WO2013031999A1

WO2013031999A1 - Extraction device, system, program, and method

Info

Publication number: WO2013031999A1
Application number: PCT/JP2012/072284
Authority: WO
Inventors: 繁細野
Original assignee: 日本電気株式会社
Priority date: 2011-09-02
Filing date: 2012-08-28
Publication date: 2013-03-07

Abstract

[Problem] To appropriately extract a processing device holding resources fulfilling requirements. [Solution] An extraction device, comprising: a resource conditions storage means that associates and stores requirement items and resource conditions including at least one resource type and the requirement amount for each resource; a resource status acquisition means that obtains the amount of each resource held in a plurality of processing devices, for each resource type; and an extraction means that obtains the requirement items from outside, and, if the resource holding for each resource type held by at least one said processing device meets the resource requirement amount for each resource type included in the resource conditions associated with the obtained requirements, extracts identification information for the at least one processing device from a plurality of processing devices and outputs same.

Description

Extraction apparatus, system, program, and method

The present invention relates to an extraction apparatus, a system, a program, and a method.

Cloud providers and the like provide resources such as a CPU (Central Processing Unit) and memory to users who develop applications that are executed in a cloud environment.
However, it is not always easy for a cloud business operator or the like to allocate resources to a user so as to match the user's request. The reason for this is that while operating the cloud environment, the same resource is shared by multiple applications, and the resources that can be used change over time. This is because resources must be allocated appropriately.
In response to this problem, cited document 1 discloses an example of a method for managing a plurality of computer resources and allocating requested computer resources to a user in response to a resource request for requesting allocation of computer resources. Also, cited document 2 discloses an example of a system that determines a combination of components from requirements with high importance based on a user request for system requirements. Also, cited document 3 discloses an example of a sizing support system that estimates hardware requirements when constructing an application system.
JP2011-18198A JP 2009-105503 A JP 2011-060053 A

However, the above-described technique has a problem that it is difficult to appropriately extract a processing device or the like having resources that satisfy a user's request from a plurality of processing devices.
Therefore, an object of the present invention is to provide an extraction device, system, program, and method that can appropriately extract processing devices and the like that have resources that satisfy the requirements in order to solve the above-described problems.

In order to achieve such an object, one aspect of the present invention is an extraction device that stores a request item, a resource condition including one or more resource types, and a request amount for each resource in association with each other. Resource condition storage means, resource status acquisition means for acquiring the amount of the resource of each of the plurality of processing devices for each type of the resource, and one or more processing devices that acquire the request item from the outside When the amount of resources held by the resource satisfies the resource request amount included in the resource condition corresponding to the acquired request item, the identification information of the one or more processing devices is obtained from the plurality of processing devices. Extracting means for extracting and outputting.
Further, the present invention provides a computer including resource condition storage means for storing a request item, a resource condition including one or more resource types and a request amount for each resource, in association with each resource type. In addition, a resource status acquisition step for acquiring the amount of the resource held by each of the plurality of processing devices, and the request item is acquired from the outside, and the amount of the resource held by one or more of the processing devices is acquired. Extraction that extracts and outputs identification information of the one or more processing devices from the plurality of processing devices when the resource request amount for each resource type included in the resource condition corresponding to the request item is satisfied And an extraction program for executing the steps.
Further, the present invention stores a request item, a resource condition including one or more resource types and a request amount for each resource in association with each other, and each of the plurality of processing devices for each resource type. The resource holding amount is acquired, the request item is acquired from the outside, and the resource holding amount held by one or more of the processing devices includes the resource condition corresponding to the acquired request item Provided is an extraction method for extracting the identification information of the one or more processing devices from the plurality of processing devices when the resource requirement amount for each type is satisfied.

The present invention provides an extraction device, a system, a program, and a method that can appropriately extract a processing device or the like having a resource that satisfies a request.

It is a figure which shows an example of a structure of 1st Embodiment. It is a figure which shows an example of the resource condition storage part of 1st Embodiment. It is a figure which shows an example of the resource state storage part of 1st Embodiment. It is a figure which shows an example of operation | movement of a resource management server. It is a figure which shows an example of operation | movement of an extracting device. It is a figure which shows an example of operation | movement of an extracting device. It is a figure which shows an example of the resource condition storage part of 2nd Embodiment. It is a figure which shows an example of operation | movement of the extraction apparatus of 2nd Embodiment. It is a figure which shows an example of a structure of an extraction apparatus. It is a figure which shows an example of a structure of the extraction apparatus of 3rd Embodiment.

