JP2013206101A - Virtual system, resource management server, resource management method, and resource management program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a virtual system in which when a plurality of devices for realizing a function defined by a service SLA are provided, an optimal device is selected.SOLUTION: A resource management server 100 includes: configuration candidate evaluation means 102 for determining which should be adopted between a configuration using a dedicated device for realizing a service SLA set in a virtual machine 202 and a configuration using a general-purpose device; and optimum arrangement calculation means 103 for preparing a constitution plan by using an adopted configuration candidate, and adopting a configuration most satisfying a configuration plan evaluation criteria based on a prescribed resource policy. On the basis of a dedicated function resource amount range, which determines a range of a required resource amount in which an electric energy required when the service SLA is realized with the dedicated device becomes smaller than an electric energy required when the service SLA is realized with the general-purpose device, the configuration candidate evaluation means 102 determines that a dedicated device should be used when a total requested resource amount requested from the service SLA falls within a range of the dedicated function resource amount range.

Description

  The present invention relates to a virtualization system, and more particularly to a technique for performing resource management according to a service SLA.

  In recent years, a technique called server virtualization has been widely used. Server virtualization is the operation of multiple programs on the server that behave in the same way as the server, and by operating applications that provide OS and services on the program. It is a technology that can behave as if there is a server. Server virtualization allows you to freely customize resources such as CPU time and memory amount allocated to applications. Multiple services can share one system and control resource distribution according to service load. become.

  Further, as a technology for networking storage such as a hard disk device or a magnetic tape device and a server, there is a technology called SAN (Storage Area Network). Rather than providing each server with a hard disk (HDD) that the server uses as a data storage area, a separate disk array device is prepared, and the disk array device and the server are connected via a network to manage the HDD. This is a separate technology. The disk array apparatus can handle a plurality of HDDs virtually as one large HDD by RAID technology, and has a function that does not affect data reading and writing even when a small number of HDDs fail. Further, the disk array device has various functions for stored data, such as a data backup function and an encryption function using an HDD having an encryption function.

  In addition, there is a contract form called Service Level Agreement (SLA) as a system in which a communication service provider guarantees service quality to users.

  The SLA is a contract between a resource provider that provides hardware resources such as a server and a disk array device, and a service provider that operates the application using the hardware resources. For example, the SLA Specifies the amount of resources allocated to. The resource amount may be specified directly, but the quality of service, for example, the response time or the access amount per unit time, etc., may be specified, and the resource provider may allocate resources that satisfy the specified performance. .

  In addition to performance, functional restrictions such as data encryption may be tied as SLA. The resource provider allocates resources to the service provider application to satisfy the SLA.

  In the case of using the virtualization technology, one server can be shared by a plurality of services, and the amount of allocated resources can be flexibly adjusted, so that the flexibility of distributed resources is increased. In the server, the resource is a CPU or a memory for running an application (which constitutes a service). An area for an application is allocated not only to the server but also to the disk array device, and data can be stored.

  Also for the network, a bandwidth is secured according to the SLA. Run the virtual machine on which the application runs on the allocated resource.

  Some SLA may impose restrictions other than the amount of allocated resources. For example, data can be backed up regularly. In this case, measures such as enabling the backup function in the disk array device are taken.

  For devices that do not use any services, power consumption can be reduced by turning off the power. A server that is not running any service can be powered off. The unit that can be stopped differs for each device. For example, in the case of a disk array device, power consumption can be suppressed by stopping each HDD that is not used. In this way, the resource provider can reduce costs by minimizing the number of devices that operate while satisfying the SLA.

  An example of a technique for minimizing the power consumption of the entire system while satisfying the SLA is disclosed in Patent Document 1.

  In the technology disclosed in Patent Literature 1, priorities are set in consideration of power consumption for each server, distance from air cooling, and ease of cooling due to positional relationships, and allocation to VMs based on the priorities is performed. By determining the server, the power consumption of the system is minimized.

  Here, as a related technique, Patent Document 2 describes that a table including information on all servers operating in a computer system is provided. Patent Document 2 also describes that a table including information related to all operations to be operated in the computer system is provided. Further, Patent Document 2 describes that whether or not aggregation is possible is determined according to the required performance of business.

  As another related technique, Patent Document 3 describes that power consumption is suppressed while satisfying an SLA. Patent Document 2 describes that the operating frequency of the CPU is lowered to reduce the power consumption of the server.

JP 2011-013822 A JP 2011-090704 A Special table 2011-518393 gazette

  In a system for determining resources to be allocated to virtual machines (hereinafter referred to as VMs) constituting the service based on the SLA set for the service, all the SLA on the service side are satisfied, and at the same time, the system as a request from the resource provider side Sometimes we want to reduce overall power consumption.

  For example, “data encryption” is designated in the service-side SLA (hereinafter referred to as service SLA). In order to realize data encryption, there are a plurality of methods such as loading an encrypted physical disk into a disk array device and storing the data in the disk array device and operating encryption software on the VM.

  If the encryption function on the disk array device side is used, the encryption processing on the virtual machine side becomes unnecessary, but the encrypted physical disk must be operated. If the number of VMs using the encrypted physical disk is small, the power consumption of the entire system can be suppressed by operating the encryption software on the VM side and stopping the operation of the encrypted physical disk.

  The first problem in the background art, the selection of the environment for implementing the service SLA, as described above, in a situation such devices are a plurality of for implementing the functions defined in the service SLA, in advance either means It is only possible to decide whether to use it or not, so that depending on the situation, power consumption may be excessive.

  The second problem in the background art is that the administrator needs to execute the function defined in the service SLA when changing the device that realizes it in order to optimize the power consumption as described above. It is. Depending on the usage status of each function, it is determined which device is to be used, and if the setting of the device needs to be changed at that time, the administrator needs to implement it. These processes need to be performed for all VMs that need to be changed, and there are problems in terms of labor and cost.

  Note that the technique described in Patent Document 2 moves work between apparatuses having the same function in order to reduce power consumption. The technology described in Patent Document 3 limits the use of resource resources according to the work load. For this reason, even if they are combined, in a situation where there are a plurality of devices for realizing the functions defined in the service SLA, it is not possible to automatically determine which means to use and change the setting. .

(Object of invention)
An object of the present invention is to solve the above-described problem and, when there are a plurality of devices that realize the function defined by the service SLA, a virtualization system, a resource management server, A resource management method and a resource management program are provided.

