JP2014157546A - Backup resource provision device, backup resource provision method and backup resource provision program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a backup resource provision device, a backup resource provision method and a backup resource provision program capable of achieving high reliability with a much smaller amount of backup resources.SOLUTION: A backup resource provision device comprises: a reception part; a first calculation part; a second calculation part; a determination part; and a notification part. The reception part receives information from a plurality of information processing systems. The first calculation part calculates the upper limit value of backup resources to be used by each of a plurality of information processing systems on the basis of the received information. The second calculation part calculates the total amount of the backup resources to be used when a plurality of information processor systems are defined as one system as a whole. The determination part compares the total of a request amount included in an assignment request and the use amount of the backup resources used by the information processing system with the upper limit value. The determination part assigns the backup resources to the information processing system on the basis of the comparison result. The notification part notifies the information processing system of the amount of the assigned backup resources.

Description

  The present invention relates to a reserve resource providing apparatus, a reserve resource providing method, and a reserve resource providing program.

  In recent years, as represented by cloud computing, information processing systems that provide services using resources via a network have been spreading.

  If a resource used by the information processing system fails, the quality of the service provided decreases. Therefore, in order to increase the tolerance of the information processing system against failure and improve reliability, a reserve resource is prepared in advance, and when a failure occurs, the failed resource is switched to the reserve resource and used.

Dong Seong Kim, Fumio Machida, Kishor S. Trivedi, “Availability Modeling and Analysis of a Virtualized System”, 15th IEEE Pacific Rim International Symposium on Dependable Computing-PRDC, pp. 365-371, 2009 Ramendra K. Sahoo, Anand Sivasubramaniam, Mark S. Squillante, Yanyong Zhang, “Failure Data Analysis of a Large-Scale Heterogeneous Server Environment”, Proceedings of the 2004 International Conference on Dependable Systems and Networks, 28 June-1 July 2004

  However, in order to ensure high reliability of the information processing system, spare resources that can cope with all possible failures are prepared. Therefore, as the required reliability increases, the amount of spare resources to be prepared also increases.

  For example, the required reliability is represented by a numerical value 10 to 1, and the required reliability is more severe as the numerical value is larger. Then, in an information processing system including 10 servers, consider the amount of spare resources to be prepared when the reliability of 10 to 1 is achieved. For example, with a reliability of 10, it is assumed that all faults must be dealt with immediately and processing should continue. In this case, spare servers are prepared for all servers. That is, 10 spare servers are prepared. On the other hand, with reliability 1, it is assumed that only one out of ten failures is dealt with immediately and other failures are dealt with sequentially. In this case, it is only necessary to prepare one spare server.

  As described above, when each information processing system prepares a reserve resource in order to ensure high reliability against a failure, the amount of the reserve resource increases as the reliability criterion is tightened, and the cost increases accordingly.

  The present invention has been made in view of the above, and it is an object of the present invention to provide a spare resource providing apparatus, a spare resource providing method, and a spare resource providing program capable of realizing high reliability with a smaller spare resource amount. And

  In order to solve the above-described problem and achieve the object, a reserve resource providing apparatus according to an embodiment of the present invention is provided for calculating the amount of a reserve resource from a plurality of information processing systems that execute processing using resources. Receive information. Further, the reserve resource providing apparatus calculates an upper limit value of the reserve resource used by each of the plurality of information processing systems based on the received information. Then, the spare resource providing apparatus calculates the total amount of spare resources used by the system when the plurality of information processing systems are made one system based on the received information. Further, the reserve resource providing apparatus receives an allocation request for requesting allocation of a reserve resource from one information processing system among the plurality of information processing systems. The spare resource providing apparatus compares the upper limit with the sum of the request amount included in the allocation request and the usage amount of the spare resource used by one information processing system until the allocation request is received. The spare resource providing apparatus allocates spare resources to one information processing system based on the comparison result. The spare resource providing apparatus notifies one information processing system of the amount of spare resources allocated.

  The spare resource providing apparatus, spare resource providing method, and spare resource providing program according to the present invention have an effect that high reliability can be realized with a smaller spare resource amount.

FIG. 1 is a diagram illustrating an example of a configuration of a spare resource providing apparatus according to the first embodiment. FIG. 2 is a diagram for explaining the merit of scale when a plurality of information processing systems are regarded as one information processing system and the reserve resource amount is determined. FIG. 3A is a diagram for describing an example of information stored in the management information storage unit according to the first embodiment. FIG. 3B is a diagram for describing an example of information stored in the allocation information storage unit according to the first embodiment. FIG. 3C is a diagram for describing an example of information stored in the operation information storage unit according to the first embodiment. FIG. 4 is a diagram illustrating an example of a processing flow of the reserve resource providing method according to the first embodiment. FIG. 5 is a diagram illustrating an example in which the first embodiment is applied to an intercloud system. FIG. 6 is a diagram illustrating that information processing by the reserve resource providing program, which is a program for executing a series of processes by the reserve resource providing apparatus, is specifically realized using a computer.