Hereinafter, embodiments of the present invention will be described with reference to the drawings. In all the drawings, the same components are denoted by the same reference numerals, and description thereof will be omitted as appropriate.
In addition, each part which comprises the apparatus of each embodiment is comprised by hardware, such as a logic circuit. Each unit includes a computer control unit, a memory, a program loaded in the memory, a storage unit such as a hard disk for storing the program, a network connection interface, and the like, and may be realized by any combination of hardware and software. Good. And unless there is particular notice, the realization method and apparatus are not limited.
The control unit is composed of a CPU (Central Processing Unit) or the like, and operates an OS (Operating System) to control the entire apparatus and the like. For example, a program and data are stored in a memory from a recording medium mounted on a drive device or the like. Read and execute various processes according to this. The recording medium is, for example, an optical disk, a flexible disk, a magnetic optical disk, an external hard disk, a semiconductor memory, or the like, and records a computer program so that the computer can read it. The computer program may be downloaded from an external computer (not shown) connected to the communication network.
<Embodiment 1>
Next, a first embodiment of the present invention will be described with reference to the drawings. FIG. 1 shows an extraction system 4 according to the present embodiment.
The extraction system 4 includes an extraction device 1, a resource management server 2, and a server group 3. An example of the extraction system 4 is shown in FIG. The extraction device 1 and the resource management server 2 are connected by a communication line or the like. The resource management server 2 and the server group 3 are connected by a communication line or the like.
The server group 3 includes a plurality of servers (information processing apparatuses), and each server includes resources such as a CPU, a memory, and a communication line. The hardware included in each server has characteristics such as quantity and performance that affect the performance and reliability of the system using the server, and each characteristic is called a resource type. The types of resources included in each server include CPU performance and network bandwidth. Also, the resource holding amount is defined corresponding to the resource type. The resource holding amount is a numerical value indicating the degree to which the characteristic contributes to performance and reliability. That is, the amount of resources held by each server is not limited to the amount of physical resources held by each server, but includes the performance value of each server. For example, the resource holding amount is xMIPS (Million Instructions Per Second) for CPU performance, y for the number of CPU cores, zGbps (Gigabit per second) for the network bandwidth, and the like.
The extraction device 1 includes a request input unit 11, an extraction unit 12, a resource condition storage unit 13, a resource state acquisition unit 14, and a display unit 15.
The request input unit 11 is an input means for a user or the like to input a function request or a non-function request. The user or the like may use the request input unit 11 to input a resource type or a resource request amount that the user or the like requests from the cloud environment system.
Here, the resource type is a type for distinguishing resources, and is not limited to the amount of hardware such as the number of CPU cores as described above, but also includes performance such as CPU performance and network bandwidth. The resource request amount is an amount by which a user or the like requests each resource type. For example, xMIPS (Million Instructions Per second) for CPU performance, y for the number of CPU cores, and zGbps (for network bandwidth). Gigabit per second).
The request input by the user or the like may include a request item and a request level. The request item is a non-functional request item such as response time, operation time, reliability, and extensibility requested by the user or the like to the cloud environment system. The request item may be a function request item such as hot standby or encryption. The request level indicates whether a request from a user or the like is high or low for each request item. For example, if the request item is a response time, the request level is within 10 seconds, and the request item is an operation time. If so, the required level is, for example, an average failure time of 6 months. In some cases, the request does not include the request level and is only a request item.
A user or the like inputs a request via the request input unit 11. The request input unit 11 outputs the input request to the extraction unit 12 described later.
As shown in FIG. 2, the resource condition storage unit 13 stores the request and the resource condition in association with each other. As shown in FIG. 2, the resource condition is information in which one or more resource types are associated with a resource request amount for each resource type.
At the top of the table in FIG. 2, the resource condition for satisfying the request whose request item is the response time and the request level is within 10 seconds is the resource type and the resource request amount of the resource type. Combination (CPU performance is aMIPS, number of CPU cores is 1, network bandwidth is bGbps, HD (Hard Disc) rotation speed is crpm (revolution per minute / rotation per minute), maximum IO (Input / Output) waiting time is dmsec ( milli-second)). In this way, the resource condition storage unit 13 stores, for example, a request (request item and its request level) and a resource condition (one or more resource types and its resource request amount) satisfying the request in association with each other. Yes.