  A first virtualization system of the present invention includes a virtualization server on which a virtual machine that provides a service operates, a disk array device including a plurality of disks, and a resource management server, and the resource management server is a virtual machine. For each set service SLA, configuration candidate evaluation means for determining which of the configuration candidate using a dedicated device having a dedicated function for realizing the service SLA and the configuration candidate using a general-purpose device is adopted. And an optimal placement calculation unit that creates a configuration plan using the configuration candidates adopted by the configuration candidate evaluation unit and adopts a configuration that best matches the configuration plan evaluation criteria determined based on a predetermined resource policy; And a configuration execution means for executing a change in the operation and settings of the virtual machine and the disk array device based on the adopted configuration. However, the dedicated function resource amount range that defines the range of the requested resource amount in which the power amount required when the service SLA is realized by the dedicated device is smaller than the power amount required when the service SLA is realized by the general-purpose device. If the total requested resource amount obtained from the service SLA is within the range of the dedicated function resource amount range, it is determined to use the dedicated device.

  A first resource management server of the present invention is a resource management server in a virtualization system including a virtualization server on which a virtual machine that provides a service operates, a disk array device including a plurality of disks, and a resource management server. For each service SLA set in the virtual machine, it is determined whether to adopt a configuration candidate that uses a dedicated device having a dedicated function for realizing the service SLA or a configuration candidate that uses a general-purpose device. The configuration candidate is created using the configuration candidate evaluation means to be configured and the configuration candidate adopted by the configuration candidate evaluation means, and the configuration that best matches the configuration plan evaluation criteria determined based on a predetermined resource policy is adopted. Optimal placement calculation means and placement that changes the operation and settings of virtual machines and disk array devices based on the adopted configuration A request resource amount that is required when the configuration candidate evaluation unit realizes the service SLA with the dedicated device and less than the power amount required when the service SLA is realized with the general-purpose device. If the total requested resource amount obtained from the service SLA is within the range of the dedicated function resource amount range based on the dedicated function resource amount range that defines the range of

  The first resource management method of the present invention provides a resource by a resource management server in a virtualization system comprising a virtualization server on which a virtual machine providing a service operates, a disk array device including a plurality of disks, and a resource management server. In this management method, the configuration candidate evaluation unit uses a configuration candidate that uses a dedicated device having a dedicated function for realizing the service SLA and a general-purpose device for each service SLA set in the virtual machine. The configuration candidate evaluation step for determining which of the configuration candidates is to be adopted, and the optimum placement calculation means create a configuration plan using the configuration candidates adopted in the configuration candidate evaluation step, and based on a predetermined resource policy The optimal placement calculation step that adopts the configuration that best matches the configuration plan evaluation criteria determined by the A placement execution step for changing the operation and setting of the virtual machine and the disk array device based on the adopted configuration, and the power required when the service SLA is realized by the dedicated device in the configuration candidate evaluation step The total required resource amount required from the service SLA is determined based on the dedicated function resource amount range that defines the required resource amount range that is less than the amount of power required when the service SLA is realized with a general-purpose device. If it is within the functional resource amount range, it is decided to use the dedicated device.

  A first resource management program according to the present invention configures a resource management server in a virtualization system including a virtualization server on which a virtual machine that provides a service operates, a disk array device including a plurality of disks, and a resource management server A resource management program that operates on a computer that performs configuration candidate evaluation using a dedicated device having a dedicated function for realizing the service SLA for each service SLA set in the virtual machine in the configuration candidate evaluation unit And a configuration candidate evaluation process that determines which of the configuration candidates using the general-purpose device is to be adopted, and the optimal layout calculation means creates a configuration plan using the configuration candidates adopted in the configuration candidate evaluation step. The configuration that best matches the configuration plan evaluation criteria determined based on a predetermined resource policy is adopted. To execute the optimal placement calculation process, and to cause the placement execution means to execute the placement execution process to change the operation and settings of the virtual machine and disk array device based on the adopted configuration. Based on a dedicated function resource amount range that defines the range of required resource amount that requires less power than the amount of power required when a service SLA is realized with a general-purpose device. When the total requested resource amount obtained from the service SLA is within the range of the dedicated function resource amount range, it is determined that the dedicated device is used.

  According to the present invention, when there are a plurality of devices that realize the function defined in the service SLA, it is possible to realize the function by selecting an optimum device.

It is a flowchart which shows the structure of the virtualization system in the 1st Embodiment of this invention. It is a flowchart which shows operation | movement of the virtualization system in the 1st Embodiment of this invention. It is a flowchart which shows operation | movement of the structure candidate evaluation means in the 1st Embodiment of this invention. It is a flowchart which shows operation | movement of the optimal arrangement | positioning calculation means in the 1st Embodiment of this invention. It is a figure which shows the structural example of the SLA conversion table in Example 1 of this invention. It is a figure which shows the structural example of the apparatus information table in Example 1 of this invention. It is a figure which shows the structural example of the existing VM arrangement | positioning table in Example 1 of this invention. It is a figure which shows the structural example of the existing VM arrangement | positioning table in Example 1 of this invention. It is a block diagram which shows the minimum structure of the virtualization system of this invention. It is a block diagram which shows the hardware structural example of the resource management server of this invention.

  In order to clarify the above and other objects, features and advantages of the present invention, embodiments of the present invention will be described in detail below with reference to the accompanying drawings. In addition to the above-described object of the present invention, other technical problems, means for solving the technical problems, and operational effects thereof will become apparent from the disclosure of the following embodiments.

  In all the drawings, the same reference numerals are given to the same components, and the description will be omitted as appropriate.

(First embodiment)
A first embodiment of the present invention will be described in detail with reference to the drawings.

  FIG. 1 is a block diagram showing the configuration of a virtualization system 10 according to the first embodiment of the present invention.

  Referring to FIG. 1, a virtualization system 10 according to the present embodiment includes a resource management server 100 that operates under program control, a virtualization server 200 that operates under program control, a disk array device 300, and a client terminal 400. Prepare. The virtualization server 200 and the disk array device 300 may each be one or more.

  The resource management server 100 includes a resource policy setting unit 101, a configuration candidate evaluation unit 102, an optimum arrangement calculation unit 103, an SLA conversion table 104, an existing VM arrangement table 105, a device information table 106, and a VM arrangement change request. It includes an accepting means 107, an arrangement recalculation request accepting means 108, an arrangement executing means 109, a VM operating means 110, a server operating means 111, and a storage operating means 112.