  Embodiments of a reserve resource providing apparatus, a reserve resource providing method, and a reserve resource providing program according to the present invention will be described below in detail with reference to the drawings. In addition, this invention is not limited by this embodiment.

[First Embodiment]
The spare resource providing apparatus according to the first embodiment provides spare resources to the information processing system when a failure occurs in the plurality of information processing systems. Each of the information processing systems can continue the processing while ensuring a predetermined reliability using the provided spare resource.

  The spare resource providing apparatus according to the first embodiment provides spare resources by regarding a plurality of information processing systems as a group of systems. That is, the reserve resource providing apparatus according to the first embodiment reduces the reserve resource amount using the merit of scale by regarding a plurality of information processing systems as one system. Scale merit means that even if the reliability conditions imposed on multiple information processing systems are the same, the amount of spare resources to be prepared is reduced by regarding multiple information processing systems as a single system as a whole. The advantage is that you can.

  The spare resource providing apparatus according to the first embodiment calculates the amount of spare resources necessary for the entire system (hereinafter also simply referred to as a spare resource total amount) when a plurality of information processing systems are regarded as one system. . The spare resource providing apparatus is also referred to as an upper limit value (hereinafter also simply referred to as an upper limit value) of spare resources to be provided to each information processing system based on information relating to a failure or the like that occurs in the information processing system received from each information processing system. ) Is calculated. When the reserve resource providing apparatus receives a request for the reserve resource from each information processing system, the requested resource amount (hereinafter also simply referred to as a request amount), an upper limit value calculated in advance, and the information processing system already The amount of spare resources to be provided is determined on the basis of the amount of spare resources used (hereinafter also referred to as the amount of use).

[Example of configuration of spare resource providing apparatus 100]
FIG. 1 is a diagram illustrating an example of the configuration of the backup resource providing apparatus 100 according to the first embodiment. The spare resource providing apparatus 100 is communicably connected to a plurality of information processing systems 200A, 200B, and 200C via the network 300. Further, the spare resource providing apparatus 100 manages the resource 400 as a spare resource. The resource 400 is connected to the information processing systems 200A, 200B, and 200C via the network 300. Although FIG. 1 shows three information processing systems 200A, 200B, and 200C, the number of information processing systems connected to the spare resource providing apparatus 100 is not limited to three.

  The spare resource providing apparatus 100 manages the resource 400 and provides the resource 400 as a spare resource in response to requests from a plurality of information processing systems 200A, 200B, and 200C. For example, the backup resource providing apparatus 100 is an intercloud server that manages a plurality of resources such as a server, a storage device, and a network, and provides resources in response to an external request.

  Each of the information processing systems 200A, 200B, and 200C is a system that executes predetermined information processing. For example, the information processing systems 200A, 200B, and 200C are application service provider (ASP) systems that provide application services using an intercloud system. Further, for example, the information processing systems 200A, 200B, and 200C are systems operated by SaaS (Software as a Service), IaaS (Infrastructure as a Service), and Haas (Hardware as a Service) providers. In addition, the information processing systems 200A, 200B, and 200C may be systems that are constructed by an individual and that receive provision of a spare resource from the spare resource providing apparatus 100 and execute processing.

  The network 300 connects the spare resource providing apparatus 100, the information processing systems 200A, 200B, and 200C and the resource 400 so that they can communicate with each other. The network 300 is an arbitrary network such as a wide area network (WAN) or a local area network (LAN). Note that the network connecting the spare resource providing apparatus 100 and the resource 400 and the network connecting the information processing systems 200A, 200B, and 200C and the spare resource providing apparatus 100 and the resource 400 may be different networks.

  The resource 400 is a device used for information processing, such as a server, a storage device, or a router. The resource 400 may be a data center or the like, and the backup resource providing apparatus 100 may manage a plurality of data centers via a network.

[Details of configuration of spare resource providing apparatus 100]
The spare resource providing apparatus 100 includes a control unit 110 and a storage unit 120. The control unit 110 controls processing in the standby resource providing apparatus 100. The storage unit 120 stores information used for processing in the spare resource providing apparatus 100 and information generated by processing in the spare resource providing apparatus 100.

  The control unit 110 includes a reception unit 111, a calculation unit 112, a determination unit 113, and a notification unit 114.

  The receiving unit 111 receives information related to provision of spare resources from each of the information processing systems 200A, 200B, and 200C. For example, the reception unit 111 receives information for determining the upper limit value of the spare resource provided to each system by the spare resource providing apparatus 100 from the information processing systems 200A, 200B, and 200C. The receiving unit 111 receives information for determining the total amount of spare resources necessary for providing spare resources to the information processing systems 200A, 200B, and 200C.