The resource state acquisition unit 14 acquires a resource holding amount (resource holding amount) for each resource type (resource type) included in each of the plurality of servers. The resource status acquisition unit 14 may acquire the resource holding amount of each of the plurality of servers from the resource status storage unit 22 described later, or may acquire from the server group 3 as shown in FIG. .
When the condition is satisfied, the extraction unit 12 extracts server identification information of one or more servers from the server. The condition is that the resource holding amount for each resource type held by the one or more servers satisfies the resource request amount for each resource type included in the resource condition corresponding to the request input from the request input unit 11 ( It is simply referred to as a resource condition). As will be described later, the extraction unit 12 may extract the server identification information from the resource state storage unit 22 instead of extracting the server identification information directly from the server.
Further, the extraction unit 12 outputs the extracted server identification information. Although the output destination is not limited, for example, the extracting unit 12 may output the extracted server identification information to the display unit 15. In addition, when the above-described server does not exist, the extraction unit 12 may output to the display unit 15 that no server that satisfies the resource condition exists.
In addition, the extraction unit 12 includes a plurality of servers in which a total amount of resource holding amounts for each resource type held by a plurality of servers satisfies a resource request amount for each resource type included in a resource condition corresponding to the input request. The identification information may be extracted from the server group 3 and output. For example, as one of the resource conditions corresponding to the request input by the user, when the resource type is CPU performance and the resource request amount is 100 MIPS, the server identification information is A server, and the server identification information is B server. In the case where the CPU performances in total are 100 MIPS or more, the extraction unit 12 may extract the server identification information A and B.
As described above, the extraction unit 12 extracts a plurality of servers in which the total amount of resources held by each server satisfies the resource condition, thereby constructing a cloud environment that cannot be realized by a single server. It becomes possible.
In addition, when a plurality of requests are input from the request input unit 11, the extraction unit 12 receives the server identification information of one or more servers that satisfy all the resource conditions corresponding to each of the requests, the resource state storage unit 22, and the like. May be extracted from Specific examples will be described later.
The display unit 15 is a display unit such as a display that displays the server identification information acquired from the extraction unit 12. The user looks at the server identification information displayed on the display unit 15 or sees information indicating that there is no server that satisfies the resource condition, thereby determining whether there is a server that satisfies the user's request. I can grasp it.
The resource management server 2 includes a resource management unit 21 and a resource state storage unit 22.
The resource management unit 21 periodically obtains, from the server group 3, the identification information of the server that holds the currently available resource, the resource type of the resource held by each server, and the resource holding amount for each resource type. And stored in the resource state storage unit 22. The server identification information, the resource type, and the resource holding amount of the server that holds the currently available resource, which is information acquired by the resource management unit 21, are also referred to as a resource state. For example, the resource management unit 21 may periodically acquire a resource state every predetermined time and store it in the resource state storage unit 22.
The resource state storage unit 22 stores the resource state acquired by the resource management unit 21. FIG. 3 is an example of a resource state stored in the resource state storage unit 22. The top row of the table of FIG. 3 indicates that there is a server whose server identification information is A in the server group 3 at a certain point in time. The server A resource type and its resource holding amount are: CPU performance: eMIPS, number of CPU cores: 2, network bandwidth: fGbps, HD rotation speed: grpm, maximum IO wait time: hmsec, standby system 3 units, HDRAID 1 (Redundant Arrays of Independent Disks): 2 units.
The resource management server 2 may be managed by a cloud provider or the like different from the extraction device 1. In this case, there is an advantage that the person who operates the extraction apparatus 1 does not have to manage the server group 3 directly. In addition, a cloud operator or the like that manages the resource management server 2 can appropriately correct the contents of the resource state acquired by the resource management unit 21 via a correction unit (not shown) provided in the management server 2. . For example, in addition to resources that are currently available, a cloud business operator or the like adds resources that are scheduled to become available soon (for example, resources that are scheduled to be purchased or that will end maintenance) to the resource state storage unit 22. May be. Conversely, the cloud service provider deletes resources that the user does not want to allocate from the resource state storage unit 22 because maintenance is required or the user does not want to share resources with other users. Also good.