  The virtualization server 200 includes server setting execution means 201, a plurality of virtual machines (VM) 202, and VM setting execution means 203 attached to each virtual machine 202.

  The disk array device 300 includes a disk array device setting execution unit 301, a logical disk 302, a physical disk 303, an encrypted physical disk 304, and a pool 305.

  Each of these means generally operates as follows.

  The resource policy setting unit 101 sets a resource policy that becomes a constraint condition when providing resources to a VM constituting a service in accordance with an external resource policy setting request. When the resource policy setting unit 101 receives the resource policy setting request, the resource policy setting unit 101 records the resource policy, and changes the consumed resource amount range of the dedicated function of the configuration candidate evaluation unit 102 and the configuration plan evaluation criteria of the optimal arrangement calculation unit 103. .

  The configuration candidate evaluation unit 102 stores a dedicated function resource amount range determined based on the resource policy set by the resource policy setting unit 101.

  Also, the configuration candidate evaluation unit 102 is a dedicated unit that is obtained from the configuration candidate of the newly created VM service SLA from the VM allocation change request receiving unit 107 and the configuration candidate of the existing VM service SLA recorded in the existing VM allocation table 105. The requested resource amount to the device providing the function and the dedicated function resource amount range are compared, and it is determined whether or not to adopt a configuration candidate that uses the device providing the dedicated function depending on whether or not it falls within the range. .

  For example, for the dedicated function “data encryption”, when the dedicated function resource amount range is set to a requested resource amount of a certain amount or more, the total amount of requested resources of all VMs that request “data encryption” is If it is above a certain value, select a configuration candidate that uses an encrypted physical disk that is a device that provides a dedicated function. If the total amount of requested resources is less than a certain value, a configuration candidate that uses an encrypted physical disk is Discard it, allocate extra CPU resources of the server, which is a general-purpose function, and select a configuration candidate that operates the encryption function on the OS.

  The optimum arrangement calculation unit 103 stores the configuration plan evaluation criteria determined by the resource policy set by the resource policy setting unit 101, creates a configuration plan using the configuration candidates adopted by the configuration candidate evaluation unit 102, Among the configuration plans, the configuration plan that most closely matches the criteria is selected in light of the configuration plan evaluation criteria. For example, when “minimize power consumption” is set as the resource policy, a configuration plan with the smallest expected power consumption is selected from the created configuration plans.

  The SLA conversion table 104 stores arrangement candidates for realizing the service SLA for the service SLA set in the VM, and returns a list of arrangement candidates by searching using the service SLA as a key. Furthermore, the procedure and cost for changing from one placement candidate to another placement candidate are stored, and the configuration change procedure and cost are returned by searching using the pre-change configuration and the post-change configuration as keys.

  The existing VM arrangement table 105 stores the configuration candidates already selected for the VM and the distributed resources, and returns the information.

  The device information table 106 stores information on a device that is a substance of a resource distributed to a VM. The device information includes information indicating the capacity of the resource, that is, how much resource amount can be distributed to the VM, how much power is consumed at the time of distribution, and the dedicated function of the resource.

  A dedicated function provides a function required only by a VM having a specific SLA, and its resources are used to provide the function. For example, each device has the following information.

  If it is a server, the CPU's data processing capacity and memory can be distributed as resources, and the resources on the device can be stopped without being distributed to any VM. In the case of a disk array device, the capacity of a loaded physical disk (HDD) can be distributed as a resource, and can be stopped for each pool created by bundling several HDDs. A pool created from an encrypted HDD has encryption as a dedicated function.

  The VM arrangement change request accepting unit 107 accepts a VM arrangement change request from the client terminal 400 together with the service SLA of the target VM, and passes the information to the optimum arrangement calculating unit 103. The VM placement change request includes information on the service SLA with the VM to be added and information on the VM to be deleted.

  The arrangement recalculation request accepting unit 108 accepts an arrangement recalculation request from the client terminal 400 and requests the optimum arrangement calculation unit 103 to execute the arrangement recalculation. The placement recalculation request is a request for recalculating the configuration of resources distributed to the already operating VMs and changing the placement based on the calculation result.

  The placement execution unit 109 receives the placement information determined by the optimum placement calculation unit 103, assembles a placement change command for the operation target device from the placement information, and sends the placement change command to the VM operation unit 110 and the server operation unit 111 for each operation target device. And the storage operation means 112.

  The VM operation unit 110 receives an arrangement change command from the arrangement execution unit 109 and sends it to the VM setting execution unit 203.

  The server operation unit 111 receives an arrangement change command from the arrangement execution unit 109 and sends it to the server setting execution unit 201.

  The storage operation unit 112 receives an arrangement change command from the arrangement execution unit 109 and sends it to the disk array device setting execution unit 301.

  The server setting execution unit 201 receives an arrangement change command from the server operation unit 111 and changes the operation and settings of the virtualization server 200 based on the arrangement change command.

  The virtual machine 202 is a virtual server built on the server, and the OS and application program operate on the virtual server 202 to provide services. The virtual machine 202 operates by being allocated by the virtualization server 200 using CPU data processing capability or a part of memory as a resource.

  The VM setting execution unit 203 receives an arrangement change command from the server operation unit 111 and changes the operation and settings of the virtual machine 202 based on the arrangement change command.

  The disk array device setting execution unit 301 receives an arrangement change command from the storage operation unit 112 and changes the operation and settings of the disk array device 300 based on the arrangement change command.

  The logical disk 302 is a resource allocated to the VM. The VM stores data on the logical disk. The entity of the logical disk 302 is a part of the pool 305 created by bundling the physical disks 303 and the encrypted physical disks 304. If the pool 305 from which the logical disk 302 is taken out is an encrypted physical disk 304, the data stored therein is encrypted.

  The physical disk 303 is a device that stores data. The disk array device 300 has a plurality of physical disks 303, stores data from the VM in the physical disk 303, and returns data stored in the physical disk 303 in response to a data retrieval request from the VM.

  The encrypted physical disk 304 is a device that encrypts and stores data. It is used in exactly the same way as the physical disk 303, but the data stored on the encrypted physical disk 304 is automatically encrypted and cannot be read by unrelated others.

  The pool 305 is a data storage area in which the physical disks 303 and the encrypted physical disks 304 are bundled so that they can be handled as one virtual large physical disk. The characteristics of the pool 305 depend on the characteristics of the physical disk 303 and the encrypted physical disk 304 that constitute the pool 305. For example, if data is stored in a pool 305 composed of the encrypted physical disk 304, the data is encrypted and stored.