  For example, the receiving unit 111 receives information about the resources that each of the information processing systems 200A, 200B, and 200C has, for example, the number of resources. Moreover, the receiving part 111 receives the information showing each failure characteristic from information processing system 200A, 200B, 200C, for example. In addition, the reception unit 111 receives information representing the reliability target of the information processing systems 200A, 200B, and 200C, for example. For example, the receiving unit 111 receives information such as a failure model, a scale, an average failure rate, and required reliability from the information processing systems 200A, 200B, and 200C.

  The failure model is a simplified model assuming a failure that may occur in the information processing systems 200A, 200B, and 200C. For example, failures that may occur in the information processing systems 200A, 200B, and 200C, such as abnormalities between parts and abnormalities caused by environmental factors, are modeled. Further, although the failure rate varies depending on the time frame, the failure model or the failure function represents the probability that each failure rate appears. For example, if the probability that the failure rate “0.2” appears is “0.1”, the event that the server fails at a rate of 0.2 in 10 time frames is 10 × 0.1. = Occurs once.

  The scale is information such as the number, performance, storage capacity, and the like of resources provided in the information processing systems 200A, 200B, and 200C. For example, the scale is information that the information processing system 200A includes 10 servers, each server has a 4 GB memory, and a 4-core CPU (Central Processing Unit) is mounted.

  The average failure rate is an average value of the number of failure occurrences per predetermined time. For example, the average failure rate is an average of the number of failure occurrences per hour. The failure rate indicates the probability that a failure will occur in the information processing systems 200A, 200B, and 200C.

  The required reliability is the reliability required for the information processing systems 200A, 200B, and 200C. Reliability refers to the probability that a system or device is operating within a unit time. The required reliability may be a service level agreement (SLA). A service level agreement defines the required level of service content, scope, and quality determined between a service provider and a service contractor. In the first embodiment, the reliability condition defined between the spare resource providing apparatus 100 and the information processing systems 200A, 200B, and 200C may be used.

  Information received by the reception unit 111 is stored in the management information storage unit 121 included in the storage unit 120. Details of the storage unit 120 will be described later.

  Based on the information received by the receiving unit 111, the calculating unit 112 calculates the upper limit value of the spare resource provided to each of the information processing systems 200A, 200B, and 200C. That is, the calculation unit 112 is a spare resource that enables a predetermined quality process to be executed even when a failure occurs in the information processing systems 200A, 200B, and 200C based on the information received by the reception unit 111. The upper limit amount of is calculated. At this time, the calculation unit 112 does not consider the merit of the scale when the information processing systems 200A, 200B, and 200C are regarded as one system, and does not consider the merit of the spare resources allocated to the information processing systems 200A, 200B, and 200C. Is calculated.

  In the first embodiment, the calculation unit 112 divides a day into predetermined time frames, and calculates an upper limit amount of spare resources for each time frame. However, the calculation unit 112 may calculate an upper limit amount per day, an upper limit amount per several days, or the like, or may assign the same upper limit amount to each time frame.

  The calculation unit 112 also calculates a total amount of spare resources required when all the information processing systems 200A, 200B, and 200C that receive provision of spare resources from the spare resource providing apparatus 100 are regarded as one information processing system. .

  For example, the calculation unit 112 configures a failure function with a failure model, a failure rate, and a scale for each information processing system. And the calculation part 112 synthesize | combines the failure function at the time of considering information processing system 200A, 200B, 200C as one system by a convolution calculation. In addition, the calculation unit 112 combines the required reliability of the plurality of information processing systems 200A, 200B, and 200C as one reliability value using each scale and each reliability target. Thereafter, the calculation unit 112 calculates the total amount of spare resources as a whole using the combined failure function and required reliability.

  The convolution operation is performed by a generally known method. For example, consider a case where a failure function is synthesized for an information processing system A with a probability of failure of one server of 0.3 and an information processing system B with a probability of failure of one server of 0.4. In this case, the probability of failure of two servers simultaneously, that is, one server of the information processing system A and one server of the information processing system B is 0.3 × 0.4 = 0.12.

  When the information processing systems 200A, 200B, and 200C are collectively regarded as one information processing system, the merit of scale can be used. For this reason, the total amount of spare resources required when the entire information processing system is regarded as one information processing system is the sum of the amount of spare resources required when each information processing system 200A, 200B, and 200C is regarded as a separate system. It was n’t.

  The merit of scale when a plurality of information processing systems are regarded as one information processing system will be described with reference to FIG. FIG. 2 is a diagram for explaining the merit of scale when a plurality of information processing systems are regarded as one information processing system and the reserve resource amount is determined.