Next, operation | movement of the extraction system 4 of this Embodiment is demonstrated.
The operation of the resource management server 2 will be described. FIG. 4 shows the operation of the resource management server 2. The resource management unit 21 of the resource management server 2 periodically acquires from the server group 3 server identification information of servers that have resources available at that time, resource types of resources held by each server, and resource types. Each resource holding amount is acquired (step S1), and those resource states are stored in the resource state storage unit 22 (step S2). In addition, the cloud business operator etc. which manage the resource management server 2 may correct the content of the resource state which the resource management part 21 acquired suitably.
The operation of the extraction device 1 will be described. 5 and 6 show the operation of the extraction device 1.
First, the request input unit 11 acquires a request from a user or the like (step S11). Next, the extraction unit 12 acquires a resource condition corresponding to the request input from the user or the like in step S11 from the resource condition storage unit 13 (step S12). For example, when a user or the like inputs a request that the response time is within 10 seconds, the extraction unit 12 refers to the resource condition storage unit 13 and extracts a resource condition corresponding to the request. In this case, as shown in FIG. 2, the resource conditions corresponding to the request are CPU performance: aMIPS, number of CPU cores: 1, network bandwidth: b Gbps, HD rotation speed: c rpm, and maximum IO waiting time: dmsec. .
Next, the extraction unit 12 searches the resource state storage unit 22 for the server identification information that satisfies the resource condition extracted in step S12. If there is server identification information that satisfies the resource conditions, the server identification information is extracted and output. If there is no server identification information that satisfies the resource condition, a process of outputting that there is no server that satisfies the resource condition (server extraction process) is performed (step S13).
The detailed operation of the server extraction process in step S13 will be described with reference to FIG.
First, the extraction unit 12 sets N = 1 (step S131). Subsequently, identification information of N (here, 1) servers whose resource holding amount for each resource type of the extracted resource condition satisfies the resource condition extracted in step S12 exists in the resource state storage unit 22. It is determined whether or not (step S132). This determination is made with reference to the resource state acquired by the resource state acquisition unit 14 from the resource state storage unit 22.
If there are N (1 here) servers that satisfy the resource condition, the extraction unit 12 extracts the server identification information of such servers from the resource state storage unit 22 and outputs the extracted server identification information to the display unit 15 (step 15). S133).
On the other hand, when there are N (here, 1) servers that satisfy the resource condition, the extraction unit 12 adds 1 to N (step S134). Further, it is determined whether N exceeds a predetermined value (step S135). The predetermined value is, for example, a value designated in advance by a cloud operator or the like.
If N does not exceed the predetermined value, the extraction unit 12 repeats step S132. That is, it is determined by referring to the resource state acquired by the resource state acquisition unit 14 whether or not there are N servers that satisfy the resource condition (N is 1 in this case because N is added in step S134). (Step S132). That is, the extraction unit 12 makes the total amount of resources held for each resource type held by N (here 2) servers satisfy the resource request amount for each resource type corresponding to the input request. It is determined whether there are N (here, 2) servers.
If there are N (here 2) servers that satisfy the resource condition, the extraction unit 12 extracts the server identification information of such servers from the server group 3 and the resource state storage unit 22 and displays them on the display unit 15 and the like. Output (step S133).
On the other hand, when there are N (here, 2) servers that satisfy the resource condition, the extraction unit 12 adds 1 to N again (step S134), and determines whether N exceeds a predetermined value (step S134). S135). If N does not exceed the predetermined value, the extraction unit 12 performs Step S132 again. As described above, as long as N does not exceed the predetermined value, the extraction unit 12 repeats step S132, and when there are N servers that satisfy the resource condition, the value of N is sequentially increased by one in step S134. Repeat the process.
On the other hand, if the extraction unit 12 determines that N exceeds a predetermined value in step S135, the extraction unit 12 outputs to the display unit 15 or the like that there is no server that satisfies the resource condition (step S136).