  The client terminal 400 is a setting terminal used by the resource manager. A function to send a resource policy setting request to the resource policy setting setting unit 101, a function to send a VM placement change request to the VM placement change request accepting unit 107, and a relocation It has a function of sending a calculation request to the arrangement recalculation request receiving means 108.

  The present invention has the above-described configuration, and among the service SLA, there are both a method using a dedicated device and a method realized by combining a general-purpose device and software as a method for realizing the function of the service SLA. For both, the configuration candidate using the dedicated device and the configuration candidate realized by combining the general-purpose device and software are linked to the service SLA. The resource policy is also set on the resource side. A resource policy may be to minimize power consumption.

  The resource policy includes a “dedicated function resource amount range” indicating whether or not to use a dedicated device. The range of the total required resource amount to the function provided by the dedicated device obtained from the service SLAs of all VMs is included in the resource policy. If the total requested resource amount is within the dedicated function resource amount range, the configuration candidate using the dedicated device is adopted, and if the total requested resource amount exceeds the dedicated function resource amount range, the configuration candidate using the dedicated device is selected. Not adopted. When a configuration candidate using a dedicated device is not adopted, a configuration candidate combining a general-purpose device linked to the same service SLA (that is, realizing the same function) and software is adopted.

  Furthermore, using the configuration candidates adopted based on the “dedicated function resource amount range”, a plurality of configuration plans are created so as to satisfy the service SLA of all VMs, and the “configuration plan evaluation criteria included in the resource policy” To select a configuration plan.

  By configuring in this way, it is possible to determine the situation in which the dedicated device should be moved, such as when there are more than a certain number of required resources for the functions defined in the service SLA, and to implement the dedicated device, general-purpose device and software. By properly using the combined implementation, it is possible to reduce the power consumption of the entire system.

  Furthermore, a conversion method between configuration candidates associated with the same service SLA is provided in advance. When the configuration candidate to be adopted changes due to a change in the situation, the configuration candidate is converted based on the conversion method between the configuration candidates. Perform conversion. By configuring in this way, with regard to the functions defined in the service SLA, configuration candidates that use dedicated devices, and configuration candidates that are realized by combining configuration candidates using the dedicated devices, general-purpose devices, and software can be changed from time to time. It is possible to automatically move to a configuration that suppresses power consumption by reselecting following the change in the situation and automatically converting to the selected configuration candidate.

  As described above, the present invention realizes the performance and functions required by the service running on the virtual machine, calculates the optimal placement to satisfy the constraints on the resources for running the virtual machine, and realizes the placement. . In particular, there are multiple configuration candidates for realizing the performance and functions required by services running on virtual machines, and dedicated functions that provide specific functions for the realization of certain functions due to overall system usage and resource constraints It is characterized by determining which of a device or a general-purpose device is to be used.

(Description of the operation of the first embodiment)
Next, the operation of the virtualization system 10 according to the present embodiment will be described in detail with reference to the drawings.

  Next, the operation of the virtualization system 10 according to the present embodiment will be described in detail with reference to the flowcharts of FIG. 1 and FIG.

  First, a resource policy change request is sent from the client terminal 400 to the resource policy setting means 101 (step A01).

  Next, a dedicated function resource amount range corresponding to the resource policy included in the resource policy change request is set in the configuration candidate evaluation unit 102 (step A02).

  Next, a configuration plan evaluation criterion corresponding to the set resource policy is set in the optimum placement calculation means 103 (step A03).

  Thereafter, the VM arrangement change request accepting unit 107 accepts a request for adding a new VM from the client terminal 400 together with the service SLA (step A04).

  Next, the new VM information is stored in the existing VM allocation table 105 as an unallocated VM together with the information of the service SLA (step A05).

  Next, the configuration candidate evaluation unit 102 uses for configuration among the configuration candidates of the service SLA of all VMs registered in the existing VM allocation table based on the dedicated function resource amount range set in step A02. A configuration candidate is determined and passed to the optimum arrangement calculation means 103 (step A06).

  Here, the operation of the configuration candidate evaluation unit 102 will be described in detail with reference to FIG.

  First, the configuration candidate evaluation unit 102 searches the existing VM arrangement table 105 for all the VMs to be arranged using the VM as a key, and acquires a service SLA (step B01).

  Next, a configuration candidate is extracted from the SLA conversion table 104 for each service SLA extracted in step B01 (step B02).

  Next, a list of devices / resources is extracted from the device information table 106 (step B03), and a list of dedicated functions is generated from the list of devices / resources (step B04).

  For each dedicated function included in the list of dedicated functions generated in step A04, out of the configuration candidates extracted in step B02, those requiring the dedicated function are extracted (step B05).

  A configuration plan is constructed with only configuration candidates that require the dedicated function extracted in step B05. At this time, each configuration plan does not include a plurality of configuration candidates belonging to the same service SLA of the same VM (step B06).

  Next, for each of the configuration plans constructed in step B06, for the dedicated function extracted in step B05, the required resource amount to the device providing the dedicated function is calculated (step B07).

  The consumption resource amount calculated in step B07 is compared with the dedicated function resource amount range indicated in the resource policy to check whether there is a configuration plan in which the consumption resource amount is included in the dedicated function resource amount range (step B08). .

  If there is such a configuration plan, a configuration candidate in which the configuration plan included in the dedicated function resource amount range is constructed in step B07 is adopted, and among the configuration candidates belonging to the same service SLA as the adopted configuration candidate, a general-purpose device is selected. The configuration candidate to be used is discarded (step B09).

  If there is no configuration plan that meets the conditions in step B08, the configuration candidate requesting the dedicated function extracted in step B05 is discarded (step B10).

  Steps B05 to B10 are performed for all the dedicated functions extracted in step B04 (step B11).

  Finally, with respect to the VM obtained in step B01 and its service SLA, the configuration candidates taken out in step B09 and step B10 out of the configuration candidates extracted in step B02 are excluded and transferred to the optimum arrangement calculation unit 103.

  Returning to FIG. 2, next, the optimal arrangement calculation unit 103 creates a configuration plan using the configuration candidates passed in step A06, and evaluates the configuration plan based on the configuration plan evaluation criteria set in step A03. Then, the configuration plan that most closely matches the reference is selected and transferred to the placement execution means 109 together with the difference from the current placement of the configuration plan (step A07).

  Here, the operation of the optimum arrangement calculating unit 103 will be described in detail with reference to FIG.

