the scheduled load column 0306 is, for example, a value input by a user of the virtual machine by predicting the load of the virtual machine scheduled to operate.
- the memory consumption is exemplified as an example of the load of the virtual machine as with the value entered in the load 0403 of the VM information table 0400.
- the CPU clock number and the disk I Other resources assigned to the virtual machine such as / O or a combination thereof may be used.
- the value stored in the planned load 0306 may be an absolute value or a relative value with the computer resource amount of the physical computer.
- the value stored in the scheduled load 0306 need not be a single value, but may be a set of a plurality of values. For example, it is 2.0 G from 9 am to 9 pm and 1.0 G from 9 pm to 9 am.
- the row 0311 indicates that the virtual machine “VM1” has been operating on the physical machine “P1” from April 1, 2010, and 2.0 GB of the total memory capacity of the physical machine “P1” is allocated. This means that 2.0 GB, which is the memory capacity allocated on September 1, 2012, is returned to the physical computer “P1”.
- the resource management program 0110 determines that the identifier stored in the VM identifier column 0302 of the reserved virtual machine is the same as the identifier of the active virtual machine, the resource management program 0110 and the start time of the reserved virtual machine When the former is the time before the latter by comparing with the end time of the virtual machine, an error is displayed at the time of inputting the reservation information, or the VM identifier of the virtual machine to be reserved is used as the VM identifier of the virtual machine to be reserved The administrator may be prompted to enter a value different from the identifier.
- FIG. 21 is a reservation information input screen of the virtual machine displayed on the display 0106 by the resource management program 0110 via the output I / F.
- the placement destination physical computer of the virtual computer may be designated via the reservation information input screen.
- the placement destination of the virtual computer is described as a physical computer, but this may be a hypervisor.
- the user may group a plurality of hypervisors and use the resource group as a virtual machine deployment destination. This grouping can limit the range of physical computers in which virtual computers are optimally arranged.
- FIG. 5 is a flowchart for performing the processing.
- the resource management program 0110 executes the flowchart of FIG.
- Optimization means placing virtual machines so that they match the “policy”.
- the policy is set as a policy file in the resource management program 0110 by the management user.
- a plurality of virtual machines may be arranged in a plurality of physical machines so that the load of the virtual machines is leveled between the plurality of physical machines.
- the load leveling may be executed based on the load value exerted on the physical computer by the virtual computer, or based on the remaining capacity of the computer resource of the physical computer.
- a virtual computer may be deployed to a plurality of physical computers separated by a certain distance or more.
- the resource management program 0110 executes step S0501 at an arbitrary time.
- the arbitrary time is, for example, the time set by the user in the resource management server 0100.
- Step S0501 is executed by the arrangement calculation processing 0112, and the processing up to step S0504 is repeatedly performed until all of the plurality of pieces of physical computer information stored in the physical computer information table 0200 of FIG. 2 are referred to.
- Step S0502 selects one piece of physical computer information to be referred to. Specifically, one piece of physical computer information stored in the physical computer information table 0200 is selected, and data for one row of the physical computer information table 0200 is stored in the memory 0102.
- step S0503 the VM information table 0400 in FIG. 3 is referred to, and VM identifier information in which the identifier of the physical computer identifier 0201 of the physical computer information selected in step S0502 matches the identifier of the physical computer identifier column 0402 is obtained from the VM information table 0400. Extract all.
- step S0504 the placement score of the physical computer is calculated using the value in the memory total capacity column 0202 of the physical computer information selected in step S0502 and the value in the load column 0403 of all VM information extracted in step S0503. Record in the placement score table 0600.
- the placement score is a value related to the high priority at which a virtual computer can be deployed in each physical computer in order to realize an optimal placement of the virtual computer. It is determined that a physical computer having a larger placement score has a higher priority in mounting a virtual computer.
- the resource management server 0100 selects, as an index for optimally allocating virtual machines to physical computers, the leveling of the memory space between the plurality of physical computers constituting the computer system between the plurality of physical computers To do. From this point of view, a physical computer having a larger memory capacity is more suitable for deploying a virtual computer scheduled to operate. Therefore, the free capacity of the physical computer becomes the placement score of the physical computer.
- the physical computer information selected in step S0502 is row 0211
- the physical computer identifier column 0201 is “P1”
- FIG. 6 shows data recorded in the placement score table 0600 in step S0504.
- the placement score table 0600 includes a physical computer identifier column 0601 and a placement score column 0602.
- the physical computer identifier column 0601 stores the identifier of the physical computer identifier column 0201 of the physical computer information 0200 selected in step S0502.
- the placement score column 0602 stores the placement score of each physical computer calculated in step S0504.
- the physical computer “P1” is stored in the placement score table 0600 as shown in the row 0611.
- the identifier “P1” is stored in the identifier column 0601 and the placement score “4.0” is stored in the placement score column 0602.
- Step S0505 in FIG. 5 is a terminal step corresponding to S0501 which is the head of the repetition step, and steps S0502 to S0504 are repeatedly executed until all physical computer information stored in the physical computer information table 0200 is referred to.
- step S0506 based on the information stored in the placement score table 0600 in FIG. 6 and the reservation information table 0300 in FIG. 4, the physical computer stored in the deployment destination physical computer column 0303 in the reservation information table 0300 is displayed. The identifier is read, and the physical computer to which the computer resource is allocated to the virtual computer scheduled to operate is determined. Details of step S0506 are shown in the flowchart of FIG.
- FIG. 7 is a flowchart for achieving the process (S0506 in FIG. 5) for determining the destination physical computer in which the virtual computer scheduled to operate is placed.
- This flowchart shows that the management server 0100 is scheduled to operate every “predetermined period” from the “start time” when executing (re) allocation of virtual machines to a plurality of physical computers existing in the computer system.
- This is an example of a process for determining which physical computer is optimally arranged from among a plurality of physical computers.
- the management server 0100 acquires information of “(relocation execution) scheduled time” and “predetermined period” by input from the administrator user.
- the “scheduled time” may be any time after the time when the process of FIG. 5 is completed.
- the “predetermined period” is a predetermined period from the “scheduled time” to the next “scheduled time”, and is, for example, one week or one month.
- Step S0702 refers to the reservation information table 0300 in FIG. 4 and extracts all reservation information in a row whose time stored in the start time column 0304 is within the “predetermined period” from the “scheduled time”. For example, when the resource management program 0110 acquires “scheduled time” as “May 1, 2010 0:00” and a certain period as “1 month” in step S0701, step S0702 displays the reservation information table 0300 in FIG. , A row 0313 in which the time stored in the start time column 0304 is between 0:00 on May 1, 2010 and May 31, 2010 is extracted.
- step S0703 the processing up to step S0707 is repeatedly performed until all the reservation information extracted in step S0702 is referred to.
- step S0704 one piece of extracted reservation information is selected.
- step S0705 the arrangement of the virtual computers scheduled to operate is determined based on the arrangement score table 0600 shown in FIG. 6, and the deployment destination physical computer column of the reservation information table is updated based on the result. Specifically, the reservation information table is updated so that the identifier of the placement destination physical computer column of the reservation information selected in step S0703 becomes the identifier of the physical computer with the highest score in the placement score table 0600.
- the management program 0110 refers to the placement score column 0602 of the placement score table 0600 (FIG. 6), the row with the largest placement score is 0612, and the reservation information selected in step S0704 is the reservation information table 0300 (FIG. 4).
- the virtual machine “VM3” scheduled to be operated indicated by the VM identifier column 0302 is deployed and the physical computer to be operated is the physical computer “P2” indicated by the physical computer identifier column 0601 of row 0612. judge.
- the deployment destination physical computer identifier 0303 in the row 0313 is “P1”, but the management program 0110 updates the deployment destination physical computer identifier 0303 to the identifier “P2”. Even when the deployment-destination physical computer identifier 0303 in the row 0313 is “null”, the identifier is updated to “P2”.