In addition, when a plurality of requests are input from the request input unit 11, the extraction unit 12 receives the server identification information of one or more servers that satisfy all the resource conditions corresponding to each of the requests, the resource state storage unit 22, and the like. May be extracted from A specific example will be described with reference to FIG. For example, when a response time: within 10 seconds and an operation time: an average failure time of 6 months are input as requests, the extraction unit 12 determines the CPU performance as a resource condition corresponding to the request with a response time: within 10 seconds. : AMIPS, number of CPU cores: 1, network bandwidth: b Gbps, HD rotation speed: c rpm, maximum IO waiting time: dmsec are extracted. Further, the extraction unit 12 extracts one or more HDRAID 1: 1, which is a resource condition corresponding to a request of operating time: average failure time of 6 months. Then, the extraction unit 12 extracts server identification information of one or more servers that satisfy all of the extracted resource conditions from the resource state storage unit 22 and the like. As described above, the extraction unit 12 regards a condition obtained by combining resource conditions corresponding to each of a plurality of requests as a new resource condition. Whether or not there is a server that satisfies the new resource condition may be extracted according to the operations shown in FIGS.
Also, for example, when a response time: within 10 seconds and an operation time: an average failure time of 10 months are input as requests, the extraction unit 12 is a resource condition corresponding to the request with a response time: within 10 seconds. CPU performance: aMIPS, number of CPU cores: 1, network bandwidth: b Gbps, HD rotation speed: crpm, maximum IO waiting time: dmsec are extracted. In addition, the extraction unit 12 extracts one standby system that is a resource condition corresponding to a request of operating time: average failure time of 10 months. Here, when the extracted resource condition includes “standby system”, the extraction unit 12 displays the server identification information of the server that satisfies all the resource conditions excluding the “standby system” condition as “standby system”. An extra amount is extracted from the resource state storage unit 22 and the like by the required resource amount required for the “system”. That is, in this example, the extraction unit 12 selects one or more servers that satisfy CPU performance: aMIPS, number of CPU cores: 1, network bandwidth: b Gbps, HD rotation speed: c rpm, and maximum IO waiting time: dmsec. Only one resource, which is the required resource amount required for the “standby system”, is extracted from the resource state storage unit 22 and the like. That is, two sets of server identification information of one or more servers satisfying CPU performance: aMIPS, number of CPU cores: 1, network bandwidth: b Gbps, HD rotation speed: c rpm, and maximum IO waiting time: dmsec are extracted.
The above description is based on the assumption that the resource management server 2 exists. When the resource management server 2 does not exist, the following may be performed. That is, the extraction unit 12 may perform a process (server extraction process) for directly searching the server group 3 as to whether or not the server group 3 includes a server that satisfies the resource condition extracted in step S12. In this process, if a server that satisfies the resource condition exists in the server group 3, the server identification information is extracted and output. If there is no server identification information that satisfies the resource condition, a message that no server satisfies the resource condition is output.
According to the present embodiment, for each resource type, the amount of resource possessed by each of the plurality of servers is acquired, and the amount of resource retained for each resource type possessed by one or more servers is determined by the user, etc. When the resource request amount corresponding to the resource type corresponding to the request input from is satisfied, the identification information of the one or more servers is extracted. Therefore, it is possible to appropriately extract a processing apparatus that has resources that satisfy a user's request.
In particular, the extraction unit 12 can extract identification information of a plurality of servers in which the total amount of resources held satisfies the resource request amount corresponding to the input request. For this reason, even if one server does not satisfy the resource request amount, the plurality of servers are allocated to the user when the total amount of the resource holding amount of the plurality of servers satisfies the resource request amount. In this way, it is possible to construct a cloud environment that satisfies the user's request.
<Embodiment 2>
Next, a second embodiment of the present invention will be described with reference to the drawings. The configuration diagram of the extraction system 4 of the present embodiment is the same as that shown in FIG. 1, but the information stored in the resource condition storage unit 13 and the processing of the extraction unit 12 are the same as those in the first embodiment. Different from form.
The resource condition storage unit 13 of this embodiment will be described.
FIG. 7 shows an example of information stored in the resource condition storage unit 13 in the present embodiment. As illustrated in FIG. 7, the resource condition storage unit 13 associates a plurality of resource conditions including a plurality of resource types and a request amount of each resource of the plurality of resources with respect to the same request. Storing. Thus, the second embodiment is different from the first embodiment in that a plurality of resource conditions that satisfy the same request are stored.
When there are various combinations of resource types and resource request amounts that satisfy the same request, each resource condition is set as an alternative condition that satisfies the same request.