  First, a list of arrangement target VMs, their service SLA, and service SLA configuration candidates is received from the configuration candidate evaluation unit 102 (step C01).

  A configuration plan is constructed using the configuration candidates received in step C01. At this time, in each configuration plan, it is a condition that any one of the configuration candidates is used for all service SLAs of each VM (step C02).

  Next, the difference between the configuration plan constructed in step C02 and the current arrangement status is calculated (step C03), the SLA conversion table is searched for each difference, and the cost of the arrangement change is calculated (step C04). .

  Next, for the configuration plan constructed in step C02, the device information table is searched for each resource used in the configuration plan, power consumption is obtained, and the power consumption of the configuration plan is obtained from the total ( Step C05).

  Next, the arrangement conversion cost calculated in step C04 and the power consumption calculated in step C05 are compared with the resource policy arrangement evaluation criteria, and the configuration plan that best matches the criteria is selected (step C06). .

  Finally, the configuration plan selected in step C06 is transferred to the placement execution means 109 together with the difference in the current placement status calculated in step C03 for the configuration plan (step C07).

  Returning to FIG. 2, next, the placement execution unit 109 searches the SLA conversion table 104 using the difference between the configuration candidates obtained in step A07 as a key, and obtains an instruction for each device type and its target (step A08). ), A command for each device type is sent to the VM operation unit 110, the server operation unit 111, and the storage operation unit 112 for each device type (step A09).

  The VM operation means 110 sends the instruction obtained in step A09 to the VM operation execution means 203 of the target VM included in the instruction (step A10).

  The server operation unit 111 sends the command obtained in step A09 to the server operation execution unit 201 of the target server included in the command (step A11).

  The storage operation unit 112 sends the command obtained in step A09 to the disk array device operation execution unit 301 of the target disk array device included in the command (step A12).

  Finally, the placement execution unit 109 stores the configuration plan obtained in Step A07 in the existing VM placement table 105 (Step A13).

  Next, the present invention will be described using specific examples.

  FIG. 5 shows a specific example of the SLA conversion table 104. FIG. 6 shows a specific example of the device information table 106. Further, FIG. 7 shows a specific example of the original existing VM arrangement table 105.

  The resource policy is set to “minimum power consumption”. In this resource policy, it is assumed that a configuration plan with the least power consumption is selected as a configuration plan evaluation criterion. In addition, it is assumed that the resource consumption amount 200G or more is set for the service SLA “data encryption” as the dedicated function resource amount range.

  Referring to a specific example of the existing VM arrangement table 105 shown in FIG. 7, three VMs having the “data encryption” service SLA are already arranged. However, the required resource amount for a device having a dedicated function for encryption is 150 G when the three are combined, and does not match the above-described dedicated function resource amount range.

  For this reason, “Discardray-01-pool-02”, which is a resource having a dedicated function for encryption, is not used and is in a stopped state, and its power consumption is zero.

  Here, it is assumed that VMs “Service03-01” and “Service03-02” having high performance, small memory, and data encryption are newly added as service SLA.

  From the device information table 106 shown in FIG. 6, it is understood that “encryption” and “load balance” are prepared as dedicated functions.

  The configuration candidates that use the “encryption” dedicated function are service SLA “data encryption” possessed by “Service02-01”, “Service02-02”, “Service02-03”, “Service03-01”, and “Service03-02” The configuration candidate ID is “1”. The total requested resource amount is 50G * 5 = 250G, which matches the consumption resource amount range of the dedicated function.

  Therefore, it is assumed that this configuration candidate is adopted, and the configuration candidate with the configuration candidate ID: 2 that is another configuration candidate of the same service SLA “data encryption” is not used. “Load balance”, which is another dedicated function, is not subject to the calculation of configuration candidate selection because it is not a policy of the target VM.

  Furthermore, “high performance”, “medium performance”, “medium capacity”, “large memory”, and “small memory” of the remaining service SLA each have one configuration candidate.

  Using these configuration candidates, the optimum arrangement calculation means 103 creates a configuration plan. In this case, “Discardray-01-pool-02” which is a resource having a dedicated function of “encryption” is used, and the resources allocated to the VM are changed as shown in FIG.

  An operation occurs for the difference between FIG. 7 and FIG. New VMs “Service03-01” and “Service03-02” are created on Server02. Each area is allocated from “Discardray-01-pool-02”.

  In addition, the existing VMs “Service02-01”, “Service02-02”, and “Service02-03” also use storage resources from “Discardray-01-pool-01” to “Discardray-01-pool-02”. To "". In this change, in addition to the data movement that is the movement of the storage, it is necessary to invalidate the encryption software to the VM that is the deletion process set to the configuration candidate ID: 2. This command is sent to the VM setting execution means 203 of each of “Service02-01”, “Service02-02”, and “Service02-03” through the VM operation means 110.

(Effects of the first embodiment)
The first effect of the present embodiment is that the function defined by the service SLA is dedicated in a situation where the realization can be realized by using either a dedicated device such as a storage or a general-purpose device such as a server. When a required resource amount range in which the amount of power required when realized by the device is less than the amount of power required for realizing by the general-purpose device is obtained in advance, and the required resource amount is within the range Determines the configuration to implement the function with a dedicated device, and when the requested resource amount falls outside the range, the dedicated device stops and determines the configuration to be implemented with a general-purpose device. By realizing the above, it is possible to suppress the power consumption of the entire system.

  The second effect of the present embodiment is that the function defined by the service SLA can be realized by using either a dedicated device such as a storage or a general-purpose device such as a server. By saving the mutual switching method between the realization of the function by the dedicated device and the realization of the general-purpose device, when the VM using the function is already operating, the realization by the dedicated device and the general-purpose device are again performed. It is possible to reduce the power consumption of the entire system by calculating which of the implementations reduces power consumption and automatically shifting to a configuration that suppresses power consumption.

