WO2015140973A1 - Computer control method, management apparatus, and computer system - Google Patents

Computer control method, management apparatus, and computer system Download PDF

Info

Publication number
WO2015140973A1
WO2015140973A1 PCT/JP2014/057647 JP2014057647W WO2015140973A1 WO 2015140973 A1 WO2015140973 A1 WO 2015140973A1 JP 2014057647 W JP2014057647 W JP 2014057647W WO 2015140973 A1 WO2015140973 A1 WO 2015140973A1
Authority
WO
WIPO (PCT)
Prior art keywords
computer
route
communicable
power
management device
Prior art date
Application number
PCT/JP2014/057647
Other languages
French (fr)
Japanese (ja)
Inventor
雅巳 平松
秀一 内山
吉田　賢一
Original Assignee
株式会社日立製作所
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 株式会社日立製作所 filed Critical 株式会社日立製作所
Priority to PCT/JP2014/057647 priority Critical patent/WO2015140973A1/en
Publication of WO2015140973A1 publication Critical patent/WO2015140973A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F1/00—Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
    • G06F1/26—Power supply means, e.g. regulation thereof
    • G06F1/32—Means for saving power
    • G06F1/3203—Power management, i.e. event-based initiation of a power-saving mode
    • G06F1/3234—Power saving characterised by the action undertaken
    • G06F1/3287—Power saving characterised by the action undertaken by switching off individual functional units in the computer system
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Definitions

  • This relates to a method for controlling a plurality of computers that construct an internal network connected to an external network.
  • Patent Document 1 JP 2010-191814 A (Patent Document 1). This publication states that “the switch management unit determines the first port to which the computer to be activated is connected, notifies the PCI switch, and instructs the power supply control unit to activate the computer connected to the first port”. Techniques are described (see summary).
  • the communication unit and other communication units there is a path connecting between the communication unit and other communication units, and the route connects the communication unit and other communication units via the computer as an intermediate point.
  • the communication unit and other communication units can communicate if power is supplied to the computer, and the communication unit and other communication units cannot communicate if the computer is powered off. .
  • Between the communication unit and another communication unit may be, for example, between a plurality of computers, between a computer and a port of a network switch, or between a port and another port. It may be between.
  • Patent Literature 1 when the configuration of the above-described computer system is not assumed and the communication unit and other communication units cannot communicate with each other, the computer on the path between the communication unit and the other communication units is powered on. Is not disclosed, and the route is controlled to be communicable. For this reason, it is necessary to supply power to all the computers, and power consumption cannot be reduced.
  • the present invention controls the power availability state of the computer on the path between the communication unit and the other communication unit, thereby controlling the communication availability state between the communication unit and the other communication unit, and the power consumption
  • An object of the present invention is to provide a method for controlling the power state of a computer that reduces the power consumption.
  • the present invention provides a computer control method in a management device that manages a plurality of computers that construct an internal network connected to an external network.
  • the connection is communicable
  • the connection between the computer to which power is not supplied and the other computer connected to the computer is not communicable
  • the management device passes only through the communicable connection,
  • Communicable route information for managing a communicable route to the external network and a usable route to the external network via the connection between the computers regardless of whether the communication is possible or not Information on available routes to be stored
  • the management device refers to the available route information and determines whether each computer is supplied with the power.
  • a communicable route to the external network satisfies a predetermined condition, and when it is determined that the communicable route does not satisfy a predetermined condition, the management device can use the usable route information. And a route other than the currently communicable route is identified from the available routes from the computer that does not satisfy the predetermined condition to the external network, and the management device is supplied with power on the identified route.
  • a control method characterized by instructing the supply of power to a computer that is not connected.
  • the present invention by controlling the power state of the computer on the path between the communication unit and the other communication unit, the communication availability state between the communication unit and the other communication unit is controlled, and the power consumption Can be provided.
  • FIG. 1 is an explanatory diagram of a computer system according to Embodiment 1.
  • FIG. 3 is an explanatory diagram of a computer state table according to Embodiment 1.
  • FIG. It is explanatory drawing of the connectable table of Example 1.
  • FIG. It is explanatory drawing of the connection state table of Example 1.
  • FIG. It is explanatory drawing of the external path
  • FIG. 10 is an explanatory diagram of an external connection policy table according to the first embodiment. It is explanatory drawing of the available path
  • FIG. It is explanatory drawing of the switch table of Example 1.
  • FIG. 6 is a flowchart of policy update processing according to the first embodiment.
  • 3 is a flowchart of policy determination processing according to the first exemplary embodiment.
  • FIG. 3 is a flowchart of processing target computer policy determination processing according to the first embodiment.
  • 3 is a flowchart of a startup computer selection process according to the first embodiment.
  • 3 is a flowchart of failure detection processing according to the first embodiment.
  • 3 is a flowchart of computer activation processing according to the first embodiment.
  • 4 is a flowchart of end-time response processing according to the first exemplary embodiment. It is explanatory drawing of the computer system of Example 2.
  • Example 1 will be described with reference to FIGS.
  • FIG. 1 is an explanatory diagram of the computer system according to the first embodiment.
  • the computer system includes a plurality of computers N1 (1A) to a computer N4 (1D), a control device 5, a plurality of ports P1 (3A) to a port P2 (3B), a network switch 8, and a management device 9. .
  • the computer N1 (1A) to the computer N4 (1D) are collectively referred to as the computer 1, and the port P1 (3A) to the port P2 (3B) are collectively referred to as the port 3.
  • the number of computers 1 and the number of ports 3 and the connection form between the computers 1 are not limited to the numbers shown in FIG.
  • the computer N1 (1A) is connected to the network switch 8 via the port P1 (3A), and the computer N2 (1B) is connected to the network switch 8 via the port P2 (3B).
  • the network switch 8 is connected to an external network 7. Further, the computer N1 and the computer N2 (1B) are connected, the computer N1 (1A) and the computer N3 (1C) are connected, the computer N2 (1B) and the computer N4 (1D) are connected, and the computer N3 ( 1C) and the computer N4 (1D) are connected.
  • the computer 1 executes various processes such as a Web content distribution process, a streaming distribution process, or a data cache process. Since the computer 1 also functions as a relay device that relays data to other computers 1 or the port 3, a network is constructed by the computer 1 and the port 3, and the network is referred to as an internal network. This internal network is connected to the network 7 via the network switch 8. The network 7 is called an external network with respect to the internal network. Port 3 is set to a network interface (not shown) that connects the internal network to the network switch 8. For example, when the computer group 6 is mounted on one housing, the network interface is mounted on the housing.
  • the computer N1 (1A) includes a control unit 11 and a storage unit 12.
  • the control unit 11 is, for example, a processor
  • the storage unit 12 is, for example, a memory.
  • the storage unit 12 stores programs corresponding to various processes executed by the computer 1, and the control unit 11 executes the various processes by executing the programs stored in the storage unit 12. Since the other computers N2 (1B) to N4 (1D) have the same configuration as the computer N1 (1A), the description thereof is omitted.
  • the control device 5 is connected to the computer 1.
  • the control device 5 is connected to the management device 9 via the network switch 8.
  • the control device 5 controls the power state of the computer 1 and manages the presence / absence of a failure in the computer 1 and the power state.
  • the computer 1 that can control the power state by the control device 5 is referred to as a computer group 6.
  • the control device 5 may supply power to each computer 1 from a collective power supply unit (not shown).
  • Each computer 1 has a power supply unit, and the power supply unit of each computer 1 supplies power to each computer 1. May be supplied.
  • the control device 5 may have a collective power supply unit, or another device may have a collective power supply unit, but the collective power supply unit is connected so that power can be supplied to each computer 1. There is a need.
  • each computer 1 has a power supply unit
  • the state in which no power is supplied to each computer 1 is a state in which at least the control device 5 and each computer 1 can communicate with each other, and the computer 1 is completely supplied with power. Not in a state that is not.
  • the control device 5 includes a control unit 51 and a storage unit 52.
  • the control unit 51 is, for example, a processor, and the storage unit 52 is, for example, a memory.
  • the storage unit 52 stores a program corresponding to the power control process and the power state management process executed by the control unit 51, as well as a computer state table 521, a connectable table 522, and a connection state table 523.
  • the control unit 51 executes the power control process and the power state management process by executing a program corresponding to the power control process and the power state management process.
  • the computer state table 521 is a table for managing the power state of the computer 1 and the presence or absence of a failure, and details will be described with reference to FIG.
  • the connectable table 522 is a table for managing the connection relationship between the computer 1 and the port 3, and will be described in detail with reference to FIG.
  • the connection state table 523 is a table for managing connection destinations that are currently communicable between the computer 1 and the port 3, and will be described in detail with reference to FIG.
  • the network switch 8 specifies the port 3 corresponding to the destination of the data received from the network 7, and outputs the received data from the specified port 3.
  • the network switch 8 includes a control unit 81 and a storage unit 82.
  • the control unit 81 is, for example, a processor, and the storage unit 82 is a memory or the like.
  • a switch table 821 is stored in the storage unit 82, and the control unit 81 refers to the switch table 821 and identifies the port 3 corresponding to the destination of the received data.
  • the switch table 821 will be described in detail with reference to FIG.
  • the management device 9 provides the user with an interface for setting a policy required for each computer, and identifies a computer that starts supplying power to satisfy the policy.
  • the management device 9 includes a control unit 91 and a storage unit 92.
  • the control unit 91 is, for example, a processor
  • the storage unit 92 is, for example, a memory.
  • the storage unit 92 includes a program that executes various processes executed by the management apparatus 9, an external path state table 921, an external connection policy, and the like.
  • a table 922 and an available route table 923 are stored.
  • Various processes are executed by the control unit 91 executing various programs.
  • the management device 9 includes an input device (not shown) (for example, a keyboard or a mouse) that receives input from the user, and an output device (not shown).
  • the output device is a display device such as a display.
  • the external path status table 921 manages the computer 1 and the port 3 on the communicable path from each computer 1 to each port 3, and the communication bandwidth of each communicable path, and will be described in detail with reference to FIG. To do.
  • the external connection policy table 922 is a table for managing a policy set for the route of each computer, and will be described in detail with reference to FIG.
  • the available route table 923 manages the computers 1 and 3 on the available route from each computer 1 to each port 3 and the communication bandwidth of each available route, and will be described in detail with reference to FIG. To do.
  • the available routes include all routes that can be set in the internal network, including routes that can be communicated and routes that cannot be communicated but can be communicated if any computer 1 is supplied with power. It is a route.
  • the management device 9 may have the function of the control device 5. For this reason, in the claims, a device having the functions of the management device 9 and the control device 5 is described as a management device. Further, for example, the control device 5, the computer 1, and the port 3 of the computer group 6 may be mounted in one housing.
  • FIG. 2 is an explanatory diagram of the computer state table 521 according to the first embodiment.
  • the computer state table 521 includes a computer 5211, a power state 5212, and an availability 5213. Identification information of the computer 1 is registered in the computer 5211, and information indicating whether the power is supplied to each computer 1 or shut off is registered in the power state 5212. If “ON” is registered in the power state 5212, it indicates that power is being supplied to the computer 1, and if "OFF" is registered in the power state 5212, the supply of power to the computer 1 is cut off. Indicates that In the present embodiment, an example will be described in which power is supplied to the computer N1 (1A), the computer N2 (1B), and the computer N4 (1D), and the power supply to the computer N3 (1C) is interrupted. .
  • the availability 5213 information indicating whether each computer 1 is available or unavailable is registered.
  • “available” is registered in the record availability 5213 corresponding to all the computers 1, but “unusable” is recorded in the record availability 5213 corresponding to the computer 1 in which a failure or the like has occurred. Is registered.
  • the control device 5 periodically acquires the power supply state and the failure state from the computer 1 and updates the computer state table 521.
  • the computer 1 may notify the control device 5 when the power supply state is changed, or may notify the control device 5 when the computer 1 detects a failure.
  • the control device 5 periodically transmits an acquisition request for the power supply state and the failure state to the computer 1, and when the computer 1 receives the acquisition request, the control device 5 transmits its own power supply state and failure state to the control device 5. May be.
  • FIG. 3 is an explanatory diagram of the connectable table 522 of the first embodiment.
  • the connectable table 522 includes a point 5221 and a connection destination column group 5222.
  • the point 5221 identification information of all the computers 1 or ports 3 constituting the internal network is registered.
  • the connection destination column group 5222 the identification information of the computer 1 or the identification information of the port 3 physically connected to the computer 1 or the port 3 and the physical bandwidth value of the route to each connection destination are registered.
  • connection destination A 5222A of the connection destination column group 5222 of the record in which the identification information “N1” of the computer N1 (1A) is registered at the point 5221 includes the identification information (P1) of the port P1 (3A) and the computer N1 (1A).
  • the bandwidth value “10.0 Gbps” is registered.
  • the identification information (N2) of the computer N2 (1B) and the bandwidth value “10.0 Gbps” of the route from the computer N1 (1A) to the computer N2 (1B) are registered.
  • the identification information “N3” of the computer N3 and the bandwidth value “10.0 Gbps” of the route from the computer N1 (1A) to the computer N3 (1C) are registered.
  • the connectable table 522 is set in advance based on the connection relationship of the computer 1 or the port 3 configuring the internal network, and is updated when the connection relationship of the computer 1 or the port 3 is changed.
  • FIG. 4 is an explanatory diagram of the connection state table 523 according to the first embodiment.
  • the connection state table 523 includes a point 5231 and a connection destination column group 5232.
  • the identification information of the computer 1 or the port 3 to which the power is supplied among the computers 1 or the ports 3 configuring the internal network is registered.
  • the connection destination column group 5232 the identification information of the computer 1 or port 3 to which the power is supplied out of the computer 1 or port 3 physically connected to the computer 1 or port 3, and the route to each connection destination A physical bandwidth value is registered.
  • the identification information of the computer N3 (1C) is deleted from the connectable table 522 shown in FIG. Has been.
  • the connection state table 523 illustrated in FIG. 4 does not include a record in which the identification information (N3) of the computer N3 (1C) is registered at the point 5231.
  • the connection destination column group 5232 of the record in which the identification information (N1) of the computer N1 (1A) is registered at the point 5231 does not include the identification information of the computer N3 (1C), and the identification of the computer N4 (1D) is included at the point 5231.
  • the connection destination column group 5232 of the record in which the information (N4) is registered does not include the identification information of the computer N3 (1C).
  • connection state table 523 is generated by deleting the identification information of the computer 1 whose power supply is cut off from the record of the connectable table 523 based on the power state of the computer 1 acquired by the control device 5. .
  • FIG. 5 is an explanatory diagram of the external route state table 921 according to the first embodiment.
  • the external route state table 921 includes a computer 9211, a route column group 9212, and a band column group 9213.
  • the path column group 9212 includes a path 9212A to P1 and a path 9212B to P2.
  • the identification information of the computer 1 and the port P1 (3A) on the communicable path from each computer 1 to the port P1 (3A) is registered as an ordered list.
  • the identification information of the computer 1 and the port P2 (3B) on the communicable path from each computer 1 to the port P2 (3B) is registered as an ordered list.
  • a communicable route is a route through which power is supplied to all the computers 1 on the route.
  • the band column group 9213 includes a band 9213A to P1 and a band 9213B to P2.
  • a bandwidth value of a communicable route from each computer 1 to the port P1 (3A) is registered.
  • a bandwidth value of a communicable route from each computer 1 to the port P2 (3B) is registered.
  • the management device 9 Based on the connection state table 523 acquired from the control device 5, the management device 9 uses a route search algorithm such as the Dijkstra method to find the shortest route from each computer 1 to which power is supplied to each port 3. The route from each computer 1 to each port 3 is specified. Then, the management device 9 registers the identification information of the computer 1 on the identified route in the route column group 9212 and registers the minimum bandwidth value of the identified route in the bandwidth column group 9213.
  • a route search algorithm such as the Dijkstra method
  • FIG. 6 is an explanatory diagram of the external connection policy table 922 according to the first embodiment.
  • the external connection policy table 922 includes a computer 9221, a maximum used bandwidth 9222, a minimum used bandwidth 9223, a redundancy 9224, and an activation policy 9225.
  • identification information of all the computers 1 constituting the internal network is registered.
  • the maximum use bandwidth 9222 the maximum bandwidth value of the route assigned to each computer 1 is registered.
  • the minimum use band 9223 the minimum band value of the route assigned to each computer 1 is registered.
  • the redundancy 9224 the number of routes assigned to each computer 1 is registered.
  • the activation policy 9225 when each computer 1 does not satisfy the conditions registered in the maximum use bandwidth 9222, the minimum use bandwidth 9223, and the redundancy 9224, it is allowed to start another computer 1 and generate an additional route. Information indicating whether or not to be performed is registered.
  • the external connection policy table 922 is generated by the management apparatus 9 executing the policy update process shown in FIG.
  • FIG. 7 is an explanatory diagram of the available route table 923 according to the first embodiment.
  • the available route table 923 includes a computer 9231, a route column group 9232, and a bandwidth column group 9233.
  • the path column group 9232 includes a path 9232A to P1 and a path 9232B to P2.
  • the identification information of the computer 1 and the port P1 (3A) on the available route from each computer 1 to the port P1 (3A) is registered as an ordered list.
  • the identification information of the computer 1 and the port P2 (3B) on the available route from each computer 1 to the port P2 (3B) is registered as an ordered list.
  • An available route is a route that passes through the connected computer 1 regardless of whether power is supplied or cut off.
  • the band column group 9233 includes a band 9223A to P1 and a band 9233B to P2.
  • a bandwidth value of an available route from each computer 1 to the port P1 (3A) is registered.
  • a bandwidth value of an available route from each computer 1 to the port P2 (3B) is registered.
  • the external route state table 921 shown in FIG. 5 does not include a record in which the identification information (N3) of the computer N3 (1C) is registered in the computer 9211. There is a route that passes through the computer N3 (3C) and the computer N1 (3A) as an available route from the computer N4 (1D) to the port P1 (3A), but the power supply to the computer N3 (1C) is cut off. Therefore, the route is not a communicable route. Therefore, in the external path state table 921 shown in FIG.
  • NULL is registered in the path 9212A to the P1 of the record in which the identification information (N4) of the computer N4 (1D) is registered in the computer 9211, and the P1 of the record is recorded.
  • “0 Gbps” is registered in the band 9213A.
  • the generation method of the available route table 923 is the same as the generation method of the external route state table 921, and thus the description thereof is omitted.
  • FIG. 8 is an explanatory diagram of the switch table 821 of the first embodiment.
  • the switch table 821 includes a destination 8211 and a port 8212.
  • the destination 8211 identification information of all the computers 1 constituting the internal network is registered.
  • the port 8212 the identification information of the port 3 of the communication path from each computer 1 is registered.
  • control unit 81 of the network switch 8 When the control unit 81 of the network switch 8 receives data from the external network 7, the control unit 81 acquires a destination included in the data from the received data.
  • the control unit 81 refers to the switch table 821 and acquires the identification information of the port 3 registered in the port 8212 of the record in which the destination acquired in the destination 8211 is registered. Next, the control unit 81 transmits the received data to the port 3 identified by the acquired identification information of the port 3.
  • the control unit 91 of the management device 9 refers to the external route state table 921 and identifies the port 3 with which each computer 1 can communicate.
  • the identification information (P1) of the port P1 (3A) is connected to the route 9212A to the P1 of the record in which the identification information (N1) of the computer N1 (1A) is registered in the computer 9211. Is registered, and the identification information (P2) of the port P2 (3B) is registered in the path 9212B to the P2, the control unit 91 determines that the communicable port 3 of the computer N1 (1A) is the port P1 (3A). And the identification information (P1) of the computer N1 (1A), the identification information (P1) of the port P1 (3A), and the identification information (P2) of the port P2 (3B). get.
  • the control unit 91 transmits a switch table update instruction including the acquired identification information of the computer 1 and identification information of the port 3 to the network switch 8.
  • the control unit 81 of the network switch 8 sets the switch table 821 based on the received switch update instruction. For example, when the switch table update instruction includes N1, P1, and P2, if there is a record in which N1 is registered in the destination 8211 of the switch table 821, the control unit 81 of the network switch 8 sets P1 to the port 8212 of the record. And P2. If there is no record in which N1 is registered in the destination 8211 of the switch table 821, the control unit 81 of the network switch 8 adds a new record and registers P1 and P2 in the port 8212 of the added record.
  • the timing when the switch table 821 is set includes when the external route state table 921 is updated and when a new route is set.
  • FIG. 9 is a flowchart of the policy update process according to the first embodiment.
  • the policy update process is a process in which the management apparatus 9 updates the external connection policy table 922 based on a policy update request from the user.
  • the management device 9 receives an input of a policy update request from the user (S101).
  • the user inputs a policy update request via an input device (not shown) of the management device 9.
  • the policy update request includes the identification information of the computer 1 to be updated and the updated policy.
  • the updated policy includes information registered in the column to be updated among the columns of the maximum used bandwidth 9222, the minimum used bandwidth 9223, the redundancy 9224, and the activation policy 9225 of the external connection policy table 922.
  • the management device 9 updates the external connection policy table 922 based on the policy update request (S102). Specifically, the management device 9 specifies a record in which the identification information of the computer 1 registered in the computer 9221 of the external connection policy table 922 matches the identification information of the computer 1 included in the policy update request. Then, the management apparatus 9 registers the updated information in the columns to be updated among the maximum used bandwidth 9222, the minimum used bandwidth 9223, the redundancy 9224, and the activation policy 9225 of the specified record.
  • the policy process is a process for determining whether or not a communicable route of the internal network satisfies the policy of the external connection policy table 922, and details will be described with reference to FIG.
  • the management device 9 determines whether or not the communicable route of the internal network satisfies the policy based on the result of the policy determination process (S104).
  • the management apparatus 9 notifies the user that the update of the external connection policy table 922 is completed (S105), and ends the process. .
  • the management device 9 may display that the update of the external connection policy table 922 has been completed on a display device or the like (not shown).
  • the management apparatus 9 returns to the external connection policy table 922 before being updated in the process of S102, and proceeds to the process of S105.
  • the management apparatus 9 notifies the user that the external connection policy table 922 could not be updated because the communicable path of the internal network does not satisfy the policy.
  • the user can grasp that the communicable route of the internal network does not satisfy the policy.
  • FIG. 10 is a flowchart of the policy determination process according to the first embodiment.
  • the management device 9 acquires the computer state table 521 and the connection state table 523 from the storage unit 52 of the control device 5, and generates the external path state table 921 based on the acquired computer state table 521 and the connection state table 523.
  • the management apparatus 9 includes the computer 1 registered in the computer 5211 of the record in which “ON” is registered in the power state 5212 of the computer state table 521 and “available” is registered in the availability 5213. Get identification information for.
  • the management device 9 adds records as many as the acquired identification information of the computer 1 to the external path state table 921 and registers the acquired identification information of the computer 1 in the computer 9211 of the added record.
  • the management device 9 specifies the communication path to each port 3 of each computer 1 by specifying the connection relationship of each computer 1 with reference to the acquired connection state table 523, and the specified communication is possible.
  • the identification information of the computer 1 on the simple route and the identification information of the port 3 are registered in the route column group 9212 of the external route state table 921.
  • the management device 9 registers the bandwidth value registered in the connection destination column group 5232 registered in the connection state table 523 in the bandwidth column group 9233 of the external path state table 921.
  • the management apparatus 9 selects the identification information of the computer 1 to be processed from the identification information of the computer 1 registered in the computer 9211 of the external path state table 921 generated in the process of S201, and proceeds to the process of S203 ( S202). Since the computer 9211 in the external path state table 921 is supplied with power and the identification information of the computer 1 in which no abnormality has occurred is registered, in the process of S202, power is supplied and no abnormality has occurred.
  • the identification information of the computer 1 is selected as a processing target.
  • the computer 1 identified by the identification information of the processing target computer 1 is referred to as a processing target computer 1.
  • the processing target computer policy determination processing refers to the external connection policy table 922, and determines whether or not a communicable path from the processing target computer 1 satisfies policies such as maximum used bandwidth, minimum used bandwidth, and redundancy. This is a determination process and will be described in detail with reference to FIG.
