JP5483784B1 - CONTROL DEVICE, COMPUTER RESOURCE MANAGEMENT METHOD, AND COMPUTER RESOURCE MANAGEMENT PROGRAM - Google Patents

Abstract

An object of the present invention is to appropriately operate a calculation resource in consideration of a calculation resource associated with a calculation resource in which an event has occurred.
A control device disclosed in the present application includes a determination unit and an operation unit. The decision unit is triggered by the occurrence of an event in a computing resource operating inside the information processing device group, based on the state of the computing resource in which the event has occurred and the status of other computing resources related to the computing resource in which the event has occurred. The operation to be performed on the computing resource in which the event has occurred and the other computing resource is determined. The operation unit executes the operation determined by the determination unit for the calculation resource in which the event has occurred and the other calculation resource.
[Selection] Figure 4

Description

  The present invention relates to a technique related to a control device, a calculation resource management method, and a calculation resource management program, and particularly relates to a technique related to automation of calculation resource management of an information processing system.

  Conventionally, in the operation of information processing systems, devices and functions are manually installed and started, and then devices, functions, and other events such as failures, performance degradation, overload, and other changes in the operating environment are detected. Is monitored. When such an event occurs, it is common to manually perform operations such as recovery from a failure, addition of equipment, replacement, and movement.

  However, it is not economical to monitor the information processing system for 24 hours 365 days and to be ready to work according to the event. This is particularly noticeable in cases where the system has already been used for a long period of time, and experience has been accumulated and stylized regarding the detection of events, determination of the contents of countermeasures, and work according to the contents of countermeasures. For this reason, a method of automatically performing routine operations without requiring manual operation is disclosed.

ZABBIX-JP Japanese Zabbix Community, Documents What is Zabbix? Function, [online], [Search May 23, 2013], Internet <URL: http://www.zabbix.jp/documents/functions>

  However, in the above-described conventional technology, there is a problem that only the calculation resource in which the event has occurred is considered and other related calculation resources are not considered, and thus the calculation resource cannot be appropriately operated.

  For example, in the prior art, a monitoring device installed separately from the application server collects the operation status of a plurality of items collected by a virtual machine operating in the application server. Then, the monitoring device determines whether or not a failure has occurred in the information processing system by determining whether or not the collected operating status exceeds a preset threshold value. Here, if the monitoring apparatus determines that a failure has occurred, the monitoring apparatus executes predetermined processing defined for each item of the failure that has occurred. In this case, in the information processing system, for example, even if another computing resource has a surplus capacity, the computing resource having the surplus capacity is not used.

  The disclosed technique has been made in view of the above, and an object thereof is to appropriately operate a calculation resource in consideration of a calculation resource associated with a calculation resource in which an event has occurred.

  The control device disclosed in the present application includes a determination unit and an operation unit. The decision unit is triggered by the occurrence of an event in a computing resource operating inside the information processing device group, based on the state of the computing resource in which the event has occurred and the status of other computing resources related to the computing resource in which the event has occurred. The operation to be performed on the computing resource in which the event has occurred and the other computing resource is determined. The operation unit executes the operation determined by the determination unit for the calculation resource in which the event has occurred and the other calculation resource.

  According to one aspect of the disclosed control device, calculation resource management method, and calculation resource management program, there is an effect that the calculation resource can be appropriately operated in consideration of the calculation resource related to the calculation resource in which the event has occurred. Play.

FIG. 1 is a diagram illustrating a configuration example of an information processing system. FIG. 2 is a diagram illustrating a flow of information between the devices at the time of initial setting. FIG. 3 is a diagram illustrating a flow of information between devices when an event occurs. FIG. 4 is a functional block diagram showing the configuration of the control device. FIG. 5 is a diagram illustrating an example of the inclusion relationship. FIG. 6 is a diagram illustrating an example of the inclusion relationship. FIG. 7 is a diagram illustrating an example of a connection relationship. FIG. 8 is a diagram illustrating a definition example of a data structure stored in the computational resource relevance information table. FIG. 9 is a diagram illustrating an example of entity values stored in the computational resource relevance information table. FIG. 10 is a diagram illustrating an example of a data structure stored in the calculation resource monitoring content information table. FIG. 11 is a diagram illustrating an example of a data structure stored in the application target determination conditional expression template selection information table. FIG. 12 is a diagram illustrating an example of a data structure stored in the determination condition formula table. FIG. 13 is a diagram illustrating an example of a calculation resource operation request. FIG. 14 is a diagram for explaining the calculation resource monitoring condition information. FIG. 15 is a sequence diagram for explaining an operation example of the initial setting process. FIG. 16 is a sequence diagram illustrating an operation example of the change process. FIG. 17 is a sequence diagram for explaining an operation example of the computational resource operation processing when an event occurs. FIG. 18 is a flowchart showing the procedure of the initial setting process. FIG. 19 is a flowchart showing the procedure of the resource operation process. FIG. 20 is a flowchart illustrating a procedure of the determination condition table changing process. FIG. 21 is a flowchart illustrating the procedure of the monitoring condition change process. FIG. 22 is a flowchart showing a processing procedure when an event occurs. FIG. 23 is a diagram for explaining the processing operation in the case of automatic scale-out. FIG. 24 is a diagram for explaining a processing operation in the case of automatically preventing performance degradation of the virtual machine server device. FIG. 25 is a diagram for explaining the processing operation in the case where the temperature of the server room is prevented from rising locally. FIG. 26 is a diagram for explaining a processing operation in the case of automatically performing a degenerate operation at night. FIG. 27 is a diagram illustrating that the information processing by the computing resource management program for executing the processing by the computer system is specifically realized using a computer.

  Hereinafter, embodiments of the disclosed control device, calculation resource management method, and calculation resource management program will be described in detail based on the drawings. The invention disclosed by this embodiment is not limited.

(First embodiment)
FIG. 1 is a diagram illustrating a configuration example of the information processing system 100. As illustrated in FIG. 1, the information processing system 100 includes a user terminal 200, an information processing device group 300, a monitoring device 400, and a control device 500.

  The user terminal 200 is a console device that is connected to the control device 500 and includes an input / output device that is used when the user operates the control device 500. For example, the user is an administrator of the information processing apparatus group 300.

  The information processing device group 300 is a collection of computing resources connected to the control device 500 and the monitoring device 400, and is, for example, a server device. The information processing apparatus group 300 operates one or more calculation resources in which calculation resources are arranged based on an operation from the control apparatus 500 and whose operation status is collected from the monitoring apparatus 400.

  The computing resources mentioned here include a CPU (Central Processing Unit), a memory, a data holding area, a device having a network communication function, a CPU, a memory, a device having a function of transferring data, a server room, etc. Installation locations and their virtualization devices are included. More specifically, computing resources include computer devices including server devices and personal computers, storage devices for permanently storing information, network devices for interconnecting computer devices, and power to each device. In addition to physical computing resources such as a power supply device for supplying power and cables connecting the devices, virtual computing resources such as virtual machines, virtual networks, and virtual disks are also included.

  In addition, a calculation resource inside the information processing apparatus group 300 may have a relationship with one or more other calculation resources. In the example illustrated in FIG. 1, the information processing device group 300 includes a calculation resource 301a and a calculation resource 301b, and the calculation resource 301a and the calculation resource 301b are related to each other. The “relationship” mentioned here includes, for example, an inclusion relationship between a virtual machine and a computer device on which the virtual machine operates, a connection relationship between the computer device and a network device, and the like. Details of the “relationship” will be described later. Further, in the following description, when the calculation resource 301a and the calculation resource 301b are generalized without being distinguished, they are described as the calculation resource 301.