  Here, FIG. 9 shows a minimum configuration capable of solving the problems of the present invention. The virtualization system 10 includes a virtualization server 200 on which a virtual machine 202 that provides a service operates, a disk array device 300 including a plurality of disks, and a resource management server 100, and the resource management server 100 includes the virtual machine 202. For each service SLA set to, a configuration candidate evaluation that determines which of a configuration candidate that uses a dedicated device having a dedicated function for realizing the service SLA and a configuration candidate that uses a general-purpose device is adopted. A configuration plan is created using the configuration candidates adopted by the means 102 and the configuration candidate evaluation means 102, and an optimum arrangement is adopted that adopts the configuration that best matches the configuration plan evaluation criteria determined based on a predetermined resource policy. Based on the calculation unit 103 and the adopted configuration, the operation and setting change of the virtual machine and the disk array device are performed. And the configuration candidate evaluation unit 102 has an amount of power required when the service SLA is realized by the dedicated device than that required when the service SLA is realized by the general-purpose device. Based on the dedicated function resource amount range that defines the range of the requested resource amount to be reduced, if the total requested resource amount obtained from the service SLA is within the range of the dedicated function resource amount range, it is determined to use the dedicated device. Thus, the above-described problems of the present invention can be solved.

  Next, a hardware configuration example of the resource management server 100 of the present invention will be described with reference to FIG. FIG. 10 is a block diagram illustrating a hardware configuration example of the resource management server 100.

  Referring to FIG. 10, the resource management server 100 of the present invention has a hardware configuration similar to that of a general computer device, and includes data such as a CPU (Central Processing Unit) 1001 and a RAM (Random Access Memory). The main storage unit 1002 used for the work area and the temporary data storage area, the communication unit 1003 that transmits / receives data via the network, the input device 1005, the output device 1006, and the storage device 1007 are connected to transmit / receive data. An input / output interface unit 1004 and a system bus 1008 for connecting the above-described components to each other are provided. The storage device 1007 is realized by, for example, a hard disk device including a non-volatile memory such as a ROM (Read Only Memory), a magnetic disk, and a semiconductor memory.

  Each function of the resource management server 100 according to the present invention is implemented by hardware by mounting circuit components, which are hardware components such as LSI (Large Scale Integration), incorporating a program. As another example, the program that provides the function may be stored in the storage device 1007, loaded into the main storage unit 1002, and executed by the CPU 1001 to be realized in software.

  The virtualization server 200 of the present invention also has the hardware configuration as described above, and implements each function of the virtualization server 200 in terms of hardware or software.

  The present invention has been described above with reference to preferred embodiments. However, the present invention is not necessarily limited to the above embodiments, and various modifications can be made within the scope of the technical idea. it can.

  It should be noted that any combination of the above-described constituent elements and a conversion of the expression of the present invention between a method, an apparatus, a system, a recording medium, a computer program, etc. are also effective as an aspect of the present invention.

  The various components of the present invention do not necessarily have to be independent of each other. A plurality of components are formed as a single member, and a single component is formed of a plurality of members. It may be that a certain component is a part of another component, a part of a certain component overlaps with a part of another component, or the like.

  Moreover, although the several procedure is described in order in the method and computer program of this invention, the order of the description does not limit the order which performs a several procedure. For this reason, when implementing the method and computer program of this invention, the order of the several procedure can be changed in the range which does not interfere in content.

  The plurality of procedures of the method and the computer program of the present invention are not limited to being executed at different timings. For this reason, another procedure may occur during the execution of a certain procedure, or some or all of the execution timing of a certain procedure and the execution timing of another procedure may overlap.

  Further, a part or all of the above-described embodiment can be described as in the following supplementary notes, but is not limited thereto.

(Appendix 1)
A virtualization server on which a virtual machine providing a service operates;
A disk array device including a plurality of disks;
A resource management server,
The resource management server is
For each service SLA set in the virtual machine, it is determined whether to adopt a configuration candidate using a dedicated device having a dedicated function for realizing the service SLA or a configuration candidate using a general-purpose device. Configuration candidate evaluation means,
Creating a configuration plan using the configuration candidates adopted by the configuration candidate evaluation unit, and adopting a configuration that best matches a configuration plan evaluation criterion determined based on a predetermined resource policy; and
An arrangement execution means for executing operation and setting change of the virtual machine and the disk array device based on the adopted configuration;
The configuration candidate evaluation means
Dedicated functional resource that defines a range of required resource amount that requires less power when the service SLA is realized by the general-purpose device than when the service SLA is realized by the general-purpose device. The virtualization system according to claim 1, wherein when the total requested resource amount obtained from the service SLA is within the range of the dedicated function resource amount range based on the amount range, the dedicated device is determined to be used.

(Appendix 2)
The dedicated device is the disk array device;
The virtualization system according to appendix 1, wherein the general-purpose device is the virtualization server.

(Appendix 3)
The service SLA is data encryption;
The virtualization system according to appendix 1 or appendix 2, wherein the disk array device includes an encrypted physical disk.

(Appendix 4)
If the resource policy is to minimize power consumption,
The virtualization system according to any one of appendix 1 to appendix 3, wherein the optimum arrangement calculation unit employs a configuration with the least expected power consumption.

(Appendix 5)
An existing VM placement table for recording the virtual machine and the service SLA in association with each other;
An SLA conversion table for recording the requested resource amount of the service SLA;
The configuration candidate evaluation means
The number of the virtual machines associated with the service SLA is specified with reference to the existing VM placement table, the requested resource amount of the service SLA is specified with reference to the SLA conversion table, and the total required resource amount is calculated The virtualization system according to any one of appendix 1 to appendix 4, characterized in that:

(Appendix 6)
A resource that receives the setting request for the resource policy from the outside, sets the resource policy based on the setting request, and changes the dedicated function resource amount range and the configuration plan evaluation criteria based on the set resource policy The virtualization system according to any one of supplementary notes 1 to 5, further comprising policy setting means.

(Appendix 7)
A resource management server in a virtualization system comprising a virtualization server on which a virtual machine providing a service operates, a disk array device including a plurality of disks, and a resource management server,
For each service SLA set in the virtual machine, it is determined whether to adopt a configuration candidate using a dedicated device having a dedicated function for realizing the service SLA or a configuration candidate using a general-purpose device. Configuration candidate evaluation means,
Creating a configuration plan using the configuration candidates adopted by the configuration candidate evaluation unit, and adopting a configuration that best matches a configuration plan evaluation criterion determined based on a predetermined resource policy; and
An arrangement execution means for executing operation and setting change of the virtual machine and the disk array device based on the adopted configuration;
The configuration candidate evaluation means
Dedicated functional resource that defines a range of required resource amount that requires less power when the service SLA is realized by the general-purpose device than when the service SLA is realized by the general-purpose device. The resource management server according to claim 1, wherein when the total requested resource amount obtained from the service SLA is within the range of the dedicated function resource amount range based on the amount range, the dedicated device is determined to be used.

(Appendix 8)
The dedicated device is the disk array device;
The resource management server according to appendix 7, wherein the general-purpose device is the virtualization server.