For example, among a plurality of resource conditions corresponding to a certain request, the resource type included in one resource condition is the same as the resource type included in another resource condition, and the resource request amount corresponding to the resource type is different. There is a case. That is, when satisfying the same request, a shortage of one resource may be compensated by an increase in other resources. For example, among a plurality of resource conditions corresponding to a certain request, the CPU performance included in a certain resource condition is 1000 MIPS, the network bandwidth is 1 Gbps, the CPU performance included in other resource conditions is 50 MIPS, and the network bandwidth is 20 Gbps. There may be. This is a case where communication data compression can be simplified when the CPU performance is low, for example. In addition, for example, in some resource conditions, the CPU resource request amount is small instead of the CPU resource request amount, and in other resource conditions, the CPU resource request amount is small but the memory resource request amount is large. . In this way, each resource condition is set as an alternative condition that satisfies the same request. A plurality of resource conditions including different resource types may exist for the same request.
In the present embodiment, the extraction unit 12 includes identification information of one or more servers that satisfy any of the resource conditions stored in the resource condition storage unit 13 and corresponding to the request input from the user or the like. Extract and output.
Further, as shown in FIG. 7, the resource condition storage unit 13 may store a resource condition and a priority order in association with each resource condition. And the extraction part 12 may extract and output the identification information of one or more servers which satisfy | fill the resource conditions with high priority among resource conditions. The priority order may be preset by, for example, a cloud operator.
Next, the operation of the extraction system 4 of the present embodiment will be described with reference to FIGS. Since the operation of the resource management server 2 is the same as that of the first embodiment, the description thereof is omitted.
8 and 6 show the operation of the extraction device 1.
First, the request input unit 11 acquires a request from a user or the like (step S21). Next, the extraction unit 12 acquires a resource condition corresponding to the request input from the user or the like in step S21 from the resource condition storage unit 13 (step S22). For example, when the user or the like inputs a request that the response time is within 10 seconds, the extraction unit 12 refers to the resource condition storage unit 13 and, as shown in FIG. CPU performance: aMIPS, number of CPU cores: 1, network bandwidth: b Gbps, HD rotation speed: c rpm, maximum IO waiting time: dmsec are extracted. In the present embodiment, since a plurality of resource conditions satisfying the same request are stored in the resource condition storage unit 13, the extraction unit 12 satisfies the same request stored in the resource condition storage unit 13. Extract all resource conditions. This point is different from the first embodiment.
Next, the extraction unit 12 sets K = 1 (step S23), and searches for whether or not the identification information of the server that satisfies the Kth (here, 1) priority resource condition exists in the resource state storage unit 22 Then, the extraction process (server extraction process) is performed (step S24).
The server extraction process in step S24 is the same as the server extraction process of FIG.
Next, the extraction unit 12 determines whether or not server identification information satisfying the resource condition of the priority K (here, 1) is obtained as a result of the server extraction process (step S25).
When the identification information of the server that satisfies the resource condition of priority K (here, 1) is obtained (step S25, Yes), the extraction unit 12 displays the identification information of the server in the resource state storage unit 22 (resource The resource state acquired by the resource state acquisition unit 14 from the state storage unit 22 is extracted and output to the display unit 15 or the like.
On the other hand, when the identification information of the server that satisfies the resource condition of priority K (here 1) is not obtained (No in step S25), the extraction unit 12 adds 1 to K (step S27). Next, the extraction unit 12 determines whether or not K exceeds a predetermined value (step S28). The predetermined value is, for example, a value designated in advance by a cloud operator or the like.
When K does not exceed the predetermined value (step S28, Yes), the extraction unit 12 performs step S24 again. As described above, when the identification information of the server with the Kth priority cannot be extracted, the extraction unit 12 repeats Step S24, Step S25, and Step S27 until K exceeds a predetermined value. On the other hand, if K exceeds a predetermined value (step S28, No), the extraction unit 12 outputs to the display unit 15 or the like that there is no server that satisfies the resource condition (step S29).
As a result of the above processing, the extraction device 1 is the server that satisfies the resource condition of the Kth priority, and the identification information of the N servers whose total resource holding amount for each resource type satisfies the resource request amount is the resource. Whether or not it exists in the state storage unit 22 can be searched while increasing the values of K and N sequentially.
In the above processing, an example has been described in which K, which is a priority number associated with a resource condition, is first determined, and then the number N of servers satisfying the Kth resource condition is sequentially increased. .