  The monitoring device 400 is connected to the control device 500 and the information processing device group 300. The monitoring device 400 is a device that has a function of collecting measured values such as temperature and electric energy and an alarm notification function in addition to the CPU, memory, data holding area, and network communication function, and monitors the information processing device group 300. By doing so, an event occurring in the information processing apparatus group 300 is detected. The “event” mentioned here includes a failure, performance degradation, overload, and other changes in the operating environment that have occurred to the device or function.

  The control device 500 is connected to the user terminal 200, the information processing device group 300, and the monitoring device 400. The control device 500 is a device having a CPU, a memory, a data holding area, and a network communication function. In response to the occurrence of an event in the computing resource 301 operating inside the information processing apparatus group 300, the control device 500 receives the computing resource 301 in which the event has occurred and other computing resources related to the computing resource in which the event has occurred. Based on the state of 301, an operation to be performed on the computing resource 301 in which the event has occurred and other computing resources 301 is determined. Then, the control device 500 executes the determined operation on the computing resource 301 in which the event has occurred and other computing resources 301.

  In addition, although the connection between each apparatus and the mutual connection of the control apparatus 500 and the user terminal 200 are via a communication network, a communication network is a local area network (LAN), the Internet, You may comprise including a public telephone network. A plurality of user terminals 200 may be connected to the control device 500. The user terminal 200 may be connected to the monitoring device 400.

  Next, the flow of information between devices in the information processing system 100 will be described with reference to FIGS. FIG. 2 is a diagram illustrating a flow of information between the devices at the time of initial setting. In the example illustrated in FIG. 2, the flow of information when the user terminal 200 performs initial setting of the information processing apparatus group 300 is illustrated. As illustrated in FIG. 2, when starting operation of the information processing apparatus group 300, the user terminal 200 transmits a “calculation resource operation request” to the control apparatus 500 (step S1).

  Then, the control device 500 operates the calculation resource 301 of the information processing device group 300 based on the “calculation resource operation request” (step S2). When notified from the information processing device group 300 that the operation of the computing resource 301 has been successful (step S3), the control device 500 changes the relationship within the control device 500. Subsequently, the control device 500 transmits “calculation resource monitoring condition information” to the monitoring device 400 (step S4).

  Then, the monitoring device 400 monitors the information processing device group 300 based on the “computation resource monitoring condition information” (step S5). For example, the monitoring device 400 determines the response status to the life / death inquiry of the plurality of computing resources 301 operating in the information processing device group 300 based on the “computation resource monitoring condition information” received from the control device 500, the CPU and the memory. Operating status such as network usage rate, network device packet transmission / reception and bandwidth usage rate. Then, the information processing device group 300 returns a response to the monitoring device 400 (step S6).

  FIG. 3 is a diagram illustrating a flow of information between devices when an event occurs. In the example illustrated in FIG. 3, the flow of information when the monitoring apparatus 400 detects the occurrence of an event in the information processing apparatus group 300 is illustrated. As illustrated in FIG. 3, when the monitoring device 400 detects a change in state for each computing resource based on the operation status collected from the information processing device group 300, the monitoring device 400 transmits the content of the change to the control device 500 as event information ( Step S11).

  Based on the relationship, the control device 500 determines the operation content for the computing resource 301 and operates the computing resource 301 of the information processing device group 300 (step S12). When notified from the information processing device group 300 that the operation of the computing resource 301 has been successful (step S13), the control device 500 changes the relationship within the control device 500. Subsequently, the control device 500 transmits “calculation resource monitoring condition information” to the monitoring device 400 (step S14).

  Then, the monitoring device 400 monitors the information processing device group 300 based on the “computation resource monitoring condition information” (step S15). Then, the information processing device group 300 returns a response to the monitoring device 400 (step S16).

  Next, the functional configuration of the control device 500 shown in FIG. 1 will be described with reference to FIG. FIG. 4 is a functional block diagram showing the configuration of the control device 500. The control device 500 includes a communication control unit 501, a storage unit 510, and a control unit 520.

  The communication control unit 501 is a communication interface, and transmits / receives data to / from external devices such as the user terminal 200, the information processing device group 300, and the monitoring device 400.

  The storage unit 510 is, for example, a storage device such as a semiconductor memory device or a hard disk, and includes a calculation resource relevance information table 511, a calculation resource monitoring content information table 512, an application target determination conditional expression template selection information table 513, a determination A conditional expression table 514.

  The computational resource relevance information table 511 stores “relationship information” for identifying what kind of relation is present between a certain computational resource and another computational resource. For example, the “relationship information” includes an inclusion relationship between a virtual machine and a computer device on which the virtual machine is to operate, a connection relationship between the computer device and a network device, and the like. Here, before explaining the data structure stored in the computational resource relevance information table 511, the inclusion relationship and the connection relationship will be described with reference to FIGS.

  FIG. 5 is a diagram illustrating an example of the inclusion relationship. The inclusion relationship includes “logical inclusion” and “physical inclusion”, and FIG. 5 shows an example of logical inclusion. In the example shown in FIG. 5, a VMC (Virtual Machine Cluster) 5a (virtual server or server cluster) operates a plurality of VMs (Virtual Machines) 5b to 5f. That is, the VMC 5a logically includes a plurality of VMs 5b to 5f. In such a case, the VMC 5a and the VMs 5b to 5f are referred to as being in an inclusive relationship. In addition, in the inclusion relationship, when the calculation resource A wraps the calculation resource B, in other words, when the calculation resource B is included in the calculation resource A, the calculation resource B is referred to as a “main item” and the calculation resource A May be referred to as a “subordinate item”. In the example illustrated in FIG. 5, the VMs 5 b to 5 f are “main items”, and the VMC 5 a is a “subordinate item”. The relationship between the “main item” and the “subordinate item” is common to “logical inclusion” and “physical inclusion”.

  FIG. 6 is a diagram illustrating an example of the inclusion relationship. FIG. 6 shows an example of physical inclusion. In the example shown in FIG. 6, the region 6a physically includes a building 6b, and this building 6b physically includes a server room 6c. In the example shown in FIG. 6, the server room 6c physically includes a rack 6d, and the rack 6d physically includes a physical server 6e. In the example shown in FIG. 6, the physical server 6e logically includes a VM 6f (or a virtual server). As described above, in the “logical inclusion” and “physical inclusion” relationship, the calculation resource 301 has a one-to-one correspondence relationship with the related calculation resource 301.

  FIG. 7 is a diagram illustrating an example of a connection relationship. In the example shown in FIG. 7, the router 7a is connected to a switch (SW) 7d. The router 7b is connected to SW7d and SW7e. The router 7c is connected to the SW 7e. In the example illustrated in FIG. 7, the SW 7d is connected to the VM 7f and the VM 7g. The SW 7e is connected to the VM 7g and the VM 7h. Thus, when the computing resources 301 are connected, it is called a connection relationship. Note that when the VMs 7f to 7h are devices higher than the SWs 7d and 7e, and the SWs 7d and 7e are devices higher than the routers 7a to 7c, they are positioned lower than the calculation resource A and lower in the connection relationship. When the computing resource B to be connected is connected, the computing resource A located at the upper level may be referred to as “main item”, and the computing resource B located at the lower level may be referred to as “subordinate item”. In the example illustrated in FIG. 7, VMs 7f to 7h are “main items”, and SWs 7d and 7e are “subordinate items”.