  • the management device 9 determines whether or not the determination result of the processing in S203 indicates that the processing target computer 1 satisfies the policy (S204).
  • the management apparatus 9 uses the identification information of all the computers 1 registered in the computer 9211 of the external path state table 921 generated in the process of S201. The processes of S202 to S204 are repeated until it is determined that the identified computer 1 satisfies the policy.
  • the management device 9 Is determined to satisfy the policy of the external connection policy table 922 (S205), and the policy determination process is terminated.
  • the management apparatus 9 stores the identification information of the processing target computer 1 registered in the computer 9221 of the external connection policy table 922. It is determined whether or not activation of another computer is registered in the activation policy 9225 (S206).
  • the management apparatus 9 does not satisfy the policy of the external connection policy table 922 for the communicable route of the internal network. (S212) and the process is terminated. This is because the number of communication paths cannot be increased by supplying power to other computers 1.
  • the management device 9 acquires the connectable table 522 and the computer state table 521 from the storage unit 52 of the control device 5. Based on the acquired connectable table 522 and the computer state table 521, an available route table 923 is generated (S207).
  • the management device 9 acquires the identification information of the computer 1 registered in the computer 5211 of a record other than the record in which “unusable” is registered in the availability 5213 of the computer state table 521. Then, the management apparatus 9 adds records as many as the acquired identification information of the computer 1 to the available route table 923, and registers the acquired identification information of the computer 1 in the computer 9231 of the added record. Next, the management device 9 specifies the communicable route to each port 3 of each computer 1 by referring to the acquired connectable table 522 and specifying the connection relationship of each computer 1, and the specified communication possible The identification information of the computer 1 on the simple route and the identification information of the port 3 are registered in the route column group 9232 of the available route table 923. Further, the management apparatus 9 registers the bandwidth value registered in the connection destination column group 5222 registered in the connectable table 522 in the bandwidth column group 9233 of the available route table 923.
  • the management device 9 executes a startup computer selection process for selecting the computer 1 to be started by supplying power (S208).
  • the startup computer selection process will be described in detail with reference to FIG.
  • the management device 9 determines whether or not the computer 1 to be activated in the process of S208 has been selected (S209). If it is determined in S209 that the computer 1 to be activated has not been selected, the process proceeds to S212, and the management apparatus 9 determines that the communicable route of the internal network does not satisfy the policy of the external connection policy table 922. Then, the process ends.
  • step S209 if it is determined in step S209 that the computer 1 to be activated is selected, the management device 9 instructs the control device 5 to supply power to the selected computer 1 (S210).
  • the processing instruction in S210 includes identification information of the computer 1 that supplies power.
  • the control device 5 receives an instruction from the management device 9, the control device 5 causes the computer 1 identified by the identification information of the computer 1 included in the instruction to start supplying power. In this case, the control device 5 changes the power state 5212 of the record in which the identification information of the computer 1 included in the instruction is registered in the computer 5211 of the computer state table 521 to “ON”.
  • control device 5 adds a new record to the connection state table 523 and registers the identification information of the computer 1 included in the instruction at the point 5231 of the added record. Then, the control device 5 refers to the connectable table 522 and specifies the connection destination of the computer 1 identified by the identification information of the computer 1 included in the instruction. The control device 5 registers the identification information of the connection destination specified in the connection destination column group 5232 of the added record in the connection state table 523.
  • control device 5 when the control device 5 starts supplying power to the computer 1 identified by the identification information of the computer 1 included in the received instruction, the control device 5 transmits a response to the received instruction to the management device 9. When receiving the response, the management device 9 updates the external route state table 921.
  • the management device 9 adds a new record to the external route state table 921 and registers the identification information of the computer 1 that is activated by the computer 9211 of the added record.
  • the management apparatus 9 uses the identification information registered in the path column group 9232 of the record in which the identification information of the computer 1 activated by the computer 9231 in the available path table 923 is registered and the band registered in the band column group 9233. Get the value.
  • the management device 9 registers the acquired identification information in the route column group 9212 of the added record in the external route state table 921 and registers the acquired bandwidth value in the bandwidth column group 9213.
  • the management device 9 specifies a column in which the identification information of the computer 1 activated in the route column group 9232 of the available route table 923 exists.
  • the management apparatus 9 identifies the identification information registered in the identified column, the band value registered in the band column group 9233 corresponding to the column, and the identification information of the computer 1 registered in the computer 9231 of the record including the column. To get.
  • the management apparatus 9 registers the acquired identification information in the path column group 9212 of the record in which the identification information of the computer 1 acquired in the computer 9211 of the external path state table 921 is registered, and the acquired bandwidth in the bandwidth column group 9213 Register the value.
  • the management device 9 instructs the network switch 8 to register the correspondence relationship between the identification information of the activated computer 1 and the identification information of the port 3 capable of communicating with the computer 1 in the switch table 821 (S211). The process returns to S201. Then, the management device 9 determines again whether or not the policy is satisfied, including the route that has become communicable by the computer 1 to which power is newly supplied.
  • FIG. 11 is a flowchart of processing target computer policy determination processing according to the first embodiment.
  • the management device 9 refers to the external connection policy table 922 and acquires the redundancy of the processing target computer 1 (S301). Specifically, the management device 9 acquires the number of routes registered in the redundancy 9224 of the record in which the identification information of the processing target computer 1 is registered in the computer 9221 of the external connection policy table 922.
  • the management device 9 refers to the external route status table 921 and acquires the number of routes that can be communicated from the processing target computer 1 (S302). Specifically, the management device 9 stores the column 3 in which the identification information of port 3 is registered in the path column group 9212 of the record in which the identification information of the computer 1 to be processed is registered in the computer 9211 of the external path state table 921. Get the number as the number of paths.
  • the management device 9 determines whether or not the number of paths acquired in the process of S302 is equal to or greater than the number of paths acquired in the process of S301 (S303). In the process of S303, when it is determined that the number of paths acquired in the process of S302 is less than the number of paths acquired in the process of S301, the management apparatus 9 has a path through which communication from the processing target computer 1 is possible. It is determined that the redundancy is not satisfied and the processing target computer 1 does not satisfy the policy (S304), and the processing is terminated.
  • the management apparatus 9 performs processing in S305 to S309. It is determined whether or not a communicable route from the computer 1 satisfies the minimum usable bandwidth.
  • the management device 9 refers to the external connection policy table 922 and acquires the minimum usable bandwidth of the processing target computer 1 (S305). Specifically, the management apparatus 9 acquires the bandwidth value registered in the minimum used bandwidth 9223 of the record in which the identification information of the processing target computer 1 is registered in the computer 9221 of the external connection policy table 922.
  • the management device 9 refers to the external route state table 921 and determines whether the number of routes that can be communicated from the processing target computer 1 is greater than 1 (S306).
  • the management apparatus 9 uses the bandwidth value acquired in the processing of S305 from the processing target computer 1. Dividing by the number of communicable paths (S307), the process proceeds to S308.
  • the management device 9 holds surplus bandwidth information (not shown) for each route to the port 3.
  • a bandwidth value obtained by subtracting the minimum usable bandwidth of each computer 1 from the bandwidth of the route to the port 3 is registered.
  • the bandwidth value of the route to each port 3 is registered in the surplus bandwidth information in the initial state. For example, 10 Gbps registered in the bandwidth 9213A to P1 is registered in the surplus bandwidth information in the initial state of the route to P1, and the surplus bandwidth information in the initial state of the route to P2 is in the bandwidth 9213B to P2.
  • the registered 10 Gbps is registered.
  • the management device 9 subtracts the division value calculated in the processing of S307 from the bandwidth value registered in the surplus bandwidth information of the route to each port 3 (S308).
  • step S306 determines whether the number of communicable paths from the processing target computer 1 is 1, the process proceeds to step S308, and the management apparatus 9 corresponds to one communicable path.
  • the bandwidth value acquired in S305 is subtracted from the bandwidth value registered in the surplus bandwidth information of the route to the port 3.
  • the management device 9 determines whether or not the subtraction value calculated in the process of S308 is 0 or more (S309).
  • the process of S309 if it is determined that the subtraction value calculated in the process of S308 is less than 0, that is, a negative value, the path from the computer 1 to be processed does not satisfy the minimum usable bandwidth, so the process of S304 The management apparatus 9 determines that the processing target computer 1 does not satisfy the policy, and ends the processing.
  • the management device 9 can communicate with the processing target computer 1 in the process of S310 to S314. Determines whether or not the maximum bandwidth is satisfied.
  • the management device 9 refers to the external connection policy table 922 and acquires the maximum usable bandwidth of the processing target computer 1 (S310). Specifically, the management device 9 acquires the bandwidth value registered in the maximum used bandwidth 9222 of the record in which the identification information of the processing target computer 1 is registered in the computer 9221 of the external connection policy table 922.
  • the management device 9 refers to the external route state table 921 and determines whether the number of routes that can be communicated from the processing target computer 1 is greater than 1 (S311).
  • the management apparatus 9 uses the bandwidth value acquired in the processing of S310 from the processing target computer 1. Dividing by the number of communicable paths (S312), the process proceeds to S313.
  • the management device 9 subtracts the division value calculated in the process of S312 from the band value registered in the band column group 9213 of the external path state table 921 (S313).
  • the process proceeds to S313, and the management apparatus 9 performs the bandwidth column group of the external path status table 921.
  • the band value acquired in the process of S310 is subtracted from the band value registered in the column corresponding to the one communicable path 9213.
  • the management device 9 determines whether or not the subtraction value calculated in the process of S313 is 0 or more (S314).
  • the process of S3144 if it is determined that the subtraction value calculated in the process of S314 is less than 0, that is, a negative value, the path from the computer 1 to be processed does not satisfy the maximum usable bandwidth, so the process of S304 The management apparatus 9 determines that the processing target computer 1 does not satisfy the policy, and ends the processing.
  • the management device 9 determines that the communicable path from the processing target computer 1 satisfies the policy. (S315), the process ends.
  • FIG. 12 is a flowchart of the startup computer selection process according to the first embodiment.
  • the management device 9 refers to the available route table 923 and obtains a route that can be used by the computer 1 that is determined not to satisfy the policy (S401). Specifically, the management device 9 acquires the identification information registered in the route column group 9232 in which the identification information of the computer 1 determined not to satisfy the policy in the computer 9231 of the available route table 923 is registered.
  • the management device 9 selects a processing target route from the routes acquired in the process of S401, and proceeds to the process of S403 (S402).
  • the management device 9 refers to the external route state table 921 and acquires a communicable route of the computer 1 that is determined not to satisfy the policy (S403). Specifically, the management device 9 acquires the identification information registered in the route column group 9212 of the record in which the identification information of the computer 1 that does not satisfy the policy is registered in the computer 9221 of the external route state table 921.
  • the management device 9 determines whether the available route to be processed is a communicable route (S404). Specifically, the identification information registered in the route column group 9212 corresponding to each communicable route acquired in the process of S403 does not match the identification information registered in the route column group 9232 corresponding to the processing target route. In this case, the management device 9 determines that the available route to be processed is not a communicable route.
  • the process returns to S403, and the management apparatus 9 processes the other available routes acquired in S401.
  • the target is selected, and the processes of S403 and S404 are executed.
  • the management device 9 determines that there is no computer 1 to be activated (S405). ), The process is terminated.
  • the management device 9 is not supplied with power among the computers 1 on the available route to be processed.
  • the computer is selected as the computer 1 to be activated (S406), and the process is terminated.
  • the policy update request in this case is a request for updating the external connection policy table 922 to the value shown in FIG.
  • the management apparatus 9 receives an input of a policy update request in the process of S101, and updates the external connection policy table 922 as shown in FIG. 6 in the process of S102. Next, the management device 9 executes policy determination processing.
  • the management device 9 acquires the connection status table 523 shown in FIG. 4 and the computer status table 521 shown in FIG. 2 from the control device 5 in the processing of S201, and the external route shown in FIG. A state table 921 is generated.
  • the management apparatus 9 selects the identification information of the computer N1 (1A) from the external path state table 921 shown in FIG. 5 as a processing target in the processing of S202, and performs the processing target computer policy determination processing shown in FIG. 11 in the processing of S203. Execute.
  • the management apparatus 9 acquires the redundancy “2” of the computer N1 (1A) by referring to the external connection policy table 922 shown in FIG.
  • the management apparatus 9 refers to the external route state table 921 and acquires the number of routes “2” that can be communicated from the computer N1 (1A). This is because “P1” is registered in the path 9212A to P1 of the record in which “N1” is registered in the computer 9211 of the external path status table 921, and “P2” is registered in the path 9212B to P2. is there.
  • the management apparatus 9 proceeds to the process of S305, refers to the external connection policy table 922, and calculates the computer N1 (1A).
  • the minimum usable bandwidth “0.5 Gbps” is acquired. Since the number of paths that can be communicated from the computer N1 (1A) is “2” in the process of S306, the process proceeds to S307.
  • the management apparatus 9 divides the minimum usable bandwidth “0.5 Gbps” by “2” to obtain a divided value “0.25 Gbps”.
  • the management device 9 subtracts the division value “0.25 Gbps” from the surplus bandwidth “10 Gbps” of P1 in the initial state and the surplus bandwidth “10 Gbps” of P2 in the initial state in the process of S308. Since the surplus bandwidth of P1 and the surplus bandwidth of P2 are “9.75 Gbps” which is 0 or more, the process proceeds to S310. Note that the surplus bandwidth of P1 and the surplus bandwidth of P2 remain “9.75 Gbps”. The surplus bandwidth of P1 and the surplus bandwidth S202 of P2 are returned to the initial state values when it is determined that the policy is satisfied in the process of S205, or when the policy is not satisfied in the process of S212.
  • the management device 9 refers to the external connection policy table 922 in the process of S310, acquires the maximum usable bandwidth “5 Gbps” of the computer N1 (1A), and can communicate from the computer N1 (1A) in the process of S311. Since the number of routes is “2”, the process proceeds to S312. In the process of S312, the management apparatus 9 divides the maximum usable bandwidth “5 Gbps” by “2” to obtain a divided value “2.5 Gbps”.
  • the management device 9 obtains a division value “2.5 Gbps” from the P1 band 9213A “10 Gbps” and the P2 band 9213B “10 Gbps” to the computer N1 (1A) in the external path state table 921. Subtract. Since the bandwidth of P1 and the bandwidth of P2 are “7.5 Gbps” and become 0 or more, the process proceeds to S315, and the management apparatus 9 determines that the computer N1 (1A) satisfies the policy.
  • the management apparatus 9 selects the identification information of the computer N2 (1B) from the external path state table 921 as a processing target, and the processing target computer shown in FIG. Execute policy judgment processing. Since the number of communicable paths from the computer N2 (1B) is “2” and the redundancy is “2”, the communicable paths from the computer N2 (1B) satisfy the policy regarding redundancy.
  • the management device 9 divides the minimum usable bandwidth “1 Gbps” of the computer N2 (1B) by the number of routes “2” that can be communicated from the computer N2 (1B) to obtain a divided value “0.5 Gbps”.
  • the division value “0.5 Gbps” is subtracted from the surplus bandwidth “9.75 Gbps” of P1 and the surplus bandwidth “9.75 Gbps” of P2
  • the surplus bandwidth “9.25 Gbps” of P1 and the surplus bandwidth “9.25 Gbps” of P2 Since these are 0 or more, the communicable path from the computer N2 (1B) satisfies the policy regarding the minimum usable bandwidth.
  • the management device 9 divides the maximum usable bandwidth “10 Gbps” of the computer N2 (1B) by the number of routes “2” that can be communicated from the computer N2 (1B) to obtain a divided value “5 Gbps”.
  • the division value “5 Gbps” is subtracted from the P1 band 9213A “10 Gbps” and the P2 band 9213B “10 Gbps” to the computer N2 (1B) in the external path state table 921.
  • the surplus bandwidth of P1 and the surplus bandwidth of P2 are “5 Gbps” and become 0 or more, and the communicable path from the computer N2 (1B) satisfies the policy regarding the maximum usable bandwidth. Proceeding to the processing of S315, the management device 9 determines that the computer N2 (1B) satisfies the policy.
  • the management apparatus 9 selects the identification information of the computer N3 (1C) from the external path state table 921 as a processing target, and the processing target computer shown in FIG. Execute policy judgment processing.
  • the processing target computer policy determination processing of the computer N3 (1C) is the same as the computer N1 (1A) and the computer N2 (1B), and it is determined that the computer N3 (1C) satisfies the policy.
  • the management apparatus 9 selects the identification information of the computer N4 (1D) from the external path state table 921 as a processing target, and the processing target computer shown in FIG. Execute policy judgment processing.
  • the management device 9 determines that the computer N4 (1D) does not satisfy the policy.
  • the management apparatus 9 refers to the external connection policy table 922, and the activation policy 9225 of the computer N4 (1D) registers that other computers may be activated. Proceed to processing.
  • the management apparatus 9 acquires the connectable table 522 and the computer state table 521 from the control apparatus 5, generates an available route table 923, and executes the startup computer selection process shown in FIG. 12 in the process of S208. To do.
  • the management device 9 refers to the available route table 923 and acquires the available route of the computer N4 (1D).
  • the route to P1 (N3, N1, P1) and the route to P2 (N2, P2) are acquired.
  • the management apparatus 9 selects a path (N3, N1, P1) to P1 as a process target path.
  • the management device 9 refers to the external route state table 921 and acquires a route (N2, P2) to P2 as a currently communicable route of the computer N4 (1D).
  • the route to P1, which is the processing target route (N3, N1, P1) is different from the route to P2 (N2, P2) as the currently communicable route of the computer N4 (1D). Proceed to the process.
  • the management apparatus 9 selects the computer N3 (1C) to which power is not supplied as a computer to be activated, and ends the process.
  • the process proceeds to S210, and the management apparatus 9 starts up the computer N3 (1C) in the control apparatus 5.
  • the control device 5 registers “ON” in the power supply state 5212 of the computer N3 (1C) in the computer state table 521. Further, since the power is supplied to all the computers 1, the control device 5 updates the connection state table 523 so that the value registered in the connection state table 523 is the same as the connectable table 522. Similarly, the management device 9 updates the external route state table 921 so that the value registered in the external route state table 921 is the same as the available route table 923.
  • the management apparatus 9 can communicate with the computer N3 (1C) and the ports P1 (3A) and P2 (3B) by supplying power to the computer N3 (1C). ) And the port P2 (3B), the switch table 821 shown in FIG. Specifically, a record in which “P1” and “P2” are registered in the port 8212 of the record in which “N3” is registered in the destination 8211 of the switch table 821 shown in FIG. "P1" is further registered in the port 8212.
  • the management device 9 executes the processing subsequent to S202 again on the communicable path after power is supplied to the computer N3 (1C).
  • the present invention it is not necessary to supply power to all the computers 1 constituting the internal network, and when a communication path from a certain computer 1 does not satisfy a predetermined condition, The power source of the computer 1 is supplied. For this reason, the power consumption of the whole computer 1 can be reduced, satisfy
  • the management device 9 When power is newly supplied to the computer 1, the management device 9 specifies a path through which communication is possible when power is supplied to the computer 1, and the computer 1 on the specified path is newly added. The port 3 that can communicate is specified. Then, the management device 9 instructs the network switch 8 to register the relationship between the computer 1 and the port 3 in the switch table 821. As a result, when power is newly supplied to the computer 1, the administrator does not need to manually update the switch table 821 of the network switch 8, so the burden on the administrator can be reduced.
  • the management device 9 generates an available route table 923 when the processing target computer 1 is permitted to start another computer in the processing of S206 shown in FIG. As a result, the available route table 923 is generated only when the available route table 923 is required, so that the processing load on the management device 9 can be reduced.
  • the user since the user is informed that the communicable route of the internal network does not satisfy the policy, the user can grasp that fact.
  • the policy includes redundancy, minimum used bandwidth, and maximum used bandwidth.
  • the communication path from each computer 1 satisfies the redundancy, minimum used bandwidth, and maximum used bandwidth, and the conditions requested by the user. Can be met.
  • the redundancy, the minimum used bandwidth, and the maximum used bandwidth have been described as an example of the policy.
  • the policy may be, for example, a threshold value of power consumption of all the computers 1. In this case, it may be determined that the policy is not satisfied when the power consumption of all the computers 1 is equal to or greater than the threshold value.
  • the timing at which the policy determination process is executed is not limited to this.
  • the policy determination process may be executed, for example, when a failure of the computer 1 is detected (see FIG. 13) or when supply of power to the computer 1 is started (see FIG. 14).
  • FIG. 13 is a flowchart of the failure detection process according to the first embodiment.
  • the control device 5 detects a failure of the computer 1 and updates the computer state table 521 and the connection state table 523 (S501).
  • the control device 5 transmits a response request to the computer 1 at a predetermined cycle, and when there is a computer 1 that does not receive a response even after a predetermined time has elapsed after transmitting the response request, even if a failure of the computer 1 is detected Good.
  • the failure notification of the computer 1 may be detected by transmitting a failure notification to the control device 5 and receiving the failure notification.
  • the control device 5 registers “OFF” in the power state 5212 of the record in which the identification information of the computer 1 that detected the failure is registered in the computer 5211 of the computer state table 521. Unusable is registered in the availability 5213. Further, in the update process of the connection state table 523, the control device 5 deletes the record in which the identification information of the computer 1 that detected the failure is registered at the point 5231 of the connection state table 523 and is registered in the connection destination column group 5232. The identification information of the computer 1 that detected the failure is deleted.
  • control device 5 transmits a failure detection notification including identification information of the computer 1 that has detected the failure to the management device 9 (S502).
  • the management device 9 executes the policy determination process shown in FIG. 10 (S503).
  • the management device 9 determines whether or not the communicable route of the internal network satisfies the policy based on the result of the policy determination process (S504).
  • the management device 9 notifies the user that the computer 1 has failed (S505), and ends the process.
  • the management device 9 may display on the display (not shown) that the computer 1 has failed.
  • the management device 9 informs the user that the communicable route of the internal network does not satisfy the policy (S506), proceeds to the processing of S505, informs the user that the computer 1 has failed, and ends the processing. .
  • the management device 9 executes the policy determination process when the computer 1 fails, even if the communicable route of the internal network does not satisfy the policy due to the failure of the computer 1, the management device 9 By supplying power, a communicable route in the internal network can satisfy the policy. Even if the policy determination process is executed, if the communicable route of the internal network is not satisfied, the management device 9 can notify the user to that effect.
  • FIG. 14 is a flowchart of computer activation processing according to the first embodiment.
  • the management device 9 accepts a startup request for the computer 1 from the user (S601).
  • the activation request includes identification information of the computer 1 that the user desires to start supplying power.
  • the management device 9 instructs the control device 5 to supply power to the computer 1 that has received the activation request (S602).
  • the instruction includes identification information of the computer 1 that starts supplying power.
  • the control device 5 receives an instruction from the management device 9, the control device 5 supplies power to the computer 1 that starts supplying power, and updates the computer state table 521 and the connection state table 523.
  • the specific description of the update process of these tables by the control device 5 is the same as the process of S209 of the policy determination process shown in FIG.
  • the control device 5 causes the computer 1 to start supplying power, the control device 5 transmits a response to the management device 9.
  • the management device 9 executes the policy determination process shown in FIG. 10 (S603).
  • the management device 9 determines whether or not the communicable route of the internal network satisfies the policy based on the result of the policy determination process (S604). If it is determined in S604 that the communicable route of the internal network satisfies the policy, the management device 9 notifies the user that the supply of power to the computer 1 specified by the activation request has been started (S605). The process is terminated. As an example of notification to the user, the management device 9 may display on the display device (not shown) that the computer 1 has failed.
  • step S604 if it is determined in step S604 that the internal network communicable route does not satisfy the policy, the internal network communicable route cannot satisfy the updated external connection policy table 922 policy.
  • the management device 9 instructs the control device 5 to stop the power supply of the computer 1 that has supplied power to the control device 5 in the process of S602 (S606). Then, the management apparatus 9 proceeds to the process of S605, notifies the user that power cannot be supplied to the computer 1 specified by the activation request, and ends the process.