That is, for example, the extraction unit 12 first searches whether there is one server that satisfies the first priority resource condition. When one server does not exist, the extraction unit 12 searches whether there are two servers that satisfy the first resource condition of the priority order.
When there are no two servers, the extraction unit 12 increases the number N of servers sequentially in the same manner, and determines whether or not there are N servers that satisfy the first priority resource condition. Search for.
When N exceeds a predetermined value, the extraction unit 12 next increases the priority by 1 and searches whether there is a server that satisfies the second priority resource condition. In the same manner, first, the value of K is determined while sequentially increasing the priority K, and whether or not there are N servers satisfying the Kth resource priority is determined by sequentially increasing N. Search for.
This method emphasizes the construction of a cloud environment by extracting servers that satisfy the higher priority resource conditions rather than emphasizing the construction of a cloud environment with a small number of servers. It is a method to do.
On the other hand, the extraction device 1 may first determine the number N of servers, and then sequentially increase the priority number K.
That is, for example, the extraction unit 12 first searches whether there is a server that satisfies the first resource condition with the number of servers being one. If there is no server, the extraction unit 12 searches for a set of servers that satisfy the second priority resource condition with one server. If there is no such server, the extraction unit 12 increases the priority number K sequentially in the same manner, and determines whether there is one server that satisfies the Kth resource condition. Search for no.
When K exceeds a predetermined value, the extraction unit 12 then increases the number of servers by 1, and whether there is a server that satisfies the first resource condition with the number of servers being 2 and the first priority. Search for. Similarly, the extracting unit 12 determines the value of N while sequentially increasing the number N of servers, and then sequentially increases the priority number K to satisfy the resource condition of the Kth priority. Search whether a server exists.
This method focuses on building a cloud environment with a small number of servers, rather than focusing on building a cloud environment by extracting servers that satisfy the higher priority resource conditions when building a cloud environment. It is a method to do.
According to the present embodiment, the resource condition storage unit 13 stores a plurality of resource conditions in association with the same request. Therefore, the extraction unit 12 can extract and output identification information of one or more servers that satisfy any of a plurality of resource conditions corresponding to the input request.
Further, since the resource condition storage unit 13 stores the priority for each resource condition, the extraction unit 12 identifies the identification information of one or more servers that satisfy the resource condition with the higher priority among the plurality of resource conditions. Can be extracted and output.
As described above, according to the extraction system 4 of the present embodiment, it is possible to appropriately extract a server having resources that satisfy a request from a user or the like.
<Embodiment 3>
Next, a third embodiment of the present invention will be described with reference to the drawings. FIG. 10 shows an example of the configuration of the extraction device 1 according to the present embodiment.
The extraction device 1 includes a resource condition storage unit 13, a resource state acquisition unit 14, and an extraction unit 12.
The resource condition storage unit 13 stores a request and a resource condition including the resource type and the requested amount of the resource in association with each other.
The resource status acquisition unit 14 acquires the resource holding amount of each of the plurality of information processing apparatuses for each resource type.
The extraction unit 12 satisfies the resource request amount for each resource type stored in the resource condition storage unit 13 corresponding to the input request, with the resource holding amount for each resource type held by one or more information processing apparatuses. In this case, the identification information of the one or more information processing devices is extracted from a plurality of information processing devices and output. Here, the extraction unit 12 may extract the identification information directly from the information processing apparatus (server group 3) (see FIG. 9) or may be extracted from the resource management server 2 (see FIG. 1).
According to the present embodiment, an extraction device, a system, a program, and a method that can extract an information processing device that has a resource that satisfies a request are provided.
This application claims the priority on the basis of Japanese application Japanese Patent Application No. 2011-191897 for which it applied on September 2, 2011, and takes in those the indications of all here.
While the present invention has been described with reference to the embodiments, the present invention is not limited to the above embodiments. Various changes that can be understood by those skilled in the art can be made to the configuration and details of the present invention within the scope of the present invention. For example, the extraction unit 12 may extract not only a server but also other devices such as a disk device.