  In FIG. 2, the horizontal axis represents a preset time frame, and the vertical axis represents the failure rate of failures in the information processing systems 200A, 200B, and 200C that occurred within each time frame. In FIG. 2, the time frame of 1 hour is set and the failure rate for every hour is shown. As shown in FIG. 2, the failure rate of the information processing system 200A in the time frame “1” is about 0.02, while the failure rate of the information processing system 200B is 0.1. Further, the failure rate of the information processing system 200C in the time frame “14” is about 0.2, but the failure rate of the information processing system 200A is about 0.01.

  In the case of FIG. 2, the information processing systems 200A, 200B, and 200C are regarded as independent systems, and the spare resource amount is calculated. In the information processing system 200A, the failure rate has a maximum value of 0.1 in the time frame “11”. That is, when the information processing system 200A has 20 servers, there is a possibility that two servers will fail at the same time. Therefore, two spare servers are required to continue stable operation when a failure occurs in the information processing system 200A.

  In the information processing system 200B, the failure rate has a maximum value of 0.2 in the time frame “3”. That is, when the information processing system 200B has 20 servers, there is a possibility that four servers will fail at the same time. Therefore, four spare servers are necessary to continue stable operation when a failure occurs in the information processing system 200B.

  Furthermore, in the information processing system 200C, the failure rate has a maximum value of 0.2 in the time frames “14” and “23”. That is, when the information processing system 200C has 20 servers, there is a possibility that four servers will fail at the same time. Therefore, four spare servers are required to continue stable operation when a failure occurs in the information processing system 200C.

  That is, when the information processing systems 200A, 200B, and 200C are regarded as independent systems and spare servers corresponding to the respective systems are prepared, ten spare servers are required in total.

  However, when the information processing systems 200A, 200B, and 200C are regarded as one information processing system as a whole, the number of failures in the same time frame increases due to the increase in the number of information processing systems, and the law of large numbers According to the central limit theorem, the total number of faults in the same time frame has little variation, approaches the average value of the total number of faults, and is more stable than fluctuations in the number of faults in each information processing system. I can say that.

  In other words, the information processing systems 200A, 200B, and 200C are less likely to occur at the maximum failure rate at the same time, and 10 units do not fail at the same time within the target time frame as shown in FIG. If this probability is negligible, it is permissible as a whole to prepare spare servers with a number smaller than the total maximum failure rate of each information processing system, and separately prepare spare resources for each information processing system. The amount of spare resources to be prepared can be reduced as compared with the case of preparing.

  As described above, when the information processing systems 200A, 200B, and 200C are regarded as one information processing system as a whole, fluctuations in the number of faults are leveled, and the influence of fluctuations in the number of faults in each system can be reduced. If the scale merit is used in this way, the amount of spare resources prepared as a whole can be reduced.

  In FIG. 2, the failure rate is set higher than usual for ease of illustration. The failure rate in an actual system is usually lower than the value shown.

  As described above, the calculation unit 112 regards the information processing systems 200A, 200B, and 200C as one system and uses the scale merit to calculate the total amount of spare resources provided to the entire system.

  As described above, when the scale merit is used, as the number of information processing systems to be linked, that is, the number of information processing systems regarded as one system increases, the effect of reducing the total spare resources increases. Therefore, in order to maximize the effect of scale merit, it is desirable to link more information processing systems.

  However, for example, when the reserve resource providing apparatus 100 provides a reserve resource to a large number of information processing systems, a plurality of information processing systems are appropriately combined to form a plurality of groups, and each group is regarded as one system. Good. Then, the spare resource providing apparatus 100 may adjust the information processing systems to be combined so that the total amount of spare resources allocated to one group can be reduced. Thereby, the necessary amount of spare resources can be further reduced. In this case, the calculation unit 112 also executes processing for calculating a combination of information processing systems.

  The total reserve resource amount calculated by the calculation unit 112 is stored in the allocation information storage unit 122 included in the storage unit 120. The upper limit value calculated by the calculation unit 112 is stored in the operation information storage unit 123 included in the storage unit 120. The allocation information storage unit 122 and the operation information storage unit 123 will also be described later.

The determination unit 113 receives a request for a spare resource from each of the information processing systems 200A, 200B, and 200C when a failure occurs during the operation of each of the information processing systems 200A, 200B, and 200C. That is, the determination unit 113 receives a request amount _{Q R} spare resources. Then, the determination unit 113, the time frame corresponding to the required amount Q _R, reads pre resource amount information processing system that sent the request is already using the (usage amount Q _U) from operation information storage unit 123. Determination unit 113 sums the and usage _{Q U} and demand _{Q R.} Then, the determination unit 113 compares the usage _{Q U} sum of the required amount _{Q R,} the upper limit value _{Q L} the calculation unit 112 has calculated.