  • the control device 5 receives an instruction from the management device 9, the control device 5 stops the power supply of the computer 1, and the computer state table 521 and the connection state table 523 updated when the power supply to the computer 1 is supplied.
  • the management device 9 executes the policy determination process when power is supplied to the designated computer 1, so that a path through which the internal network can communicate by supplying power to the designated computer 1 is determined. Even if the policy is not satisfied, the communication path of the internal network can satisfy the policy by supplying power to the new computer 1. Even if the policy determination process is executed, if the communicable path of the internal network is not satisfied, the management device 9 can notify the user of the fact without supplying power to the designated computer 1.
  • FIG. 15 is a flowchart of end-time response processing in the first embodiment.
  • the management device 9 1 is a process of continuing the supply of power to 1.
  • the management device 9 receives a request for termination of a certain computer 1 from the user (S701).
  • the termination request includes identification information of the computer 1 (the computer 1 scheduled to be terminated) that the user desires to terminate.
  • the management device 9 acquires the computer state table 521 and the connection state table 523 from the storage unit 52 of the control device 5 in the process of S201, and based on the acquired computer state table 521 and connection state table 523, the external path A state table 921 is generated.
  • the management device 9 updates the external route state table 921 generated in the processing of S201 so as to indicate the communicable route of the internal network when the supply of power to the computer 1 scheduled to end is stopped (S702). . Specifically, the management apparatus 9 deletes the record in which the identification information of the computer 1 scheduled to be terminated is registered in the computer 9211 of the external route state table 921. In addition, the management device 9 deletes the identification information of the computer 1 scheduled to end from the route column group 9212 of the external route state table 921.
  • the management apparatus 9 selects the identification information of the computer 1 to be processed from the identification information of the computer 1 registered in the computer 9211 of the external path state table 921 updated in the processing of S702, and proceeds to the processing of S704. (S703). That is, the processing target computer 1 is selected from the computers 1 to which power other than the computer 1 scheduled to be terminated is supplied.
  • the management apparatus 9 refers to the external path state table 921 updated in S702, executes a processing target computer policy determination process (S704), and proceeds to the process of S204.
  • the management apparatus 9 determines whether the determination result of the process of S704 satisfies the processing target computer 1 satisfying the policy.
  • the process proceeds to S206.
  • the management apparatus 9 registers whether or not to start another computer in the activation policy 9225 of the record in which the identification information of the computer 1 to be processed is registered in the computer 9221 of the external connection policy table 922. Determine whether.
  • the management device 9 does not instruct the control device 5 to cut off the power supply of the computer 1 scheduled to be terminated, continues the power supply of the computer 1 scheduled to be terminated (S707), and there is a communication path on the internal network. Since the policy is not satisfied, the user is notified that the scheduled computer 1 has not been terminated (S706), and the process is terminated.
  • the policy determination process is executed at some timing. Again, it is determined that the processing target computer 1 does not satisfy the policy, and the computer 1 scheduled to end is activated. For this reason, in the present embodiment, when the computer 1 to be processed does not satisfy the policy and the activation of another computer is permitted, the management device 9 stops the power supply of the computer 1 scheduled to be terminated. Continue supplying power. However, if it is determined in S204 that the processing target computer 1 does not satisfy the policy, the process may proceed to S707 without executing S206.
  • step S206 it is determined that activation of another computer is not registered in the activation policy 9225 of the record in which the identification information of the computer 1 to be processed is registered in the computer 9221 of the external connection policy table 922. If it is determined in step S204 that the processing target computer 1 satisfies the policy, the process returns to step S703, and the management apparatus 9 selects another computer 1 as the processing target computer 1, and the processing in step S704 is performed. Proceed to processing. The management apparatus 9 repeats the processes of S703, S704, and S204 for the computer 1 identified by the identification information of all the computers 1 registered in the computer 9211 of the external path state table 921 updated in the process of S702.
  • the management device 9 determines that the computer 1 scheduled to be terminated.
  • the control device 5 is instructed to shut off the supply of power (S705).
  • the control device 5 stops the power supply of the computer 1 and updates the computer state table 521 and the connection state table 523.
  • the control device 5 registers “OFF” in the power state 5212 of the record in which the identification information of the computer 1 scheduled to be completed is registered in the computer 5211 of the computer state table 521.
  • control device 5 deletes the record in which the identification information of the computer 1 scheduled to end at the point 5231 of the connection state table 523 is registered, and is registered in the connection destination column group 5232. The identification information of the computer 1 scheduled to be terminated is deleted.
  • the management apparatus 9 proceeds to the process of S706, notifies the user that the computer 1 has been terminated, and ends the process.
  • the management apparatus 9 also terminates the computer 1 that is scheduled to be terminated, but also indicates that there is a computer 1 that does not satisfy the policy. Also notify.
  • the management device 9 When an instruction to stop the supply of power to a certain computer 1 is given, if the communicable route of the internal network after the termination of the computer 1 does not satisfy the policy, the management device 9 The power supply can be continued.
  • Example 2 will be described with reference to FIG.
  • the management apparatus 9 controls the power supply state of the computers 1 of one computer group 6.
  • the present invention is applied to a larger network configuration.
  • the power state of the computer 1 is controlled.
  • FIG. 16 is an explanatory diagram of the computer system according to the second embodiment.
  • the same structure as FIG. 1 of Example 1 among the structures shown in FIG. 16 gives the same code
  • the computer system of this embodiment includes a computer group 6A, a computer group 6B, a network switch 8, a management device 9, and an overall control device 10.
  • a computer group 6A a computer group 6A
  • a computer group 6B a network switch 8
  • a management device 9 a management device 9
  • an overall control device 10 the configurations of the computer 1, the control device 5, the network switch 8, and the management device 9 are omitted, but these are the same as those in FIG. 1.
  • the computer group 6A is the computer 1 whose power is controlled by the control device 5A
  • the computer group 6B is the computer 1 whose power is controlled by the control device 5B.
  • the computer groups 6A and 6B are collectively referred to as a computer group 6.
  • the computer group 6A has the same configuration as the computer group 6 shown in FIG.
  • the computer group 6B includes an internal network constructed by the computers N5 (1E) to N8 (1H), the port P3 (3C), and the port P4 (4C).
  • the port P3 (3C) and the port P4 (4C) are connected to the network switch 8, and are connected to the external network 7 via the network switch 8.
  • connection form of each computer 1 and port 3 in the computer group 6B is the same as the connection form of each computer 1 and port 3 in the computer group 6A.
  • connection form is not limited to this. May be different.
  • the number of computers 1 in the computer groups 6A and 6B is not limited to this, and each computer group 6A and 6B only needs to have a plurality of computers 1.
  • control devices 5A and 5B (hereinafter collectively referred to as the control device 5) are connected to the overall control device 10, and the overall control device 10 is connected to each computer group 6 via each control device 5 of each computer group 6.
  • the power source of each computer 1 is controlled.
  • Each control device 5 holds a computer state table 521, a connectable table 522, and a connection state table 523, respectively.
  • the management device 9 holds an external route state table 921, an external connection policy table 922, and an available route table 923 for each computer group 6.
  • FIGS. 9 to 15 are the same as those in the first embodiment, and thus description thereof is omitted.
  • this invention is not limited to the above-mentioned Example, Various modifications are included.
  • the above-described embodiments have been described in detail for easy understanding of the present invention, and are not necessarily limited to those having all the configurations described.
  • a part of the configuration of a certain embodiment can be replaced with the configuration of another embodiment, and the configuration of another embodiment can be added to the configuration of a certain embodiment.
  • each of the above-described configurations, functions, processing units, processing means, and the like may be realized by hardware by designing a part or all of them with, for example, an integrated circuit.
  • Each of the above-described configurations, functions, and the like may be realized by software by interpreting and executing a program that realizes each function by the processor.
  • Information such as programs, tables, and files for realizing each function can be stored in a recording device such as a memory, a hard disk, an SSD (Solid State Drive), or a recording medium such as an IC card, an SD card, or a DVD.
  • control lines and information lines indicate what is considered necessary for the explanation, and not all the control lines and information lines on the product are necessarily shown. Actually, it may be considered that almost all the components are connected to each other.

Landscapes

  • Engineering & Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Hardware Design (AREA)
  • Computing Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)

Abstract

Provided is a method for controlling the state of power supply to a computer in a management apparatus for managing a plurality of computers that constitute an internal network connected to an external network. A computer to which power is supplied and another computer to which power is supplied are connected to each other so as to be communicable with each other, while a computer to which no power is supplied and another computer connected to the computer are connected to each other so as to be incommunicable with each other. The management apparatus holds communicable path information for managing communicable paths and available path information for managing available paths. The method is characterized by the management apparatus determining whether a communicable path from each computer to which power is supplied to the external network meets a predetermined condition, referring to the available path information, identifying a path other than the currently communicable path, and instructing power supply to a computer to which no power is supplied on the identified path.

Description

計算機の制御方法、管理装置、及び計算機システムComputer control method, management apparatus, and computer system
　外部ネットワークに接続される内部ネットワークを構築する複数の計算機の制御方法に関する。 This relates to a method for controlling a plurality of computers that construct an internal network connected to an external network.
　本技術分野の背景技術として、特開２０１０－１９１８１４号公報（特許文献１）がある。この公報には、「スイッチ管理部は、起動する計算機が接続された第１のポートを判定し、ＰＣＩスイッチに通知し、第１のポートに接続された計算機の起動を電源制御部に指令」する技術が記載されている（要約参照）。 As a background art in this technical field, there is JP 2010-191814 A (Patent Document 1). This publication states that “the switch management unit determines the first port to which the computer to be activated is connected, notifies the PCI switch, and instructs the power supply control unit to activate the computer connected to the first port”. Techniques are described (see summary).
特開２０１０－１９１８１４号公報JP 2010-191814 A
　計算機システム内に、通信部と他の通信部との間を接続する経路があり、当該経路は中間点として計算機を経由して通信部と他の通信部とを接続する。この経路においては、計算機に電源が供給されていれば通信部と他の通信部とが通信可能であり、計算機の電源が遮断されていれば通信部と他の通信部とが通信不能である。 In the computer system, there is a path connecting between the communication unit and other communication units, and the route connects the communication unit and other communication units via the computer as an intermediate point. In this path, the communication unit and other communication units can communicate if power is supplied to the computer, and the communication unit and other communication units cannot communicate if the computer is powered off. .
　通信部と他の通信部との間とは、例えば、複数の計算機の間であってもよいし、計算機とネットワークスイッチのポートとの間であってもよいし、ポートと他のポートとの間であってもよい。 Between the communication unit and another communication unit may be, for example, between a plurality of computers, between a computer and a port of a network switch, or between a port and another port. It may be between.
　特許文献１では、上記した計算機システムの構成を想定しておらず、通信部と他の通信部とが通信不能である場合、通信部と他の通信部との間の経路上の計算機に電源を供給し、当該経路を通信可能な状態に制御する点については開示されていない。このため、全ての計算機に電源を供給しておく必要があり、消費電力を低減させることはできない。 In Patent Literature 1, when the configuration of the above-described computer system is not assumed and the communication unit and other communication units cannot communicate with each other, the computer on the path between the communication unit and the other communication units is powered on. Is not disclosed, and the route is controlled to be communicable. For this reason, it is necessary to supply power to all the computers, and power consumption cannot be reduced.
　そこで、本発明は、通信部と他の通信部との間の経路上の計算機の電源状態を制御することによって、通信部と他の通信部との間の通信可否状態を制御し、消費電力を低減させる計算機の電力状態の制御方法を提供することを目的とする。 Therefore, the present invention controls the power availability state of the computer on the path between the communication unit and the other communication unit, thereby controlling the communication availability state between the communication unit and the other communication unit, and the power consumption An object of the present invention is to provide a method for controlling the power state of a computer that reduces the power consumption.
　上記課題を解決するために、本発明は、外部ネットワークに接続される内部ネットワークを構築する複数の計算機を管理する管理装置における前記計算機の制御方法であって、電源が供給されている計算機同士の接続は通信可能であり、電源が供給されていない計算機と当該計算機に接続された他の計算機との間の接続は通信不能であり、前記管理装置は、前記通信可能な接続のみを経由し、前記外部ネットワークに至る通信可能な経路を管理する通信可能経路情報と、前記通信可能か前記通信不能かにかかわらずに前記計算機間の接続を経由し、前記外部ネットワークに至る利用可能な経路を管理する利用可能経路情報と、を保持し、前記方法は、前記管理装置が、前記通信可能経路情報を参照し、前記電源が供給されている各計算機から前記外部ネットワークに至る通信可能な経路が所定の条件を満たすか否かを判定し、前記通信可能な経路が所定の条件を満たさないと判定された場合、前記管理装置が、前記利用可能経路情報を参照し、前記所定の条件を満たさない計算機から前記外部ネットワークに至る利用可能な経路から現在通信可能な経路以外の経路を特定し、前記管理装置が、前記特定した経路上の電源が供給されてない計算機への電源の供給を指示することを特徴とする制御方法。 In order to solve the above-described problems, the present invention provides a computer control method in a management device that manages a plurality of computers that construct an internal network connected to an external network. The connection is communicable, the connection between the computer to which power is not supplied and the other computer connected to the computer is not communicable, and the management device passes only through the communicable connection, Communicable route information for managing a communicable route to the external network and a usable route to the external network via the connection between the computers regardless of whether the communication is possible or not Information on available routes to be stored, and in the method, the management device refers to the available route information and determines whether each computer is supplied with the power. It is determined whether or not a communicable route to the external network satisfies a predetermined condition, and when it is determined that the communicable route does not satisfy a predetermined condition, the management device can use the usable route information. And a route other than the currently communicable route is identified from the available routes from the computer that does not satisfy the predetermined condition to the external network, and the management device is supplied with power on the identified route. A control method characterized by instructing the supply of power to a computer that is not connected.
　本発明によれば、通信部と他の通信部との間の経路上の計算機の電源状態を制御することによって、通信部と他の通信部との間の通信可否状態を制御し、消費電力を低減させる計算機の電力状態の制御方法を提供できる。上記した以外の課題、構成及び効果は、以下の実施形態の説明により明らかにされる。 According to the present invention, by controlling the power state of the computer on the path between the communication unit and the other communication unit, the communication availability state between the communication unit and the other communication unit is controlled, and the power consumption Can be provided. Problems, configurations, and effects other than those described above will be clarified by the following description of embodiments.
実施例１の計算機システムの説明図である。1 is an explanatory diagram of a computer system according to Embodiment 1. FIG. 実施例１の計算機状態テーブルの説明図である。3 is an explanatory diagram of a computer state table according to Embodiment 1. FIG. 実施例１の接続可能テーブルの説明図である。It is explanatory drawing of the connectable table of Example 1. FIG. 実施例１の接続状態テーブルの説明図である。It is explanatory drawing of the connection state table of Example 1. FIG. 実施例１の外部経路状態テーブルの説明図である。It is explanatory drawing of the external path | route state table of Example 1. FIG. 実施例１の外部接続ポリシーテーブルの説明図である。FIG. 10 is an explanatory diagram of an external connection policy table according to the first embodiment. 実施例１の利用可能経路テーブルの説明図である。It is explanatory drawing of the available path | route table of Example 1. FIG. 実施例１のスイッチテーブルの説明図である。It is explanatory drawing of the switch table of Example 1. FIG. 実施例１のポリシー更新処理のフローチャートである。6 is a flowchart of policy update processing according to the first embodiment. 実施例１のポリシー判定処理のフローチャートである。3 is a flowchart of policy determination processing according to the first exemplary embodiment. 実施例１の処理対象計算機ポリシー判定処理のフローチャートである。3 is a flowchart of processing target computer policy determination processing according to the first embodiment. 実施例１の起動計算機選択処理のフローチャートである。3 is a flowchart of a startup computer selection process according to the first embodiment. 実施例１の故障検出処理のフローチャートである。3 is a flowchart of failure detection processing according to the first embodiment. 実施例１の計算機起動処理のフローチャートである。3 is a flowchart of computer activation processing according to the first embodiment. 実施例１の終了時対応処理のフローチャートである。4 is a flowchart of end-time response processing according to the first exemplary embodiment. 実施例２の計算機システムの説明図である。It is explanatory drawing of the computer system of Example 2. FIG.
　以下、図面を参照しつつ、本発明を実施するための形態を説明する。説明の明確化のため、以下の記載及び図面は、適宜、省略及び簡略化がなされている。また、各図面において、同一要素には同一の符号が付されており、説明の明確化のため、必要に応じて重複説明は省略されている。 Hereinafter, embodiments for carrying out the present invention will be described with reference to the drawings. For clarity of explanation, the following description and drawings are omitted and simplified as appropriate. Moreover, in each drawing, the same code | symbol is attached | subjected to the same element and the duplication description is abbreviate | omitted as needed for clarification of description.
　以下、実施例１を図１～図１５を用いて説明する。 Hereinafter, Example 1 will be described with reference to FIGS.
　図１は、実施例１の計算機システムの説明図である。 FIG. 1 is an explanatory diagram of the computer system according to the first embodiment.
　本実施例の計算機システムは、複数の計算機Ｎ１（１Ａ）～計算機Ｎ４（１Ｄ）、制御装置５、複数のポートＰ１（３Ａ）～ポートＰ２（３Ｂ）、ネットワークスイッチ８、及び管理装置９を備える。なお、計算機Ｎ１（１Ａ）～計算機Ｎ４（１Ｄ）を総称する場合、計算機１と記載し、ポートＰ１（３Ａ）～ポートＰ２（３Ｂ）を総称する場合、ポート３と記載する。なお、計算機１の数及びポート３の数、並びに計算機１間の接続形態は図１に示す数に限定されない。 The computer system according to this embodiment includes a plurality of computers N1 (1A) to a computer N4 (1D), a control device 5, a plurality of ports P1 (3A) to a port P2 (3B), a network switch 8, and a management device 9. . The computer N1 (1A) to the computer N4 (1D) are collectively referred to as the computer 1, and the port P1 (3A) to the port P2 (3B) are collectively referred to as the port 3. The number of computers 1 and the number of ports 3 and the connection form between the computers 1 are not limited to the numbers shown in FIG.
　計算機Ｎ１（１Ａ）はポートＰ１（３Ａ）を介してネットワークスイッチ８に接続され、計算機Ｎ２（１Ｂ）はポートＰ２（３Ｂ）を介してネットワークスイッチ８に接続される。なお、ネットワークスイッチ８は、外部のネットワーク７に接続される。また、計算機Ｎ１と計算機Ｎ２（１Ｂ）とが接続され、計算機Ｎ１（１Ａ）と計算機Ｎ３（１Ｃ）とが接続され、計算機Ｎ２（１Ｂ）と計算機Ｎ４（１Ｄ）とが接続され、計算機Ｎ３（１Ｃ）と計算機Ｎ４（１Ｄ）とが接続される。 The computer N1 (1A) is connected to the network switch 8 via the port P1 (3A), and the computer N2 (1B) is connected to the network switch 8 via the port P2 (3B). The network switch 8 is connected to an external network 7. Further, the computer N1 and the computer N2 (1B) are connected, the computer N1 (1A) and the computer N3 (1C) are connected, the computer N2 (1B) and the computer N4 (1D) are connected, and the computer N3 ( 1C) and the computer N4 (1D) are connected.
　計算機１は、例えば、Ｗｅｂコンテンツの配信処理、ストリーミング配信処理、又はデータのキャッシュ処理等の各種処理を実行する。また、計算機１は、他の計算機１又はポート３にデータを中継する中継装置としても機能するので、計算機１及びポート３によってネットワークが構築され、当該ネットワークを内部ネットワークという。この内部ネットワークは、ネットワークスイッチ８を介してネットワーク７に接続される。ネットワーク７は、内部ネットワークに対して外部ネットワークという。また、ポート３は、内部ネットワークをネットワークスイッチ８に接続する図示しないネットワークインタフェースに設定される。例えば、計算機グループ６が一つの筐体に実装される場合には、ネットワークインタフェースは当該筐体に実装される。 The computer 1 executes various processes such as a Web content distribution process, a streaming distribution process, or a data cache process. Since the computer 1 also functions as a relay device that relays data to other computers 1 or the port 3, a network is constructed by the computer 1 and the port 3, and the network is referred to as an internal network. This internal network is connected to the network 7 via the network switch 8. The network 7 is called an external network with respect to the internal network. Port 3 is set to a network interface (not shown) that connects the internal network to the network switch 8. For example, when the computer group 6 is mounted on one housing, the network interface is mounted on the housing.
　計算機Ｎ１（１Ａ）は、制御部１１及び記憶部１２を有する。制御部１１は例えばプロセッサ等であり、記憶部１２は例えばメモリ等である。記憶部１２には計算機１が実行する各種処理に対応するプログラムが格納されており、制御部１１が記憶部１２に格納されたプログラムを実行することによって、各種処理を実行する。なお、他の計算機Ｎ２（１Ｂ）～計算機Ｎ４（１Ｄ）は、計算機Ｎ１（１Ａ）と同じ構成であるので、説明を省略する。 The computer N1 (1A) includes a control unit 11 and a storage unit 12. The control unit 11 is, for example, a processor, and the storage unit 12 is, for example, a memory. The storage unit 12 stores programs corresponding to various processes executed by the computer 1, and the control unit 11 executes the various processes by executing the programs stored in the storage unit 12. Since the other computers N2 (1B) to N4 (1D) have the same configuration as the computer N1 (1A), the description thereof is omitted.
　制御装置５は、計算機１に接続される。また、制御装置５は、ネットワークスイッチ８を介して管理装置９に接続される。制御装置５は、計算機１の電源状態を制御し、計算機１における障害の有無及び電源状態等を管理する。なお、制御装置５が電源状態を制御可能な計算機１を計算機グループ６という。制御装置５は図示しない集合電源供給部から各計算機１に電源を供給してもよいし、各計算機１が電源供給部を有しており、各計算機１の電源供給部が各計算機１に電源を供給してもよい。制御装置５が集合電源供給部を有していてもよいし、他の装置が集合電源供給部を有してもよいが、集合電源供給部は各計算機１に電源を供給可能に接続される必要がある。また、各計算機１が電源供給部を有する場合、各計算機１に電源が供給されない状態とは、少なくとも制御装置５と各計算機１とが通信可能な状態であり、完全に計算機１の電源が供給されていない状態ではない。 The control device 5 is connected to the computer 1. The control device 5 is connected to the management device 9 via the network switch 8. The control device 5 controls the power state of the computer 1 and manages the presence / absence of a failure in the computer 1 and the power state. The computer 1 that can control the power state by the control device 5 is referred to as a computer group 6. The control device 5 may supply power to each computer 1 from a collective power supply unit (not shown). Each computer 1 has a power supply unit, and the power supply unit of each computer 1 supplies power to each computer 1. May be supplied. The control device 5 may have a collective power supply unit, or another device may have a collective power supply unit, but the collective power supply unit is connected so that power can be supplied to each computer 1. There is a need. When each computer 1 has a power supply unit, the state in which no power is supplied to each computer 1 is a state in which at least the control device 5 and each computer 1 can communicate with each other, and the computer 1 is completely supplied with power. Not in a state that is not.
　制御装置５は、制御部５１及び記憶部５２を有する。制御部５１は例えばプロセッサ等であり、記憶部５２は例えばメモリ等である。記憶部５２には、制御部５１が実行する電源制御処理及び電源状態管理処理に対応するプログラム、並びに計算機状態テーブル５２１、接続可能テーブル５２２及び接続状態テーブル５２３が格納される。制御部５１が電源制御処理及び電源状態管理処理に対応するプログラムを実行することによって、電源制御処理及び電源状態管理処理を実行する。 The control device 5 includes a control unit 51 and a storage unit 52. The control unit 51 is, for example, a processor, and the storage unit 52 is, for example, a memory. The storage unit 52 stores a program corresponding to the power control process and the power state management process executed by the control unit 51, as well as a computer state table 521, a connectable table 522, and a connection state table 523. The control unit 51 executes the power control process and the power state management process by executing a program corresponding to the power control process and the power state management process.