DESCRIPTION OF SYMBOLS 1 Extraction apparatus 11 Request input part 12 Extraction part 13 Resource condition storage part 14 Resource state acquisition part 15 Display part 2 Resource management server 21 Resource management part 22 Resource state storage part 3 Server group

Claims

Resource condition storage means for storing a request item, a resource condition including one or more resource types and a request amount for each resource, in association with each other;
Resource status acquisition means for acquiring the amount of the resource held by each of a plurality of processing devices for each type of the resource,
The request item is acquired from the outside, and the possession amount of the resource for each resource type held by one or more of the processing devices is the resource type included in the resource condition corresponding to the acquired request item. An extraction device comprising: extraction means for extracting the identification information of the one or more processing devices from the plurality of processing devices and outputting them when the resource request amount is satisfied.
The extraction unit is configured to obtain identification information of a plurality of the processing devices in which a total amount of the resources held satisfies the resource request amount for each resource type included in the resource condition corresponding to the acquired request item. The extraction apparatus according to claim 1, wherein the extraction apparatus extracts and outputs from the plurality of processing apparatuses.
The resource condition storage unit stores a plurality of resource conditions in association with a plurality of resource types and a request amount of each resource of the plurality of resources for the same request item,
The extraction unit extracts and outputs identification information of one or more of the processing devices that satisfy any one of the plurality of resource conditions stored in the resource condition storage unit corresponding to the acquired request item. The extraction device according to any one of 1 to 2.
The resource condition storage means stores the resource condition for each of a plurality (n, n is a natural number of 1 or more) of the request items,
The extraction means acquires a plurality (m, m are natural numbers of 1 or more, m ≦ n) of the request items, and one unit that satisfies the resource condition corresponding to each of the m acquired request items The extraction apparatus according to claim 1, wherein the identification information of the processing apparatus is extracted from the plurality of processing apparatuses and output.
The resource condition storage means stores a priority for each resource condition,
The extraction device according to claim 3, wherein the extraction unit extracts and outputs identification information of one or more of the processing devices that satisfy a resource condition having a high priority among the resource conditions.
A resource management server comprising resource management means for periodically collecting the resource type and the resource holding amount from the processing device and storing them in a resource state storage means;
An extraction system comprising: the resource state acquisition unit that acquires the resource type and the resource holding amount from the resource state storage unit.
A computer comprising resource condition storage means for storing a request item, a resource condition including one or more resource types and a request amount for each resource, in association with each other,
A resource status acquisition step of acquiring the amount of the resource held by each of a plurality of processing devices for each resource type;
The request item is acquired from the outside, and the possession amount of the resource for each resource type held by one or more of the processing devices is the resource type included in the resource condition corresponding to the acquired request item. An extraction program for executing an extraction step of extracting identification information of the one or more processing devices from the plurality of processing devices and outputting them when the resource request amount is satisfied.
The identification information of the plurality of processing devices satisfying the resource request amount for each of the resource types included in the resource condition corresponding to the acquired request item is the total amount of the resource possessed. The extraction program according to claim 7, wherein the extraction step of extracting and outputting from a processing device is executed by the computer.
The resource condition storage unit stores a plurality of resource conditions in association with a plurality of resource types and a request amount of each resource of the plurality of resources for the same request item,
The extraction step of extracting and outputting identification information of one or more processing devices that satisfy any one of the plurality of resource conditions stored in the resource condition storage unit corresponding to the acquired request item to the computer The extraction program according to any one of claims 7 to 8, which is executed.
The resource condition storage means stores the resource condition for each of a plurality (n, n is a natural number of 1 or more) of the request items,
A plurality (m, m are natural numbers greater than or equal to 1 and m ≦ n) is acquired, and one or more processing devices satisfying the resource condition corresponding to each of the m acquired request items The extraction program according to any one of claims 7 to 9, which causes the computer to execute the extraction step of extracting and outputting the identification information from the plurality of processing devices.
The resource condition storage means stores a priority for each resource condition,
The extraction program according to claim 9, which causes the computer to execute the extraction step of extracting and outputting identification information of one or more of the processing devices satisfying a resource condition having a high priority among the resource conditions.
A request item, one or more resource types, and a resource condition including a request amount for each resource are stored in association with each other,
For each resource type, obtain the amount of the resource held by each of a plurality of processing devices,
The resource for each resource type included in the resource condition corresponding to the acquired request item is acquired from the outside, and the amount of the resource for each resource type held by one or more of the processing devices is included in the resource condition corresponding to the acquired request item An extraction method for extracting identification information of the one or more processing devices from the plurality of processing devices and outputting them when the required amount is satisfied.
The identification information of the plurality of processing devices satisfying the resource request amount for each of the resource types included in the resource condition corresponding to the acquired request item is the total amount of the resource possessed. The extraction method according to claim 12, wherein the data is extracted from the processing device and output.
For the same request, a plurality of resource conditions including a plurality of resource types and a request amount of each resource of the plurality of resources are stored in association with each other,
The extraction method according to claim 12, wherein identification information of one or more processing devices that satisfy any of the resource conditions corresponding to the acquired request is extracted and output.
The resource condition is stored for each of the plurality of request items (n, n is a natural number of 1 or more),
A plurality (m, m are natural numbers greater than or equal to 1 and m ≦ n) is acquired, and one or more processing devices satisfying the resource condition corresponding to each of the m acquired request items The extraction method according to claim 12, wherein the identification information is extracted from the plurality of processing devices and output.
Store priorities for each resource condition,
The extraction method according to claim 14, wherein identification information of one or more of the processing devices that satisfy a resource condition having a high priority among the resource conditions is extracted and output.