- Step S0706 is a case where the virtual machine scheduled for operation indicated by the VM identifier 0302 of the reservation information selected in step S0704 is assigned as a computer resource from the physical computer determined in step S0705 to the load indicated in the scheduled load column 0306.
- the placement score of the physical computer is recalculated, and the recalculated placement score is updated and registered in the placement score table 0600.
- the physical computer on which the virtual computer scheduled to operate is determined as “P2” determined in step S0705, and the reservation information selected in step S0704 is row 0313 of the reservation information table 0300.
- the value before the update of the arrangement score column 0602 in the row 0612 indicating the arrangement score of the physical computer “P2” is “7.0”
- the VM identifier column 0302 in the row 0313 is “ VM3 ”and the scheduled load column 0306 is“ 3.0 GB ”.
- the free capacity of the memory of the physical computer “P2” becomes 4.0 G (7.0 GB-3.0 GB) when the virtual computer “VM3” is newly allocated, and therefore the row 0612 of the arrangement score table 0600 The value of the arrangement score column 0602 is updated to 4.0G.
- Step S0707 is a termination step corresponding to S0703, which is the head of the repetition step.
- the management program 0110 repeatedly executes the above steps until step S0707 until all the reservation information extracted in step S0702 is referred to.
- the resource management program 0110 displays that the virtual computer related to the operation schedule cannot be allocated to the physical computer.
- the management program 0110 moves the physical computer identified by the identifier stored in the deployment destination physical computer column 0303 of the reservation information table 0300 as the deployment processing 0115 (FIG. 1).
- the virtual machine identified in the VM identifier column 0302 is deployed to the target physical computer at the time stored in the start time column 0304 of the reservation information table 0800C. Thereby, the optimal arrangement of the virtual machines scheduled to be operated is realized.
- the management server 0100 changes the identifier of the deployment destination physical computer column in the row 0313 of the reservation information table 0300 from the physical computer “P1” to the physical computer “
- the virtual machine “VM3” on the physical computer “P2” from May 5, 2010, from May 5, 2010 to September 1, 2010, Realize the optimal placement of virtual machines by making the free capacity of both the physical computer "P1” and the physical computer “P2” 4.0 GB and leveling the free capacity of multiple physical computers that make up the computer system To do.
- step S0703 to step S0707 in FIG. 7 determines the arrangement of virtual machines
- the order of determining the arrangement of virtual machines is n floors. There is a ride. Therefore, in the process of FIG. 7, the virtual machine layout determination process is executed with the virtual machine layout determination order fixed in one way. However, the processing of FIG. 7 repeatedly executes the virtual machine placement determination process in the order of m (m ⁇ n factorial), and all the physical in the placement of the virtual machine scheduled for operation determined in each order. You may change so that the arrangement
- the computer system in the above-described embodiment is currently operating load balance adjustment of a plurality of physical computers on which a plurality of virtual computers are mounted when determining an optimal arrangement of a plurality of virtual computers.
- the load balance of the entire system is optimized without repeating the optimal placement process of multiple virtual machines when the virtual machines that are scheduled to operate are actually operating Can be adjusted.
- the optimal placement processing of multiple virtual machines is performed without the migration of the operating virtual machines. In order to achieve this, an increase in the load on the network associated with the migration of virtual machines among a plurality of physical machines is prevented.
- the virtual machine When migrating a virtual machine that is installed and running on a physical machine between multiple physical machines, the virtual machine is transferred to the physical machine to which the virtual machine is migrated. Copying from a computer, the migration destination physical computer must create a new virtual computer based on the copied information, and stop the copy source virtual computer. At this time, if the storage information in the copy source memory is updated before the copy is completed, the migration source physical computer needs to copy the updated information to the migration destination physical computer again. Therefore, if the amount of information to be copied is large, it takes a long time to migrate the virtual machine. Since the computer system according to the above-described embodiment is not accompanied by migration of an operating virtual machine, such a problem is solved.
- the management server realizes the optimal placement of virtual machines, assuming that the virtual machines scheduled for operation can be mounted on all physical computers that make up the computer system. May be restricted. Such a physical computer can be registered on the reservation screen (FIG. 21). For virtual machines that need to be placed on a specific physical calculation on the reservation screen and do not want to be optimally placed, the management user registers the combination of this virtual machine and physical computer on the reservation screen. be able to.
- start timing of optimal placement of a plurality of virtual servers is periodically generated.
- this is a manual trigger, addition of reservation, change of reservation (start time, end time, load) ), Deleting a reservation, or deleting a virtual machine.
- the “certain period” is described as one month, but this is an example. If the “certain period” is long, the “optimal placement” will not be realized for a long time until the virtual machine scheduled to start operation starts. On the other hand, if this period is short, the virtual machine will be relocated frequently. Will have to be implemented. Therefore, the “certain period” is set within a reasonable range for the operation of the computer system.
- the management server sets a target value related to the load on each physical computer belonging to the computer system, and optimally arranges the virtual computers scheduled to operate. If the target value cannot be achieved simply by relocating the virtual machines that are in operation, that is, relocating the virtual machines that are in operation when the optimal placement of the virtual machines that are scheduled to operate is achieved. It is the point that tries to achieve the value. However, in the computer system according to this embodiment, the frequency and number of virtual computers in operation are reduced as much as possible as follows.
- FIGS. 8A to 8C show the physical computer information table 0800A (FIG. 8A), the VM information table 0800B (FIG. 8B), and the reservation information table 0800C (FIG. 8C) according to the second embodiment.
- FIG. 8 (C)) is shown.
- the physical computer information table 0800A has the same structure as the physical computer information table 0200 in the first embodiment.
- the VM information table 0800B has the same structure as the VM information table 0400 in the first embodiment.
- the reservation information table 0800C has the same structure as the reservation information table 0300 of the first embodiment.
- the data registered in the management table of the first embodiment may differ from the data registered in the management table shown in FIGS. 8A to 8C.
- FIG. 9 shows a flowchart of processing for optimally arranging virtual machines in a plurality of physical computers in the second embodiment.
- the resource management program 0110 shown in FIG. 1 executes the flowchart of FIG.
- the processing shown in FIG. 9 is based on the flowcharts of FIGS. 5 and 7 on the premise of the determined optimal arrangement of the virtual machines scheduled to be operated, and includes a plurality of existing virtual machines in the computer system. This is to determine whether or not the optimal arrangement of virtual machines can be maintained. If this determination is affirmed, the resource management program 0110 terminates the virtual machine placement process, and if this determination is negative, both the active virtual machine and the virtual machine that is scheduled to operate are both a plurality of physical computers. Change the placement for.
- the resource management program 0110 executes the optimum placement processing for the scheduled virtual machine to be operated according to step S0901 at an arbitrary time set by the user of the resource management server 0100.
- Step S0901 corresponds to the flowcharts of FIGS. 5 and 7 described above.
- step S0902 it is possible to improve the balance of the load among a plurality of physical computers by simply placing the virtual computer scheduled to be operated in the target physical computer, which is determined in step S0901. Determine if it can be achieved. If step S0902 affirms this determination, the process for optimal placement of virtual machines is terminated.
- the deployment process 0115 (FIG. 1) is stored in the VM identifier column 0302 in the physical computer identified by the identifier stored in the deployment destination physical computer column 0303 of the reservation information table 0800C (FIG. 8C).
- the reserved virtual machine identified by the identifier is set to the time stored in the start time column 0304.
- the process proceeds to step S0903.
- step S0701 in FIG. 7 within the “predetermined period” (eg, January) from the “scheduled time” (eg, 0:00 on May 1, 2010), the free memory capacity of each physical computer and all the physical computers The difference from the average value of the empty memory capacity is within 0.5 GB in all physical computers. Note that the states of the tables shown in FIGS. 8A to 8C are those after the execution of step S0901.
- the virtual computer “VM2” having a load of “2.0 GB” is operating, and within a certain period (one month) from the relocation time (00:00 on May 1, 2010).
- step S0903 is executed.