　計算機状態テーブル５２１は、計算機１の電源状態及び障害の有無を管理するためのテーブルであり、図２で詳細を説明する。接続可能テーブル５２２は、計算機１及びポート３の接続関係を管理するためのテーブルであり、図３で詳細を説明する。接続状態テーブル５２３は、計算機１及びポート３の現在通信可能な接続先を管理するためのテーブルであり、図４で詳細を説明する。 The computer state table 521 is a table for managing the power state of the computer 1 and the presence or absence of a failure, and details will be described with reference to FIG. The connectable table 522 is a table for managing the connection relationship between the computer 1 and the port 3, and will be described in detail with reference to FIG. The connection state table 523 is a table for managing connection destinations that are currently communicable between the computer 1 and the port 3, and will be described in detail with reference to FIG.
　ネットワークスイッチ８は、ネットワーク７から受信したデータの宛先に対応するポート３を特定し、受信したデータを特定したポート３から出力する。ネットワークスイッチ８は、制御部８１及び記憶部８２を有する。制御部８１は例えばプロセッサ等であり、記憶部８２はメモリ等である。記憶部８２にはスイッチテーブル８２１が格納され、制御部８１は、スイッチテーブル８２１を参照し、受信したデータの宛先に対応するポート３を特定する。スイッチテーブル８２１は、図８で詳細に説明する。 The network switch 8 specifies the port 3 corresponding to the destination of the data received from the network 7, and outputs the received data from the specified port 3. The network switch 8 includes a control unit 81 and a storage unit 82. The control unit 81 is, for example, a processor, and the storage unit 82 is a memory or the like. A switch table 821 is stored in the storage unit 82, and the control unit 81 refers to the switch table 821 and identifies the port 3 corresponding to the destination of the received data. The switch table 821 will be described in detail with reference to FIG.
　管理装置９は、各計算機に対して要求するポリシーを設定するインタフェースをユーザに提供し、ポリシーを満たすために電源の供給を開始する計算機を特定する。管理装置９は、制御部９１及び記憶部９２を有する。制御部９１は例えばプロセッサ等であり、記憶部９２は例えばメモリ等である、記憶部９２には、管理装置９が実行する各種処理を実行するプログラム、並びに、外部経路状態テーブル９２１、外部接続ポリシーテーブル９２２、及び利用可能経路テーブル９２３が格納される。制御部９１が各種プログラムを実行することによって、各種処理を実行する。また、管理装置９は、ユーザからの入力を受け付ける図示しない入力装置（例えば、キーボード又はマウス等）、及び図示しない出力装置を有する。出力デバイスは、例えばディスプレイ等の表示装置である。 The management device 9 provides the user with an interface for setting a policy required for each computer, and identifies a computer that starts supplying power to satisfy the policy. The management device 9 includes a control unit 91 and a storage unit 92. The control unit 91 is, for example, a processor, and the storage unit 92 is, for example, a memory. The storage unit 92 includes a program that executes various processes executed by the management apparatus 9, an external path state table 921, an external connection policy, and the like. A table 922 and an available route table 923 are stored. Various processes are executed by the control unit 91 executing various programs. In addition, the management device 9 includes an input device (not shown) (for example, a keyboard or a mouse) that receives input from the user, and an output device (not shown). The output device is a display device such as a display.
　外部経路状態テーブル９２１は、各計算機１から各ポート３までの通信可能な経路上の計算機１及びポート３、並びに各通信可能な経路の通信帯域を管理するものであり、図５で詳細に説明する。外部接続ポリシーテーブル９２２は、各計算機の経路に設定されたポリシーを管理するためのテーブルであり、図６で詳細に説明する。利用可能経路テーブル９２３は、各計算機１から各ポート３までの利用可能な経路上の計算機１及びポート３、並びに各利用可能な経路の通信帯域を管理するものであり、図７で詳細に説明する。なお、利用可能な経路は、通信可能な経路と、通信不能な経路であるがいずれかの計算機１に電源が供給されれば通信可能となる経路とを含み、内部ネットワークに設定可能な全ての経路である。 The external path status table 921 manages the computer 1 and the port 3 on the communicable path from each computer 1 to each port 3, and the communication bandwidth of each communicable path, and will be described in detail with reference to FIG. To do. The external connection policy table 922 is a table for managing a policy set for the route of each computer, and will be described in detail with reference to FIG. The available route table 923 manages the computers 1 and 3 on the available route from each computer 1 to each port 3 and the communication bandwidth of each available route, and will be described in detail with reference to FIG. To do. The available routes include all routes that can be set in the internal network, including routes that can be communicated and routes that cannot be communicated but can be communicated if any computer 1 is supplied with power. It is a route.
　なお、管理装置９は制御装置５の機能を有していてもよい。このため、特許請求の範囲では、管理装置９及び制御装置５の機能を有する装置を管理装置として記載している。また、例えば、計算機グループ６の制御装置５、計算機１、及びポート３は一つの筐体に実装されていてもよい。 The management device 9 may have the function of the control device 5. For this reason, in the claims, a device having the functions of the management device 9 and the control device 5 is described as a management device. Further, for example, the control device 5, the computer 1, and the port 3 of the computer group 6 may be mounted in one housing.
　図２は、実施例１の計算機状態テーブル５２１の説明図である。 FIG. 2 is an explanatory diagram of the computer state table 521 according to the first embodiment.
　計算機状態テーブル５２１は、計算機５２１１、電源状態５２１２、及び利用可能性５２１３を含む。計算機５２１１には計算機１の識別情報が登録され、電源状態５２１２には、各計算機１に電源が供給されているか遮断されているかを示す情報が登録される。電源状態５２１２に「ＯＮ」が登録されていれば、計算機１に電源が供給されていることを示し、電源状態５２１２に「ＯＦＦ」が登録されていれば、計算機１への電源の供給が遮断されていることを示す。本実施例では、計算機Ｎ１（１Ａ）、計算機Ｎ２（１Ｂ）、及び計算機Ｎ４（１Ｄ）に電源が供給され、計算機Ｎ３（１Ｃ）への電源の供給が遮断されていることを例に説明する。 The computer state table 521 includes a computer 5211, a power state 5212, and an availability 5213. Identification information of the computer 1 is registered in the computer 5211, and information indicating whether the power is supplied to each computer 1 or shut off is registered in the power state 5212. If "ON" is registered in the power state 5212, it indicates that power is being supplied to the computer 1, and if "OFF" is registered in the power state 5212, the supply of power to the computer 1 is cut off. Indicates that In the present embodiment, an example will be described in which power is supplied to the computer N1 (1A), the computer N2 (1B), and the computer N4 (1D), and the power supply to the computer N3 (1C) is interrupted. .
　利用可能性５２１３には、各計算機１が利用可能か利用不能かを示す情報が登録される。本実施例では、全ての計算機１に対応するレコードの利用可能性５２１３に「利用可能」が登録されるが、故障等が発生した計算機１に対応するレコードの利用可能性５２１３に「利用不能」が登録される。 In the availability 5213, information indicating whether each computer 1 is available or unavailable is registered. In this embodiment, “available” is registered in the record availability 5213 corresponding to all the computers 1, but “unusable” is recorded in the record availability 5213 corresponding to the computer 1 in which a failure or the like has occurred. Is registered.
　なお、制御装置５は、計算機１から電源状態及び故障状態を周期的に取得し、計算機状態テーブル５２１を更新する。計算機１が電源状態の変更時にその旨を制御装置５に通知してもよいし、計算機１が自身に故障を検出した場合にその旨を制御装置５に通知してもよい。また、制御装置５が、電源状態及び故障状態の取得要求を周期的に計算機１に送信し、計算機１は取得要求を受信した場合に、自身の電源状態及び故障状態を制御装置５に送信してもよい。 The control device 5 periodically acquires the power supply state and the failure state from the computer 1 and updates the computer state table 521. The computer 1 may notify the control device 5 when the power supply state is changed, or may notify the control device 5 when the computer 1 detects a failure. In addition, the control device 5 periodically transmits an acquisition request for the power supply state and the failure state to the computer 1, and when the computer 1 receives the acquisition request, the control device 5 transmits its own power supply state and failure state to the control device 5. May be.
　図３は、実施例１の接続可能テーブル５２２の説明図である。 FIG. 3 is an explanatory diagram of the connectable table 522 of the first embodiment.
　接続可能テーブル５２２は、ポイント５２２１、及び接続先カラム群５２２２を含む。ポイント５２２１には、内部ネットワークを構成する全ての計算機１又はポート３の識別情報が登録される。接続先カラム群５２２２には、計算機１又はポート３に物理的に接続される計算機１の識別情報又はポート３の識別情報、及び各接続先までの経路の物理的な帯域値が登録される。 The connectable table 522 includes a point 5221 and a connection destination column group 5222. In the point 5221, identification information of all the computers 1 or ports 3 constituting the internal network is registered. In the connection destination column group 5222, the identification information of the computer 1 or the identification information of the port 3 physically connected to the computer 1 or the port 3 and the physical bandwidth value of the route to each connection destination are registered.
　例えば、ポイント５２２１に計算機Ｎ１（１Ａ）の識別情報「Ｎ１」が登録されたレコードの接続先カラム群５２２２の接続先Ａ５２２２Ａには、ポートＰ１（３Ａ）の識別情報（Ｐ１）及び計算機Ｎ１（１Ａ）からポートＰ１（３Ａ）までの経路の帯域値「１０．０Ｇｂｐｓ」が登録される。また、当該レコードの接続先Ｂ５２２２Ｂには、計算機Ｎ２（１Ｂ）の識別情報（Ｎ２）及び計算機Ｎ１（１Ａ）から計算機Ｎ２（１Ｂ）までの経路の帯域値「１０．０Ｇｂｐｓ」が登録される。当該レコードの接続先Ｃ５２２２Ｃには計算機Ｎ３の識別情報「Ｎ３」及び計算機Ｎ１（１Ａ）から計算機Ｎ３（１Ｃ）までの経路の帯域値「１０．０Ｇｂｐｓ」が登録される。 For example, the connection destination A 5222A of the connection destination column group 5222 of the record in which the identification information “N1” of the computer N1 (1A) is registered at the point 5221 includes the identification information (P1) of the port P1 (3A) and the computer N1 (1A). ) To the port P1 (3A), the bandwidth value “10.0 Gbps” is registered. Also, in the connection destination B5222B of the record, the identification information (N2) of the computer N2 (1B) and the bandwidth value “10.0 Gbps” of the route from the computer N1 (1A) to the computer N2 (1B) are registered. In the connection destination C5222C of the record, the identification information “N3” of the computer N3 and the bandwidth value “10.0 Gbps” of the route from the computer N1 (1A) to the computer N3 (1C) are registered.
　接続可能テーブル５２２は、内部ネットワークを構成する計算機１又はポート３の接続関係に基づいて予め設定され、計算機１又はポート３の接続関係が変更された場合に更新される。 The connectable table 522 is set in advance based on the connection relationship of the computer 1 or the port 3 configuring the internal network, and is updated when the connection relationship of the computer 1 or the port 3 is changed.
　図４は、実施例１の接続状態テーブル５２３の説明図である。 FIG. 4 is an explanatory diagram of the connection state table 523 according to the first embodiment.
　接続状態テーブル５２３は、ポイント５２３１、及び接続先カラム群５２３２を含む。ポイント５２３１には、内部ネットワークを構成する計算機１又はポート３のうち、電源が供給されている計算機１又はポート３の識別情報が登録される。接続先カラム群５２３２には、計算機１又はポート３に物理的に接続される計算機１又はポート３のうち電源が供給されている計算機１又はポート３の識別情報、及び各接続先までの経路の物理的な帯域値が登録される。 The connection state table 523 includes a point 5231 and a connection destination column group 5232. In the point 5231, the identification information of the computer 1 or the port 3 to which the power is supplied among the computers 1 or the ports 3 configuring the internal network is registered. In the connection destination column group 5232, the identification information of the computer 1 or port 3 to which the power is supplied out of the computer 1 or port 3 physically connected to the computer 1 or port 3, and the route to each connection destination A physical bandwidth value is registered.
　本実施例では計算機Ｎ３（１Ｃ）への電源の供給が遮断されていないので、図４に示す接続状態テーブル５２３では、図３に示す接続可能テーブル５２２から計算機Ｎ３（１Ｃ）の識別情報が削除されている。具体的には、図４に示す接続状態テーブル５２３は、ポイント５２３１に計算機Ｎ３（１Ｃ）の識別情報（Ｎ３）が登録されたレコードを含まない。また、ポイント５２３１に計算機Ｎ１（１Ａ）の識別情報（Ｎ１）が登録されたレコードの接続先カラム群５２３２は計算機Ｎ３（１Ｃ）の識別情報を含まず、ポイント５２３１に計算機Ｎ４（１Ｄ）の識別情報（Ｎ４）が登録されたレコードの接続先カラム群５２３２は計算機Ｎ３（１Ｃ）の識別情報を含まない。 In the present embodiment, since the supply of power to the computer N3 (1C) is not interrupted, in the connection state table 523 shown in FIG. 4, the identification information of the computer N3 (1C) is deleted from the connectable table 522 shown in FIG. Has been. Specifically, the connection state table 523 illustrated in FIG. 4 does not include a record in which the identification information (N3) of the computer N3 (1C) is registered at the point 5231. Further, the connection destination column group 5232 of the record in which the identification information (N1) of the computer N1 (1A) is registered at the point 5231 does not include the identification information of the computer N3 (1C), and the identification of the computer N4 (1D) is included at the point 5231. The connection destination column group 5232 of the record in which the information (N4) is registered does not include the identification information of the computer N3 (1C).
　接続状態テーブル５２３は、制御装置５が取得した計算機１の電源状態に基づいて、接続可能テーブル５２３のレコードから電源の供給が遮断されている計算機１の識別情報を消去することによって、生成される。 The connection state table 523 is generated by deleting the identification information of the computer 1 whose power supply is cut off from the record of the connectable table 523 based on the power state of the computer 1 acquired by the control device 5. .
　図５は、実施例１の外部経路状態テーブル９２１の説明図である。 FIG. 5 is an explanatory diagram of the external route state table 921 according to the first embodiment.
　外部経路状態テーブル９２１は、計算機９２１１、経路カラム群９２１２、及び帯域カラム群９２１３を含む。計算機９２１１には、電源が供給されている計算機１の識別情報が登録される。経路カラム群９２１２は、Ｐ１への経路９２１２Ａ及びＰ２への経路９２１２Ｂを含む。Ｐ１への経路９２１２Ａには、各計算機１からポートＰ１（３Ａ）までの通信可能な経路上の計算機１及びポートＰ１（３Ａ）の識別情報が順序付きリストとして登録される。Ｐ２への経路９２１２Ｂには、各計算機１からポートＰ２（３Ｂ）までの通信可能な経路上の計算機１及びポートＰ２（３Ｂ）の識別情報が順序付きリストとして登録される。通信可能な経路とは、当該経路上の全ての計算機１に電源が供給されている経路である。 The external route state table 921 includes a computer 9211, a route column group 9212, and a band column group 9213. In the computer 9211, identification information of the computer 1 to which power is supplied is registered. The path column group 9212 includes a path 9212A to P1 and a path 9212B to P2. In the path 9212A to P1, the identification information of the computer 1 and the port P1 (3A) on the communicable path from each computer 1 to the port P1 (3A) is registered as an ordered list. In the path 9212B to P2, the identification information of the computer 1 and the port P2 (3B) on the communicable path from each computer 1 to the port P2 (3B) is registered as an ordered list. A communicable route is a route through which power is supplied to all the computers 1 on the route.
　帯域カラム群９２１３は、Ｐ１への帯域９２１３Ａ及びＰ２への帯域９２１３Ｂを含む。Ｐ１への帯域９２１３Ａには、各計算機１からポートＰ１（３Ａ）までの通信可能な経路の帯域値が登録される。Ｐ２への帯域９２１３Ｂには、各計算機１からポートＰ２（３Ｂ）までの通信可能な経路の帯域値が登録される。 The band column group 9213 includes a band 9213A to P1 and a band 9213B to P2. In the bandwidth 9213A to P1, a bandwidth value of a communicable route from each computer 1 to the port P1 (3A) is registered. In the bandwidth 9213B to P2, a bandwidth value of a communicable route from each computer 1 to the port P2 (3B) is registered.
　管理装置９は、制御装置５から取得した接続状態テーブル５２３に基づいて、管理装置９は、電源が供給されている各計算機１から各ポート３までの最短経路をダイクストラ法等の経路探索アルゴリズムを用いて、各計算機１から各ポート３までの経路を特定する。そして、管理装置９は、特定した経路上の計算機１の識別情報を経路カラム群９２１２に登録し、特定した経路の最小の帯域値を帯域カラム群９２１３に登録する。 Based on the connection state table 523 acquired from the control device 5, the management device 9 uses a route search algorithm such as the Dijkstra method to find the shortest route from each computer 1 to which power is supplied to each port 3. The route from each computer 1 to each port 3 is specified. Then, the management device 9 registers the identification information of the computer 1 on the identified route in the route column group 9212 and registers the minimum bandwidth value of the identified route in the bandwidth column group 9213.
　図６は、実施例１の外部接続ポリシーテーブル９２２の説明図である。 FIG. 6 is an explanatory diagram of the external connection policy table 922 according to the first embodiment.
　外部接続ポリシーテーブル９２２は、計算機９２２１、最大使用帯域９２２２、最小使用帯域９２２３、冗長性９２２４、及び起動ポリシー９２２５を含む。 The external connection policy table 922 includes a computer 9221, a maximum used bandwidth 9222, a minimum used bandwidth 9223, a redundancy 9224, and an activation policy 9225.
　計算機９２２１には、内部ネットワークを構成する全ての計算機１の識別情報が登録される。最大使用帯域９２２２には各計算機１に割り当てられる経路の最大の帯域値が登録される。最小使用帯域９２２３には各計算機１に割り当てられる経路の最小の帯域値が登録される。冗長性９２２４には各計算機１に割り当てられる経路の数が登録される。起動ポリシー９２２５には、各計算機１が最大使用帯域９２２２、最小使用帯域９２２３、及び冗長性９２２４に登録される条件を満たさない場合に、他の計算機１を起動して追加の経路を生成が許容されるか否かを示す情報が登録される。 In the computer 9221, identification information of all the computers 1 constituting the internal network is registered. In the maximum use bandwidth 9222, the maximum bandwidth value of the route assigned to each computer 1 is registered. In the minimum use band 9223, the minimum band value of the route assigned to each computer 1 is registered. In the redundancy 9224, the number of routes assigned to each computer 1 is registered. In the activation policy 9225, when each computer 1 does not satisfy the conditions registered in the maximum use bandwidth 9222, the minimum use bandwidth 9223, and the redundancy 9224, it is allowed to start another computer 1 and generate an additional route. Information indicating whether or not to be performed is registered.
　管理装置９がユーザの指示の入力を受け付けた場合、管理装置９が図９に示すポリシー更新処理を実行することによって、外部接続ポリシーテーブル９２２は生成される。 When the management apparatus 9 receives an input of a user instruction, the external connection policy table 922 is generated by the management apparatus 9 executing the policy update process shown in FIG.
　図７は、実施例１の利用可能経路テーブル９２３の説明図である。 FIG. 7 is an explanatory diagram of the available route table 923 according to the first embodiment.
　利用可能経路テーブル９２３は、計算機９２３１、経路カラム群９２３２、及び帯域カラム群９２３３を含む。計算機９２３１には、内部ネットワークの全ての計算機１の識別情報が登録される。経路カラム群９２３２は、Ｐ１への経路９２３２Ａ及びＰ２への経路９２３２Ｂを含む。Ｐ１への経路９２３２Ａには、各計算機１からポートＰ１（３Ａ）までの利用可能な経路上の計算機１及びポートＰ１（３Ａ）の識別情報が順序付きリストとして登録される。Ｐ２への経路９２３２Ｂには、各計算機１からポートＰ２（３Ｂ）までの利用可能な経路上の計算機１及びポートＰ２（３Ｂ）の識別情報が順序付きリストとして登録される。利用可能な経路とは、電源が供給されているか遮断されているかにかかわらず接続された計算機１を経由する経路である。 The available route table 923 includes a computer 9231, a route column group 9232, and a bandwidth column group 9233. In the computer 9231, identification information of all the computers 1 in the internal network is registered. The path column group 9232 includes a path 9232A to P1 and a path 9232B to P2. In the route 9232A to P1, the identification information of the computer 1 and the port P1 (3A) on the available route from each computer 1 to the port P1 (3A) is registered as an ordered list. In the route 9232B to P2, the identification information of the computer 1 and the port P2 (3B) on the available route from each computer 1 to the port P2 (3B) is registered as an ordered list. An available route is a route that passes through the connected computer 1 regardless of whether power is supplied or cut off.
　帯域カラム群９２３３は、Ｐ１への帯域９２２３Ａ及びＰ２への帯域９２３３Ｂを含む。Ｐ１への帯域９２３３Ａには、各計算機１からポートＰ１（３Ａ）までの利用可能な経路の帯域値が登録される。Ｐ２への帯域９２１３Ｂには、各計算機１からポートＰ２（３Ｂ）までの利用可能な経路の帯域値が登録される。 The band column group 9233 includes a band 9223A to P1 and a band 9233B to P2. In the bandwidth 9233A to P1, a bandwidth value of an available route from each computer 1 to the port P1 (3A) is registered. In the bandwidth 9213B to P2, a bandwidth value of an available route from each computer 1 to the port P2 (3B) is registered.
　本実施例では、計算機Ｎ３（１Ｃ）への電源の供給が遮断されているため、計算機Ｎ３（１Ｃ）を経由する経路は通信可能でない。このため、図５に示す外部経路状態テーブル９２１は、計算機９２１１に計算機Ｎ３（１Ｃ）の識別情報（Ｎ３）が登録されたレコードを含まない。計算機Ｎ４（１Ｄ）からポートＰ１（３Ａ）までの利用可能な経路として計算機Ｎ３（３Ｃ）及び計算機Ｎ１（３Ａ）を経由する経路があるが、計算機Ｎ３（１Ｃ）への電源の供給が遮断されているため、当該経路は通信可能な経路でない。したがって、図５に示す外部経路状態テーブル９２１では、計算機９２１１に計算機Ｎ４（１Ｄ）の識別情報（Ｎ４）が登録されたレコードのＰ１への経路９２１２ＡにはＮＵＬＬが登録され、当該レコードのＰ１への帯域９２１３Ａには「０Ｇｂｐｓ」が登録される。 In the present embodiment, since the power supply to the computer N3 (1C) is cut off, the route via the computer N3 (1C) is not communicable. Therefore, the external route state table 921 shown in FIG. 5 does not include a record in which the identification information (N3) of the computer N3 (1C) is registered in the computer 9211. There is a route that passes through the computer N3 (3C) and the computer N1 (3A) as an available route from the computer N4 (1D) to the port P1 (3A), but the power supply to the computer N3 (1C) is cut off. Therefore, the route is not a communicable route. Therefore, in the external path state table 921 shown in FIG. 5, NULL is registered in the path 9212A to the P1 of the record in which the identification information (N4) of the computer N4 (1D) is registered in the computer 9211, and the P1 of the record is recorded. “0 Gbps” is registered in the band 9213A.
　なお、利用可能経路テーブル９２３の生成方法は、外部経路状態テーブル９２１の生成方法と同様であるので、説明を省略する。 Note that the generation method of the available route table 923 is the same as the generation method of the external route state table 921, and thus the description thereof is omitted.
　図８は、実施例１のスイッチテーブル８２１の説明図である。 FIG. 8 is an explanatory diagram of the switch table 821 of the first embodiment.
　スイッチテーブル８２１は、宛先８２１１及びポート８２１２を含む。宛先８２１１には、内部ネットワークを構成する全ての計算機１の識別情報が登録される。ポート８２１２には、各計算機１からの通信可能な経路のポート３の識別情報が登録される。 The switch table 821 includes a destination 8211 and a port 8212. In the destination 8211, identification information of all the computers 1 constituting the internal network is registered. In the port 8212, the identification information of the port 3 of the communication path from each computer 1 is registered.