Determination unit 113, if the sum of the usage Q _U and the required amount Q _R exceeds the upper limit value Q _L is the amount obtained by subtracting the usage quantity Q _U from the upper limit value Q _L a limit, allocates the spare resources. Determination unit 113, the sum of the usage Q _U and the required amount Q _R is the case of more than the upper limit, allocates the spare resource request amount Q _R. Then, the determination unit 113 updates the usage Q _U stored in the operation information storage unit 123.

  The notification unit 114 notifies the allocated resource amount as a response to the reserve resource request of the information processing systems 200A, 200B, and 200C.

  Next, information stored in the storage unit 120 will be described with reference to FIGS. 3A to 3C. FIG. 3A is a diagram for describing an example of information stored in the management information storage unit 121 according to the first embodiment. FIG. 3B is a diagram for describing an example of information stored in the allocation information storage unit 122 according to the first embodiment. FIG. 3C is a diagram for describing an example of information stored in the operation information storage unit 123 according to the first embodiment.

  The storage unit 120 includes a management information storage unit 121, an allocation information storage unit 122, and an operation information storage unit 123.

  The management information storage unit 121 stores information on each of the information processing systems 200A, 200B, and 200C received by the receiving unit 111. For example, as illustrated in FIG. 3A, the management information storage unit 121 stores information about resources of the information processing systems 200A, 200B, and 200C, in this case, servers. In the example of FIG. 3A, resource information is stored in association with the target system ID (Identifier) “200A” that uniquely identifies the information processing system 200A for the information processing system 200A. In the example of FIG. 3A, it is shown that the information processing system 200A includes 10 servers and has a storage capacity of 6 GB. In addition, although not shown, the management information storage unit 121 also stores other information such as a failure model received by the reception unit 111.

  The allocation information storage unit 122 stores the reserve resource total amount calculated by the calculation unit 112. For example, when the spare resource providing apparatus 100 divides the information processing system into a plurality of groups and regards each as one system, the spare resource total amount of each group is stored. In the example of FIG. 3B, the information processing systems 200A, 200B, and 200C are regarded as one system as a whole. In the example of FIG. 3B, the ID “200A, 200B, 200C” of each information processing system and the total amount of spare resources “10 servers” are associated with the system ID (Identifier) “S01” that uniquely identifies the system. Is stored.

  The operation information storage unit 123 stores the upper limit values of the information processing systems 200A, 200B, and 200C calculated by the calculation unit 112. Further, the operation information storage unit 123 stores the amount as a usage amount when a spare resource is provided to each of the information processing systems 200A, 200B, and 200C. Specifically, the reserve resource amount allocated to each information processing system by the processing in the determination unit 113 is stored.

  In the example of FIG. 3C, the operation information storage unit 123 stores an upper limit value and a usage amount in association with each time frame. For example, the upper limit “2 servers” and the usage amount “0” of the time frame “1” of the information processing system 200A are stored. Information stored in the operation information storage unit 123 is updated each time a spare resource is provided to the information processing system.

[Example of spare resource provision processing flow]
FIG. 4 is a diagram illustrating an example of a processing flow of the reserve resource providing method according to the first embodiment. With reference to FIG. 4, an example of the processing flow of the reserve resource providing method will be described.

  First, since the information processing system 200A receives provision of a spare resource from the spare resource providing apparatus 100, the spare resource providing process starts by performing registration with the spare resource providing apparatus 100. For example, in response to a request from the administrator of the information processing system 200A, the administrator of the spare resource providing apparatus 100 registers the information processing system 200A that has newly joined the spare resource providing apparatus 100. Alternatively, the information processing system 200A transmits a new subscription request to the spare resource providing apparatus 100, and the spare resource providing apparatus 100 starts the spare resource providing process accordingly.

  First, the backup resource providing apparatus 100 transmits an information transmission request to the newly subscribed information processing system 200A (step S401). The information processing system 200A transmits the requested information to the spare resource providing apparatus 100. That is, the information processing system 200A transmits information such as a failure model, a scale, an average failure rate, and required reliability.

  The receiving unit 111 of the standby resource providing apparatus 100 receives information transmitted from the information processing system 200A (step S402). Then, based on the received information, the calculation unit 112 calculates the upper limit value of the reserve resource amount allocated to the information processing system 200A (step S403). The calculated upper limit value is stored in the operation information storage unit 123.

  Further, the calculation unit 112 calculates the necessary reserve resource total amount by regarding the newly-added information processing system 200A and the already-added information processing systems 200B and 200C as one system as a whole (step S404). Then, the calculating unit 112 sets the reserve resource total amount by storing the calculated total amount in the allocation information storage unit 122 (step S405).

  When the storage of the upper limit value and the reserve resource total amount is completed, the counting of the time in the preset time frame is started (step S406). For example, a number is assigned to each time frame in advance, and the number of the time frame to start counting is substituted for the time frame number F (F = n (n is a natural number of 1 or more)). When a failure occurs in the information processing system 200 </ b> A, the information processing system 200 </ b> A transmits a spare resource request including information indicating the amount of the spare resource requested to the spare resource providing apparatus 100. The determination unit 113 of the backup resource providing apparatus 100 receives the backup resource request (step S407).