- Step S0903 executes arithmetic processing for determining an optimal arrangement of a plurality of virtual machines including a running virtual machine and a scheduled virtual machine. At this time, the number of active virtual machines to be migrated between a plurality of physical computers is reduced.
- the resource management program 0110 changes the identifier of the physical computer identifier 0402 in the VM information table 0800B to the identifier of the migration destination physical computer for the operating virtual computer to be migrated to another physical computer based on the calculation result. To do. Further, for the virtual computer scheduled to be operated, the identifier of the deployment destination physical computer 0303 in the reservation information table 0800C is changed to the identifier of the placement destination physical computer of the operation-scheduled virtual computer re-determined in step S0903. A detailed flowchart of step S0903 will be described with reference to FIG.
- FIG. 23 shows a management table corresponding to the arrangement form of a plurality of virtual machines obtained by the optimum arrangement process of the virtual machines.
- (A) is a physical computer configuration table
- (B) is a VM information table related to a virtual machine after optimal placement
- (C) is a reservation information table for a virtual machine reserved for operation after optimal placement. .
- VM3 currently operating virtual machine
- step S0904 it is determined whether or not to change the virtual machine arrangement in the computer system to the virtual machine arrangement determined in step S0903. That is, the management program 0100 compares the virtual machine layout determined in step S0901 with the virtual machine layout determined in step S0903, and the layout determined in step S0903 is targeted. Determine whether they are close. If the arrangement determined in step S0903 is closer to the optimal arrangement target of the virtual machine, the process proceeds to step S0905. If the arrangement determined in step S0901 is closer to the optimal arrangement target of the virtual machine, the process proceeds to step S0906. In step S0906, the arrangement of the virtual machines scheduled to operate and the arrangement of the operating virtual machines are returned to the state before execution of step S0903.
- step S0904 is aimed at "arrangement of a plurality of virtual machines in which the free capacity of the memory of all physical computers belonging to the computer system is leveled"
- the operating virtual machine determined in step S0901 The standard deviation of the free space of the memory for all the physical computers after the optimal allocation of the virtual machines scheduled to operate and the relocation of the operating virtual machines determined in step S0903 are allowed without relocation of the virtual machines.
- the standard deviation of the free capacity of the memory for all the physical computers in the state is compared, and if the latter is smaller than the former, the process proceeds to step S0905, and if vice versa, the process proceeds to S0906. If both are the same, move to either.
- step S0904 the management program 0110 compares the virtual machine layout determined in step S0901 with the virtual machine layout determined in step S0903, but is determined in step S0903. Similarly to step S0902, it may be determined whether or not the placement of the virtual machines has achieved the goal related to the optimum placement of the virtual machines.
- step S0905 the VM migration process 0113 (FIG. 1) of the resource management program 0110 is executed, and the running virtual machine is migrated so that the virtual machine arrangement determined in step S0903 is obtained.
- This migration process starts at the “relocation execution scheduled time” acquired in step S0701.
- step S0906 the physical computer identifier 0402 in the VM information table 0800B and the deployment destination physical computer identifier 0303 in the reservation information table 0800C changed in step S0903 are returned to the state before step S0903 is executed.
- FIG. 10 is a flowchart relating to processing for creating a plan for arranging the active virtual machine and the virtual machine scheduled to be operated on the physical computer in an optimal form, which is executed in step S0903 of FIG. This flowchart is executed by the resource management program 0110.
- Step S1001 determines a boundary condition, for example, “capacity condition” for each physical computer for realizing the optimal arrangement of the virtual machines.
- the “capacity condition” is an index related to the memory capacity of the physical computer that the resource management program 0110 considers when determining whether to change the arrangement of the virtual machines operating on each physical computer. .
- the resource management program 0110 aims to equalize the free capacity of each memory of a plurality of physical computers, and each physical computer within a certain period from the time when the relocation of the plurality of virtual computers is to be executed. Is set as a capacity condition that the free capacity is equal to or greater than the average value of the free capacity of all physical computers.
- the average of the free capacity of all physical computers within a certain period from the relocation execution time is 4.0 GB, so the capacity condition of each physical computer is “empty”.
- the capacity is 4.0 GB or more. If the operating virtual machine is not migrated, the resource management program determines the physical computer that is the migration destination of the operating virtual machine based on the placement score only when this condition is not satisfied.
- step S1002 the processing up to step S1009 is repeated until all the individual virtual machine information stored in the VM information table 0800B is referred to.
- step S1003 one piece of VM information to be referred to is selected.
- step S1004 the VM information of the active virtual machine whose arrangement has already been determined in the iterative processing steps S1002 to S1009 is used to calculate the load of the physical computer on which the virtual machine selected in step S1003 is operating. To do.
- step S1002 to step S1009 is executed twice, the arrangement of the virtual machine with the VM identifier “VM1” in the VM information table 0800B is the physical machine “P1”, and the arrangement of the virtual machine with the VM identifier “VM2” Is determined as the physical computer “P2”, and the identifiers “P1” and “P2” of the respective physical computers are stored in the physical computer identifier column 0402 of the VM information table 0800B.
- the operating virtual machine selected from the VM information table 0800B in step S1003 is assumed to be a virtual machine identified by the VM identifier “VM3”.
- the physical computer on which “VM3” operates is the physical computer “P1” identified in the physical computer identifier column 0413 in row 0413. It is determined that the virtual machine “VM1” is allocated to the physical machine “P1”, and the load is “2.0 GB” by referring to the load column 0403 in the row 0411 of the VM information table 0800B. Therefore, the load on the physical computer “P1” in step S1004 is 2.0 GB.
- step S1005 when the operating virtual machine selected in step S1003 is not transferred from the current physical computer to another physical computer, the load of the physical computer on which the selected virtual machine is currently operating is determined. In this step, it is determined whether or not the capacity condition set in step S1001 is satisfied. If the capacity condition is not satisfied, the process proceeds to step S1007, and if the capacity condition is satisfied, the process proceeds to step S1009.
- step S1001 “the free capacity of each physical computer is set to 4.0 GB or more” is set as the capacity condition, and the operating virtual machine selected from the VM information table 0800B in step S1003 has the VM identifier “VM3”.
- the total memory capacity of the physical computer “P1” in which “VM3” is installed is 6.0 GB as shown in the total memory capacity column 0202, and the virtual computer “VM3”
- the load is 1.0 GB according to the load column 0403 of the VM information table 0800B.
- the calculated load of the physical computer “P1” is 2.0 GB.
- step S1007 the placement score of a plurality of physical computers is determined using the load of the operating virtual computer whose placement with respect to the physical computer has already been determined by the repeated processing from step S1002 to step S1009.
- the concept of the arrangement score is the same as that in step S0504 in FIG.
- step S1008 based on the arrangement score calculated in step S1007, the virtual machine selected in step S1003 is migrated from the currently installed physical computer to determine another physical computer to be mounted, and the VM information
- the identifier of the other physical computer is stored in the physical computer identifier column 0402 of the row where the selected virtual computer exists in the table 0800B.
- the free space of the memory is used as the placement score of each physical computer.
- step S1007 the iterative processing from step S1002 to step S1009 has already been executed twice, and the virtual computer identified by the VM identifier “VM1” in the VM information table 0800B is the physical computer “P1”.
- the virtual machine identified by the VM identifier “VM2” is arranged in the physical computer “P2”, and these identifiers “P1” and “P2” are determined in the VM information table 0800B. It is assumed that it is stored in the physical computer identifier column 0402.
- the placement scores are 4.0 and 6.0, respectively.
- the arrangement of the virtual machine (VM3) selected in step S1003 is determined to be the physical machine “P2” having the highest arrangement score, and row 0413 indicating the virtual machine (VM3) in the VM information table 0800B is displayed.
- the identifier of the physical computer identifier column 0402 is changed and registered from “P1” to “P2”.
- step S1003 if the placement score of the physical computer on which the virtual computer selected in step S1003 is the largest, the virtual computer is not transferred to another computer. However, since the flowchart of FIG. 10 (S0903) is executed after the determination in step S0902 is denied, at least one operating virtual machine has the most margin in resource capacity from the currently operating computer. Migrated to a physical computer.