  Next, a data structure stored in the computational resource relevance information table 511 will be described with reference to FIGS. 8 and 9. FIG. 8 is a diagram illustrating a definition example of a data structure stored in the computational resource relevance information table 511. In other words, FIG. 8 shows an example of definition of relationship information between computing resources. A plurality of pieces of this relationship information are defined for each computing resource.

  For example, as shown in FIG. 8, the relationship information is defined by “relationship ID”, “main item”, “relationship”, “subordinate item”, and “relationship type”. Here, the “relationship ID” is an identifier of the relationship information. For example, data values such as “0001” and “0002” are stored in “Relationship ID”.

  The “main item” and the “subordinate item” each indicate a calculation resource. For example, data values such as “VM number”, “service name”, “temperature sensor”, and “server number” are stored in “main item”. The “subordinate item” stores data values such as “server number”, “VM number”, “router number”, “VM cluster number”, “load balancer number”, and “server room number”.

  “Relationship” indicates the relationship between the “main item” and the “subordinate item”. For example, in “Relation”, “on” indicating that the calculation resource specified as the main item starts on the calculation resource specified as the subordinate item, the calculation resource specified as the main item is specified as the subordinate item. “Based_on” indicating that the calculation resource is based on the calculation resource, “Member_of” indicating that the calculation resource specified as the main item is a part of the group formed by the calculation resource specified as the subordinate item, and the main item "Attached_by" indicating that the computing resource designated as the subordinate item is installed in the computing resource designated as the subordinate item, and the computing resource designated as the main item exists within the computing resource designated as the subordinate item A data value such as “in” is stored.

  “Relationship type” indicates a relationship between a certain computing resource and another computing resource. For example, “inclusion” or “connection” is stored in “relationship type”.

  For example, in the definition example of the data structure stored in the computational resource relevance information table 511 shown in FIG. 8, when the “relationship ID” is “0001”, the VM number is included in the server number. Define gender.

  FIG. 9 is a diagram illustrating an example of entity values stored in the computational resource relevance information table 511. The example shown in FIG. 9 shows an example of the entity value stored in the computational resource relevance information table 511 registered based on the definition of FIG. In the computational resource relevance information table 511 shown in FIG. 9, “Relationship ID”, “Main Item”, “Relationship”, “Subordinate Item”, and “Relationship Type” are the same as the items shown in FIG. Detailed description will be omitted.

  In the example illustrated in FIG. 9, the calculation resource relevance information table 511 includes a server number “sv0002” for a calculation resource whose “relationship ID” is “0001” and whose VM number is “vm0001”. Indicates a relationship. Similarly, in the example illustrated in FIG. 9, the calculation resource relevance information table 511 has a VM number “vm0001” for a calculation resource whose “relationship ID” is “0002” and whose service name is “Svc0001”. Indicates that the relationship is included. Note that the relationship information stored in the calculation resource relationship information table 511 is updated as a result of the operation of the calculation resource 301.

  Returning to FIG. 4, the calculation resource monitoring content information table 512 associates information for identifying an event to be monitored for the computing resource among events occurring in the computing resource for each computing resource. Information (also referred to as resource status information) "is stored. Here, at the time of initial setting, information for identifying the initial state of monitoring of the computing resource is set in the “computing resource monitoring content information” stored in the computing resource monitoring content information table 512. For example, information indicating that the response from the computing resource to the communication request to the computing resource is in a normal state or that the processing amount in the computing resource does not exceed a certain threshold is set. The The “computation resource monitoring content information” is set to an initial value every time the computation resource is operated.

  The “computation resource monitoring content information” is updated when an event occurs in the computation resource. For example, when an event in which a response from a calculation resource to a calculation request for a calculation resource is not performed or an event in which the processing amount of the calculation resource exceeds a certain threshold occurs, the calculation resource monitoring content information table 512 is displayed. In the stored “computation resource monitoring content information”, an event that has occurred in the computation resource is set.

  FIG. 10 is a diagram illustrating an example of a data structure stored in the calculation resource monitoring content information table 512. As illustrated in FIG. 10, the computing resource monitoring content information table 512 stores information in which “type”, “monitoring target”, “monitoring item”, and “monitoring state (initial value)” are associated with each other. . Here, the “type” stored in the calculation resource monitoring content information table 512 indicates the type of the calculation resource. For example, the “type” stores data values such as “VM”, “server”, and “server rack”.

  The “monitoring target” stored in the computing resource monitoring content information table 512 indicates the identifier of the computing resource corresponding to the type. For example, data values such as “vm0001” and “vm0002” are stored in “monitoring target”.

  The “monitoring item” stored in the computing resource monitoring content information table 512 indicates an item to be monitored for the monitoring target. For example, data values such as “life and death”, “CPU usage rate”, “memory usage rate”, “temperature”, “power consumption”, and “rack usage rate” are stored in the “monitoring item”.

  The “monitoring status” stored in the computing resource monitoring content information table 512 indicates the status of the monitoring target. For example, the “monitoring state” stores data values such as “green” indicating that a response has been obtained from the computing resource and “red” indicating that no response has been obtained from the computing resource. In the “monitoring state”, data values such as “low”, “midium”, and “high” regarding the usage rate are stored.

  As an example, the computing resource monitoring content information table 512 shown in FIG. 10 monitors the life and death of the VM identified by the calculation resource “vm0001”, and the life and alive state of “vm0001” is “green”. Indicates a state. Similarly, the calculation resource monitoring content information table 512 shown in FIG. 10 monitors the CPU usage rate of the VM identified by the calculation resource “vm0001”, and the CPU usage rate of “vm0001” is “low”. Indicates a low state.

  Returning to FIG. 4, the application target determination conditional expression template selection information table 513 stores “determination condition expression template information” for identifying a determination condition expression template to be applied in response to an event that occurs in a computing resource. The application target determination conditional expression template selection information table 513 includes, as information, a variable indicating the calculation resource itself in which the event has occurred and a variable indicating one or more other calculation resources having a special relationship with the calculation resource. . In addition, the application target determination conditional expression template selection information table 513 includes a determination conditional expression for determining an operation to be executed, defined as a logical product of a plurality of determination items representing operation states in one or more target calculation resources, It includes information that is combined with information indicating the content of the operation to be executed that is determined as a result of the determination.

  FIG. 11 is a diagram illustrating an example of a data structure stored in the application target determination conditional expression template selection information table 513. As illustrated in FIG. 11, the application target determination conditional expression template selection information table 513 includes “determination condition expression template identification information”, “event occurrence calculation resource”, “related calculation resource”, and “determination condition expression”. , Information associated with “operation contents” is stored.

  Here, the “judgment condition expression template identification information” stored in the application target judgment condition expression template selection information table 513 indicates an identifier of “judgment condition expression template information”. For example, data values such as “000A” and “000B” are stored in “judgment condition expression template identification information”.

  The “event occurrence calculation resource” stored in the application target determination conditional expression template selection information table 513 indicates the type of the calculation resource in which the event has occurred. For example, data values such as “service number”, “virtual machine cluster number,“ server device ”,“ temperature sensor ”, and“ time activation ”are stored in“ event occurrence calculation resource ”.

  The “related calculation resource” stored in the application target determination conditional expression template selection information table 513 indicates a calculation resource related to the calculation resource in which the event has occurred. For example, data values such as “router number”, “virtual machine number”, and “server device” are stored in “related calculation resources”.

  Further, the “determination condition expression” stored in the application target determination condition expression template selection information table 513 is an expression indicating a condition for determining whether or not to perform an operation on a calculation resource. For example, the “judgment condition” includes “service = red && router = green”, “(virtual server # 1 load = high) && (virtual server # 2 load = high) &&... (Virtual server #N load = high) ”,“ CPU load = high ”, and“ night time zone && server device CPU = low ”.