The determination unit 113 reads the reserve resource amount (usage amount Q _U ) already used by the information processing system 200A in the time frame from the operation information storage unit 123. Further, the determination unit 113 reads the upper limit value (Q _L ) of the spare resource that can be used by the information processing system 200A in the time frame from the operation information storage unit 123 (step S408).

Determination unit 113 reads the usage quantity Q by summing the _U and demand Q _R, as compared with the upper limit value Q _L in the time frame, usage Q _U and the required amount Q _R and the total upper limit value Q _L in It is determined whether it is larger than (step S409). If the sum of the usage _{Q U} and the required amount _{Q R} is larger than the upper limit value _{Q L} (step S409, the affirmative), the determination unit 113, by subtracting the usage quantity _{Q U} from the upper limit value _{Q L} in the information processing system 200A Minutes of spare resources are allocated (step S410). Also, if the sum of the usage _{Q U} and the required amount _{Q R} is equal to or less than the upper limit value _{Q L} (step S409, the negative), the determination unit 113 assigns a spare resource request amount _{Q R} component to the information processing system 200A ( Step S411). Then, the determination unit 113 adds the allocated resource amount to the usage amount Q _U read from the operation information storage unit 123, and updates the usage amount Q _U stored in the operation information storage unit 123 (step S412). ).

  The notification unit 114 notifies the information processing system 200A of the amount of spare resources allocated by the determination unit 113 (step S413). Then, the notification unit 114 returns the process to the determination unit 113. The determination unit 113 determines whether or not the time frame has ended (step S414). If it determines with the said time frame having been complete | finished (step S414, affirmation), the determination part 113 will transfer to the next time frame (F = F + 1, step S415). Then, the process returns to step S407 again. On the other hand, if it is determined that the time frame has not ended (No at step S414), the process returns to step S407 as it is. The spare resource providing apparatus 100 repeats this process while the spare resource providing process continues.

  In the above description, it is assumed that the reserve resource request is transmitted when provision of the reserve resource becomes necessary. However, the present invention is not limited to this, the occurrence of a failure is predicted in advance in the information processing systems 200A, 200B, and 200C, and a reserve resource request is transmitted before the time frame that the user wants to receive. You may comprise so that it may receive. In this case, the reserve resource request may be transmitted including information on the time frame to be provided in addition to the requested amount.

  In the first embodiment, the information processing system 200A receives notification of the amount of reserved resources allocated after the reserved resource providing apparatus 100 updates the storage unit 120 (FIG. 4, step S412). (FIG. 4, step S413). However, the backup resource providing apparatus 100 may first notify the information processing system 200A of the allocated amount and update the storage unit 120 after receiving a confirmation response from the information processing system 200A. Further, the information processing system 200A may be configured to be able to reject the allocation of the spare resource by the spare resource providing apparatus 100 as a response to the notification.

[Effect of the first embodiment]
As described above, the reserve resource providing apparatus according to the first embodiment receives information for calculating the amount of the reserve resource from a plurality of information processing systems that execute processing using resources. Then, the reserve resource providing apparatus calculates an upper limit value of the reserve resource used by each of the plurality of information processing systems based on the received information. Further, the spare resource providing apparatus calculates the total amount of spare resources used by the system when the plurality of information processing systems are made one system based on the received information. The reserve resource providing apparatus receives an allocation request for requesting allocation of a reserve resource from one information processing system among the plurality of information processing systems. The spare resource providing apparatus compares the total amount of the request amount included in the received allocation request with the usage amount of the spare resource used by the one information processing system until the allocation request is received, and the upper limit value. Then, based on the comparison, the spare resource providing apparatus allocates the spare resource to one information processing system and notifies the one information processing system of the amount of the spare resource allocated. As described above, the reserve resource providing apparatus according to the first embodiment calculates the reserve resource amount by regarding the plurality of information processing systems as one large system as a whole. Further, the spare resource providing apparatus according to the first embodiment calculates the upper limit value of the spare resource provided for each information processing system.

  Thus, the merit of scale can be utilized by regarding a plurality of information processing systems as one large system. That is, fluctuations in the amount of failure occurring in each information processing system are leveled, and the amount of spare resources required as a whole can be reduced. Therefore, it is possible to ensure high reliability in each information processing system while reducing the total amount of spare resources to be prepared as a whole, compared to the case of preparing spare resources in each information processing system.

  Further, by providing an upper limit value for the spare resource provided to each information processing system, fairness among the information processing systems using the spare resource can be maintained. For this reason, it is possible to provide a fair reserve resource.