- Step S1009 is a termination step corresponding to S1002, which is the head of the repetition step. Until the resource management program S0110 refers to all the virtual machine information stored in the VM information table 0800B, S1002 to S1009 are repeatedly executed.
- Step S1010 is a step of rearranging virtual machines scheduled to be operated based on the arrangement of operating virtual machines determined in steps S1002 to S1009, and is the same as the flowchart of FIG.
- FIG. 22 is an input screen corresponding to step S0903 (flowchart in FIG. 10).
- step S0903 continues the optimum placement plan creation process.
- FIG. 22 shows that the virtual machine (VM1) that is operating on the physical computer (P1) is migrated to another physical computer (P2), and the virtual machine (VM3) that is scheduled to operate is the original scheduled physical computer (P1). It shows that the shift to the other physical computer (P3) is output as the optimum arrangement. The latter is the optimal arrangement determined in step S1010.
- FIG. 10 shows an example of a method for simultaneously determining the optimal arrangement of the virtual machines that are in operation and the optimal arrangement of the virtual machines that are scheduled to operate.
- the placement order of the placement includes n levels. There is a ride.
- FIG. 10 has been described assuming that the order for determining the placement of virtual machines is one, but the resource management program 0110 examines the placement pattern of virtual machines in the order of m ways (m ⁇ n factorial). However, the arrangement of the patterns with the smallest standard deviation of the free capacity of all the physical computers may be the optimum arrangement.
- the resource management program 0110 determines the arrangement of virtual machines scheduled to operate in order to realize the optimal arrangement of virtual machines at regular intervals from the scheduled time.
- the target in the optimal arrangement of a plurality of virtual machines including the computer cannot be achieved, the optimum arrangement of the plurality of virtual machines as a whole is realized by shifting the operating virtual machines.
- the resource management program 0110 reduces the frequency and the number of times the operating virtual machine is migrated by changing the arrangement of the operating virtual machine when the capacity condition described above is not satisfied. As a result, the resource management program reduces the time required for migration of the virtual machines that must be migrated, and stably maintains the performance of the plurality of virtual machines in the computer system.
- the resource management program can also place restrictions on physical computers to which virtual computers that are in operation and / or scheduled to operate are migrated.
- the resource management program calculates the standard deviation of the free capacity of all physical computers and the number of virtual computers to be migrated for all combinations of multiple virtual machines that are in operation and planned to be operated. Optimize the virtual machine by adopting an arrangement that minimizes the number of virtual machines that should be migrated from the currently running physical machine to another physical machine and that minimizes the standard deviation of the placement score. An arrangement may be realized.
- the virtual machine that has already been operating for a certain period from the time when the operation of the scheduled virtual machine starts and the virtual machine that has started operating during this period are not terminated, interrupted, or stopped.
- the operation of the active computer may end during this period, and the optimum arrangement of a plurality of virtual computers including the operation scheduled computer is determined in consideration of this.
- the resource management server 0110 determines not only the operation start time of the virtual machine but also the operation end time as elements for determining the optimum arrangement, and determines the arrangement of the virtual machines scheduled to operate.
- the resource management program determines the placement of multiple virtual machines scheduled for operation in the order of the start time of operation, and when determining the placement of a virtual machine scheduled for operation, starts the operation of the virtual machine scheduled for operation. If there is a virtual machine that terminates operation before the time, the corresponding load is subtracted from the physical computer load, and the actual value of the physical computer load immediately before the operation start time of the scheduled virtual machine is calculated. Based on the calculated load of each physical computer, the arrangement of the virtual computers that are scheduled to operate is determined.
- the third embodiment will be described based on a flowchart. Also in this embodiment, as an index for optimally allocating a virtual computer to a physical computer, the virtual computer is allocated so that the free capacities of a plurality of physical computers in the computer system are leveled.
- the third embodiment differs from the previous two embodiments in that the processing in the third embodiment reconfigures the arrangement of a plurality of virtual machines in consideration of the end time of the scheduled virtual machine. It is.
- FIG. 11A shows a physical computer information table 1100A according to this embodiment
- FIG. 11B shows a VM information table 1100B
- FIG. 11C shows a reservation information table 1100C.
- the configuration of the table excluding the reservation information table is the same as that of the above-described embodiment.
- This reservation information table is different from the reservation information table of the above-described embodiment in that an operation status column 0307 is provided.
- the operating status column 0307 stores an identifier indicating the operating status of the virtual machine identified in the VM identifier column 0302 in each row of the reservation information table 1100C.
- operation status There are two types of operation status: “operation” and “stop”. “Operating” indicates a state in which the virtual computer is operated on the physical computer by the reservation. “Stop” indicates that the virtual machine is not operated on the physical computer by the reservation.
- operation status column 0307 For the row in which “operation” is stored in the operation status column 0307, the virtual machine identifier stored in the VM identifier column 0302 always exists in the VM identifier column 0401 of the VM information table 1100B.
- the row 0311 of the reservation information table 1100C in FIG. 11 includes the VM information table 1100B.
- the VM identifier column 0401 there is a row 0411 in which the identifier “VM1” is stored. If the virtual machine is operating but not operating due to the reservation, “stopped” is stored in the operating status column 0307. For example, in row 0316 of the reservation information table 1100C in FIG.
- the identifier “VM1” of the operating virtual machine is stored in the VM identifier column 0302, but the virtual machine “VM1” is not row 0316, but row 0311 Since it is operating according to the reservation shown, “stop” is stored in the operation status column 0307 of the row 0316.
- FIG. 12 is a flowchart for determining the optimal arrangement of the virtual machines scheduled to operate in the third embodiment. This is executed by the resource management program 0110.
- the resource management program 0110 executes step S1201 at an arbitrary time.
- the arbitrary time is, for example, the time set by the user in the resource management server 0100.
- Step S1201 is the same processing as the processing from step S0501 to step S0505 in the flowchart of FIG.
- the resource management program 0110 calculates the placement score of each physical computer from the load of the operating virtual computer and the total memory capacity of the physical computer, and records it in the placement score table 0600 of FIG.
- Step S1202 is the same process as step S0701 of FIG.
- Step S1203 is the same process as step S0702 of the flowchart of FIG.
- step S1204 the reservation information extracted in step S1203 is sorted in ascending order by start time.
- Step S1205 sets the current time as an initial value of time information (hereinafter referred to as time information) recorded in a predetermined area of the management server memory 0102.
- time information time information
- step S1206 the processing from step S1207 to step S1219 is repeatedly performed until all the reservation information extracted in step S1203 is referred to.
- step S1207 one piece of extracted reservation information is selected.
- step S1208 the reservation information table 1100C is referred to, and all the reservation information whose operation ends during the period of the start time of the reservation information selected from the time information is extracted. For example, when the time information is 0:00 on May 1, 2010 and the reservation information selected in step S1207 is row 0313, the start time column 0304 of row 0313 is May 10, 2010, so step S1208 Extracts the row 0312 whose end time column 0305 is May 5, 2010.
- step S1209 the processing up to step S1214 is repeated until all the reservation information extracted in step S1208 is referred to.
- step S1210 one piece of reservation information extracted in step S1208 is selected.
- step S1211 it is determined whether the reservation information selected in step S1210 is the reservation information of the operating virtual machine or the reservation information of the virtual machine scheduled to be operated. In the case of an operating virtual machine, the process proceeds to step S1212. In the case of a virtual machine scheduled to operate, the process proceeds to step S1213. Specifically, if the identifier stored in the operation status column 0307 of the reservation information selected in step S1210 is “operation”, the process proceeds to step S1212, and if it is “stop”, the process proceeds to step S1213. .