  The “operation content” stored in the application target determination conditional expression template selection information table 513 indicates the content of the operation to be executed on the computing resource. For example, the “operation content” includes “service restart”, “add virtual machine”, “new virtual server creation stop”, “new virtual server creation stop, destination search, migration of existing virtual server”, and “virtual Data values such as server destination search, virtual server movement, and server device power off are stored.

  As an example, in the application target determination conditional expression template selection information table 513 shown in FIG. 11, the “determination conditional expression template information” identified by “000A” indicates that an event has occurred in the service, and When the related router is normal, it indicates information for restarting the service. Similarly, in the application target determination conditional expression template selection information table 513 shown in FIG. 11, the “determination conditional expression template information” identified by “000B” indicates that an event has occurred in a cluster of virtual machines, When the load on each virtual machine constituting the cluster of machines is high, this indicates information for adding a virtual machine.

  The determination condition expression table 514 stores “determination condition expression information” associated with each calculation resource. The determination condition expression table 514 stores determination condition expression information for each calculation resource based on the “determination condition expression template information” illustrated in FIG. 11.

  FIG. 12 is a diagram illustrating an example of a data structure stored in the determination condition formula table 514. As illustrated in FIG. 12, the determination condition expression table 514 includes “determination condition expression template identification information”, “event occurrence calculation resource”, “related calculation resource”, “determination condition expression”, and “operation content”. Is stored. The items stored in the determination condition formula table 514 are the same as the items stored in the application target determination condition formula model selection information table 513 shown in FIG.

  As an example, the determination condition expression table 514 shown in FIG. 12 shows that when an event occurs in the service identified by “svc0001”, the “determination condition expression template information” identified by “000A” If the related router “rt0001” is normal, this indicates information for restarting the service “svc0001”. Similarly, the determination condition expression table 514 illustrated in FIG. 12 indicates that the server apparatus “sv0001” is generated when an event occurs in the server apparatus identified by “sv0001” in the “determination condition expression template information” identified by “000C”. If the CPU load is high, it indicates that the information is to stop creating a new virtual server.

  Returning to FIG. 4, the control unit 520 is an electronic circuit such as a CPU (Central Processing Unit) or an MPU (Micro Processing Unit), and includes a determination unit 521, a calculation resource operation unit 522, and a change unit 523. .

  The determination unit 521 is triggered by the occurrence of an event in the computing resource 301 operating inside the information processing apparatus group 300, and the other computing resources related to the computing resource 301 in which the event has occurred and the computing resource 301 in which the event has occurred. Based on the state of 301, an operation to be performed on the computing resource 301 in which the event has occurred and the other computing resource 301 is determined.

  For example, when the event information from the monitoring device 400 is received, the determination unit 521 is triggered by reception of the event information from the monitoring device 400 and one or more calculation resources (hereinafter, “ The content of the operation is determined based on the determination result obtained by applying the value of the state of “target computing resource” to the determination conditional expression.

  First, when the event information is received from the monitoring device 400, the determination unit 521 updates the “computation resource monitoring content information” stored in the computing resource monitoring content information table 512. For example, the determination unit 521 notifies the item “monitoring status” corresponding to the “type”, “monitoring target”, and “monitoring item” of the computing resource in which the event has occurred, in the event monitoring information. Change to the state that was set.

  Subsequently, the determination unit 521 determines an operation to be executed with reference to “determination condition expression information” stored in the determination condition expression table 514. For example, the determination unit 521 specifies a calculation resource that matches the identifier of the calculation resource in which the event has occurred in the “event generation calculation resource” of the determination condition formula information. Then, the determination unit 521 specifies the “related calculation resource” and the “judgment condition expression” associated with the specified calculation resource.

  Then, the determination unit 521 matches the “monitoring state” associated with the “monitoring target” that matches the identifier of the computing resource in which the event occurred in the “computing resource monitoring content information” stored in the computing resource monitoring content information table 512. To identify the state of the computing resource in which the event occurred. Similarly, the determination unit 521 matches the identifier of the computing resource (also referred to as a related computing resource) related to the computing resource in which the event has occurred in the “computing resource monitoring content information” stored in the computing resource monitoring content information table 512. The “monitoring state” associated with “monitoring target” is read, and the state of the related computing resource is specified.

  Further, the determination unit 521 determines whether or not the condition of the calculation resource in which the event has occurred and the condition of the related calculation resource satisfy the condition of the specified determination conditional expression. Then, when the condition of the determination condition formula is satisfied, the determination unit 521 determines to execute the operation content associated with the “event occurrence calculation resource” of the determination condition formula information. On the other hand, the determination unit 521 determines that the operation for the calculation resource is not executed when the condition of the determination conditional expression is not satisfied.

  Specifically, in the case of the “determination condition expression information” stored in the determination condition expression table 514 described with reference to FIG. 12, when an event occurs in the service “svc0001”, the determination unit 521 indicates the state of “svc0001” And the state of “rt0001” are acquired from the computing resource monitoring content information. Then, the determination unit 521 determines whether the state of “svc0001” and the state of “rt0001” satisfy the condition of the determination conditional expression. In such a case, “svc0001” is “red”. For example, the determination unit 521 determines that the condition of the determination condition expression is satisfied if “rt0001” is “green”, and satisfies the condition of the determination condition expression if “rt0001” is “red”. Judge that there is no. In other words, the judgment condition information is represented by a logical product of the state of the computing resource in which the event has occurred and the state of the computing resource related to the computing resource in which the event has occurred.

  In addition, the determination unit 521 transmits a “calculation resource operation request” related to the execution of the determined operation on the target calculation resource to the calculation resource operation unit 522. FIG. 13 is a diagram illustrating an example of a calculation resource operation request. As illustrated in FIG. 13, the determination unit 521 generates a calculation resource operation request in which “operation”, “operation target”, and “operation argument” are associated with each other.

  Here, “operation” in the calculation resource operation request indicates a command type that defines an operation to be performed on the calculation resource to be operated. For example, the “operation” includes “initialize” instructing initialization, “activate” instructing activation, “poweroff” instructing power-off, “cleanup” instructing erasing, “connect” instructing connection, Data values such as “addMember” for instructing addition, “migrateTo” for instructing movement, and “stopNewServer” for instructing stop of creation of a new virtual server are stored.

  “Operation target” is a calculation resource to be operated, and indicates a calculation resource in which an event has occurred. “Operation target” includes data such as “vm0001” and “vm0002” for identifying virtual machines, “Vmc0003” for identifying a cluster of virtual machines, “LB0001” for identifying a load balancer, and “sv0001” for identifying a server device. Stores the value.

  The “operation argument” indicates a calculation resource that is related to an operation condition or an operation target according to the operation content. For example, the “operation argument” stores data values such as “stop time to 3 minutes later”, “vm0002”, and the like.

  As an example, the computational resource operation request shown in FIG. 13 indicates that the VM identified by “vm0001” is initialized.

  When the calculation resource operation unit 522 receives the calculation resource operation request, the calculation resource operation unit 522 operates the calculation resource 301 in the information processing apparatus group 300 according to the content of the operation request specified by the calculation resource operation request. For example, the calculation resource operation unit 522 performs the operation determined by the determination unit 521 for the calculation resource 301 in which the event has occurred and the other calculation resources 301. For example, when the calculation resource operation unit 522 receives the calculation resource operation request from the determination unit 521, the calculation resource operation unit 522 operates the calculation resource 301 in the information processing apparatus group 300 according to the content of the operation request specified by the calculation resource operation request. Then, when the processing for operating the calculation resource 301 is completed, the calculation resource operation unit 522 notifies the change unit 523 that the operation has been completed and the operation content.