(Appendix 9)
The service SLA is data encryption;
9. The resource management server according to appendix 7 or appendix 8, wherein the disk array device includes an encrypted physical disk.

(Appendix 10)
If the resource policy is to minimize power consumption,
The resource management server according to any one of appendix 7 to appendix 9, wherein the optimal arrangement calculation unit employs a configuration with the least expected power consumption.

(Appendix 11)
An existing VM placement table for recording the virtual machine and the service SLA in association with each other;
An SLA conversion table for recording the requested resource amount of the service SLA;
The configuration candidate evaluation means
The number of the virtual machines associated with the service SLA is specified with reference to the existing VM placement table, the requested resource amount of the service SLA is specified with reference to the SLA conversion table, and the total required resource amount is calculated The resource management server according to any one of appendix 7 to appendix 10, characterized by:

(Appendix 12)
A resource that receives the setting request for the resource policy from the outside, sets the resource policy based on the setting request, and changes the dedicated function resource amount range and the configuration plan evaluation criteria based on the set resource policy The resource management server according to any one of supplementary note 7 to supplementary note 11, comprising policy setting means.

(Appendix 13)
A resource management method by a resource management server in a virtualization system comprising a virtualization server on which a virtual machine providing a service operates, a disk array device including a plurality of disks, and a resource management server,
For each service SLA set in the virtual machine, the configuration candidate evaluation unit selects either a configuration candidate using a dedicated device having a dedicated function for realizing the service SLA or a configuration candidate using a general-purpose device. Configuration candidate evaluation step for determining whether to adopt,
The optimal arrangement calculation means creates a configuration plan using the configuration candidates adopted in the configuration candidate evaluation step, and adopts the configuration that best matches the configuration plan evaluation criteria determined based on a predetermined resource policy. An optimal placement calculation step;
An arrangement execution unit has an arrangement execution step for executing an operation or setting change of the virtual machine or the disk array device based on the adopted configuration,
In the configuration candidate evaluation step,
Dedicated functional resource that defines a range of required resource amount that requires less power when the service SLA is realized by the general-purpose device than when the service SLA is realized by the general-purpose device. A resource management method comprising: determining that the dedicated device is to be used when a total required resource amount obtained from the service SLA is within the range of the dedicated function resource amount range based on a quantity range.

(Appendix 14)
The dedicated device is the disk array device;
14. The resource management method according to appendix 13, wherein the general-purpose device is the virtualization server.

(Appendix 15)
The service SLA is data encryption;
15. The resource management method according to appendix 13 or appendix 14, wherein the disk array device includes an encrypted physical disk.

(Appendix 16)
If the resource policy is to minimize power consumption,
The resource management method according to any one of supplementary note 13 to supplementary note 15, wherein a configuration with the smallest expected power consumption is adopted in the optimal allocation calculation step.

(Appendix 17)
In the configuration candidate evaluation step,
With reference to an existing VM arrangement table that records the virtual machine and the service SLA in association with each other, the number of the virtual machines associated with the service SLA is specified,
Any one of appendix 13 to appendix 16, wherein the requested resource amount of the service SLA is specified with reference to an SLA conversion table that records the requested resource amount of the service SLA, and the total requested resource amount is calculated. The resource management method described in the section.

(Appendix 18)
The resource policy setting means receives the resource policy setting request from the outside, sets the resource policy based on the setting request, and sets the dedicated function resource amount range and the configuration plan based on the set resource policy. The resource management method according to any one of supplementary note 13 to supplementary note 17, further comprising: a resource policy setting step for changing an evaluation criterion.

(Appendix 19)
A resource management program that operates on a computer constituting a resource management server in a virtualization system including a virtualization server on which a virtual machine that provides a service operates, a disk array device that includes a plurality of disks, and a resource management server. And
For each service SLA set in the virtual machine, either a configuration candidate that uses a dedicated device having a dedicated function for realizing the service SLA or a configuration candidate that uses a general-purpose device. Execute configuration candidate evaluation process to decide whether to adopt,
A configuration plan is created by using the configuration candidate adopted in the configuration candidate evaluation step, and a configuration that best matches the configuration plan evaluation criteria determined based on a predetermined resource policy is adopted as the optimal arrangement calculation means. Run the optimal placement calculation process,
Causing the placement execution means to execute placement execution processing for changing the operation or setting of the virtual machine or the disk array device based on the adopted configuration;
In the configuration candidate evaluation process,
Dedicated functional resource that defines a range of required resource amount that requires less power when the service SLA is realized by the general-purpose device than when the service SLA is realized by the general-purpose device. A resource management program characterized in that, based on a quantity range, when the total requested resource quantity obtained from the service SLA is within the range of the dedicated function resource quantity range, the dedicated device is determined to be used.

(Appendix 20)
The dedicated device is the disk array device;
The resource management program according to appendix 19, wherein the general-purpose device is the virtualization server.

(Appendix 21)
The service SLA is data encryption;
The resource management program according to appendix 19 or appendix 20, wherein the disk array device includes an encrypted physical disk.

(Appendix 22)
If the resource policy is to minimize power consumption,
The resource management program according to any one of appendix 19 to appendix 21, wherein a configuration with the smallest expected power consumption is employed in the optimal allocation calculation process.

(Appendix 23)
In the configuration candidate evaluation process,
With reference to an existing VM arrangement table that records the virtual machine and the service SLA in association with each other, the number of the virtual machines associated with the service SLA is specified,
Any one of appendix 19 to appendix 22, wherein the requested resource amount of the service SLA is specified with reference to an SLA conversion table that records the requested resource amount of the service SLA, and the total requested resource amount is calculated. The resource management program described in the section.

(Appendix 24)
The resource policy setting means receives the resource policy setting request from the outside, sets the resource policy based on the setting request, and sets the dedicated function resource amount range and the configuration plan based on the set resource policy. 24. The resource management program according to any one of appendix 19 to appendix 23, wherein a resource policy setting process for changing an evaluation criterion is executed.

  ADVANTAGE OF THE INVENTION According to this invention, in the system which provides resources, such as a data center, to a some service, it can utilize for the system which calculates distribution of resources. In particular, the present invention can be used for a system that automatically determines resource distribution and implements it.