- Step S1212 updates the placement score table 0600 of FIG. 6 based on the load of the operating virtual machine identified by the VM identifier column 0302 of the reservation information selected in Step S1210. Specifically, a row in which the VM identifier 0401 matches the identifier stored in the VM identifier column 0302 of the reservation information selected in step S1210 is extracted from the VM information table 1100B. The physical computer placement score when the load of the virtual machine stored in the extracted row load column 0403 is removed from the load of the physical computer identified by the identifier stored in the physical computer identifier column 0402 of that row. Recalculation is performed, and the placement score is updated and registered in the placement score table 0600.
- the placement score is defined as the free capacity of each physical computer and the reservation information selected in step S1210 is row 0312 of the reservation information table 1100C
- the reservation target virtual computer is stored in the column 0302 of 0312.
- the virtual machine with the identifier “VM2” is based on the VM information table 1100B, and the line whose VM identifier column 0401 is “VM2” is 0412.
- the load column 0403 in the row 0412 of the VM information table 1100B is “1.0 GB”
- the physical computer identifier 0402 is “P2”
- “P2” is stored in the physical computer identifier column 0601 of the arrangement score table shown in FIG.
- the row that has been set is row 0612
- the placement score column 0602 of row 0612 is “7.0”.
- the free memory capacity of the physical computer P2 is 7.0 GB.
- the load “1.0 GB” of the VM 12 indicated by the row 0412 is removed from the load of the physical computer P2
- the actual free capacity of the physical computer P2 is 8.0 GB. Therefore, 8.0 is stored in the placement score column 0602 of the row 0612 of the placement score table 0600.
- Step S1213 updates the arrangement score table 0600 of FIG. 6 based on the load stored in the scheduled load column 0306 of the reservation information selected in Step S1210. Specifically, in step S1210, the load stored in the scheduled load column 0306 of the selected reservation information is removed from the load of the physical computer identified by the identifier stored in the deployment destination physical computer column 0303. The placement score of the physical computer is calculated, and the placement score is stored in the placement score table 0600.
- the resource management program 0110 defines the placement score as the free capacity of the memory of each physical computer
- the reservation information selected in step S1210 is row 0314 in the reservation information table 1100C
- the scheduled load column 0306 in row 0314 is “1.0 GB”
- the deployment destination physical computer column 0402 is “P1”
- the row in which “P1” is stored in the physical computer identifier column 0601 of the placement score table shown in FIG. 4.0 is stored in the arrangement score column 0602 of the row 0611.
- step S1213 when the free capacity of the memory of the physical computer P1 is 4.0 GB and the planned load “1.0 GB” of the VM indicated by the row 0314 is removed from the load of the physical computer P1, the free space of the physical computer P2 Since the capacity is 5.0 GB, 5.0 is stored in the placement score column 0602 of the row 0611 of the placement score table 0600.
- Step S1214 is a termination step corresponding to S1209 which is the head of the repetition step. The above-described steps are repeatedly executed until all the reservation information extracted in step S1208 is referred to.
- step S1215 and S1217 The processing in steps S1215 and S1217 is the same as the processing in steps S0705 and S0706 described with reference to FIG.
- step S1218 the time stored in the start time column 0304 of the reservation information selected in step S1207 is overwritten and recorded in the memory initialized in step S1205.
- step S1219 is a termination step corresponding to S1206 which is the head of the return step, and the above-described steps are repeatedly executed until all the reservation information extracted in step S1203 is referred to.
- the load of each physical computer between the start time and the end time of the selected reservation information is set to the planned load and start time of the virtual machine that is in operation and the virtual machine that is scheduled to be operated first.
- the placement score of each physical computer it is not necessary to determine the placement of the operation-scheduled virtual computer from the earliest start time.
- the resource management program selects a virtual machine scheduled for operation and decides the placement, it determines the operation period of the selected virtual machine from the load of the virtual machine that is operating in the operation period of the selected virtual machine. Calculate the load on each physical computer and determine the placement of the selected virtual machine to be operated based on the calculated load on each physical machine, so that the virtual machine that is currently operating or the virtual machine that is scheduled to operate is relocated. Even when the operation is terminated within a certain period from the time, it is possible to determine the optimal arrangement of the virtual machines scheduled to operate.
- FIG. 13A to FIG. 13C show that the resource management program 0110 does not need to consider the end time of the operating virtual machine when determining the placement of the virtual machine to be operated.
- the management table includes a physical computer information table 0800A (FIG. 13A), a VM information table 0800B (FIG. 13B), and a reservation information table 0800C (FIG. 13C).
- FIG. 14 is a graph showing the displacement of the load on the virtual machine with respect to the total memory capacity of the physical server (P3).
- the virtual machine (VM10) that was scheduled to operate is already operating on the physical server (P3) at the current time (March 1, 2010), and the current time is one month from the current time.
- the virtual machine (VM11) and the virtual machine (VM12) continue to operate in the physical server (P3), and during that time, the three virtual machines (VM10, VM11, VM 12) does not finish operation. Therefore, when the resource management program 0110 determines the placement of the virtual machines (VM11, VM12) to be operated on the physical server (P3) at the current time and operates these virtual machines, the physical computer (P3) has already been used. It is not necessary to reduce the load of the virtual machines already arranged in the total capacity of the physical computer (P3) memory.
- FIG. 15 is a modification of the reservation information table according to FIG. According to the reservation information table of FIG. 15, within one month from the current time (March 1, 2010), the virtual machine (VM10) and the virtual machine (VM11) are temporarily placed on the physical machine (P3). However, the operation will be completed by April 1, 2010. Therefore, the actual planned load of the virtual machine arranged in the physical computer (P3) during this period is the value of the planned load of the virtual machine (VM11) (FIG. 16). Therefore, when the resource management program 0110 calculates the above-described placement score of the physical computer (P3), it must be based on the planned load value of the physical computer (P3).
- the virtual machine load is not present in the physical machine (P3), as shown in FIG.
- the placement score is based on these accumulations and is accumulated in the load of the computer (VM12), and the management program has no allowance even though the capacity of the physical computer (P3) has an allowance.
- the placement destination of the virtual machine (VM11) and / or the virtual machine (VM12) is determined by another physical machine, and there is a possibility that the objective of the optimum placement of the virtual machine scheduled to operate cannot be achieved.
- FIGS. 18-20 are other examples of FIGS. 15-17.
- FIG. 18 is a reservation information table
- FIG. 19 shows the load displacement of the virtual machine in the physical computer (P3) when the end of the operation of the virtual machine is considered
- FIG. 20 shows the end of the operation of the virtual machine This shows the displacement of the load of the virtual computer in the physical computer (P3) when the above is not considered.
- This example is different from the previous example in FIG. 19 in that the maximum value of the planned load between the current time (March 1, 2010) and a certain period (January) is the virtual machine (VM10) and virtual When the operating periods of the computer (VM 11) partially overlap, they are added values.
- the management user can also specify a physical server on which a virtual machine scheduled to operate is to be deployed. For example, if a virtual machine is deployed on a special physical server and you want to run the virtual machine on that physical server, the management user specifies the physical server where the virtual machine is to be placed, and the virtual machine is not subject to relocation If you want to limit a certain virtual machine to move only between specific physical machines, the management user specifies the range of the virtual machines where the virtual machines are to be placed, and determines the placement destination when the virtual machines are optimally placed. The placement of virtual machines is determined within the range of physical machines specified at times.
- the management user can also set restrictions on the placement of the virtual machine. For example, when operating a specified virtual machine on the same physical computer, operating a specified virtual machine on a different physical computer, a physical computer with a network distance as close as possible to the specified virtual machines For example.