　ネットワークスイッチ８の制御部８１は、外部のネットワーク７からデータを受信すると、受信したデータから当該データに含まれる宛先を取得する。そして、制御部８１は、スイッチテーブル８２１を参照し、宛先８２１１に取得した宛先が登録されたレコードのポート８２１２に登録されたポート３の識別情報を取得する。次に、制御部８１は、取得したポート３の識別情報によって識別されるポート３に受信したデータを送信する。 When the control unit 81 of the network switch 8 receives data from the external network 7, the control unit 81 acquires a destination included in the data from the received data. The control unit 81 refers to the switch table 821 and acquires the identification information of the port 3 registered in the port 8212 of the record in which the destination acquired in the destination 8211 is registered. Next, the control unit 81 transmits the received data to the port 3 identified by the acquired identification information of the port 3.
　次に、スイッチテーブル８２１の設定方法について説明する。管理装置９の制御部９１は、外部経路状態テーブル９２１を参照し、各計算機１が通信可能なポート３を特定する。例えば、図５に示す外部経路状態テーブル９２１では、計算機９２１１に計算機Ｎ１（１Ａ）の識別情報（Ｎ１）が登録されたレコードのＰ１への経路９２１２ＡにポートＰ１（３Ａ）の識別情報（Ｐ１）が登録され、Ｐ２への経路９２１２ＢにポートＰ２（３Ｂ）の識別情報（Ｐ２）が登録されているので、制御部９１は、計算機Ｎ１（１Ａ）の通信可能なポート３がポートＰ１（３Ａ）及びポートＰ２（３Ｂ）であることを認識し、計算機Ｎ１（１Ａ）の識別情報（Ｎ１）、ポートＰ１（３Ａ）の識別情報（Ｐ１）、及びポートＰ２（３Ｂ）の識別情報（Ｐ２）を取得する。 Next, a method for setting the switch table 821 will be described. The control unit 91 of the management device 9 refers to the external route state table 921 and identifies the port 3 with which each computer 1 can communicate. For example, in the external route state table 921 shown in FIG. 5, the identification information (P1) of the port P1 (3A) is connected to the route 9212A to the P1 of the record in which the identification information (N1) of the computer N1 (1A) is registered in the computer 9211. Is registered, and the identification information (P2) of the port P2 (3B) is registered in the path 9212B to the P2, the control unit 91 determines that the communicable port 3 of the computer N1 (1A) is the port P1 (3A). And the identification information (P1) of the computer N1 (1A), the identification information (P1) of the port P1 (3A), and the identification information (P2) of the port P2 (3B). get.
　次に、制御部９１は、取得した計算機１の識別情報及びポート３の識別情報を含むスイッチテーブル更新指示をネットワークスイッチ８に送信する。ネットワークスイッチ８の制御部８１は、受信したスイッチ更新指示に基づいてスイッチテーブル８２１を設定する。例えば、スイッチテーブル更新指示が、Ｎ１、Ｐ１及びＰ２を含む場合、ネットワークスイッチ８の制御部８１は、スイッチテーブル８２１の宛先８２１１にＮ１が登録されたレコードがあれば、当該レコードのポート８２１２にＰ１及びＰ２を登録する。ネットワークスイッチ８の制御部８１は、スイッチテーブル８２１の宛先８２１１にＮ１が登録されたレコードがなければ、新たなレコードを追加し、追加したレコードのポート８２１２にＰ１及びＰ２を登録する。なお、スイッチテーブル８２１が設定されるタイミングとしては、外部経路状態テーブル９２１が更新された場合、及び新たな経路が設定された場合等がある。 Next, the control unit 91 transmits a switch table update instruction including the acquired identification information of the computer 1 and identification information of the port 3 to the network switch 8. The control unit 81 of the network switch 8 sets the switch table 821 based on the received switch update instruction. For example, when the switch table update instruction includes N1, P1, and P2, if there is a record in which N1 is registered in the destination 8211 of the switch table 821, the control unit 81 of the network switch 8 sets P1 to the port 8212 of the record. And P2. If there is no record in which N1 is registered in the destination 8211 of the switch table 821, the control unit 81 of the network switch 8 adds a new record and registers P1 and P2 in the port 8212 of the added record. The timing when the switch table 821 is set includes when the external route state table 921 is updated and when a new route is set.
　図９は、実施例１のポリシー更新処理のフローチャートである。ポリシー更新処理は、管理装置９がユーザからのポリシー更新要求に基づいて外部接続ポリシーテーブル９２２を更新する処理である。 FIG. 9 is a flowchart of the policy update process according to the first embodiment. The policy update process is a process in which the management apparatus 9 updates the external connection policy table 922 based on a policy update request from the user.
　まず、管理装置９は、ユーザからポリシー更新要求の入力を受け付ける（Ｓ１０１）。ユーザは、管理装置９の図示しない入力装置を介してポリシー更新要求を入力する。ポリシー更新要求は、更新の対象となる計算機１の識別情報、及び更新後のポリシーを含む。更新後のポリシーは、外部接続ポリシーテーブル９２２の最大使用帯域９２２２、最小使用帯域９２２３、冗長性９２２４及び起動ポリシー９２２５のカラムのうち、更新するカラムに登録される情報を含む。 First, the management device 9 receives an input of a policy update request from the user (S101). The user inputs a policy update request via an input device (not shown) of the management device 9. The policy update request includes the identification information of the computer 1 to be updated and the updated policy. The updated policy includes information registered in the column to be updated among the columns of the maximum used bandwidth 9222, the minimum used bandwidth 9223, the redundancy 9224, and the activation policy 9225 of the external connection policy table 922.
　次に、管理装置９は、ポリシー更新要求に基づいて、外部接続ポリシーテーブル９２２を更新する（Ｓ１０２）。具体的には、管理装置９は、外部接続ポリシーテーブル９２２の計算機９２２１に登録された計算機１の識別情報がポリシー更新要求に含まれる計算機１の識別情報と一致するレコードを特定する。そして、管理装置９は、特定したレコードの最大使用帯域９２２２、最小使用帯域９２２３、冗長性９２２４及び起動ポリシー９２２５のうち更新するカラムに更新後の情報を登録する。 Next, the management device 9 updates the external connection policy table 922 based on the policy update request (S102). Specifically, the management device 9 specifies a record in which the identification information of the computer 1 registered in the computer 9221 of the external connection policy table 922 matches the identification information of the computer 1 included in the policy update request. Then, the management apparatus 9 registers the updated information in the columns to be updated among the maximum used bandwidth 9222, the minimum used bandwidth 9223, the redundancy 9224, and the activation policy 9225 of the specified record.
　次に、管理装置９は、ポリシー判定処理を実行する（Ｓ１０３）。ポリシー処理は、内部ネットワークの通信可能な経路が外部接続ポリシーテーブル９２２のポリシーを満たすか否かを判定する処理であり、図１０で詳細を説明する。 Next, the management device 9 executes policy determination processing (S103). The policy process is a process for determining whether or not a communicable route of the internal network satisfies the policy of the external connection policy table 922, and details will be described with reference to FIG.
　次に、管理装置９は、ポリシー判定処理の結果に基づいて内部ネットワークの通信可能な経路がポリシーを満たすか否かを判定する（Ｓ１０４）。Ｓ１０４の処理で内部ネットワークの通信可能な経路がポリシーを満たすと判定された場合、管理装置９は、外部接続ポリシーテーブル９２２の更新が完了したことをユーザに報知し（Ｓ１０５）、処理を終了する。ユーザへの報知の例としては、管理装置９は、外部接続ポリシーテーブル９２２の更新が完了した旨を図示しない表示装置等に表示してもよい。 Next, the management device 9 determines whether or not the communicable route of the internal network satisfies the policy based on the result of the policy determination process (S104). When it is determined in the process of S104 that the communicable route of the internal network satisfies the policy, the management apparatus 9 notifies the user that the update of the external connection policy table 922 is completed (S105), and ends the process. . As an example of notification to the user, the management device 9 may display that the update of the external connection policy table 922 has been completed on a display device or the like (not shown).
　一方、Ｓ１０４の処理で内部ネットワークの通信可能な経路がポリシーを満たしていないと判定された場合、内部ネットワークの通信可能な経路が更新後の外部接続ポリシーテーブル９２２のポリシーを満たすことができないので、管理装置９は、Ｓ１０２の処理で更新される前の外部接続ポリシーテーブル９２２に戻し、Ｓ１０５の処理に進む。Ｓ１０５の処理では、管理装置９は、内部ネットワークの通信可能な経路がポリシーを満たさなくなることが原因で外部接続ポリシーテーブル９２２が更新できなかった旨をユーザに報知する。これによって、ユーザは、内部ネットワークの通信可能な経路がポリシーを満たさない旨を把握できる。 On the other hand, if it is determined in S104 that the internal network communicable route does not satisfy the policy, the internal network communicable route cannot satisfy the updated external connection policy table 922 policy. The management apparatus 9 returns to the external connection policy table 922 before being updated in the process of S102, and proceeds to the process of S105. In the process of S105, the management apparatus 9 notifies the user that the external connection policy table 922 could not be updated because the communicable path of the internal network does not satisfy the policy. Thus, the user can grasp that the communicable route of the internal network does not satisfy the policy.
　図１０は、実施例１のポリシー判定処理のフローチャートである。 FIG. 10 is a flowchart of the policy determination process according to the first embodiment.
　まず、管理装置９は、制御装置５の記憶部５２から計算機状態テーブル５２１及び接続状態テーブル５２３を取得し、取得した計算機状態テーブル５２１及び接続状態テーブル５２３に基づいて外部経路状態テーブル９２１を生成する（Ｓ２０１）。具体的には、管理装置９は、計算機状態テーブル５２１の電源状態５２１２に「ＯＮ」が登録され、かつ利用可能性５２１３に「利用可能」が登録されたレコードの計算機５２１１に登録された計算機１の識別情報を取得する。そして、管理装置９は、外部経路状態テーブル９２１に、取得した計算機１の識別情報の数分のレコードを追加し、追加したレコードの計算機９２１１に取得した計算機１の識別情報を登録する。次に、管理装置９は、取得した接続状態テーブル５２３を参照し各計算機１の接続関係を特定することによって、各計算機１の各ポート３までの通信可能な経路を特定し、特定した通信可能な経路上の計算機１の識別情報及びポート３の識別情報を外部経路状態テーブル９２１の経路カラム群９２１２に登録する。また、管理装置９は、接続状態テーブル５２３に登録された接続先カラム群５２３２に登録された帯域値を外部経路状態テーブル９２１の帯域カラム群９２３３に登録する。 First, the management device 9 acquires the computer state table 521 and the connection state table 523 from the storage unit 52 of the control device 5, and generates the external path state table 921 based on the acquired computer state table 521 and the connection state table 523. (S201). Specifically, the management apparatus 9 includes the computer 1 registered in the computer 5211 of the record in which “ON” is registered in the power state 5212 of the computer state table 521 and “available” is registered in the availability 5213. Get identification information for. Then, the management device 9 adds records as many as the acquired identification information of the computer 1 to the external path state table 921 and registers the acquired identification information of the computer 1 in the computer 9211 of the added record. Next, the management device 9 specifies the communication path to each port 3 of each computer 1 by specifying the connection relationship of each computer 1 with reference to the acquired connection state table 523, and the specified communication is possible The identification information of the computer 1 on the simple route and the identification information of the port 3 are registered in the route column group 9212 of the external route state table 921. In addition, the management device 9 registers the bandwidth value registered in the connection destination column group 5232 registered in the connection state table 523 in the bandwidth column group 9233 of the external path state table 921.
　次に、管理装置９は、Ｓ２０１の処理で生成した外部経路状態テーブル９２１の計算機９２１１に登録された計算機１の識別情報から処理対象の計算機１の識別情報を選択し、Ｓ２０３の処理に進む（Ｓ２０２）。外部経路状態テーブル９２１の計算機９２１１には、電源が供給され、かつ異常が発生していない計算機１の識別情報が登録されるので、Ｓ２０２の処理では、電源が供給され、異常が発生していない計算機１の識別情報が処理対象として選択されることになる。なお、処理対象の計算機１の識別情報によって識別される計算機１を処理対象の計算機１と記載する。 Next, the management apparatus 9 selects the identification information of the computer 1 to be processed from the identification information of the computer 1 registered in the computer 9211 of the external path state table 921 generated in the process of S201, and proceeds to the process of S203 ( S202). Since the computer 9211 in the external path state table 921 is supplied with power and the identification information of the computer 1 in which no abnormality has occurred is registered, in the process of S202, power is supplied and no abnormality has occurred. The identification information of the computer 1 is selected as a processing target. The computer 1 identified by the identification information of the processing target computer 1 is referred to as a processing target computer 1.
　次に、管理装置９は処理対象計算機ポリシー判定処理を実行する（Ｓ２０３）。処理対象計算機ポリシー判定処理は、外部接続ポリシーテーブル９２２を参照し、処理対象の計算機１からの通信可能な経路が、最大使用帯域、最小使用帯域、及び冗長性等のポリシーを満たすか否かを判定する処理であり、図１１で詳細に説明する。 Next, the management device 9 executes processing target computer policy determination processing (S203). The processing target computer policy determination processing refers to the external connection policy table 922, and determines whether or not a communicable path from the processing target computer 1 satisfies policies such as maximum used bandwidth, minimum used bandwidth, and redundancy. This is a determination process and will be described in detail with reference to FIG.
　次に、管理装置９は、Ｓ２０３の処理の判定結果が、処理対象の計算機１がポリシーを満たすか否かを判定する（Ｓ２０４）。 Next, the management device 9 determines whether or not the determination result of the processing in S203 indicates that the processing target computer 1 satisfies the policy (S204).
　Ｓ２０４の処理で処理対象の計算機１がポリシーを満たすと判定された場合、管理装置９は、Ｓ２０１の処理で生成した外部経路状態テーブル９２１の計算機９２１１に登録された全ての計算機１の識別情報によって識別される計算機１がポリシーを満たすと判定されるまで、Ｓ２０２～Ｓ２０４の処理を繰り返す。そして、Ｓ２０１の処理で生成した外部経路状態テーブル９２１の計算機９２１１に登録された全ての計算機１の識別情報によって識別される計算機１がポリシーを満たすと判定された場合、管理装置９は、内部ネットワークの通信可能な経路が外部接続ポリシーテーブル９２２のポリシーを満たすと判定し（Ｓ２０５）、ポリシー判定処理を終了する。 When it is determined that the processing target computer 1 satisfies the policy in the process of S204, the management apparatus 9 uses the identification information of all the computers 1 registered in the computer 9211 of the external path state table 921 generated in the process of S201. The processes of S202 to S204 are repeated until it is determined that the identified computer 1 satisfies the policy. When it is determined that the computers 1 identified by the identification information of all the computers 1 registered in the computer 9211 of the external path state table 921 generated in the process of S201 satisfy the policy, the management device 9 Is determined to satisfy the policy of the external connection policy table 922 (S205), and the policy determination process is terminated.
　一方、Ｓ２０４の処理で処理対象の計算機１がポリシーを満たさないと判定された場合、管理装置９は、外部接続ポリシーテーブル９２２の計算機９２２１に処理対象の計算機１の識別情報が登録されたレコードの起動ポリシー９２２５に他の計算機を起動する旨が登録されているか否かを判定する（Ｓ２０６）。 On the other hand, if it is determined in the process of S204 that the processing target computer 1 does not satisfy the policy, the management apparatus 9 stores the identification information of the processing target computer 1 registered in the computer 9221 of the external connection policy table 922. It is determined whether or not activation of another computer is registered in the activation policy 9225 (S206).
　Ｓ２０６の処理で、起動ポリシー９２２５に他の計算機を起動する旨が登録されていないと判定された場合、管理装置９は、内部ネットワークの通信可能な経路が外部接続ポリシーテーブル９２２のポリシーを満たさないと判定し（Ｓ２１２）、処理を終了する。これは、他の計算機１に電源を供給することによって通信可能な経路を増やすことができないためである。 If it is determined in the process of S206 that activation of the other computer is not registered in the activation policy 9225, the management apparatus 9 does not satisfy the policy of the external connection policy table 922 for the communicable route of the internal network. (S212) and the process is terminated. This is because the number of communication paths cannot be increased by supplying power to other computers 1.
　一方、Ｓ２０６の処理で、起動ポリシー９２２５に他の計算機を起動する旨が登録されている場合、管理装置９は、制御装置５の記憶部５２から接続可能テーブル５２２及び計算機状態テーブル５２１を取得し、取得した接続可能テーブル５２２及び計算機状態テーブル５２１に基づいて、利用可能経路テーブル９２３を生成する（Ｓ２０７）。 On the other hand, in the process of S206, when the activation policy 9225 registers that another computer is to be activated, the management device 9 acquires the connectable table 522 and the computer state table 521 from the storage unit 52 of the control device 5. Based on the acquired connectable table 522 and the computer state table 521, an available route table 923 is generated (S207).
　具体的には、管理装置９は、計算機状態テーブル５２１の利用可能性５２１３に「利用不能」が登録されたレコード以外のレコードの計算機５２１１に登録された計算機１の識別情報を取得する。そして、管理装置９は、利用可能経路テーブル９２３に、取得した計算機１の識別情報の数分のレコードを追加し、追加したレコードの計算機９２３１に取得した計算機１の識別情報を登録する。次に、管理装置９は、取得した接続可能テーブル５２２を参照し各計算機１の接続関係を特定することによって、各計算機１の各ポート３までの通信可能な経路を特定し、特定した通信可能な経路上の計算機１の識別情報及びポート３の識別情報を利用可能経路テーブル９２３の経路カラム群９２３２に登録する。また、管理装置９は、接続可能テーブル５２２に登録された接続先カラム群５２２２に登録された帯域値を利用可能経路テーブル９２３の帯域カラム群９２３３に登録する。 Specifically, the management device 9 acquires the identification information of the computer 1 registered in the computer 5211 of a record other than the record in which “unusable” is registered in the availability 5213 of the computer state table 521. Then, the management apparatus 9 adds records as many as the acquired identification information of the computer 1 to the available route table 923, and registers the acquired identification information of the computer 1 in the computer 9231 of the added record. Next, the management device 9 specifies the communicable route to each port 3 of each computer 1 by referring to the acquired connectable table 522 and specifying the connection relationship of each computer 1, and the specified communication possible The identification information of the computer 1 on the simple route and the identification information of the port 3 are registered in the route column group 9232 of the available route table 923. Further, the management apparatus 9 registers the bandwidth value registered in the connection destination column group 5222 registered in the connectable table 522 in the bandwidth column group 9233 of the available route table 923.
　次に、管理装置９は、電源を供給して起動させる計算機１を選択する起動計算機選択処理を実行する（Ｓ２０８）。起動計算機選択処理は、図１２で詳細に説明する。 Next, the management device 9 executes a startup computer selection process for selecting the computer 1 to be started by supplying power (S208). The startup computer selection process will be described in detail with reference to FIG.
　次に、管理装置９は、Ｓ２０８の処理で起動させる計算機１が選択されたか否かを判定する（Ｓ２０９）。Ｓ２０９の処理で、起動させる計算機１が選択されなかったと判定された場合、Ｓ２１２の処理に進み、管理装置９は、内部ネットワークの通信可能な経路が外部接続ポリシーテーブル９２２のポリシーを満たさないと判定し、処理を終了する。 Next, the management device 9 determines whether or not the computer 1 to be activated in the process of S208 has been selected (S209). If it is determined in S209 that the computer 1 to be activated has not been selected, the process proceeds to S212, and the management apparatus 9 determines that the communicable route of the internal network does not satisfy the policy of the external connection policy table 922. Then, the process ends.
　一方、Ｓ２０９の処理で、起動させる計算機１が選択されたと判定された場合、管理装置９は、選択された計算機１に電源を供給するよう制御装置５に指示する（Ｓ２１０）。なお、Ｓ２１０の処理の指示は電源を供給する計算機１の識別情報を含む。制御装置５は、管理装置９からの指示を受け付けた場合、指示に含まれる計算機１の識別情報によって識別される計算機１に電源の供給を開始させる。この場合、制御装置５は、計算機状態テーブル５２１の計算機５２１１に指示に含まれる計算機１の識別情報が登録されたレコードの電源状態５２１２を「ＯＮ」に変更する。また、制御装置５は、接続状態テーブル５２３に新たなレコードを追加し、追加したレコードのポイント５２３１に指示に含まれる計算機１の識別情報を登録する。そして、制御装置５は、接続可能テーブル５２２を参照し、指示に含まれる計算機１の識別情報によって識別される計算機１の接続先を特定する。そして、制御装置５は、接続状態テーブル５２３の追加したレコードの接続先カラム群５２３２に特定した接続先の識別情報を登録する。 On the other hand, if it is determined in step S209 that the computer 1 to be activated is selected, the management device 9 instructs the control device 5 to supply power to the selected computer 1 (S210). Note that the processing instruction in S210 includes identification information of the computer 1 that supplies power. When the control device 5 receives an instruction from the management device 9, the control device 5 causes the computer 1 identified by the identification information of the computer 1 included in the instruction to start supplying power. In this case, the control device 5 changes the power state 5212 of the record in which the identification information of the computer 1 included in the instruction is registered in the computer 5211 of the computer state table 521 to “ON”. In addition, the control device 5 adds a new record to the connection state table 523 and registers the identification information of the computer 1 included in the instruction at the point 5231 of the added record. Then, the control device 5 refers to the connectable table 522 and specifies the connection destination of the computer 1 identified by the identification information of the computer 1 included in the instruction. The control device 5 registers the identification information of the connection destination specified in the connection destination column group 5232 of the added record in the connection state table 523.
　また、制御装置５は、受け付けた指示に含まれる計算機１の識別情報によって識別される計算機１に電源の供給を開始させると、受け付けた指示に対する応答を管理装置９に送信する。管理装置９は、応答を受信した場合、外部経路状態テーブル９２１を更新する。 Further, when the control device 5 starts supplying power to the computer 1 identified by the identification information of the computer 1 included in the received instruction, the control device 5 transmits a response to the received instruction to the management device 9. When receiving the response, the management device 9 updates the external route state table 921.
　具体的には、管理装置９は、外部経路状態テーブル９２１に新たなレコードを追加し、追加したレコードの計算機９２１１に起動させた計算機１の識別情報を登録する。また、管理装置９は、利用可能経路テーブル９２３の計算機９２３１に起動させた計算機１の識別情報が登録されたレコードの経路カラム群９２３２に登録された識別情報及び帯域カラム群９２３３に登録された帯域値を取得する。そして、管理装置９は、外部経路状態テーブル９２１の追加したレコードの経路カラム群９２１２に取得した識別情報を登録し、帯域カラム群９２１３に取得した帯域値を登録する。 Specifically, the management device 9 adds a new record to the external route state table 921 and registers the identification information of the computer 1 that is activated by the computer 9211 of the added record. In addition, the management apparatus 9 uses the identification information registered in the path column group 9232 of the record in which the identification information of the computer 1 activated by the computer 9231 in the available path table 923 is registered and the band registered in the band column group 9233. Get the value. Then, the management device 9 registers the acquired identification information in the route column group 9212 of the added record in the external route state table 921 and registers the acquired bandwidth value in the bandwidth column group 9213.
　また、管理装置９は、利用可能経路テーブル９２３の経路カラム群９２３２に起動させた計算機１の識別情報が存在するカラムを特定する。そして、管理装置９は、特定したカラムに登録された識別情報、当該カラムに対応する帯域カラム群９２３３に登録された帯域値、当該カラムを含むレコードの計算機９２３１に登録された計算機１の識別情報を取得する。そして、管理装置９は、外部経路状態テーブル９２１の計算機９２１１に取得した計算機１の識別情報が登録されたレコードの経路カラム群９２１２に取得した識別情報を登録し、帯域カラム群９２１３に取得した帯域値を登録する。 Further, the management device 9 specifies a column in which the identification information of the computer 1 activated in the route column group 9232 of the available route table 923 exists. The management apparatus 9 then identifies the identification information registered in the identified column, the band value registered in the band column group 9233 corresponding to the column, and the identification information of the computer 1 registered in the computer 9231 of the record including the column. To get. Then, the management apparatus 9 registers the acquired identification information in the path column group 9212 of the record in which the identification information of the computer 1 acquired in the computer 9211 of the external path state table 921 is registered, and the acquired bandwidth in the bandwidth column group 9213 Register the value.