  Furthermore, when the calculation resource operation unit 522 receives a request for operating the calculation resource 301 operating inside the information processing apparatus group 300 from the user terminal 200, the calculation resource operation unit 522 performs an operation on the calculation resource 301. The “computation resource operation request” received from the user terminal 200 is the same as the “computation resource operation request” generated by the determination unit 521 described with reference to FIG. When the processing for operating the calculation resource 301 is completed, the calculation resource operation unit 522 notifies the change unit 523 that the operation has been completed and the operation content.

  When the relationship between the calculation resource 301 that is the target of the operation and the other calculation resource 301 related to the calculation resource changes as a result of the operation being executed, the changing unit 523 changes the calculation resource relevance information table 511. The relationship information is changed for the computing resource 301 that is the target of the operation to be stored.

  For example, when adding a new calculation resource, the change unit 523 adds “relationship ID”, “main item”, “relation”, “subordinate item”, and “relation type” for the added calculation resource. "Relationship information" associated with "" is generated and stored in the computing resource relevance information table 511. In addition, when the computing resource in operation is stopped, the changing unit 523 deletes the “relationship information” of the stopped computing resource from the computing resource relevance information table 511. In addition, when restarting the operating computing resource, the changing unit 523 does not update the “relationship information” for the restarted computing resource.

  Further, when the operation is executed, the change unit 523 changes the relation between the calculation resource 301 that is the operation target and another calculation resource 301 related to the calculation resource, and the determination condition expression table 514 Change the stored conditional expression information. In other words, the change unit 523 generates a new calculation resource as a result of the operation execution determined for the target calculation resource in the calculation resource operation unit 522, and adds, corrects, or deletes the relationship between the calculation resources. When a change in the relationship between computing resources is detected, such as when a change such as is added, the relationship between the target computing resources may change (for example, the value indicating the relationship between the predetermined target computing resources may change) If so, the judgment condition information is set again for all the calculation resources to be changed.

  For example, the changing unit 523 sets the determination condition expression information again based on the application target determination condition expression model selection information and the relationship information. Specifically, the changing unit 523 refers to the relationship information stored in the calculation resource relevance information table 511 and identifies a calculation resource related to the new calculation resource. More specifically, the changing unit 523 determines, from the relationship information stored in the calculation resource relevance information table 511, the identifier of the “subordinate item” associated with the “main item” that matches the identifier of the new calculation resource. By specifying, a computing resource (related computing resource) related to the new computing resource is specified. Then, the changing unit 523 stores the identifier of the identified calculation resource in “related calculation resource” of the determination condition expression information. Also, the changing unit 523 stores the identifier of the new calculation resource in the “event occurrence calculation resource” of the determination condition formula information.

  Also, the changing unit 523 reads the determination condition expression from the application target determination condition expression template selection information, and replaces the new calculation resource identifier and the related calculation resource identifier with the determination condition expression. Then, the changing unit 523 stores the replaced determination condition expression in the “determination condition expression” of the determination condition expression information.

  Note that the changing unit 523 performs the same processing for the computing resource whose relationship between the computing resources has changed.

  The changing unit 523 changes the calculation resource monitoring condition information. The calculation resource monitoring condition information includes information for determining how to monitor the calculation resource. For example, the change unit 523 generates the calculation resource monitoring condition information when a new calculation resource is generated as a result of the operation of the calculation resource, or when the monitoring condition of the calculation resource changes, and the monitoring device 400. This computing resource monitoring condition information includes the frequency of communication requests to computing resources when monitoring no response from computing resources, the maximum waiting time for responses, and the amount of processing information when monitoring overloads on computing resources. Frequency, processing amount threshold value, destination IP (Internet Protocol) address when a monitoring device makes a communication request to a computing resource, and the like.

  FIG. 14 is a diagram for explaining the calculation resource monitoring condition information. In the example shown in FIG. 14, Examples 1 to 4 are shown as monitoring conditions. In FIG. 14, “Computing Resource Monitoring Condition Information” shown as Example 1 designates a condition for monitoring whether a computing resource is alive or dead. For example, the “computation resource monitoring condition information” shown in Example 1 causes “service = red” to be transmitted to the control device 500 as event information when a response to the ping is not obtained from the information processing device group 300 for 60 seconds or more. It shows that.

  More specifically, when the monitoring device 400 transmits a ping to the information processing device group 300 at a cycle of 10 seconds, and no response is continuously obtained from the information processing device group 300, no response to the ping. It is determined that In such a case, the monitoring device 400 transmits event information “service = red” to the control device 500.

  In FIG. 14, “computation resource monitoring condition information” shown as example 2 specifies a condition for monitoring the load of the computation resource. For example, the “computation resource monitoring condition information” shown in Example 2 indicates that “VM cluster load = high” is input to the control device 500 as event information when the total load average of the VM cluster is 5.0 or more for 5 minutes. Indicates sending.

  More specifically, the monitoring device 400 collects measured values from the information processing device group 300 for load average at a cycle of 30 seconds, totals the load of the VM cluster from the information processing device group 300, and continuously 10 times. When it becomes 5.0 or more, it determines with the total load average of a VM cluster continuing for 5 minutes and being 5.0 or more. In such a case, the monitoring apparatus 400 transmits event information “VM cluster load = high” to the control apparatus 500.

  In FIG. 14, “computation resource monitoring condition information” shown as example 3 designates a condition for monitoring the resource usage rate of the computation resource. For example, the “computation resource monitoring condition information” shown in Example 3 indicates that “CPU load = high” is transmitted to the control device 500 as event information when the CPU usage rate is 95% or more for 5 minutes. .

  More specifically, when the monitoring device 400 collects the measured values of the CPU usage rate of the information processing device group 300 in a cycle of 30 seconds and the CPU usage rate becomes 95% or more for 10 consecutive times, the CPU usage rate continues for 5 minutes. Therefore, it is determined that it is 95% or more. In such a case, the monitoring apparatus 400 transmits event information “CPU load = high” to the control apparatus 500.

  In FIG. 14, “computation resource monitoring condition information” shown as Example 4 specifies conditions for monitoring the temperature of the server room. For example, the “computational resource monitoring condition information” shown in Example 4 indicates that “server room temperature = high” is transmitted to the control device 500 as event information when the temperature of the server room is 40 ° C. or higher for 10 minutes. Show.

  More specifically, when the monitoring device 400 collects the room temperature measurement value of the server room at a cycle of 1 minute and becomes 10 degrees or more continuously for 10 times, the temperature of the server room continues for 10 minutes or more and 40 degrees or more. It is determined that In such a case, the monitoring apparatus 400 transmits event information “server room temperature = high” to the control apparatus 500.

  Note that the changing unit 523 may generate calculation resource monitoring condition information for a plurality of monitoring conditions and transmit the calculation resource monitoring condition information to the monitoring apparatus 400.

  FIG. 15 is a sequence diagram for explaining an operation example of the initial setting process. In the example illustrated in FIG. 15, a processing operation when the control device 500 receives a calculation resource operation request from the user terminal 200 will be described. As shown in FIG. 15, the user terminal 200 transmits a calculation resource operation request to the control device 500 (step S21).