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)
- Stored Programmes (AREA)
Abstract
Description
VM識別子欄0302の識別子で識別される仮想計算機のディスクイメージが未作成の場合は、リソース管理プログラム0110は、適当な固有の識別子を格納し、仮想計算機のディスクイメージが作成された時点で格納した識別子を仮想計算機の識別子とする。
ステップS0705は、図6に示す配置スコアテーブル0600に基づいて稼働予定の仮想計算機の配置を決定し、その結果に基づいて予約情報テーブルの配備先物理計算機欄を更新する。具体的には、ステップS0703で選択した予約情報の配備先物理計算機欄の識別子を、配置スコアテーブル0600で最もスコアの大きい物理計算機の識別子になるように予約情報テーブルを更新する。
また、仮想計算機が稼動していても当該予約による稼動でない場合は稼動状況欄0307には「停止」が格納される。例えば、図11の予約情報テーブル1100Cの行0316は、VM識別子欄0302に稼働中の仮想計算機の識別子「VM1」が格納されているが、仮想計算機「VM1」は行0316ではなく、行0311が示す予約によって稼動しているため、行0316の稼動状況欄0307には「停止」が格納される。
Claims (11)
- 複数の物理計算機と、
当該複数の物理計算機とネットワークを介して接続し、前記複数の物理計算機に対する複数の仮想計算機の配置を管理する管理計算機と、
を備える計算機システムであって、
前記管理計算機は、
仮想計算機を稼働させる予定情報から、稼働が予定される前記仮想計算機を決定し、
一つ又は複数の前記物理計算機に既に配置されて稼働している稼働中の仮想計算機に関する負荷に基づいて、
前記稼働が予定されている仮想計算機を配置すべき物理計算機を、当該仮想計算機の稼働前に、前記複数の物理計算機の中から決定する、
計算機システム。 - 前記管理計算機は、稼働中の仮想計算機に関する負荷を、
前記複数の物理計算機の夫々が仮想計算機に割当て可能なリソースの総量から、稼働している仮想計算機に割当てられたリソース量を減じた値から算出する、請求項1記載の計算機システム。 - 前記管理計算機は、前記稼働することが予定されている仮想計算機が登録された管理テーブルを備え、
前記管理テーブルは、当該仮想計算機が稼働を開始する時刻の情報と終了する時刻の情報とを備え、
前記管理計算機は、予定時刻から規定期間内に前記開始する時刻が存在する前記稼働することが予定される仮想計算機を前記管理テーブルから抽出し、当該抽出した仮想計算機を配置すべき前記物理計算機を決定する、請求項1記載の計算機システム。 - 前記管理計算機は、前記複数の物理計算機の何れかで稼働中の仮想計算機を他の物理計算機に移行することなく、前記稼働が予定されている仮想計算機を前記複数の物理計算機の中から決定する、請求項1記載の計算機システム。
- 前記管理テーブルは、前記稼働することが予定されている仮想計算機の配置先物理計算機の情報を含み、
前記管理計算機は、前記稼働予定されている仮想計算機を配置すべきとして決定された物理計算機が前記管理テーブルに含まれた配置先物理計算機と異なる場合には、前記決定された物理計算機の情報を前記管理テーブルに更新登録する、請求項1記載の計算機システム。 - 前記管理計算機は、前記複数の物理計算機の何れかで稼働中の仮想計算機を他の物理計算機に移行しながら、前記稼働が予定されている仮想計算機を前記複数の物理計算機の中から決定する、請求項1記載の計算機システム。
- 前記管理計算機は、
前記稼働が予定されている仮想計算機を配置すべき物理計算機を決定後、前記稼働が予定されている仮想計算機に関する負荷と、前記複数の物理計算機の少なくとも一つで稼働している他の仮想計算機に関する負荷と、が目標値を達成しているか否かを判定し、
当該判定を否定する場合には、前記複数の物理計算機の少なくとも一つで稼働している、前記複数の仮想計算機の少なくとも一つの仮想計算機を他の物理計算機に移行し、前記判定を肯定する場合には、当該移行を行うことなく、前記複数の仮想計算機の前記複数の物理計算機に対する配置を決定する、請求項
6記載の計算機システム。 - 前記管理計算機は、前記他の物理計算機を、前記複数の物理計算機の中で、前記少なくとも一つの仮想計算機に割当てることができるリソース量が最も大きい物理計算機とする、請求項7記載の計算機システム。
- 前記管理計算機は、稼働が予定されている仮想計算機が配置される目標物理計算機を決定する際、当該仮想計算機の稼働開始前に稼働した後稼働を終了する仮想計算機が前記目標物理計算機に配置されている場合、当該仮想計算機に関する負荷を前記目標物理計算機のリソース量から減じることなく、前記目標物理計算機を前記複数の物理計算機の中か決定する、請求項1記載の計算機システム。
- 前記管理計算機は、稼働中の仮想計算機に関する負荷を、前記複数の物理計算機の夫々が仮想計算機に割当て可能なリソースの総量から、稼働している仮想計算機に割当てられたリソース量を減じた値から算出し、
前記稼働することが予定されている仮想計算機が登録された管理テーブルを備え、
前記管理テーブルは、当該仮想計算機が稼働を開始する時刻の情報と終了する時刻の情報と、
前記管理計算機は、さらに、予定時刻から規定期間内に前記開始する時刻が存在する前記稼働することが予定される仮想計算機を前記管理テーブルから抽出し、当該抽出した仮想計算機を配置すべき前記物理計算機を決定し、
前記管理テーブルは、前記稼働することが予定されている仮想計算機の配置先物理計算機の情報を含み、
前記管理計算機は、さらに、
前記稼働予定されている仮想計算機を配置すべきとして決定された物理計算機が前記管理テーブルに含まれた配置先物理計算機と異なる場合には、前記決定された物理計算機の情報を前記管理テーブルに更新登録し、
前記複数の物理計算機の何れかで稼働中の仮想計算機を他の物理計算機に移行しながら、前記稼働が予定されている仮想計算機を前記複数の物理計算機の中から決定し、
前記稼働が予定されている仮想計算機を配置すべき物理計算機を決定後、前記稼働が予定されている仮想計算機に関する負荷と、前記複数の物理計算機の少なくとも一つで稼働している他の仮想計算機に関する負荷と、が目標値を達成しているか否かを判定し、
当該判定を否定する場合には、前記複数の物理計算機の少なくとも一つで稼働している、前記複数の仮想計算機の少なくとも一つの仮想計算機を他の物理計算機に移行し、前記判定を肯定する場合には、当該移行を行うことなく、前記複数の仮想計算機の前記複数の物理計算機に対する配置を決定し、
前記他の物理計算機を、前記複数の物理計算機の中で、前記少なくとも一つの仮想計算機に割当てることができるリソース量が最も大きい物理計算機とし、
稼働が予定されている仮想計算機が配置される目標物理計算機を決定する際、当該仮想計算機の稼働開始前に稼働した後稼働を終了する仮想計算機が前記目標物理計算機に配置されている場合、当該仮想計算機に関する負荷を前記目標物理計算機のリソース量から減じることなく、前記目標物理計算機を前記複数の物理計算機の中か決定する、請求項1記載の計算機システム。 - 複数の物理計算機と、
当該複数の物理計算機とネットワークを介して接続し、前記複数の物理計算機に対する複数の仮想計算機の配置を管理する管理計算機と、
を備える計算機システムの仮想計算機の最適配置方法において、
前記管理計算機は、
仮想計算機を稼働させる予定情報から、稼働が予定される前記仮想計算機を決定し、
一つ又は複数の前記物理計算機に既に配置されて稼働している稼働中の仮想計算機に関する負荷に基づいて、
前記稼働が予定されている仮想計算機を配置すべき物理計算機を、当該仮想計算機の稼働前に、前記複数の物理計算機の中から決定する、
計算機システムの仮想計算機の最適配置方法。
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US13/991,274 US20130339956A1 (en) | 2011-03-03 | 2011-03-03 | Computer system and optimal arrangement method of virtual machine in computer system |
JP2013502047A JP5412599B2 (ja) | 2011-03-03 | 2011-03-03 | 計算機システム、および、計算機システムにおける仮想計算機の最適配置方法 |
PCT/JP2011/001271 WO2012117453A1 (ja) | 2011-03-03 | 2011-03-03 | 計算機システム、および、計算機システムにおける仮想計算機の最適配置方法 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/JP2011/001271 WO2012117453A1 (ja) | 2011-03-03 | 2011-03-03 | 計算機システム、および、計算機システムにおける仮想計算機の最適配置方法 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2012117453A1 true WO2012117453A1 (ja) | 2012-09-07 |
Family
ID=46757426
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2011/001271 WO2012117453A1 (ja) | 2011-03-03 | 2011-03-03 | 計算機システム、および、計算機システムにおける仮想計算機の最適配置方法 |
Country Status (3)
Country | Link |
---|---|
US (1) | US20130339956A1 (ja) |
JP (1) | JP5412599B2 (ja) |
WO (1) | WO2012117453A1 (ja) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2013152622A (ja) * | 2012-01-25 | 2013-08-08 | Ntt Data Corp | 仮想マシン配置装置、仮想マシン配置方法 |
JP2014197356A (ja) * | 2013-03-29 | 2014-10-16 | 新日鉄住金ソリューションズ株式会社 | 管理サーバ装置、情報処理方法及びプログラム |
JP2015022321A (ja) * | 2013-07-16 | 2015-02-02 | 日本電気株式会社 | 仮想マシン管理装置、仮想マシン管理方法、及びプログラム |
JP2016110248A (ja) * | 2014-12-03 | 2016-06-20 | 日本電信電話株式会社 | 仮想化実行装置、仮想化システム、および、リソース最適化方法 |
JP2016186712A (ja) * | 2015-03-27 | 2016-10-27 | 日本電気株式会社 | システム |
JP2016186713A (ja) * | 2015-03-27 | 2016-10-27 | 日本電気株式会社 | システム |
WO2017002921A1 (ja) * | 2015-06-30 | 2017-01-05 | 日本電気株式会社 | 仮想ネットワークファンクション管理装置、仮想マシン管理装置、仮想ネットワークファンクションへの資源の割り当て方法及びプログラム |
JP2017062734A (ja) * | 2015-09-25 | 2017-03-30 | ビッグローブ株式会社 | ストレージ管理装置、ストレージ管理方法、及び、プログラム |