  Further, the total amount of spare resources can be further reduced by adjusting the combination of information processing systems that are regarded as a single system.

[Second Embodiment]
Although the embodiments of the present invention have been described so far, the present invention may be implemented in other embodiments besides the above-described embodiments. Other embodiments will be described below.

[Intercloud system]
FIG. 5 is a diagram illustrating an example in which the first embodiment is applied to an intercloud system. As shown in FIG. 5, software for realizing the reserve resource providing process of the first embodiment can be installed in the intercloud server to provide the reserve resource.

  In the example of FIG. 5, a reserve resource providing program 510 is installed in the intercloud server 500. The intercloud server 500 and ASP (Application Service Provider) management apparatuses 700A, 700B, and 700C are connected via a network. The intercloud server 500 is also connected to the resource management device 600. The resource management device 600 manages the resource 610.

  The intercloud server 500 provides the resources 610 managed by the resource management device 600 to the ASP management devices 700A, 700B, and 700C as backup resources.

  The ASP management devices 700A, 700B, and 700C provide services to the user terminals 800A, 800B, and 800C using resources 710A, 710B, and 710C, respectively. The ASP management devices 700A, 700B, and 700C manage the operations of the resources 710A, 710B, and 710C, respectively. When a failure occurs in the resources 710A, 710B, and 710C, the failure information is transmitted to the ASP management devices 700A, 700B, and 700C that manage the resources. The ASP management devices 700 </ b> A, 700 </ b> B, and 700 </ b> C calculate the reserve resource amount necessary to deal with the failure, and transmit the requested reserve resource amount information to the intercloud server 500. The intercloud server 500 executes the processes of steps S402 to S415 in FIG. 4 to notify the ASP management apparatuses 700A, 700B, and 700C of the spare resource allocation. The ASP management devices 700A, 700B, and 700C use the information included in the notification to access the resource 610, and use the resource 610 to continue the service for the user terminals 800A, 800B, and 800C.

  Further, by installing the spare resource providing program 510 in the existing intercloud server, it is possible to execute the spare resource providing process in addition to the existing function.

[System configuration]
Of the processes described in the above embodiment, all or part of the processes described as being performed automatically can be performed manually, or all of the processes described as being performed manually or A part can be automatically performed by a known method. In addition, the processing procedures, control procedures, specific names, and information including various data and parameters shown in the above-described document and drawings can be arbitrarily changed unless otherwise specified.

  Further, each component of each illustrated apparatus is functionally conceptual, and does not necessarily need to be physically configured as illustrated. That is, the specific form of distribution / integration of each device is not limited to the one shown in the figure, and all or a part of the distribution / integration may be functionally or physically distributed in arbitrary units according to various loads or usage conditions. Can be integrated and configured.

  For example, in the description of the above embodiment, the standby resource providing apparatus 100 has been described as including the reception unit 111, the calculation unit 112, the determination unit 113, and the notification unit 114, but some of these functions may be combined. . Further, for example, the calculation of the upper limit value and the reserve resource total amount by the calculation unit 112 may be executed by separate functional units. In addition, the configuration of data stored in each unit of the storage unit 120 is not limited to that illustrated, and may be changed as appropriate. For example, when all information processing systems that always provide spare resources are regarded as one system, the allocation information storage unit 122 may be deleted and integrated into the management information storage unit 121.

[program]
FIG. 6 is a diagram illustrating that information processing by the reserve resource providing program, which is a program for executing a series of processes by the reserve resource providing apparatus, is specifically realized using a computer. As illustrated in FIG. 6, the computer 3000 includes, for example, a memory 3010, a CPU (Central Processing Unit) 3020, a hard disk drive 3080, and a network interface 3070. Each part of the computer 3000 is connected by a bus 3100.

  The memory 3010 includes a ROM 3011 and a RAM 3012 as illustrated in FIG. The ROM 3011 stores a boot program such as BIOS (Basic Input Output System).

  Here, as illustrated in FIG. 6, the hard disk drive 3080 stores, for example, an OS 3081, an application program 3082, a program module 3083, and program data 3084. In other words, the reserve resource providing program according to the disclosed technique is stored in, for example, the hard disk drive 3080 as the program module 3083 in which instructions executed by the computer are described. For example, a program module 3083 in which each procedure for executing the same information processing as each unit of the control unit 110 is described is stored in the hard disk drive 3080.

  Further, data used for information processing by the reserve resource providing program, such as data stored in the storage unit 120, is stored as program data 3084 in, for example, the hard disk drive 3080. The CPU 3020 reads the program module 3083 and program data 3084 stored in the hard disk drive 3080 to the RAM 3012 as necessary, and executes various procedures.