　次に、管理装置９は、起動させた計算機１の識別情報及び当該計算機１と通信可能なポート３の識別情報の対応関係をスイッチテーブル８２１に登録させるようネットワークスイッチ８に指示し（Ｓ２１１）、Ｓ２０１の処理に戻る。そして、管理装置９は、新たに電源が供給された計算機１によって通信可能となった経路を含めて、ポリシーを満たすか否かを再度判定する。 Next, the management device 9 instructs the network switch 8 to register the correspondence relationship between the identification information of the activated computer 1 and the identification information of the port 3 capable of communicating with the computer 1 in the switch table 821 (S211). The process returns to S201. Then, the management device 9 determines again whether or not the policy is satisfied, including the route that has become communicable by the computer 1 to which power is newly supplied.
　図１１は、実施例１の処理対象計算機ポリシー判定処理のフローチャートである。 FIG. 11 is a flowchart of processing target computer policy determination processing according to the first embodiment.
　まず、管理装置９は、外部接続ポリシーテーブル９２２を参照し、処理対象の計算機１の冗長性を取得する（Ｓ３０１）。具体的には、管理装置９は、外部接続ポリシーテーブル９２２の計算機９２２１に処理対象の計算機１の識別情報が登録されたレコードの冗長性９２２４に登録された経路の数を取得する。 First, the management device 9 refers to the external connection policy table 922 and acquires the redundancy of the processing target computer 1 (S301). Specifically, the management device 9 acquires the number of routes registered in the redundancy 9224 of the record in which the identification information of the processing target computer 1 is registered in the computer 9221 of the external connection policy table 922.
　次に、管理装置９は、外部経路状態テーブル９２１を参照し、処理対象の計算機１からの通信可能な経路の数を取得する（Ｓ３０２）。具体的には、管理装置９は、外部経路状態テーブル９２１の計算機９２１１に処理対象の計算機１の識別情報が登録されたレコードの経路カラム群９２１２にポート３の識別情報が登録されているカラムの数を経路の数として取得する。 Next, the management device 9 refers to the external route status table 921 and acquires the number of routes that can be communicated from the processing target computer 1 (S302). Specifically, the management device 9 stores the column 3 in which the identification information of port 3 is registered in the path column group 9212 of the record in which the identification information of the computer 1 to be processed is registered in the computer 9211 of the external path state table 921. Get the number as the number of paths.
　次に、管理装置９は、Ｓ３０２の処理で取得した経路の数がＳ３０１の処理で取得した経路の数以上であるか否かを判定する（Ｓ３０３）。Ｓ３０３の処理において、Ｓ３０２の処理で取得した経路の数がＳ３０１の処理で取得した経路の数未満であると判定された場合、管理装置９は、処理対象の計算機１からの通信可能な経路が冗長性を満たさず、処理対象の計算機１がポリシーを満たさないと判定し（Ｓ３０４）、処理を終了する。 Next, the management device 9 determines whether or not the number of paths acquired in the process of S302 is equal to or greater than the number of paths acquired in the process of S301 (S303). In the process of S303, when it is determined that the number of paths acquired in the process of S302 is less than the number of paths acquired in the process of S301, the management apparatus 9 has a path through which communication from the processing target computer 1 is possible. It is determined that the redundancy is not satisfied and the processing target computer 1 does not satisfy the policy (S304), and the processing is terminated.
　一方、Ｓ３０３の処理において、Ｓ３０２の処理で取得した経路の数がＳ３０１の処理で取得した経路の数以上であると判定された場合、管理装置９は、Ｓ３０５～Ｓ３０９の処理で、処理対象の計算機１からの通信可能な経路が最小使用帯域を満たすか否かを判定する。 On the other hand, in the process of S303, when it is determined that the number of routes acquired in the process of S302 is equal to or greater than the number of paths acquired in the process of S301, the management apparatus 9 performs processing in S305 to S309. It is determined whether or not a communicable route from the computer 1 satisfies the minimum usable bandwidth.
　まず、管理装置９は、外部接続ポリシーテーブル９２２を参照し、処理対象の計算機１の最小使用帯域を取得する（Ｓ３０５）。具体的には、管理装置９は、外部接続ポリシーテーブル９２２の計算機９２２１に処理対象の計算機１の識別情報が登録されたレコードの最小使用帯域９２２３に登録された帯域値を取得する。 First, the management device 9 refers to the external connection policy table 922 and acquires the minimum usable bandwidth of the processing target computer 1 (S305). Specifically, the management apparatus 9 acquires the bandwidth value registered in the minimum used bandwidth 9223 of the record in which the identification information of the processing target computer 1 is registered in the computer 9221 of the external connection policy table 922.
　次に、管理装置９は、外部経路状態テーブル９２１を参照し、処理対象の計算機１から通信可能な経路の数が１より大きいかを判定する（Ｓ３０６）。 Next, the management device 9 refers to the external route state table 921 and determines whether the number of routes that can be communicated from the processing target computer 1 is greater than 1 (S306).
　Ｓ３０６の処理で、処理対象の計算機１からの通信可能な経路の数が１より大きいと判定された場合、管理装置９は、Ｓ３０５の処理で取得した帯域値を、処理対象の計算機１からの通信可能な経路の数で除算し（Ｓ３０７）、Ｓ３０８の処理に進む。 In the process of S306, when it is determined that the number of communicable paths from the processing target computer 1 is greater than 1, the management apparatus 9 uses the bandwidth value acquired in the processing of S305 from the processing target computer 1. Dividing by the number of communicable paths (S307), the process proceeds to S308.
　ここで、管理装置９は、ポート３に至る経路ごとに図示しない余剰帯域情報を保持する。余剰帯域情報には、ポート３に至る経路の帯域から各計算機１の最小使用帯域を減算した帯域値が登録される。初期状態の余剰帯域情報には各ポート３に至る経路の帯域値が登録される。例えば、Ｐ１への経路の初期状態の余剰帯域情報には、Ｐ１への帯域９２１３Ａに登録された１０Ｇｂｐｓが登録され、Ｐ２への経路の初期状態の余剰帯域情報には、Ｐ２への帯域９２１３Ｂに登録された１０Ｇｂｐｓが登録される。 Here, the management device 9 holds surplus bandwidth information (not shown) for each route to the port 3. In the surplus bandwidth information, a bandwidth value obtained by subtracting the minimum usable bandwidth of each computer 1 from the bandwidth of the route to the port 3 is registered. The bandwidth value of the route to each port 3 is registered in the surplus bandwidth information in the initial state. For example, 10 Gbps registered in the bandwidth 9213A to P1 is registered in the surplus bandwidth information in the initial state of the route to P1, and the surplus bandwidth information in the initial state of the route to P2 is in the bandwidth 9213B to P2. The registered 10 Gbps is registered.
　Ｓ３０８の処理では、管理装置９は、各ポート３に至る経路の余剰帯域情報に登録された帯域値からそれぞれＳ３０７の処理で算出された除算値を減算する（Ｓ３０８）。 In the processing of S308, the management device 9 subtracts the division value calculated in the processing of S307 from the bandwidth value registered in the surplus bandwidth information of the route to each port 3 (S308).
　一方、Ｓ３０６の処理で、処理対象の計算機１からの通信可能な経路の数が１であると判定された場合、Ｓ３０８の処理に進み、管理装置９は、一つの通信可能な経路に対応するポート３に至る経路の余剰帯域情報に登録された帯域値からＳ３０５で取得した帯域値を減算する。 On the other hand, if it is determined in step S306 that the number of communicable paths from the processing target computer 1 is 1, the process proceeds to step S308, and the management apparatus 9 corresponds to one communicable path. The bandwidth value acquired in S305 is subtracted from the bandwidth value registered in the surplus bandwidth information of the route to the port 3.
　次に、管理装置９は、Ｓ３０８の処理で算出された減算値が０以上であるか否かを判定する（Ｓ３０９）。 Next, the management device 9 determines whether or not the subtraction value calculated in the process of S308 is 0 or more (S309).
　Ｓ３０９の処理において、Ｓ３０８の処理で算出された減算値が０未満、すなわちマイナスの値であると判定された場合、処理対象の計算機１からの経路が最小使用帯域を満たさないので、Ｓ３０４の処理に進み、管理装置９は、処理対象の計算機１がポリシーを満たさないと判定し、処理を終了する。 In the process of S309, if it is determined that the subtraction value calculated in the process of S308 is less than 0, that is, a negative value, the path from the computer 1 to be processed does not satisfy the minimum usable bandwidth, so the process of S304 The management apparatus 9 determines that the processing target computer 1 does not satisfy the policy, and ends the processing.
　一方、Ｓ３０９の処理において、Ｓ３０８の処理で算出された減算値が０以上であると判定された場合、管理装置９は、Ｓ３１０～Ｓ３１４の処理で、処理対象の計算機１からの通信可能な経路が最大使用帯域を満たすか否かを判定する。 On the other hand, in the process of S309, when it is determined that the subtraction value calculated in the process of S308 is 0 or more, the management device 9 can communicate with the processing target computer 1 in the process of S310 to S314. Determines whether or not the maximum bandwidth is satisfied.
　まず、管理装置９は、外部接続ポリシーテーブル９２２を参照し、処理対象の計算機１の最大使用帯域を取得する（Ｓ３１０）。具体的には、管理装置９は、外部接続ポリシーテーブル９２２の計算機９２２１に処理対象の計算機１の識別情報が登録されたレコードの最大使用帯域９２２２に登録された帯域値を取得する。 First, the management device 9 refers to the external connection policy table 922 and acquires the maximum usable bandwidth of the processing target computer 1 (S310). Specifically, the management device 9 acquires the bandwidth value registered in the maximum used bandwidth 9222 of the record in which the identification information of the processing target computer 1 is registered in the computer 9221 of the external connection policy table 922.
　次に、管理装置９は、外部経路状態テーブル９２１を参照し、処理対象の計算機１から通信可能な経路の数が１より大きいかを判定する（Ｓ３１１）。 Next, the management device 9 refers to the external route state table 921 and determines whether the number of routes that can be communicated from the processing target computer 1 is greater than 1 (S311).
　Ｓ３１１の処理で、処理対象の計算機１からの通信可能な経路の数が１より大きいと判定された場合、管理装置９は、Ｓ３１０の処理で取得した帯域値を、処理対象の計算機１からの通信可能な経路の数で除算し（Ｓ３１２）、Ｓ３１３の処理に進む。 If it is determined in S311 that the number of paths that can be communicated from the processing target computer 1 is greater than 1, the management apparatus 9 uses the bandwidth value acquired in the processing of S310 from the processing target computer 1. Dividing by the number of communicable paths (S312), the process proceeds to S313.
　Ｓ３１３の処理では、管理装置９は、外部経路状態テーブル９２１の帯域カラム群９２１３に登録された帯域値からＳ３１２の処理で算出された除算値を減算する（Ｓ３１３）。 In the process of S313, the management device 9 subtracts the division value calculated in the process of S312 from the band value registered in the band column group 9213 of the external path state table 921 (S313).
　一方、Ｓ３１１の処理で、処理対象の計算機１からの通信可能な経路の数が１であると判定された場合、Ｓ３１３の処理に進み、管理装置９は、外部経路状態テーブル９２１の帯域カラム群９２１３の当該一つの通信可能な経路に対応するカラムに登録された帯域値からＳ３１０の処理で取得した帯域値を減算する。 On the other hand, if it is determined in S311 that the number of paths that can be communicated from the processing target computer 1 is 1, the process proceeds to S313, and the management apparatus 9 performs the bandwidth column group of the external path status table 921. The band value acquired in the process of S310 is subtracted from the band value registered in the column corresponding to the one communicable path 9213.
　次に、管理装置９は、Ｓ３１３の処理で算出された減算値が０以上であるか否かを判定する（Ｓ３１４）。 Next, the management device 9 determines whether or not the subtraction value calculated in the process of S313 is 0 or more (S314).
　Ｓ３１４の処理において、Ｓ３１４の処理で算出された減算値が０未満、すなわちマイナスの値であると判定された場合、処理対象の計算機１からの経路が最大使用帯域を満たさないので、Ｓ３０４の処理に進み、管理装置９は、処理対象の計算機１がポリシーを満たさないと判定し、処理を終了する。 In the process of S314, if it is determined that the subtraction value calculated in the process of S314 is less than 0, that is, a negative value, the path from the computer 1 to be processed does not satisfy the maximum usable bandwidth, so the process of S304 The management apparatus 9 determines that the processing target computer 1 does not satisfy the policy, and ends the processing.
　一方、Ｓ３１４の処理において、Ｓ３１３の処理で算出された減算値が０以上であると判定された場合、管理装置９は、処理対象の計算機１からの通信可能な経路はポリシーを満たすと判定し（Ｓ３１５）、処理を終了する。 On the other hand, in the process of S314, when it is determined that the subtraction value calculated in the process of S313 is 0 or more, the management device 9 determines that the communicable path from the processing target computer 1 satisfies the policy. (S315), the process ends.
　図１２は、実施例１の起動計算機選択処理のフローチャートである。 FIG. 12 is a flowchart of the startup computer selection process according to the first embodiment.
　まず、管理装置９は、利用可能経路テーブル９２３を参照し、ポリシーを満たさないと判定された計算機１が利用可能な経路を取得する（Ｓ４０１）。具体的には、管理装置９は、利用可能経路テーブル９２３の計算機９２３１にポリシーを満たさないと判定された計算機１の識別情報が登録された経路カラム群９２３２に登録された識別情報を取得する。 First, the management device 9 refers to the available route table 923 and obtains a route that can be used by the computer 1 that is determined not to satisfy the policy (S401). Specifically, the management device 9 acquires the identification information registered in the route column group 9232 in which the identification information of the computer 1 determined not to satisfy the policy in the computer 9231 of the available route table 923 is registered.
　次に、管理装置９は、Ｓ４０１の処理で取得した経路から処理対象の経路を選択し、Ｓ４０３の処理に進む（Ｓ４０２）。 Next, the management device 9 selects a processing target route from the routes acquired in the process of S401, and proceeds to the process of S403 (S402).
　管理装置９は、外部経路状態テーブル９２１を参照し、ポリシーを満たさないと判定された計算機１の通信可能な経路を取得する（Ｓ４０３）。具体的には、管理装置９は、外部経路状態テーブル９２１の計算機９２２１にポリシーを満たさない計算機１の識別情報が登録されたレコードの経路カラム群９２１２に登録された識別情報を取得する。 The management device 9 refers to the external route state table 921 and acquires a communicable route of the computer 1 that is determined not to satisfy the policy (S403). Specifically, the management device 9 acquires the identification information registered in the route column group 9212 of the record in which the identification information of the computer 1 that does not satisfy the policy is registered in the computer 9221 of the external route state table 921.
　次に、管理装置９は、処理対象の利用可能な経路が通信可能な経路であるか否かを判定する（Ｓ４０４）。具体的には、Ｓ４０３の処理で取得した通信可能な各経路に対応する経路カラム群９２１２に登録された識別情報が処理対象の経路に対応する経路カラム群９２３２に登録された識別情報と一致しない場合、管理装置９は、処理対象の利用可能な経路が通信可能な経路でないと判定する。 Next, the management device 9 determines whether the available route to be processed is a communicable route (S404). Specifically, the identification information registered in the route column group 9212 corresponding to each communicable route acquired in the process of S403 does not match the identification information registered in the route column group 9232 corresponding to the processing target route. In this case, the management device 9 determines that the available route to be processed is not a communicable route.
　Ｓ４０４の処理で、処理対象の利用可能な経路が通信可能な経路であると判定された場合、Ｓ４０３の処理に戻り、管理装置９は、Ｓ４０１の処理で取得した他の利用可能な経路を処理対象の選択し、Ｓ４０３及びＳ４０４の処理を実行する。ポリシーを満たさないと判定された計算機１の全ての利用可能な経路が通信可能な経路であるとＳ４０４の処理で判定されると、管理装置９は、起動させる計算機１がないと判定し（Ｓ４０５）、処理を終了する。 If it is determined in S404 that the available route to be processed is a communicable route, the process returns to S403, and the management apparatus 9 processes the other available routes acquired in S401. The target is selected, and the processes of S403 and S404 are executed. When it is determined in the process of S404 that all the available routes of the computer 1 determined not to satisfy the policy are communicable routes, the management device 9 determines that there is no computer 1 to be activated (S405). ), The process is terminated.
　一方、Ｓ４０４の処理で、処理対象の利用可能な経路が通信可能な経路でないと判定された場合、管理装置９は、処理対象の利用可能な経路上の計算機１のうち電源が供給されていない計算機を、起動させる計算機１として選択し（Ｓ４０６）、処理を終了する。 On the other hand, if it is determined in S404 that the available route to be processed is not a communicable route, the management device 9 is not supplied with power among the computers 1 on the available route to be processed. The computer is selected as the computer 1 to be activated (S406), and the process is terminated.
　次に、計算機Ｎ３（１Ｃ）に電源がされておらず、その他の計算機１には電源が供給された状態で、管理装置９がポリシー更新要求の入力を受け付けた場合の処理について、図９～図１２を用いて説明する。この場合のポリシー更新要求は、外部接続ポリシーテーブル９２２を図６に示す値に更新する要求であるものとする。 Next, the processing when the management apparatus 9 accepts the input of the policy update request while the computer N3 (1C) is not powered and the other computer 1 is powered is shown in FIGS. This will be described with reference to FIG. The policy update request in this case is a request for updating the external connection policy table 922 to the value shown in FIG.
　図９では、管理装置９は、Ｓ１０１の処理でポリシー更新要求の入力を受け付け、Ｓ１０２の処理で外部接続ポリシーテーブル９２２を図６に示すように更新する。次に、管理装置９は、ポリシー判定処理を実行する。 In FIG. 9, the management apparatus 9 receives an input of a policy update request in the process of S101, and updates the external connection policy table 922 as shown in FIG. 6 in the process of S102. Next, the management device 9 executes policy determination processing.
　図１０に示すポリシー判定処理では、管理装置９は、Ｓ２０１の処理で、制御装置５から図４に示す接続状態テーブル５２３及び図２に示す計算機状態テーブル５２１を取得し、図５に示す外部経路状態テーブル９２１を生成する。 In the policy determination processing shown in FIG. 10, the management device 9 acquires the connection status table 523 shown in FIG. 4 and the computer status table 521 shown in FIG. 2 from the control device 5 in the processing of S201, and the external route shown in FIG. A state table 921 is generated.
　管理装置９は、Ｓ２０２の処理で、図５に示す外部経路状態テーブル９２１から計算機Ｎ１（１Ａ）の識別情報を処理対象として選択し、Ｓ２０３の処理で図１１に示す処理対象計算機ポリシー判定処理を実行する。管理装置９は、Ｓ３０１の処理で、図６に示す外部接続ポリシーテーブル９２２を参照し、計算機Ｎ１（１Ａ）の冗長性「２」を取得する。次に、管理装置９は、Ｓ３０２の処理で、外部経路状態テーブル９２１を参照し、計算機Ｎ１（１Ａ）からの通信可能な経路数「２」を取得する。これは、外部経路状態テーブル９２１の計算機９２１１に「Ｎ１」が登録されたレコードのＰ１への経路９２１２Ａに「Ｐ１」が登録され、Ｐ２への経路９２１２Ｂに「Ｐ２」が登録されているためである。 The management apparatus 9 selects the identification information of the computer N1 (1A) from the external path state table 921 shown in FIG. 5 as a processing target in the processing of S202, and performs the processing target computer policy determination processing shown in FIG. 11 in the processing of S203. Execute. The management apparatus 9 acquires the redundancy “2” of the computer N1 (1A) by referring to the external connection policy table 922 shown in FIG. Next, in step S302, the management apparatus 9 refers to the external route state table 921 and acquires the number of routes “2” that can be communicated from the computer N1 (1A). This is because “P1” is registered in the path 9212A to P1 of the record in which “N1” is registered in the computer 9211 of the external path status table 921, and “P2” is registered in the path 9212B to P2. is there.
　次に、管理装置９は、Ｓ３０３の処理で、経路数「２」は冗長性「２」と同数であるので、Ｓ３０５の処理に進み、外部接続ポリシーテーブル９２２を参照し、計算機Ｎ１（１Ａ）の最小使用帯域「０．５Ｇｂｐｓ」を取得する。Ｓ３０６の処理で、計算機Ｎ１（１Ａ）からの通信可能な経路数「２」であるので、Ｓ３０７の処理に進む。Ｓ３０７の処理では、管理装置９は、最小使用帯域「０．５Ｇｂｐｓ」を「２」で除算し、除算値「０．２５Ｇｂｐｓ」を得る。 Next, since the number of paths “2” is the same as the redundancy “2” in the process of S303, the management apparatus 9 proceeds to the process of S305, refers to the external connection policy table 922, and calculates the computer N1 (1A). The minimum usable bandwidth “0.5 Gbps” is acquired. Since the number of paths that can be communicated from the computer N1 (1A) is “2” in the process of S306, the process proceeds to S307. In the process of S307, the management apparatus 9 divides the minimum usable bandwidth “0.5 Gbps” by “2” to obtain a divided value “0.25 Gbps”.
　次に、管理装置９は、Ｓ３０８の処理で、初期状態のＰ１の余剰帯域「１０Ｇｂｐｓ」及び初期状態のＰ２の余剰帯域「１０Ｇｂｐｓ」から除算値「０．２５Ｇｂｐｓ」を減算する。Ｐ１の余剰帯域及びＰ２の余剰帯域は「９．７５Ｇｂｐｓ」となり０以上となるため、Ｓ３１０の処理に進む。なお、Ｐ１の余剰帯域及びＰ２の余剰帯域は「９．７５Ｇｂｐｓ」のままにしておく。Ｐ１の余剰帯域及びＰ２の余剰帯域Ｓ２０２は、Ｓ２０５の処理でポリシーを満たすと判定された場合、又はＳ２１２の処理でポリシーを満たさないと判定された場合、初期状態の値に戻される。 Next, the management device 9 subtracts the division value “0.25 Gbps” from the surplus bandwidth “10 Gbps” of P1 in the initial state and the surplus bandwidth “10 Gbps” of P2 in the initial state in the process of S308. Since the surplus bandwidth of P1 and the surplus bandwidth of P2 are “9.75 Gbps” which is 0 or more, the process proceeds to S310. Note that the surplus bandwidth of P1 and the surplus bandwidth of P2 remain “9.75 Gbps”. The surplus bandwidth of P1 and the surplus bandwidth S202 of P2 are returned to the initial state values when it is determined that the policy is satisfied in the process of S205, or when the policy is not satisfied in the process of S212.
　管理装置９は、Ｓ３１０の処理では、外部接続ポリシーテーブル９２２を参照し、計算機Ｎ１（１Ａ）の最大使用帯域「５Ｇｂｐｓ」を取得し、Ｓ３１１の処理で、計算機Ｎ１（１Ａ）からの通信可能な経路数「２」であるので、Ｓ３１２の処理に進む。Ｓ３１２の処理では、管理装置９は、最大使用帯域「５Ｇｂｐｓ」を「２」で除算し、除算値「２．５Ｇｂｐｓ」を得る。 The management device 9 refers to the external connection policy table 922 in the process of S310, acquires the maximum usable bandwidth “5 Gbps” of the computer N1 (1A), and can communicate from the computer N1 (1A) in the process of S311. Since the number of routes is “2”, the process proceeds to S312. In the process of S312, the management apparatus 9 divides the maximum usable bandwidth “5 Gbps” by “2” to obtain a divided value “2.5 Gbps”.