US10158526B2 (en) | 2015-03-27 | 2018-12-18 | Nec Corporation | System that manages server function |
Families Citing this family (41)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102959506B (zh) | 2010-06-22 | 2017-04-26 | 慧与发展有限责任合伙企业 | 用于计划应用部署的方法和系统 |
JP5766346B2 (ja) * | 2011-04-07 | 2015-08-19 | ヒューレット−パッカード デベロップメント カンパニー エル.ピー.Hewlett‐Packard Development Company, L.P. | ソフトウェア・オブジェクトをバックグラウンドで移動させる方法及び装置 |
CN103827823A (zh) * | 2011-07-29 | 2014-05-28 | 惠普发展公司,有限责任合伙企业 | 迁移虚拟机 |
US8949431B2 (en) * | 2011-08-24 | 2015-02-03 | Radware, Ltd. | Method for live migration of virtual machines |
JP5725191B2 (ja) * | 2011-09-22 | 2015-05-27 | 富士通株式会社 | 電源管理装置、電源管理方法および電源管理プログラム |
US9137130B2 (en) * | 2011-09-22 | 2015-09-15 | Sap Se | Dynamic network load forecasting |
TW201324357A (zh) * | 2011-12-01 | 2013-06-16 | Univ Tunghai | 虛擬機叢集之綠能管理方法 |
JP5862359B2 (ja) * | 2012-02-23 | 2016-02-16 | 日本電気株式会社 | シンクライアントシステム、接続管理サーバ、接続管理方法、及び接続管理プログラム |
CN102724277B (zh) * | 2012-05-04 | 2016-01-06 | 华为技术有限公司 | 虚拟机热迁移和部署的方法、服务器及集群系统 |
WO2013190649A1 (ja) * | 2012-06-20 | 2013-12-27 | 富士通株式会社 | 仮想ディスクのマイグレーションに関する情報処理方法及び装置 |
US8966495B2 (en) * | 2012-09-05 | 2015-02-24 | Cisco Technology, Inc. | Dynamic virtual machine consolidation |
US9223608B2 (en) | 2012-12-14 | 2015-12-29 | Vmware, Inc. | Systems and methods for finding solutions in distributed load balancing |
US9582219B2 (en) | 2013-03-12 | 2017-02-28 | Netapp, Inc. | Technique for rapidly converting between storage representations in a virtualized computing environment |
EP2979180B1 (en) * | 2013-03-27 | 2019-10-30 | Keysight Technologies Singapore (Sales) Pte. Ltd. | Methods, systems, and computer readable media for emulating virtualization resources |
US10425481B2 (en) * | 2013-05-13 | 2019-09-24 | Telefonaktiebolaget Lm Ericsson (Publ) | Node in a telecommunications network, a virtual network element and methods for retrieving resource identification information |
US9384059B2 (en) * | 2013-05-31 | 2016-07-05 | Hitachi, Ltd. | Comparing resource costs between allocation plans in a load balance apparatus |
US9851988B1 (en) * | 2013-09-04 | 2017-12-26 | Amazon Technologies, Inc. | Recommending computer sizes for automatically scalable computer groups |
US11663025B2 (en) * | 2013-09-23 | 2023-05-30 | Bankvault Pty Ltd | Maintenance of and caching of suspended virtual computers in a pool of suspended virtual computers |
US9710308B1 (en) * | 2013-12-24 | 2017-07-18 | EMC IP Holding Company LLC | Workflow for migration planning of data storage systems |
JP6287321B2 (ja) * | 2014-02-24 | 2018-03-07 | 富士通株式会社 | 情報処理装置、情報処理方法、および情報処理プログラム |
US9948493B2 (en) * | 2014-04-03 | 2018-04-17 | Centurylink Intellectual Property Llc | Network functions virtualization interconnection gateway |
US10216531B2 (en) | 2014-05-12 | 2019-02-26 | Netapp, Inc. | Techniques for virtual machine shifting |
US9841991B2 (en) * | 2014-05-12 | 2017-12-12 | Netapp, Inc. | Techniques for virtual machine migration |
US10642635B2 (en) * | 2014-06-07 | 2020-05-05 | Vmware, Inc. | Decentralized demand-based virtual machine migration management |
US9678793B2 (en) * | 2015-02-26 | 2017-06-13 | International Business Machines Corporation | Resource-based job scheduling |
JP6477097B2 (ja) * | 2015-03-20 | 2019-03-06 | 富士通株式会社 | 情報処理プログラム、情報処理方法、および情報処理装置 |
US10210079B2 (en) | 2015-04-09 | 2019-02-19 | Sungard Availability Services, Lp | Touch free disaster recovery |
US9836365B2 (en) | 2015-04-09 | 2017-12-05 | Sungard Availability Services, Lp | Recovery execution system using programmatic generation of actionable workflows |
US9727374B2 (en) | 2015-04-21 | 2017-08-08 | International Business Machines Corporation | Temporary virtual machine migration for improved software application warmup |
US9727366B2 (en) * | 2015-04-23 | 2017-08-08 | International Business Machines Corporation | Machine learning for virtual machine migration plan generation |
JP2016224582A (ja) * | 2015-05-28 | 2016-12-28 | 富士通株式会社 | 制御方法、制御装置、及び制御プログラム |
US9946564B2 (en) * | 2015-06-23 | 2018-04-17 | International Business Machines Corporation | Adjusting virtual machine migration plans based on alert conditions related to future migrations |
CA3000952A1 (en) * | 2015-10-14 | 2017-04-20 | Sungard Availability Services, Lp | Automatic system disaster recovery |
US9710305B2 (en) * | 2015-11-12 | 2017-07-18 | International Business Machines Corporation | Virtual machine migration management |
US10395219B1 (en) * | 2015-12-18 | 2019-08-27 | Amazon Technologies, Inc. | Location policies for reserved virtual machine instances |
US10341215B2 (en) | 2016-04-06 | 2019-07-02 | Keysight Technologies Singapore (Sales) Pte. Ltd. | Methods, systems, and computer readable media for emulating network traffic patterns on a virtual machine |
US9817592B1 (en) | 2016-04-27 | 2017-11-14 | Netapp, Inc. | Using an intermediate virtual disk format for virtual disk conversion |
JP2018060378A (ja) * | 2016-10-05 | 2018-04-12 | 富士通株式会社 | 起動制御プログラム、起動制御方法及び起動制御装置 |
JP6969282B2 (ja) * | 2017-10-25 | 2021-11-24 | 富士通株式会社 | 情報処理装置、情報処理システムおよび情報処理方法 |