DESCRIPTION OF SYMBOLS 10: Virtualization system 100: Resource management server 101: Resource policy setting means 102: Configuration candidate evaluation means 103: Optimal arrangement calculation means 104: SLA conversion table 105: Existing VM arrangement table 106: Device information table 107: VM arrangement change request Acceptance means 108: Placement recalculation request acceptance means 109: Placement execution means 110: VM operation means 111: Server operation means 112: Storage operation means 200: Virtualization server 201: Server setting execution means 202: Virtual machine (VM)
203: VM setting execution means 300: Disk array device 301: Disk array device setting execution means 302: Logical disk 303: Physical disk 304: Encrypted physical disk 305: Pool 400: Client terminal 1001: CPU
1002: Main storage unit 1003: Communication unit 1004: Input / output interface unit 1005: Input device 1006: Output device 1007: Storage device 1008: System bus

Claims (10)

A virtualization server on which a virtual machine providing a service operates;
A disk array device including a plurality of disks;
A resource management server,
The resource management server is
For each service SLA set in the virtual machine, it is determined whether to adopt a configuration candidate using a dedicated device having a dedicated function for realizing the service SLA or a configuration candidate using a general-purpose device. Configuration candidate evaluation means,
Creating a configuration plan using the configuration candidates adopted by the configuration candidate evaluation unit, and adopting a configuration that best matches a configuration plan evaluation criterion determined based on a predetermined resource policy; and
An arrangement execution means for executing operation and setting change of the virtual machine and the disk array device based on the adopted configuration;
The configuration candidate evaluation means
Dedicated functional resource that defines a range of required resource amount that requires less power when the service SLA is realized by the general-purpose device than when the service SLA is realized by the general-purpose device. The virtualization system according to claim 1, wherein when the total requested resource amount obtained from the service SLA is within the range of the dedicated function resource amount range based on the amount range, the dedicated device is determined to be used. The dedicated device is the disk array device;
The virtualization system according to claim 1, wherein the general-purpose device is the virtualization server. The service SLA is data encryption;
The virtualization system according to claim 1 or 2, wherein the disk array device includes an encrypted physical disk. If the resource policy is to minimize power consumption,
The virtualization system according to any one of claims 1 to 3, wherein the optimum arrangement calculation unit employs a configuration with the least expected power consumption. An existing VM placement table for recording the virtual machine and the service SLA in association with each other;
An SLA conversion table for recording the requested resource amount of the service SLA;
The configuration candidate evaluation means
The number of the virtual machines associated with the service SLA is specified with reference to the existing VM placement table, the requested resource amount of the service SLA is specified with reference to the SLA conversion table, and the total required resource amount is calculated The virtualization system according to any one of claims 1 to 4, characterized in that: A resource that receives the setting request for the resource policy from the outside, sets the resource policy based on the setting request, and changes the dedicated function resource amount range and the configuration plan evaluation criteria based on the set resource policy The virtualization system according to any one of claims 1 to 5, further comprising policy setting means. A resource management server in a virtualization system comprising a virtualization server on which a virtual machine providing a service operates, a disk array device including a plurality of disks, and a resource management server,
For each service SLA set in the virtual machine, it is determined whether to adopt a configuration candidate using a dedicated device having a dedicated function for realizing the service SLA or a configuration candidate using a general-purpose device. Configuration candidate evaluation means,
Creating a configuration plan using the configuration candidates adopted by the configuration candidate evaluation unit, and adopting a configuration that best matches a configuration plan evaluation criterion determined based on a predetermined resource policy; and
An arrangement execution means for executing operation and setting change of the virtual machine and the disk array device based on the adopted configuration;
The configuration candidate evaluation means
Dedicated functional resource that defines a range of required resource amount that requires less power when the service SLA is realized by the general-purpose device than when the service SLA is realized by the general-purpose device. The resource management server according to claim 1, wherein when the total requested resource amount obtained from the service SLA is within the range of the dedicated function resource amount range based on the amount range, the dedicated device is determined to be used. An existing VM placement table for recording the virtual machine and the service SLA in association with each other;
An SLA conversion table for recording the requested resource amount of the service SLA;
The configuration candidate evaluation means
The number of the virtual machines associated with the service SLA is specified with reference to the existing VM placement table, the requested resource amount of the service SLA is specified with reference to the SLA conversion table, and the total required resource amount is calculated The resource management server according to claim 7, wherein: A resource management method by a resource management server in a virtualization system comprising a virtualization server on which a virtual machine providing a service operates, a disk array device including a plurality of disks, and a resource management server,
For each service SLA set in the virtual machine, the configuration candidate evaluation unit selects either a configuration candidate using a dedicated device having a dedicated function for realizing the service SLA or a configuration candidate using a general-purpose device. Configuration candidate evaluation step for determining whether to adopt,
The optimal arrangement calculation means creates a configuration plan using the configuration candidates adopted in the configuration candidate evaluation step, and adopts the configuration that best matches the configuration plan evaluation criteria determined based on a predetermined resource policy. An optimal placement calculation step;
An arrangement execution unit has an arrangement execution step for executing an operation or setting change of the virtual machine or the disk array device based on the adopted configuration,
In the configuration candidate evaluation step,
Dedicated functional resource that defines a range of required resource amount that requires less power when the service SLA is realized by the general-purpose device than when the service SLA is realized by the general-purpose device. A resource management method comprising: determining that the dedicated device is to be used when a total required resource amount obtained from the service SLA is within the range of the dedicated function resource amount range based on a quantity range. A resource management program that operates on a computer constituting a resource management server in a virtualization system including a virtualization server on which a virtual machine that provides a service operates, a disk array device that includes a plurality of disks, and a resource management server. And
For each service SLA set in the virtual machine, either a configuration candidate that uses a dedicated device having a dedicated function for realizing the service SLA or a configuration candidate that uses a general-purpose device. Execute configuration candidate evaluation process to decide whether to adopt,
A configuration plan is created by using the configuration candidate adopted in the configuration candidate evaluation step, and a configuration that best matches the configuration plan evaluation criteria determined based on a predetermined resource policy is adopted as the optimal arrangement calculation means. Run the optimal placement calculation process,
Causing the placement execution means to execute placement execution processing for changing the operation or setting of the virtual machine or the disk array device based on the adopted configuration;
In the configuration candidate evaluation process,
Dedicated functional resource that defines a range of required resource amount that requires less power when the service SLA is realized by the general-purpose device than when the service SLA is realized by the general-purpose device. A resource management program characterized in that, based on a quantity range, when the total requested resource quantity obtained from the service SLA is within the range of the dedicated function resource quantity range, the dedicated device is determined to be used.

Images