  In the control device 500, when the calculation resource operation unit 522 receives the calculation resource operation request from the user terminal 200, the calculation resource operation unit 522 operates the calculation resource 301 of the information processing device group 300 (step S22). When the operation completion is notified from the information processing apparatus group 300 (step S23), the computation resource operation unit 522 notifies the change unit 523 of the operation completion. Then, the changing unit 523 updates the relationship information stored in the calculation resource relationship information table 511 (step S24).

  FIG. 16 is a sequence diagram illustrating an operation example of the change process. In the example shown in FIG. 16, a processing operation by the changing unit 523 of the control device 500 when a calculation resource is operated will be described. As illustrated in FIG. 16, the changing unit 523 sets “computation resource monitoring content information” stored in the computing resource monitoring content information table 512 for the operated computing resource (step S31). For example, when a new computing resource is added, the changing unit 523 generates “computation resource monitoring content information” for the added computing resource and stores it in the computing resource monitoring content information table 512. In addition, when stopping a computing resource in operation, the changing unit 523 deletes the “computation resource monitoring content information” of the stopped computing resource from the computing resource monitoring content information table 512. Further, when restarting a running computing resource, the changing unit 523 sets “monitoring state” in the “computing resource monitoring content information” to an initial state for the restarted computing resource.

  The changing unit 523 obtains “computation resource monitoring content information” from the computing resource monitoring content information table 512 (step S32), and obtains “judgment condition formula template information” from the application target judgment conditional expression template selection information table 513 ( In step S33), “relationship information” is acquired from the computational resource relationship information table 511 (step S34). Then, the changing unit 523 sets “determination condition expression information” stored in the determination condition expression table 514 based on “determination condition expression template information” and “relationship information” (step S35).

  Also, the changing unit 523 generates the calculation resource monitoring condition information based on the “calculation resource monitoring content information”, the “judgment condition expression template information”, and the “relationship information”, and the generated calculation resource monitoring condition information is displayed. It transmits to the monitoring apparatus 400 (step S36). Then, the monitoring device 400 sets a calculation resource monitoring condition and monitors the calculation resource 301 of the information processing device group 300 (step S37).

  FIG. 17 is a sequence diagram for explaining an operation example of the computational resource operation processing when an event occurs. In the example illustrated in FIG. 17, a processing operation performed by the control device 500 when an event occurs in a computing resource will be described. As illustrated in FIG. 17, the monitoring device 400 monitors the information processing device group 300 and detects an abnormality or a failure that has occurred in the information processing device group 300 (step S41). When the monitoring device 400 detects a change in the state of each computing resource based on the operation status collected from the information processing device group 300, the monitoring device 400 transmits the content of the change as event information to the control device 500 (step S42).

  When receiving the event information from the monitoring device 400, the determination unit 521 in the control device 500 updates the “computation resource monitoring content information” stored in the computing resource monitoring content information table 512 (step S43). Further, the determination unit 521 acquires a determination conditional expression (step S44), determines the condition, and determines an operation to be performed on the calculation resource. The determination unit 521 generates a “calculation resource operation request” for the determined operation, and transfers the generated “computation resource operation request” to the calculation resource operation unit 522 (step S45).

  When receiving the calculation resource operation request from the determination unit 521, the calculation resource operation unit 522 operates the calculation resource of the information processing apparatus group 300 (step S46). When the operation completion is notified from the information processing apparatus group 300 (step S47), the computing resource operation unit 522 notifies the change unit 523 of the operation completion. Then, the changing unit 523 updates the relationship information stored in the calculation resource relationship information table 511 (step S48).

  Next, a processing procedure performed by the control device 500 will be described with reference to FIGS. FIG. 18 is a flowchart showing the procedure of the initial setting process. As illustrated in FIG. 18, the computational resource operation unit 522 determines whether a resource operation request has been received from the user terminal 200 (step S101). Here, when it is determined that the resource operation request has been received from the user terminal 200 (Yes in step S101), the computing resource operation unit 522 executes a resource operation process (step S102). Note that. Details of the resource operation processing will be described later with reference to FIG.

  After the end of step S102, the changing unit 523 executes a determination condition expression table changing process (step S103). Note that. Details of the judgment condition expression table changing process will be described later with reference to FIG. Further, the changing unit 523 executes a monitoring condition changing process (step S104). Note that. Details of the monitoring condition changing process will be described later with reference to FIG.

  In addition, when it is determined that the resource operation request has not been received from the user terminal 200 (No in step S101), the calculation resource operation unit 522 repeatedly executes the determination process in step S101. Further, the changing unit 523 may change the processing order of the determination condition expression table changing process in step S103 and the monitoring condition changing process in step S104.

  FIG. 19 is a flowchart showing the procedure of the resource operation process. This resource operation process corresponds to the process of step S102 shown in FIG. The calculation resource operation unit 522 executes a resource operation on the calculation resource 301 in the information processing apparatus group 300 (step S201). Then, the computing resource operation unit 522 determines whether the operation is successful (step S202). Here, when the computing resource operation unit 522 determines that the operation has not been successful (step S202, No), the processing proceeds to step S204.

  On the other hand, when the calculation resource operation unit 522 determines that the operation is successful (step S202, Yes), the calculation unit relevance information stored in the calculation resource relevance information table 511 is updated by the change unit 523 (step S203). Subsequently, the computing resource operation unit 522 determines whether or not there is an unoperated operation target (step S204). Here, if the computing resource operation unit 522 determines that there is an unoperated operation target (Yes in step S204), the processing moves to step S201 and executes the resource operation. On the other hand, when the computing resource operation unit 522 determines that there is no unoperated operation target (No in step S204), the resource operation processing ends.

  FIG. 20 is a flowchart illustrating a procedure of the determination condition table changing process. This determination condition expression table changing process corresponds to the process of step S103 shown in FIG. The changing unit 523 sets an initial value in the “computation resource monitoring content information” stored in the computing resource monitoring content information table 512 (step S301).

  Subsequently, the changing unit 523 reads the resource state (computed resource monitoring content information) from the computational resource monitoring content information table 512 (step S302). Also, the changing unit 523 reads the determination condition expression template (“determination condition expression template information”) from the application target determination condition expression template selection information table 513 (step S303). Also, the changing unit 523 reads the relationship information from the computational resource relationship information table 511 (step S304).

  Then, the changing unit 523 sets the item “judgment condition formula” in the judgment condition formula table 514 (step S305), and sets the items “event occurrence calculation resource”, “related calculation resource”, and “operation content”. (Step S306). After the process of step S306 ends, the changing unit 523 ends the determination condition expression table change process.

  FIG. 21 is a flowchart illustrating the procedure of the monitoring condition change process. This monitoring condition changing process corresponds to the process of step S104 shown in FIG. The changing unit 523 reads the resource status (computed resource monitoring content information) from the computational resource monitoring content information table 512 (step S401). Further, the changing unit 523 reads the relationship information from the calculation resource relationship information table 511 (step S402). Also, the changing unit 523 reads the determination condition expression model from the application target determination condition expression model selection information table 513 (step S403). Then, the changing unit 523 sets the monitoring condition information with reference to the calculation resource monitoring content information, the relationship information, and the determination condition formula template (step S404). The changing unit 523 transmits the set monitoring condition information to the monitoring device 400 (step S405). After the process of step S405 ends, the change unit 523 ends the monitoring condition change process.

  FIG. 22 is a flowchart showing a processing procedure when an event occurs. As illustrated in FIG. 22, the determination unit 521 determines whether event information has been received from the monitoring device 400 (step S501). Here, when determining that the event information has been received from the monitoring device 400 (Yes in step S501), the determination unit 521 updates the resource state (calculation resource monitoring content information table 512) (step S502). In addition, when it determines with the determination part 521 not having received event information from the monitoring apparatus 400 (step S501, No), it performs repeatedly the determination process of step S501.