  Note that the program module 3083 and the program data 3084 related to the spare resource providing program are not limited to being stored in the hard disk drive 3080. For example, the program module 3083 and the program data 3084 may be stored in a removable storage medium. In this case, the CPU 3020 reads data via a removable storage medium such as a disk drive. Similarly, the program module 3083 and the program data 3084 related to the reserve resource providing program are stored in another computer connected via a network (LAN (Local Area Network), WAN (Wide Area Network), etc.). Also good. In this case, the CPU 3020 reads various data by accessing another computer via the network interface 3070.

[Others]
Note that the reserve resource providing program described in the present embodiment can be distributed via a network such as the Internet. The spare resource providing program can also be executed by being recorded on a computer-readable recording medium such as a hard disk, a flexible disk (FD), a CD-ROM, an MO, or a DVD, and being read from the recording medium by the computer. .

DESCRIPTION OF SYMBOLS 100 Reserve resource provision apparatus 110 Control part 111 Reception part 112 Calculation part 113 Determination part 114 Notification part 120 Storage part 121 Management information storage part 122 Allocation information storage part 123 Operation information storage part 200A, 200B, 200C Information processing system 300 Network 400 Resource 500 Intercloud server 510 Spare resource providing program 600 Resource management device 610 Resource 700A, 700B, 700C ASP management device 710A, 710B, 710C Resource 800A, 800B, 800C User terminal

Claims (7)

A receiving unit that receives information for calculating the amount of the reserve resource from a plurality of information processing systems that perform processing by the resource;
A first calculation unit that calculates an upper limit value of a spare resource used by each of the plurality of information processing systems based on information received by the reception unit;
A second calculation unit that calculates a total amount of spare resources used by the system when the plurality of information processing systems are configured as one system based on information received by the reception unit;
An allocation request for requesting allocation of a spare resource is received from one information processing system among the plurality of information processing systems, the request amount included in the allocation request, and the one information processing system until the allocation request is received A determination unit that allocates the spare resource to the one information processing system based on a comparison result between the total of the usage amount of the spare resource used by and the upper limit value;
A notification unit for notifying the information processing system of the amount of spare resources allocated by the determination unit;
A reserve resource providing apparatus comprising:   The second calculation unit generates a failure function of each of the plurality of information processing systems using information received by the reception unit from each of the plurality of information processing systems, and synthesizes the failure function by a convolution operation. The spare resource providing apparatus according to claim 1, wherein the total amount of the spare resources is calculated.   When the determination unit determines that the sum of the request amount and the usage amount is equal to or less than the upper limit value, the determination unit allocates a reserve resource of the request amount to the one information processing system, and the request amount and the usage amount The reserve resource corresponding to the amount obtained by subtracting the usage amount from the upper limit value is allocated to the one information processing system when it is determined that the sum of the above and the upper limit value is greater than the upper limit value. Spare resource providing device.   4. The receiver according to claim 1, wherein the receiving unit receives one or more pieces of information among resources, failure characteristics, and reliability targets of each of the plurality of information processing systems. 5. The reserve resource providing apparatus according to 1.   A storage unit for storing a spare resource amount allocated to the one information processing system; and when a spare resource is newly allocated in response to the allocation request of the one information processing system, the newly allocated spare 5. The reserve resource providing apparatus according to claim 1, wherein the storage unit is updated to reflect a resource amount. 6. A receiving step of receiving information for calculating the amount of the reserve resource from a plurality of information processing systems that execute processing by the resource;
A first calculation step of calculating an upper limit value of a spare resource used by each of the plurality of information processing systems based on the information received in the reception step;
A second calculation step of calculating a total amount of spare resources used by the system when the plurality of information processing systems as one system is based on the information received in the reception step;
An allocation request for requesting allocation of a spare resource is received from one information processing system among the plurality of information processing systems, the request amount included in the allocation request, and the one information processing system until the allocation request is received A determination step of allocating a spare resource to the one information processing system based on a comparison result between the total of the usage amount of the spare resource used by and the upper limit value;
A notification step of notifying the information processing system of the amount of spare resources allocated by the determination step;
A reserve resource providing method executed by a reserve resource providing apparatus. A reception procedure for receiving information for calculating the amount of the reserve resource from a plurality of information processing systems that execute processing by the resource;
A first calculation procedure for calculating an upper limit value of a spare resource used by each of the plurality of information processing systems based on the information received in the reception procedure;
A second calculation procedure for calculating a total amount of spare resources used by the system when the plurality of information processing systems as a whole is based on the information received in the reception procedure;
An allocation request for requesting allocation of a spare resource is received from one information processing system among the plurality of information processing systems, the request amount included in the allocation request, and the one information processing system until the allocation request is received A determination procedure for allocating a spare resource to the one information processing system, based on a comparison result between the total amount of spare resources used by and the upper limit value;
A notification procedure for notifying the one information processing system of the amount of spare resources allocated by the determination procedure;
A reserve resource providing program that causes a computer to execute each process including:

Images