　次に、管理装置９は、Ｓ３１３の処理で、外部経路状態テーブル９２１の計算機Ｎ１（１Ａ）へのＰ１の帯域９２１３Ａ「１０Ｇｂｐｓ」及びＰ２の帯域９２１３Ｂ「１０Ｇｂｐｓ」から除算値「２．５Ｇｂｐｓ」を減算する。Ｐ１の帯域及びＰ２の帯域は「７．５Ｇｂｐｓ」となり０以上となるため、Ｓ３１５の処理に進み、管理装置９は、計算機Ｎ１（１Ａ）はポリシーを満たすと判定する。 Next, in the process of S313, the management device 9 obtains a division value “2.5 Gbps” from the P1 band 9213A “10 Gbps” and the P2 band 9213B “10 Gbps” to the computer N1 (1A) in the external path state table 921. Subtract. Since the bandwidth of P1 and the bandwidth of P2 are “7.5 Gbps” and become 0 or more, the process proceeds to S315, and the management apparatus 9 determines that the computer N1 (1A) satisfies the policy.
　次に、図１０に示すＳ２０２の処理に戻り、管理装置９は、外部経路状態テーブル９２１から計算機Ｎ２（１Ｂ）の識別情報を処理対象として選択し、Ｓ２０３の処理で図１１に示す処理対象計算機ポリシー判定処理を実行する。計算機Ｎ２（１Ｂ）からの通信可能な経路数は「２」であり、冗長性「２」であるので、計算機Ｎ２（１Ｂ）からの通信可能な経路は冗長性に関するポリシーを満たす。 Next, returning to the processing of S202 shown in FIG. 10, the management apparatus 9 selects the identification information of the computer N2 (1B) from the external path state table 921 as a processing target, and the processing target computer shown in FIG. Execute policy judgment processing. Since the number of communicable paths from the computer N2 (1B) is “2” and the redundancy is “2”, the communicable paths from the computer N2 (1B) satisfy the policy regarding redundancy.
　また、管理装置９は、計算機Ｎ２（１Ｂ）の最小使用帯域「１Ｇｂｐｓ」を計算機Ｎ２（１Ｂ）からの通信可能な経路数「２」で除算し、除算値「０.５Ｇｂｐs」を得る。Ｐ１の余剰帯域「９．７５Ｇｂｐｓ」及びＰ２の余剰帯域「９．７５Ｇｂｐｓ」から除算値「０．５Ｇｂｐｓ」を減算すると、Ｐ１の余剰帯域「９．２５Ｇｂｐｓ」及びＰ２の余剰帯域「９．２５Ｇｂｐｓ」となり、これらは０以上であるので、計算機Ｎ２（１Ｂ）からの通信可能な経路は最小使用帯域に関するポリシーを満たす。 Also, the management device 9 divides the minimum usable bandwidth “1 Gbps” of the computer N2 (1B) by the number of routes “2” that can be communicated from the computer N2 (1B) to obtain a divided value “0.5 Gbps”. When the division value “0.5 Gbps” is subtracted from the surplus bandwidth “9.75 Gbps” of P1 and the surplus bandwidth “9.75 Gbps” of P2, the surplus bandwidth “9.25 Gbps” of P1 and the surplus bandwidth “9.25 Gbps” of P2 Since these are 0 or more, the communicable path from the computer N2 (1B) satisfies the policy regarding the minimum usable bandwidth.
　また、管理装置９は、計算機Ｎ２（１Ｂ）の最大使用帯域「１０Ｇｂｐｓ」を計算機Ｎ２（１Ｂ）からの通信可能な経路数「２」で除算し、除算値「５Ｇｂｐs」を得る。外部経路状態テーブル９２１の計算機Ｎ２（１Ｂ）へのＰ１の帯域９２１３Ａ「１０Ｇｂｐｓ」及びＰ２の帯域９２１３Ｂ「１０Ｇｂｐｓ」から除算値「５Ｇｂｐｓ」を減算する。Ｐ１の余剰帯域及びＰ２の余剰帯域は「５Ｇｂｐｓ」となり０以上となり、計算機Ｎ２（１Ｂ）からの通信可能な経路は最大使用帯域に関するポリシーを満たす。Ｓ３１５の処理に進み、管理装置９は、計算機Ｎ２（１Ｂ）はポリシーを満たすと判定する。 Further, the management device 9 divides the maximum usable bandwidth “10 Gbps” of the computer N2 (1B) by the number of routes “2” that can be communicated from the computer N2 (1B) to obtain a divided value “5 Gbps”. The division value “5 Gbps” is subtracted from the P1 band 9213A “10 Gbps” and the P2 band 9213B “10 Gbps” to the computer N2 (1B) in the external path state table 921. The surplus bandwidth of P1 and the surplus bandwidth of P2 are “5 Gbps” and become 0 or more, and the communicable path from the computer N2 (1B) satisfies the policy regarding the maximum usable bandwidth. Proceeding to the processing of S315, the management device 9 determines that the computer N2 (1B) satisfies the policy.
　次に、図１０に示すＳ２０２の処理に戻り、管理装置９は、外部経路状態テーブル９２１から計算機Ｎ３（１Ｃ）の識別情報を処理対象として選択し、Ｓ２０３の処理で図１１に示す処理対象計算機ポリシー判定処理を実行する。計算機Ｎ３（１Ｃ）の処理対象計算機ポリシー判定処理は、計算機Ｎ１（１Ａ）及び計算機Ｎ２（１Ｂ）と同様であり、計算機Ｎ３（１Ｃ）はポリシーを満たすと判定する。 Next, returning to the processing of S202 shown in FIG. 10, the management apparatus 9 selects the identification information of the computer N3 (1C) from the external path state table 921 as a processing target, and the processing target computer shown in FIG. Execute policy judgment processing. The processing target computer policy determination processing of the computer N3 (1C) is the same as the computer N1 (1A) and the computer N2 (1B), and it is determined that the computer N3 (1C) satisfies the policy.
　次に、図１０に示すＳ２０２の処理に戻り、管理装置９は、外部経路状態テーブル９２１から計算機Ｎ４（１Ｄ）の識別情報を処理対象として選択し、Ｓ２０３の処理で図１１に示す処理対象計算機ポリシー判定処理を実行する。 Next, returning to the processing of S202 shown in FIG. 10, the management apparatus 9 selects the identification information of the computer N4 (1D) from the external path state table 921 as a processing target, and the processing target computer shown in FIG. Execute policy judgment processing.
　計算機Ｎ４（１Ｄ）からの通信可能な経路数は「１」であり、冗長性「２」であるので、計算機Ｎ４（１Ｄ）からの通信可能な経路は冗長性に関するポリシーを満たさず、Ｓ３０４の処理に進み、管理装置９は、計算機Ｎ４（１Ｄ）はポリシーを満たさないと判定する。 Since the number of routes that can be communicated from the computer N4 (1D) is “1” and the redundancy is “2”, the route that can be communicated from the computer N4 (1D) does not satisfy the redundancy policy. Proceeding to the processing, the management device 9 determines that the computer N4 (1D) does not satisfy the policy.
　次に、図１０に示すＳ２０４の処理で、計算機Ｎ４（１Ｄ）はポリシーを満たさないと判定され、Ｓ２０６の処理に進む。Ｓ２０６の処理では、管理装置９は、外部接続ポリシーテーブル９２２を参照し、計算機Ｎ４（１Ｄ）の起動ポリシー９２２５には、他の計算機を起動してもよい旨が登録されているので、Ｓ２０７の処理に進む。Ｓ２０７の処理では、管理装置９は、接続可能テーブル５２２及び計算機状態テーブル５２１を制御装置５から取得し、利用可能経路テーブル９２３を生成し、Ｓ２０８の処理で図１２に示す起動計算機選択処理を実行する。 Next, in the process of S204 shown in FIG. 10, it is determined that the computer N4 (1D) does not satisfy the policy, and the process proceeds to S206. In the process of S206, the management apparatus 9 refers to the external connection policy table 922, and the activation policy 9225 of the computer N4 (1D) registers that other computers may be activated. Proceed to processing. In the process of S207, the management apparatus 9 acquires the connectable table 522 and the computer state table 521 from the control apparatus 5, generates an available route table 923, and executes the startup computer selection process shown in FIG. 12 in the process of S208. To do.
　図１２に示すＳ４０１の処理では、管理装置９は、利用可能経路テーブル９２３を参照し、計算機Ｎ４（１Ｄ）の利用可能な経路を取得する。ここでは、Ｐ１への経路（Ｎ３、Ｎ１、Ｐ１）及びＰ２への経路（Ｎ２、Ｐ２）が取得される。次に、Ｓ４０２の処理で、管理装置９は、Ｐ１への経路（Ｎ３、Ｎ１、Ｐ１）を処理対象の経路として選択する。そして、Ｓ４０３の処理で、管理装置９は、外部経路状態テーブル９２１を参照し、計算機Ｎ４（１Ｄ）の現在通信可能な経路としてＰ２への経路（Ｎ２、Ｐ２）を取得する。Ｓ４０４の処理では、処理対象の経路であるＰ１への経路（Ｎ３、Ｎ１、Ｐ１）と計算機Ｎ４（１Ｄ）の現在通信可能な経路としてＰ２への経路（Ｎ２、Ｐ２）とは異なるため、Ｓ４０６の処理に進む。Ｓ４０６の処理では、管理装置９は、電源が供給されていない計算機Ｎ３（１Ｃ）を起動させる計算機として選択し、処理を終了する。 In the process of S401 illustrated in FIG. 12, the management device 9 refers to the available route table 923 and acquires the available route of the computer N4 (1D). Here, the route to P1 (N3, N1, P1) and the route to P2 (N2, P2) are acquired. Next, in the process of S402, the management apparatus 9 selects a path (N3, N1, P1) to P1 as a process target path. Then, in the process of S403, the management device 9 refers to the external route state table 921 and acquires a route (N2, P2) to P2 as a currently communicable route of the computer N4 (1D). In the process of S404, the route to P1, which is the processing target route (N3, N1, P1) is different from the route to P2 (N2, P2) as the currently communicable route of the computer N4 (1D). Proceed to the process. In the process of S406, the management apparatus 9 selects the computer N3 (1C) to which power is not supplied as a computer to be activated, and ends the process.
　図１０に示すＳ２０９の処理では、選択された計算機Ｎ３（１Ｃ）があるため、Ｓ２１０の処理に進み、管理装置９は、計算機Ｎ３（１Ｃ）を制御装置５に起動させる。制御装置５は、計算機状態テーブル５２１の計算機Ｎ３（１Ｃ）の電源状態５２１２に「ＯＮ」を登録する。また、全ての計算機１に電源が供給されるので、制御装置５は、接続状態テーブル５２３に登録される値が接続可能テーブル５２２と同一となるように、接続状態テーブル５２３を更新する。同様に、管理装置９は、外部経路状態テーブル９２１に登録される値が利用可能経路テーブル９２３と同一となるように、外部経路状態テーブル９２１を更新する。 In the process of S209 shown in FIG. 10, since there is the selected computer N3 (1C), the process proceeds to S210, and the management apparatus 9 starts up the computer N3 (1C) in the control apparatus 5. The control device 5 registers “ON” in the power supply state 5212 of the computer N3 (1C) in the computer state table 521. Further, since the power is supplied to all the computers 1, the control device 5 updates the connection state table 523 so that the value registered in the connection state table 523 is the same as the connectable table 522. Similarly, the management device 9 updates the external route state table 921 so that the value registered in the external route state table 921 is the same as the available route table 923.
　Ｓ２１１の処理で、管理装置９は、計算機Ｎ３（１Ｃ）に電源が供給されることによって、計算機Ｎ３（１Ｃ）とポートＰ１（３Ａ）及びＰ２（３Ｂ）とが通信可能となり、計算機Ｎ４（１Ｄ）とポートＰ２（３Ｂ）とが通信可能となるように、図８に示すスイッチテーブル８２１をネットワークスイッチ８に更新させる。具体的には、図８に示すスイッチテーブル８２１の宛先８２１１に「Ｎ３」が登録されたレコードのポート８２１２に「Ｐ１」及び「Ｐ２」が登録され、宛先８２１１に「Ｎ４」が登録されたレコードのポート８２１２に「Ｐ１」がさらに登録される。 In the process of S211, the management apparatus 9 can communicate with the computer N3 (1C) and the ports P1 (3A) and P2 (3B) by supplying power to the computer N3 (1C). ) And the port P2 (3B), the switch table 821 shown in FIG. Specifically, a record in which “P1” and “P2” are registered in the port 8212 of the record in which “N3” is registered in the destination 8211 of the switch table 821 shown in FIG. "P1" is further registered in the port 8212.
　次に、Ｓ２０１の処理に戻り、管理装置９は、計算機Ｎ３（１Ｃ）に電源供給後の通信可能な経路について再度のＳ２０２以降の処理を実行する。 Next, returning to the processing of S201, the management device 9 executes the processing subsequent to S202 again on the communicable path after power is supplied to the computer N3 (1C).
　このように、本発明では、内部ネットワークを構築する全ての計算機１を電源が供給されている必要がなく、ある計算機１からの通信可能な経路が所定の条件を満たさなくなった場合に、他の計算機１の電源が供給されるようになる。このため、所定の条件を満たしつつ、計算機１全体の消費電力を低減させることができる。 As described above, according to the present invention, it is not necessary to supply power to all the computers 1 constituting the internal network, and when a communication path from a certain computer 1 does not satisfy a predetermined condition, The power source of the computer 1 is supplied. For this reason, the power consumption of the whole computer 1 can be reduced, satisfy | filling a predetermined condition.
　また、計算機１に新たに電源が供給された場合、管理装置９は、当該計算機１に電源が供給されたことによって、通信可能となる経路を特定し、特定した経路上の計算機１が新たに通信可能となるポート３を特定する。そして、管理装置９は、この計算機１とポート３との関係をスイッチテーブル８２１に登録するようネットワークスイッチ８に指示する。これによって、計算機１に新たに電源が供給された場合、管理者は、手動でネットワークスイッチ８のスイッチテーブル８２１を更新する必要がなくなるので、管理者の負担を軽減することができる。 When power is newly supplied to the computer 1, the management device 9 specifies a path through which communication is possible when power is supplied to the computer 1, and the computer 1 on the specified path is newly added. The port 3 that can communicate is specified. Then, the management device 9 instructs the network switch 8 to register the relationship between the computer 1 and the port 3 in the switch table 821. As a result, when power is newly supplied to the computer 1, the administrator does not need to manually update the switch table 821 of the network switch 8, so the burden on the administrator can be reduced.
　また、管理装置９は、図１０に示すＳ２０６の処理で、処理対象の計算機１が他の計算機の起動を許可されている場合に、利用可能経路テーブル９２３を生成する。これによって、利用可能経路テーブル９２３が必要となる場合にのみ、利用可能経路テーブル９２３が生成されるので、管理装置９の処理負荷を軽減できる。 Further, the management device 9 generates an available route table 923 when the processing target computer 1 is permitted to start another computer in the processing of S206 shown in FIG. As a result, the available route table 923 is generated only when the available route table 923 is required, so that the processing load on the management device 9 can be reduced.
　また、内部ネットワークの通信可能な経路がポリシーを満たさない旨をユーザに報知するので、ユーザはその旨を把握できる。 Also, since the user is informed that the communicable route of the internal network does not satisfy the policy, the user can grasp that fact.
　また、ポリシーとしては、冗長性、最小使用帯域、及び最大使用帯域があり、各計算機１からの通信可能な経路は、冗長性、最小使用帯域、及び最大使用帯域を満たし、ユーザが要求した条件を満たすことができる。なお、本実施例では、ポリシーとして冗長性、最小使用帯域、及び最大使用帯域を例に説明したが、ポリシーは、例えば、全ての計算機１の消費電力の閾値であってもよい。この場合、全ての計算機１の消費電力が閾値以上となるとポリシーを満たさないと判定してもよい。 The policy includes redundancy, minimum used bandwidth, and maximum used bandwidth. The communication path from each computer 1 satisfies the redundancy, minimum used bandwidth, and maximum used bandwidth, and the conditions requested by the user. Can be met. In this embodiment, the redundancy, the minimum used bandwidth, and the maximum used bandwidth have been described as an example of the policy. However, the policy may be, for example, a threshold value of power consumption of all the computers 1. In this case, it may be determined that the policy is not satisfied when the power consumption of all the computers 1 is equal to or greater than the threshold value.
　以上、外部接続ポリシーテーブル９２２が更新される場合にポリシー判定処理が実行される例について説明したが、ポリシー判定処理が実行されるタイミングはこれに限定されない。ポリシー判定処理は、例えば、計算機１の故障が検出された場合（図１３参照）、及び計算機１に電源の供給を開始する場合（図１４参照）等に実行されてもよい。 As described above, the example in which the policy determination process is executed when the external connection policy table 922 is updated has been described, but the timing at which the policy determination process is executed is not limited to this. The policy determination process may be executed, for example, when a failure of the computer 1 is detected (see FIG. 13) or when supply of power to the computer 1 is started (see FIG. 14).
　図１３は、実施例１の故障検出処理のフローチャートである。 FIG. 13 is a flowchart of the failure detection process according to the first embodiment.
　まず、制御装置５は、計算機１の故障を検出し、計算機状態テーブル５２１及び接続状態テーブル５２３を更新する（Ｓ５０１）。制御装置５は、所定周期で応答要求を計算機１に送信し、応答要求を送信してから所定時間経過しても応答を受信しない計算機１がある場合、当該計算機１の故障を検出してもよい。また、計算機１が自身の故障を検出した場合、故障通知を制御装置５に送信し、制御装置５は故障通知を受信することによって、計算機１の故障を検出してもよい。 First, the control device 5 detects a failure of the computer 1 and updates the computer state table 521 and the connection state table 523 (S501). The control device 5 transmits a response request to the computer 1 at a predetermined cycle, and when there is a computer 1 that does not receive a response even after a predetermined time has elapsed after transmitting the response request, even if a failure of the computer 1 is detected Good. Further, when the computer 1 detects its own failure, the failure notification of the computer 1 may be detected by transmitting a failure notification to the control device 5 and receiving the failure notification.
　また、計算機状態テーブル５２１の更新処理では、制御装置５は、計算機状態テーブル５２１の計算機５２１１に故障を検出した計算機１の識別情報が登録されたレコードの電源状態５２１２に「ＯＦＦ」を登録し、利用可能性５２１３に利用不可を登録する。また、接続状態テーブル５２３の更新処理では、制御装置５は、接続状態テーブル５２３のポイント５２３１に故障を検出した計算機１の識別情報が登録されたレコードを削除し、接続先カラム群５２３２に登録された故障を検出した計算機１の識別情報を削除する。 In the update process of the computer state table 521, the control device 5 registers “OFF” in the power state 5212 of the record in which the identification information of the computer 1 that detected the failure is registered in the computer 5211 of the computer state table 521. Unusable is registered in the availability 5213. Further, in the update process of the connection state table 523, the control device 5 deletes the record in which the identification information of the computer 1 that detected the failure is registered at the point 5231 of the connection state table 523 and is registered in the connection destination column group 5232. The identification information of the computer 1 that detected the failure is deleted.
　次に、制御装置５は、故障を検出した計算機１の識別情報を含む故障検出通知を管理装置９に送信する（Ｓ５０２）。 Next, the control device 5 transmits a failure detection notification including identification information of the computer 1 that has detected the failure to the management device 9 (S502).
　管理装置９は、故障検出通知を受信した場合、図１０に示すポリシー判定処理を実行する（Ｓ５０３）。 When the management device 9 receives the failure detection notification, the management device 9 executes the policy determination process shown in FIG. 10 (S503).
　次に、管理装置９は、ポリシー判定処理の結果に基づいて内部ネットワークの通信可能な経路がポリシーを満たすか否かを判定する（Ｓ５０４）。Ｓ５０４の処理で内部ネットワークの通信可能な経路がポリシーを満たすと判定された場合、管理装置９は、計算機１が故障した旨をユーザに報知し（Ｓ５０５）、処理を終了する。ユーザへの報知の例としては、管理装置９は、計算機１が故障した旨を図示しないディスプレイ等に表示してもよい。 Next, the management device 9 determines whether or not the communicable route of the internal network satisfies the policy based on the result of the policy determination process (S504). When it is determined in S504 that the communicable path of the internal network satisfies the policy, the management device 9 notifies the user that the computer 1 has failed (S505), and ends the process. As an example of notification to the user, the management device 9 may display on the display (not shown) that the computer 1 has failed.
　一方、Ｓ５０４の処理で内部ネットワークの通信可能な経路がポリシーを満たしていないと判定された場合、内部ネットワークの通信可能な経路が更新後の外部接続ポリシーテーブル９２２のポリシーを満たすことができないので、管理装置９は、内部ネットワークの通信可能な経路がポリシーを満たしていない旨をユーザに報知し（Ｓ５０６）、Ｓ５０５の処理に進み、計算機１が故障した旨をユーザに報知して処理を終了する。 On the other hand, if it is determined in S504 that the internal network communicable route does not satisfy the policy, the internal network communicable route cannot satisfy the updated external connection policy table 922 policy. The management device 9 informs the user that the communicable route of the internal network does not satisfy the policy (S506), proceeds to the processing of S505, informs the user that the computer 1 has failed, and ends the processing. .
　以上によって、管理装置９は、計算機１が故障した場合にポリシー判定処理を実行するので、計算機１が故障したことによって内部ネットワークの通信可能な経路がポリシーを満たさなくなっても、新たな計算機１に電源を供給することによって、内部ネットワークの通信可能な経路がポリシーを満たすようにすることができる。なお、ポリシー判定処理を実行しても、内部ネットワークの通信可能な経路が満たさない場合には、管理装置９はその旨をユーザに報知できる。 As described above, since the management device 9 executes the policy determination process when the computer 1 fails, even if the communicable route of the internal network does not satisfy the policy due to the failure of the computer 1, the management device 9 By supplying power, a communicable route in the internal network can satisfy the policy. Even if the policy determination process is executed, if the communicable route of the internal network is not satisfied, the management device 9 can notify the user to that effect.
　図１４は、実施例１の計算機起動処理のフローチャートである。 FIG. 14 is a flowchart of computer activation processing according to the first embodiment.
　まず、管理装置９は、ユーザからの計算機１の起動要求を受け付ける（Ｓ６０１）。当該起動要求は、ユーザが電源の供給の開始を所望する計算機１の識別情報を含む。 First, the management device 9 accepts a startup request for the computer 1 from the user (S601). The activation request includes identification information of the computer 1 that the user desires to start supplying power.
　次に、管理装置９は、起動要求を受け付けた計算機１に電源を供給するよう制御装置５に指示する（Ｓ６０２）。当該指示は、電源の供給を開始する計算機１の識別情報を含む。制御装置５は、管理装置９から指示を受け付けた場合、電源の供給を開始する計算機１に電源を供給させ、計算機状態テーブル５２１及び接続状態テーブル５２３を更新する。制御装置５によるこれらのテーブルの更新処理の具体的な説明は、図１０に示すポリシー判定処理のＳ２０９の処理と同じであるので、説明を省略する。制御装置５は、計算機１に電源の供給を開始させると、応答を管理装置９に送信する。 Next, the management device 9 instructs the control device 5 to supply power to the computer 1 that has received the activation request (S602). The instruction includes identification information of the computer 1 that starts supplying power. When the control device 5 receives an instruction from the management device 9, the control device 5 supplies power to the computer 1 that starts supplying power, and updates the computer state table 521 and the connection state table 523. The specific description of the update process of these tables by the control device 5 is the same as the process of S209 of the policy determination process shown in FIG. When the control device 5 causes the computer 1 to start supplying power, the control device 5 transmits a response to the management device 9.
　管理装置９は、制御装置５から応答を受信した場合、図１０に示すポリシー判定処理を実行する（Ｓ６０３）。 When the management device 9 receives a response from the control device 5, the management device 9 executes the policy determination process shown in FIG. 10 (S603).