  After step S502 ends, the determination unit 521 collates the item “determination condition expression” in the determination condition expression table 514 (step S503), and determines an operation (step S504). The determination unit 521 requests the calculation resource operation unit 522 for the determined operation.

  The computing resource operation unit 522 executes resource operation processing (step S505). The details of the resource operation process are the same as the process described with reference to FIG. After the end of step S505, the changing unit 523 executes a determination condition expression table changing process (step S506). The details of the judgment condition expression table changing process are the same as those described with reference to FIG. The changing unit 523 executes monitoring condition changing processing (step S507). The details of the monitoring condition changing process are the same as those described with reference to FIG.

  As described above, the control device 500 according to the first embodiment is triggered by the occurrence of an event in the calculation resource 301 operating inside the information processing device group 300, and the calculation resource 301 in which the event has occurred and the event are Based on the state of the other computing resource 301 related to the generated computing resource 301, an operation to be performed on the computing resource 301 in which the event has occurred and the other computing resource 301 is determined. Then, the control device 500 executes the determined operation on the computing resource 301 in which the event has occurred and other computing resources 301. As a result, according to the first embodiment, it is possible to operate the calculation resource in consideration of the calculation resource related to the calculation resource in which the event has occurred. As a result, in the information processing system 100, for example, when another computing resource has surplus capacity, the computing resource having this surplus capacity can be used. can do. Hereinafter, an example in which calculation resources are effectively used by the control device 500 according to the first embodiment will be described with reference to FIGS. 23 to 26.

(Service failure automatic recovery)
A case will be described in which the monitoring conditions of the computing resource monitoring condition information are service life and death (outline monitoring) and life and death monitoring of the router on the outline monitoring route, and automatic recovery is performed when the service fails. In such a case, the control device 500 receives “(service = red) && (router = green)” as event information from the monitoring device 400. Then, the control device 500 refers to the determination condition expressions stored in the determination condition expression table 514 and determines to restart the service that is the operation target. In this case, the control device 500 generates a calculation resource operation request including “cleanup (VM)”, “initialize (VM)”, and “activate (VM)” as commands, and the service of the information processing device group 300 Restart. In this case, “(service) on (VM)” and “(service) based_on (router)” are referred to as the relationship information.

(Auto scale out)
A case where the monitoring condition of the computing resource monitoring condition information is VM performance monitoring and automatic scale-out is described. FIG. 23 is a diagram for explaining the processing operation in the case of automatic scale-out. Here, it is assumed that three virtual machines (VM # 1 to VM # 3) are operating in the virtual machine cluster (VMC).

  In such a case, the control device 500 monitors the virtual machine load average exceeding the threshold. Here, the control device 500 receives “(load Average (VM) = high) for all VM in VMC” indicating that the threshold of the load average is exceeded as event information. When the control device 500 receives event information indicating that the load average threshold has been exceeded for more than 5 minutes from the monitoring device 400, the control device 500 refers to the determination condition expression stored in the determination condition expression table 514 and refers to the virtual machine (VM It is determined that # 4) is added.

  In this case, the control device 500 uses, as commands, “add_port (VMC)”, “connect (VMC, VM # 4)”, “initialize (VM # 4)”, “activate (VM # 4)”, “add_member”. (LB, VM # 4) "is generated, and a VM # 4 is added. In this case, “(VM) member_of (VMC)”, “(VM) member_of (LB)”, and “(VM # 4) member_of (VMC)” are referred to as the relationship information.

(Automatic performance deterioration prevention)
A case where the monitoring condition of the computing resource monitoring condition information is the performance (CPU usage rate) monitoring of the virtual machine server device and the performance deterioration of the virtual machine server device is automatically prevented will be described. FIG. 24 is a diagram for explaining a processing operation in the case of automatically preventing performance degradation of the virtual machine server device. Here, three virtual machines VM # 1 to VM # 3 are operating on the virtual machine server # 1, and two virtual machines VM # 4 to VM # 5 are operating on the virtual machine server # 2. Shall.

  In such a case, the control device 500 monitors the CPU usage rate of the virtual machine server device. Here, the control device 500 receives “(cpuUsage (VMS) = high)” indicating that the CPU usage rate of the virtual machine server # 1 exceeds a threshold value (for example, 95%) as event information. Then, when the event information indicating that the CPU usage rate exceeds 95% is received from the monitoring device 400 for 10 minutes, the control device 500 refers to the determination condition formula stored in the determination condition formula table 514, and the virtual machine server It is determined not to place a new virtual machine in # 1.

  In this case, the control device 500 generates a calculation resource operation request including “serverStop (VMS)” as a command, and does not place a new virtual machine on the virtual machine server # 1. In such a case, VM # 6 is arranged in virtual machine server # 2.

(Automatic suppression of local rise in server room temperature)
A case will be described in which the monitoring condition of the computing resource monitoring condition information is the temperature monitoring of the server room, and the temperature of the server room is prevented from rising locally. FIG. 25 is a diagram for explaining the processing operation in the case where the temperature of the server room is prevented from rising locally. Here, it is assumed that physical servers 25a to 25c are installed in the server room 25, and a plurality of sensors 25d to 25k are installed in the server room 25. In addition, four virtual machine servers operate on the physical server 25a, four virtual machine servers operate on the physical server 25b, and four virtual machine servers operate on the physical server 25c. It shall be. It is assumed that a VM is running on each virtual machine server.

  In such a case, the control device 500 monitors the temperature rise of the server room 25 using the plurality of sensors 25d to 25k. Here, the control device 500 receives “temp (TS) = high” indicating that the temperature of the server room detected by the sensor 25d and the sensor 25e exceeds the threshold value as event information. Then, the control device 500 refers to the determination condition formula stored in the determination condition formula table 514 and determines to stop the creation of the new virtual machine and move the virtual machine to another virtual machine server device. In this case, the VM running on the virtual machine server installed in the vicinity of the sensor 25d and the sensor 25e is live migrated to another virtual machine server.

  In this case, the control device 500 generates a calculation resource operation request including “serverStop (VMS))” and “migrate_to (VM, search_mintemp_VMS (notVMS))” as commands, and moves the VM. In such a case, “(TS) attached_by (VMS)” and “(VM) on (VMS)” are referred to as the relationship information.

(Automatic degeneration at night)
A case will be described in which the monitoring condition of the computing resource monitoring condition information is monitoring of time activation, and the degenerate operation is automatically performed at night. FIG. 26 is a diagram for explaining a processing operation in the case of automatically performing a degenerate operation at night. Here, during the day, twelve virtual machines (VM # 1 to VM # 12) are operating on the virtual machine server # 1, and twelve virtual machines (VM # 13 to VM # 13) are running on the virtual machine server # 2. It is assumed that VM # 24) is operating.

  The control device 500 monitors the CPU usage rates of the virtual machine server # 1 and the virtual machine server # 2. Here, the control device 500 indicates, for example, “(time> 20:00) && (time <08:00) && (cpuUsage (VMS) << 20) indicating that the CPU usage rate does not exceed the threshold for 30 minutes or more after 20:00. 30%) × 30 min ”. In such a case, the control device 500 moves the VM # 13 to VM # 24 operating on the virtual machine server # 2 to the virtual machine server # 1 by live migration, and after moving the VM # 13 to VM # 24, the virtual machine server # 2 is determined to be stopped.