US11323354B1 (en) | 2020-10-09 | 2022-05-03 | Keysight Technologies, Inc. | Methods, systems, and computer readable media for network testing using switch emulation |
US11483227B2 (en) | 2020-10-13 | 2022-10-25 | Keysight Technologies, Inc. | Methods, systems and computer readable media for active queue management |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2007136021A1 (ja) * | 2006-05-24 | 2007-11-29 | Nec Corporation | 仮想マシン管理装置、仮想マシン管理方法およびプログラム |
JP2010224756A (ja) * | 2009-03-23 | 2010-10-07 | Nec Corp | 仮想マシン再配置システム、方法、プログラム、及び仮想マシン管理装置 |
WO2010122709A1 (ja) * | 2009-04-23 | 2010-10-28 | 日本電気株式会社 | 若化処理装置、若化処理システム、コンピュータプログラムおよびデータ処理方法 |
WO2010140183A1 (ja) * | 2009-06-01 | 2010-12-09 | 富士通株式会社 | サーバ管理プログラム、管理サーバ、仮想サーバ配置方法 |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070271560A1 (en) * | 2006-05-18 | 2007-11-22 | Microsoft Corporation | Deploying virtual machine to host based on workload characterizations |
US8336094B2 (en) * | 2008-03-27 | 2012-12-18 | Juniper Networks, Inc. | Hierarchical firewalls |
JP5544967B2 (ja) * | 2010-03-24 | 2014-07-09 | 富士通株式会社 | 仮想マシン管理プログラム及び仮想マシン管理装置 |
US9563479B2 (en) * | 2010-11-30 | 2017-02-07 | Red Hat, Inc. | Brokering optimized resource supply costs in host cloud-based network using predictive workloads |
-
2011
- 2011-03-03 WO PCT/JP2011/001271 patent/WO2012117453A1/ja active Application Filing
- 2011-03-03 US US13/991,274 patent/US20130339956A1/en not_active Abandoned
- 2011-03-03 JP JP2013502047A patent/JP5412599B2/ja active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2007136021A1 (ja) * | 2006-05-24 | 2007-11-29 | Nec Corporation | 仮想マシン管理装置、仮想マシン管理方法およびプログラム |
JP2010224756A (ja) * | 2009-03-23 | 2010-10-07 | Nec Corp | 仮想マシン再配置システム、方法、プログラム、及び仮想マシン管理装置 |
WO2010122709A1 (ja) * | 2009-04-23 | 2010-10-28 | 日本電気株式会社 | 若化処理装置、若化処理システム、コンピュータプログラムおよびデータ処理方法 |
WO2010140183A1 (ja) * | 2009-06-01 | 2010-12-09 | 富士通株式会社 | サーバ管理プログラム、管理サーバ、仮想サーバ配置方法 |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2013152622A (ja) * | 2012-01-25 | 2013-08-08 | Ntt Data Corp | 仮想マシン配置装置、仮想マシン配置方法 |
JP2014197356A (ja) * | 2013-03-29 | 2014-10-16 | 新日鉄住金ソリューションズ株式会社 | 管理サーバ装置、情報処理方法及びプログラム |
JP2015022321A (ja) * | 2013-07-16 | 2015-02-02 | 日本電気株式会社 | 仮想マシン管理装置、仮想マシン管理方法、及びプログラム |
JP2016110248A (ja) * | 2014-12-03 | 2016-06-20 | 日本電信電話株式会社 | 仮想化実行装置、仮想化システム、および、リソース最適化方法 |
JP2016186712A (ja) * | 2015-03-27 | 2016-10-27 | 日本電気株式会社 | システム |
JP2016186713A (ja) * | 2015-03-27 | 2016-10-27 | 日本電気株式会社 | システム |
US10158526B2 (en) | 2015-03-27 | 2018-12-18 | Nec Corporation | System that manages server function |
WO2017002921A1 (ja) * | 2015-06-30 | 2017-01-05 | 日本電気株式会社 | 仮想ネットワークファンクション管理装置、仮想マシン管理装置、仮想ネットワークファンクションへの資源の割り当て方法及びプログラム |
JPWO2017002921A1 (ja) * | 2015-06-30 | 2018-04-26 | 日本電気株式会社 | 仮想ネットワークファンクション管理装置、仮想マシン管理装置、仮想ネットワークファンクションへの資源の割り当て方法及びプログラム |
US10846119B2 (en) | 2015-06-30 | 2020-11-24 | Nec Corporation | Virtualized network function management apparatus, virtual machine management apparatus, method for allocating resources to virtual network function, and program |
JP2017062734A (ja) * | 2015-09-25 | 2017-03-30 | ビッグローブ株式会社 | ストレージ管理装置、ストレージ管理方法、及び、プログラム |
Also Published As
Publication number | Publication date |
---|---|
JP5412599B2 (ja) | 2014-02-12 |
US20130339956A1 (en) | 2013-12-19 |
JPWO2012117453A1 (ja) | 2014-07-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP5412599B2 (ja) | 計算機システム、および、計算機システムにおける仮想計算機の最適配置方法 | |
JP4659526B2 (ja) | ストレージシステムにインストールされるプログラムのライセンスを管理する管理計算機、計算機システム及び制御方法 | |
CN101681268B (zh) | 管理虚拟机存储器的系统、方法和程序 | |
JP4684864B2 (ja) | 記憶装置システム及び記憶制御方法 | |
JP5830599B2 (ja) | 計算機システム及びその管理システム | |
JP5439581B2 (ja) | ストレージシステム、ストレージ装置、ストレージシステムの記憶領域の最適化方法 | |
US8688909B2 (en) | Storage apparatus and data management method | |
JP5124551B2 (ja) | ボリューム割り当てを管理する計算機システム及びボリューム割り当て管理方法 | |
JP5973089B2 (ja) | ストレージシステムの移行方式および移行方法 | |
US10248460B2 (en) | Storage management computer | |
US20160156568A1 (en) | Computer system and computer resource allocation management method | |
JP7003692B2 (ja) | 情報処理装置,情報処理システムおよび制御プログラム | |
JP2010282420A (ja) | 管理計算機、リソース管理方法、リソース管理プログラム、記録媒体および情報処理システム | |
CN102981929A (zh) | 磁盘镜像的管理方法和系统 | |
JP6293683B2 (ja) | 計算機システム及び計算機システムの性能障害の対処方法 | |
WO2013098960A1 (ja) | 計算機システム、ファイル管理方法及び記憶媒体 | |
JP4862067B2 (ja) | キャッシュ制御装置及び方法 | |
JP6969282B2 (ja) | 情報処理装置、情報処理システムおよび情報処理方法 | |
US20150234671A1 (en) | Management system and management program | |
CN106687926A (zh) | 被克隆的虚拟机的负载均衡 | |
US20110208941A1 (en) | Scalable performance-based volume allocation for time-based storage access services | |
JP2013025547A (ja) | 演算制御装置及び演算制御方法並びにプログラム、並列プロセッサ | |
US12067413B2 (en) | Apparatus for determining resource migration schedule | |
JP7125964B2 (ja) | 計算機システムおよび管理方法 | |
JP6115575B2 (ja) | データセット多重度変更装置、サーバ、データセット多重度変更方法、およびコンピュータ・プログラム |
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: 11859821 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2013502047 Country of ref document: JP Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 13991274 Country of ref document: US |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 11859821 Country of ref document: EP Kind code of ref document: A1 |