  In this case, the control device 500 uses, as a command, “if (search_vms_have_max_position (VMSs) == VMS) then foreach (VM on VMS) migrate_to (VM, search_vms_have_min_position (fMSs) = VMSp) (VMSs) = VMSp) (VMSs) = A calculation resource operation request including “poweroff (VMS)” is generated. That is, the control device 500 searches for a surplus server device (virtual machine server # 1), moves the virtual machine to the server device, and stops the power of the server device (virtual machine server # 2) after the movement is completed. Let In such a case, “all (VMs) on (VMS)” and “(VM positions) on all (VMSs)” are referred to as the relationship information.

(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. Therefore, other embodiments will be described below.

(System configuration)
Also, among the processes described in this embodiment, all or part of the processes described as being performed automatically can be performed manually, or the processes described as being performed manually can be performed. All or a part can be automatically performed by a known method. In addition, the processing procedure, control procedure, specific name, and information including various data and parameters shown in the above-described document and drawings (for example, FIGS. 1 to 26) are arbitrarily determined unless otherwise specified. Can be changed.

  Further, the determination unit 521, the calculation resource operation unit 522, and the change unit 523 may be mounted on separate control devices, and the separate control devices may operate as an integrated control device. Further, the control device 500 and the monitoring device 400 may operate as an integrated device.

  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.

(program)
It is also possible to create a computing resource management program in which processing executed by the control device 500 according to the first embodiment is described in a language that can be executed by a computer. In this case, the same effect as the above-described embodiment can be obtained when the computer executes the calculation resource management program. Further, by recording the calculation resource management program on a computer-readable recording medium, and reading and executing the calculation resource management program recorded on the recording medium by the computer, the same processing as in the above embodiment is realized. May be. Hereinafter, an example of a computer that executes a calculation resource management program that realizes the same function as that of the control device 500 illustrated in FIG. 4 and the like will be described.

  FIG. 27 is a diagram illustrating a computer 1000 that executes a computing resource management program. As shown in FIG. 27, the computer 1000 includes, for example, a memory 1010, a CPU 1020, a hard disk drive interface 1030, a disk drive interface 1040, a serial port interface 1050, a video adapter 1060, and a network interface 1070. These units are connected by a bus 1080.

  The memory 1010 includes a ROM (Read Only Memory) 1011 and a RAM 1012. The ROM 1011 stores a boot program such as BIOS (Basic Input Output System). The hard disk drive interface 1030 is connected to the hard disk drive 1090. The disk drive interface 1040 is connected to the disk drive 1100. A removable storage medium such as a magnetic disk or an optical disk is inserted into the disk drive 1100, for example. For example, a mouse 1110 and a keyboard 1120 are connected to the serial port interface 1050. For example, a display 1130 is connected to the video adapter 1060.

  Here, as shown in FIG. 27, the hard disk drive 1090 stores, for example, an OS 1091, an application program 1092, a program module 1093, and program data 1094. The computational resource management program described in the above embodiment is stored in, for example, the hard disk drive 1090 or the memory 1010.

  Further, the computing resource management program is stored in, for example, the hard disk drive 1090 as a program module in which a command executed by the computer 1000 is described. Specifically, a program in which an operation determination procedure for executing information processing similar to that of the determination unit 521 described in the above embodiment and a calculation resource operation procedure for executing information processing similar to that of the calculation resource operation unit 522 are described. The module is stored in the hard disk drive 1090.

  Further, data used for information processing by the computational resource management program is stored as program data, for example, in the hard disk drive 1090. Then, the CPU 1020 reads out the program module and program data stored in the hard disk drive 1090 to the RAM 1012 as necessary, and executes each procedure described above.

  Note that the program modules and program data related to the computational resource management program are not limited to being stored in the hard disk drive 1090, but are stored in, for example, a removable storage medium and read out by the CPU 1020 via the disk drive 1100 or the like. May be. Alternatively, the program modules and program data related to the computational resource management program are stored in another computer connected via a network such as a LAN (Local Area Network) or a WAN (Wide Area Network), and are transmitted via the network interface 1070. It may be read by the CPU 1020.

(Other)
Note that the computing resource management program described in this embodiment can be distributed via a network such as the Internet. The computational resource management 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, and a DVD, and being read from the recording medium by the computer. .

DESCRIPTION OF SYMBOLS 100 Information processing system 200 User terminal 300 Information processing apparatus group 400 Monitoring apparatus 500 Control apparatus 501 Communication control part 510 Storage part 511 Computation resource relevance information table 512 Computation resource monitoring content information table 513 Application target judgment conditional expression template selection information table 514 Judgment Condition Expression Table 520 Control Unit 521 Determination Unit 522 Calculation Resource Operation Unit 523 Change Unit 1000 Computer 1010 Memory 1011 ROM
1012 RAM
1020 CPU
1030 Hard disk drive interface 1040 Disk drive interface 1050 Serial port interface 1060 Video adapter 1070 Network interface 1080 Bus 1090 Hard disk drive 1091 OS
1092 Application program 1093 Program module 1094 Program data 1100 Disk drive 1110 Mouse 1120 Keyboard 1130 Display

Claims (6)

Triggered by the occurrence of an event in a computing resource operating inside the information processing device group, the event is based on the state of the computing resource in which the event has occurred and the other computing resource related to the computing resource in which the event has occurred. A determination unit that determines an operation to be performed on the calculation resource in which the error occurred and the other calculation resource;
A control apparatus comprising: an operation unit that executes the operation determined by the determination unit with respect to the calculation resource in which the event has occurred and the other calculation resource. The monitoring status of the computing resource that runs inside the information processing device group, the resource status information that associates the status of the computing resource in the monitoring item, the status of the computing resource in which the event occurred, and the occurrence of the event A storage unit that stores determination condition expression information that associates an operation to be executed according to the state of another calculation resource related to the calculated resource;
The determining unit refers to the resource state information to identify the state of the computing resource in which the event has occurred and the state of the other related computing resource, and to determine the state of the computing resource in which the identified event has occurred. The control apparatus according to claim 1, wherein an operation to be executed is determined using the determination condition formula information based on a state and a state of the other computing resource. The storage unit further stores relationship information associating a calculation resource operating inside the information processing apparatus group with another calculation resource related to the calculation resource,
As a result of the execution of the operation, when the relationship between the calculation resource that is the target of the operation and the other calculation resource related to the calculation resource, which is stored as the relationship information, is changed, the operation target The control apparatus according to claim 2, further comprising a changing unit that changes the determination condition expression information with respect to a calculation resource.   The said operation part further performs operation with respect to the said calculation resource, when the request | requirement which operates the calculation resource which operates inside the information processing apparatus group is received from the user. 4. The control device according to any one of 3. The control unit
Triggered by the occurrence of an event in a computing resource operating inside the information processing device group, the event is based on the state of the computing resource in which the event has occurred and the other computing resource related to the computing resource in which the event has occurred. A determination step of determining an operation to be performed on the calculation resource in which the error occurred and the other calculation resource;
A calculation resource management method, comprising: an operation step of executing the operation determined by the determination step on the calculation resource in which the event has occurred and the other calculation resource. Based on the occurrence of an event in a computing resource operating inside the information processing device group on the computer, based on the status of the computing resource in which the event occurred and the status of other computing resources related to the computing resource in which the event occurred A determination procedure for determining an operation to be performed on the computational resource in which the event has occurred and the other computational resource;
An operation procedure for executing the determined operation on the calculation resource in which the event has occurred and the other calculation resource.

Images