　次に、管理装置９は、ポリシー判定処理の結果に基づいて内部ネットワークの通信可能な経路がポリシーを満たすか否かを判定する（Ｓ６０４）。Ｓ６０４の処理で内部ネットワークの通信可能な経路がポリシーを満たすと判定された場合、管理装置９は、起動要求で指定された計算機１に電源の供給を開始した旨をユーザに報知し（Ｓ６０５）、処理を終了する。ユーザへの報知の例としては、管理装置９は、計算機１が故障した旨を図示しない表示装置等に表示してもよい。 Next, the management device 9 determines whether or not the communicable route of the internal network satisfies the policy based on the result of the policy determination process (S604). If it is determined in S604 that the communicable route of the internal network satisfies the policy, the management device 9 notifies the user that the supply of power to the computer 1 specified by the activation request has been started (S605). The process is terminated. As an example of notification to the user, the management device 9 may display on the display device (not shown) that the computer 1 has failed.
　一方、Ｓ６０４の処理で内部ネットワークの通信可能な経路がポリシーを満たしていないと判定された場合、内部ネットワークの通信可能な経路が更新後の外部接続ポリシーテーブル９２２のポリシーを満たすことができないので、管理装置９は、Ｓ６０２の処理で制御装置５に電源を供給させた計算機１の電源の供給を停止するよう制御装置５に指示する（Ｓ６０６）。そして、管理装置９は、Ｓ６０５の処理に進み、起動要求で指定された計算機１に電源を供給できない旨をユーザに報知し、処理を終了する。なお、制御装置５は、管理装置９から指示を受け付けた場合、当該計算機１の電源の供給を停止し、当該計算機１への電源の供給時に更新した計算機状態テーブル５２１及び接続状態テーブル５２３を元に戻す。 On the other hand, if it is determined in step S604 that the internal network communicable route does not satisfy the policy, the internal network communicable route cannot satisfy the updated external connection policy table 922 policy. The management device 9 instructs the control device 5 to stop the power supply of the computer 1 that has supplied power to the control device 5 in the process of S602 (S606). Then, the management apparatus 9 proceeds to the process of S605, notifies the user that power cannot be supplied to the computer 1 specified by the activation request, and ends the process. When the control device 5 receives an instruction from the management device 9, the control device 5 stops the power supply of the computer 1, and the computer state table 521 and the connection state table 523 updated when the power supply to the computer 1 is supplied. Return to.
　以上によって、管理装置９は、指定された計算機１に電源が供給される場合にポリシー判定処理を実行するので、指定された計算機１に電源が供給されることによって内部ネットワークの通信可能な経路がポリシーを満たさなくなっても、新たな計算機１に電源を供給することによって、内部ネットワークの通信可能な経路がポリシーを満たすようにすることができる。なお、ポリシー判定処理を実行しても、内部ネットワークの通信可能な経路が満たさない場合には、管理装置９は指定された計算機１に電源を供給せず、その旨をユーザに報知できる。 As described above, the management device 9 executes the policy determination process when power is supplied to the designated computer 1, so that a path through which the internal network can communicate by supplying power to the designated computer 1 is determined. Even if the policy is not satisfied, the communication path of the internal network can satisfy the policy by supplying power to the new computer 1. Even if the policy determination process is executed, if the communicable path of the internal network is not satisfied, the management device 9 can notify the user of the fact without supplying power to the designated computer 1.
　図１５は、実施例１の終了時対応処理のフローチャートである。 FIG. 15 is a flowchart of end-time response processing in the first embodiment.
　終了時対応処理は、ある計算機１への電源の供給の停止が指示された場合、当該計算機１の終了後の内部ネットワークの通信可能な経路がポリシーを満たさない場合、管理装置９は、当該計算機１への電源の供給を継続する処理である。なお、図１５に示す処理のうち、図１０に示すポリシー判定処理と同じ処理は、同じ符号を付与し、説明を省略する。 In the case of termination processing, when an instruction to stop the supply of power to a certain computer 1 is given, if the communicable path of the internal network after termination of the computer 1 does not satisfy the policy, the management device 9 1 is a process of continuing the supply of power to 1. Of the processes shown in FIG. 15, the same processes as those in the policy determination process shown in FIG.
　まず、管理装置９は、ユーザからある計算機１の終了要求を受け付ける（Ｓ７０１）。なお、終了要求は、ユーザが終了を所望する計算機１（終了予定の計算機１）の識別情報を含む。 First, the management device 9 receives a request for termination of a certain computer 1 from the user (S701). The termination request includes identification information of the computer 1 (the computer 1 scheduled to be terminated) that the user desires to terminate.
　次に、管理装置９は、Ｓ２０１の処理で、制御装置５の記憶部５２から計算機状態テーブル５２１及び接続状態テーブル５２３を取得し、取得した計算機状態テーブル５２１及び接続状態テーブル５２３に基づいて外部経路状態テーブル９２１を生成する。 Next, the management device 9 acquires the computer state table 521 and the connection state table 523 from the storage unit 52 of the control device 5 in the process of S201, and based on the acquired computer state table 521 and connection state table 523, the external path A state table 921 is generated.
　そして、管理装置９は、終了予定の計算機１の電源の供給が停止した場合の内部ネットワークの通信可能な経路を示すように、Ｓ２０１の処理で生成した外部経路状態テーブル９２１を更新する（Ｓ７０２）。具体的には、管理装置９は、外部経路状態テーブル９２１の計算機９２１１に終了予定の計算機１の識別情報が登録されたレコードを削除する。また、管理装置９は、外部経路状態テーブル９２１の経路カラム群９２１２から終了予定の計算機１の識別情報を削除する。 Then, the management device 9 updates the external route state table 921 generated in the processing of S201 so as to indicate the communicable route of the internal network when the supply of power to the computer 1 scheduled to end is stopped (S702). . Specifically, the management apparatus 9 deletes the record in which the identification information of the computer 1 scheduled to be terminated is registered in the computer 9211 of the external route state table 921. In addition, the management device 9 deletes the identification information of the computer 1 scheduled to end from the route column group 9212 of the external route state table 921.
　次に、管理装置９は、Ｓ７０２の処理で更新された外部経路状態テーブル９２１の計算機９２１１に登録された計算機１の識別情報から処理対象の計算機１の識別情報を選択し、Ｓ７０４の処理に進む（Ｓ７０３）。すなわち、終了予定の計算機１以外の電源が供給されている計算機１から処理対象の計算機１が選択される。 Next, the management apparatus 9 selects the identification information of the computer 1 to be processed from the identification information of the computer 1 registered in the computer 9211 of the external path state table 921 updated in the processing of S702, and proceeds to the processing of S704. (S703). That is, the processing target computer 1 is selected from the computers 1 to which power other than the computer 1 scheduled to be terminated is supplied.
　次に、管理装置９は、Ｓ７０２で更新された外部経路状態テーブル９２１を参照し、処理対象計算機ポリシー判定処理を実行し（Ｓ７０４）、Ｓ２０４の処理に進む。 Next, the management apparatus 9 refers to the external path state table 921 updated in S702, executes a processing target computer policy determination process (S704), and proceeds to the process of S204.
　Ｓ２０４の処理では、管理装置９は、Ｓ７０４の処理の判定結果が、処理対象の計算機１がポリシーを満たすか否かを判定する。 In the process of S204, the management apparatus 9 determines whether the determination result of the process of S704 satisfies the processing target computer 1 satisfying the policy.
　Ｓ２０４の処理で処理対象の計算機１がポリシーを満たさないと判定された場合、Ｓ２０６の処理に進む。Ｓ２０６の処理では、管理装置９は、外部接続ポリシーテーブル９２２の計算機９２２１に処理対象の計算機１の識別情報が登録されたレコードの起動ポリシー９２２５に他の計算機を起動する旨が登録されているか否かを判定する。 When it is determined in the process of S204 that the processing target computer 1 does not satisfy the policy, the process proceeds to S206. In the process of S206, the management apparatus 9 registers whether or not to start another computer in the activation policy 9225 of the record in which the identification information of the computer 1 to be processed is registered in the computer 9221 of the external connection policy table 922. Determine whether.
　Ｓ２０６の処理で、外部接続ポリシーテーブル９２２の計算機９２２１に処理対象の計算機１の識別情報が登録されたレコードの起動ポリシー９２２５に他の計算機を起動する旨が登録されていると判定された場合、管理装置９は、終了予定の計算機１の電源の供給を遮断するよう制御装置５に指示せず、終了予定の計算機１の電源の供給を継続し（Ｓ７０７）、内部ネットワークの通信可能な経路がポリシーを満たさなくなるため、終了予定の計算機１を終了させなかった旨をユーザに報知し（Ｓ７０６）、処理を終了する。 When it is determined in the process of S206 that activation of another computer is registered in the activation policy 9225 of the record in which the identification information of the computer 1 to be processed is registered in the computer 9221 of the external connection policy table 922, The management device 9 does not instruct the control device 5 to cut off the power supply of the computer 1 scheduled to be terminated, continues the power supply of the computer 1 scheduled to be terminated (S707), and there is a communication path on the internal network. Since the policy is not satisfied, the user is notified that the scheduled computer 1 has not been terminated (S706), and the process is terminated.
　ここで、処理対象の計算機１がポリシーを満たさず、他の計算機の起動を許可されている場合に終了予定の計算機１を終了してしまうと、何らかのタイミングでポリシー判定処理が実行されたときに、再度当該処理対象の計算機１がポリシーを満たさないと判定され、終了予定の計算機１が起動されてしまう。このため、本実施例では、処理対象の計算機１がポリシーを満たさず、他の計算機の起動を許可されている場合には、管理装置９は、終了予定の計算機１の電源の供給を停止せず、電源の供給を継続する。しかしながら、Ｓ２０４の処理で、処理対象の計算機１がポリシーを満たさないと判定された場合、Ｓ２０６の処理を実行せずに、Ｓ７０７の処理に進んでもよい。 Here, when the computer 1 to be processed does not satisfy the policy and activation of another computer is permitted, if the computer 1 scheduled to end is terminated, the policy determination process is executed at some timing. Again, it is determined that the processing target computer 1 does not satisfy the policy, and the computer 1 scheduled to end is activated. For this reason, in the present embodiment, when the computer 1 to be processed does not satisfy the policy and the activation of another computer is permitted, the management device 9 stops the power supply of the computer 1 scheduled to be terminated. Continue supplying power. However, if it is determined in S204 that the processing target computer 1 does not satisfy the policy, the process may proceed to S707 without executing S206.
　一方、Ｓ２０６の処理で、外部接続ポリシーテーブル９２２の計算機９２２１に処理対象の計算機１の識別情報が登録されたレコードの起動ポリシー９２２５に他の計算機を起動する旨が登録されていないと判定された場合、又は、Ｓ２０４の処理で処理対象の計算機１がポリシーを満たすと判定された場合、Ｓ７０３の処理に戻り、管理装置９は、他の計算機１を処理対象の計算機１に選択し、Ｓ７０４の処理に進む。管理装置９は、Ｓ７０２の処理で更新した外部経路状態テーブル９２１の計算機９２１１に登録された全ての計算機１の識別情報によって識別される計算機１にＳ７０３、Ｓ７０４、及びＳ２０４の処理を繰り返す。 On the other hand, in the process of S206, it is determined that activation of another computer is not registered in the activation policy 9225 of the record in which the identification information of the computer 1 to be processed is registered in the computer 9221 of the external connection policy table 922. If it is determined in step S204 that the processing target computer 1 satisfies the policy, the process returns to step S703, and the management apparatus 9 selects another computer 1 as the processing target computer 1, and the processing in step S704 is performed. Proceed to processing. The management apparatus 9 repeats the processes of S703, S704, and S204 for the computer 1 identified by the identification information of all the computers 1 registered in the computer 9211 of the external path state table 921 updated in the process of S702.
　そして、Ｓ７０２の処理で更新した外部経路状態テーブル９２１の計算機９２１１に登録された全ての計算機１の識別情報にＳ７０３、Ｓ７０４、及びＳ２０４が実行された場合、管理装置９は、終了予定の計算機１の電源の供給を遮断するよう制御装置５に指示する（Ｓ７０５）。制御装置５は、管理装置９からの指示を受け付けた場合、当該計算機１の電源の供給を停止し、計算機状態テーブル５２１及び接続状態テーブル５２３を更新する。計算機状態テーブル５２１の更新処理では、制御装置５は、計算機状態テーブル５２１の計算機５２１１に終了予定の計算機１の識別情報が登録されたレコードの電源状態５２１２に「ＯＦＦ」を登録する。また、接続状態テーブル５２３の更新処理では、制御装置５は、接続状態テーブル５２３のポイント５２３１に終了予定の計算機１の識別情報が登録されたレコードを削除し、接続先カラム群５２３２に登録された終了予定の計算機１の識別情報を削除する。 When S703, S704, and S204 are executed on the identification information of all the computers 1 registered in the computer 9211 of the external path state table 921 updated in the processing of S702, the management device 9 determines that the computer 1 scheduled to be terminated. The control device 5 is instructed to shut off the supply of power (S705). When the control device 5 receives an instruction from the management device 9, the control device 5 stops the power supply of the computer 1 and updates the computer state table 521 and the connection state table 523. In the update process of the computer state table 521, the control device 5 registers “OFF” in the power state 5212 of the record in which the identification information of the computer 1 scheduled to be completed is registered in the computer 5211 of the computer state table 521. Further, in the update process of the connection state table 523, the control device 5 deletes the record in which the identification information of the computer 1 scheduled to end at the point 5231 of the connection state table 523 is registered, and is registered in the connection destination column group 5232. The identification information of the computer 1 scheduled to be terminated is deleted.
　次に、管理装置９は、Ｓ７０６の処理に進み、計算機１を終了させたことをユーザに報知し、処理を終了する。この場合、Ｓ２０４の処理でポリシーを満たさないと判定された計算機１が存在する場合、管理装置９は、終了予定の計算機１を終了させたがポリシーを満たさない計算機１が存在する旨もユーザに合わせて報知する。 Next, the management apparatus 9 proceeds to the process of S706, notifies the user that the computer 1 has been terminated, and ends the process. In this case, when there is a computer 1 that is determined not to satisfy the policy in the process of S204, the management apparatus 9 also terminates the computer 1 that is scheduled to be terminated, but also indicates that there is a computer 1 that does not satisfy the policy. Also notify.
　以上によって、ある計算機１への電源の供給の停止が指示された場合、当該計算機１の終了後の内部ネットワークの通信可能な経路がポリシーを満たさない場合、管理装置９は、当該計算機１への電源の供給を継続することができる。 As described above, when an instruction to stop the supply of power to a certain computer 1 is given, if the communicable route of the internal network after the termination of the computer 1 does not satisfy the policy, the management device 9 The power supply can be continued.
　以下、実施例２について図１６を用いて説明する。 Hereinafter, Example 2 will be described with reference to FIG.
　実施例１では、管理装置９は、一つの計算機グループ６の計算機１の電源状態を制御したが、本実施例では、さらに大規模なネットワーク構成に本発明を適用するため、複数の計算機グループの計算機１の電源状態を制御する。 In the first embodiment, the management apparatus 9 controls the power supply state of the computers 1 of one computer group 6. However, in this embodiment, the present invention is applied to a larger network configuration. The power state of the computer 1 is controlled.
　図１６は、実施例２の計算機システムの説明図である。なお、図１６に示す構成のうち実施例１の図１と同じ構成は、同じ符号を付与し、説明を省略する。 FIG. 16 is an explanatory diagram of the computer system according to the second embodiment. In addition, the same structure as FIG. 1 of Example 1 among the structures shown in FIG. 16 gives the same code | symbol, and abbreviate | omits description.
　本実施例の計算機システムは、計算機グループ６Ａ、計算機グループ６Ｂ、ネットワークスイッチ８、管理装置９、及び全体制御装置１０を備える。なお、図１６では、計算機１、制御装置５、ネットワークスイッチ８、管理装置９の構成の図示は省略したが、これらは図１と同じ構成である。 The computer system of this embodiment includes a computer group 6A, a computer group 6B, a network switch 8, a management device 9, and an overall control device 10. In FIG. 16, the configurations of the computer 1, the control device 5, the network switch 8, and the management device 9 are omitted, but these are the same as those in FIG. 1.
　ここで、計算機グループ６Ａは制御装置５Ａによって電源が制御される計算機１であり、計算機グループ６Ｂは制御装置５Ｂによって電源が制御される計算機１である。なお、計算機グループ６Ａ及び６Ｂを総称する場合、計算機グループ６と記載する。 Here, the computer group 6A is the computer 1 whose power is controlled by the control device 5A, and the computer group 6B is the computer 1 whose power is controlled by the control device 5B. The computer groups 6A and 6B are collectively referred to as a computer group 6.
　計算機グループ６Ａは、図１に示す計算機グループ６と同じ構成である。計算機グループ６Ｂは、計算機Ｎ５（１Ｅ）～計算機Ｎ８（１Ｈ）、ポートＰ３（３Ｃ）、及びポートＰ４（４Ｃ）によって構築される内部ネットワークを含む。ポートＰ３（３Ｃ）及びポートＰ４（４Ｃ）はネットワークスイッチ８に接続され、ネットワークスイッチ８を介して外部のネットワーク７に接続される。 The computer group 6A has the same configuration as the computer group 6 shown in FIG. The computer group 6B includes an internal network constructed by the computers N5 (1E) to N8 (1H), the port P3 (3C), and the port P4 (4C). The port P3 (3C) and the port P4 (4C) are connected to the network switch 8, and are connected to the external network 7 via the network switch 8.
　また、計算機グループ６Ｂ内での各計算機１及びポート３の接続形態は、計算機グループ６Ａ内での各計算機１及びポート３の接続形態と同一にしたが、これに限定されず、計算機グループ間で異なっていてもよい。また、計算機グループ６Ａ及び６Ｂ内の計算機１の数は、これに限定されず、各計算機グループ６Ａ及び６Ｂが複数の計算機１を有していればよい。 Further, the connection form of each computer 1 and port 3 in the computer group 6B is the same as the connection form of each computer 1 and port 3 in the computer group 6A. However, the connection form is not limited to this. May be different. The number of computers 1 in the computer groups 6A and 6B is not limited to this, and each computer group 6A and 6B only needs to have a plurality of computers 1.
　制御装置５Ａ及び５Ｂ（以下、総称する場合、制御装置５と記載）は全体制御装置１０に接続され、全体制御装置１０は、各計算機グループ６の各制御装置５を介して、各計算機グループ６の各計算機１の電源を制御する。 The control devices 5A and 5B (hereinafter collectively referred to as the control device 5) are connected to the overall control device 10, and the overall control device 10 is connected to each computer group 6 via each control device 5 of each computer group 6. The power source of each computer 1 is controlled.
　各制御装置５は、それぞれ、計算機状態テーブル５２１、接続可能テーブル５２２、及び接続状態テーブル５２３を保持する。 Each control device 5 holds a computer state table 521, a connectable table 522, and a connection state table 523, respectively.
　また、管理装置９は、計算機グループ６ごとに、外部経路状態テーブル９２１、外部接続ポリシーテーブル９２２、及び利用可能経路テーブル９２３を保持する。 Also, the management device 9 holds an external route state table 921, an external connection policy table 922, and an available route table 923 for each computer group 6.
　なお、図９～図１５に示す処理は、実施例１と同様であるので、説明を省略する。 Note that the processes shown in FIGS. 9 to 15 are the same as those in the first embodiment, and thus description thereof is omitted.
　なお、本発明は上記した実施例に限定されるものではなく、様々な変形例が含まれる。例えば、上記した実施例は本発明を分かりやすく説明するために詳細に説明したものであり、必ずしも説明した全ての構成を備えるものに限定されるものではない。また、ある実施例の構成の一部を他の実施例の構成に置き換えることも可能であり、また、ある実施例の構成に他の実施例の構成を加えることも可能である。また、各実施例の構成の一部について、他の構成の追加・削除・置換をすることが可能である。 In addition, this invention is not limited to the above-mentioned Example, Various modifications are included. For example, the above-described embodiments have been described in detail for easy understanding of the present invention, and are not necessarily limited to those having all the configurations described. Also, a part of the configuration of a certain embodiment can be replaced with the configuration of another embodiment, and the configuration of another embodiment can be added to the configuration of a certain embodiment. Further, it is possible to add, delete, and replace other configurations for a part of the configuration of each embodiment.
　また、上記の各構成、機能、処理部、処理手段等は、それらの一部又は全部を、例えば集積回路で設計する等によりハードウェアで実現してもよい。また、上記の各構成、機能等は、プロセッサがそれぞれの機能を実現するプログラムを解釈し、実行することによりソフトウェアで実現してもよい。各機能を実現するプログラム、テーブル、ファイル等の情報は、メモリや、ハードディスク、ＳＳＤ（Solid State Drive）等の記録装置、または、ＩＣカード、ＳＤカード、ＤＶＤ等の記録媒体に置くことができる。 In addition, each of the above-described configurations, functions, processing units, processing means, and the like may be realized by hardware by designing a part or all of them with, for example, an integrated circuit. Each of the above-described configurations, functions, and the like may be realized by software by interpreting and executing a program that realizes each function by the processor. Information such as programs, tables, and files for realizing each function can be stored in a recording device such as a memory, a hard disk, an SSD (Solid State Drive), or a recording medium such as an IC card, an SD card, or a DVD.
　また、制御線や情報線は説明上必要と考えられるものを示しており、製品上必ずしも全ての制御線や情報線を示しているとは限らない。実際には殆ど全ての構成が相互に接続されていると考えてもよい。 Also, the control lines and information lines indicate what is considered necessary for the explanation, and not all the control lines and information lines on the product are necessarily shown. Actually, it may be considered that almost all the components are connected to each other.

Claims (15)

  1. 　外部ネットワークに接続される内部ネットワークを構築する複数の計算機を管理する管理装置における前記計算機の制御方法であって、
    　電源が供給されている計算機同士の接続は通信可能であり、
    　電源が供給されていない計算機と当該計算機に接続された他の計算機との間の接続は通信不能であり、
    　前記管理装置は、
    　前記通信可能な接続のみを経由し、前記外部ネットワークに至る通信可能な経路を管理する通信可能経路情報と、
    　前記通信可能か前記通信不能かにかかわらずに前記計算機間の接続を経由し、前記外部ネットワークに至る利用可能な経路を管理する利用可能経路情報と、を保持し、
    　前記方法は、
    　前記管理装置が、前記通信可能経路情報を参照し、前記電源が供給されている各計算機から前記外部ネットワークに至る通信可能な経路が所定の条件を満たすか否かを判定し、
    　前記通信可能な経路が所定の条件を満たさないと判定された場合、前記管理装置が、前記利用可能経路情報を参照し、前記所定の条件を満たさない計算機から前記外部ネットワークに至る利用可能な経路から現在通信可能な経路以外の経路を特定し、
    　前記管理装置が、前記特定した経路上の電源が供給されてない計算機への電源の供給を指示することを特徴とする制御方法。     A method for controlling a computer in a management device that manages a plurality of computers that construct an internal network connected to an external network,
    Connections between computers that are supplied with power are communicable,
    The connection between a computer that is not supplied with power and another computer connected to the computer is not possible.
    The management device
    Communicable route information for managing a communicable route to the external network only through the communicable connection;
    Regardless of whether the communication is possible or not possible, the available route information for managing the available route to the external network via the connection between the computers is held.
    The method
    The management device refers to the communicable path information, determines whether a communicable path from each computer to which the power is supplied to the external network satisfies a predetermined condition,
    When it is determined that the communicable path does not satisfy a predetermined condition, the management apparatus refers to the usable path information and can be used from the computer that does not satisfy the predetermined condition to the external network. Identify a route other than the currently communicable route from
    A control method, wherein the management device instructs supply of power to a computer to which power on the specified path is not supplied.
  2. 　請求項１に記載の制御方法であって、
    　前記内部ネットワークはポート及びネットワークスイッチを介して前記外部ネットワークに接続され、
    　前記ポートは前記計算機に接続され、
    　前記ネットワークスイッチは、
    　前記内部ネットワークを構築する計算機と当該計算機宛のデータを出力するポートとを対応付けるスイッチ情報を保持し、
    　前記外部ネットワークからデータを受信した場合、前記スイッチ情報を参照し、前記受信したデータの宛先となる計算機に対応付けられたポートを特定し、
    　前記受信したデータを前記特定したポートから前記内部ネットワークに送信し、
    　前記方法は、
    　前記電源が供給されていない計算機への電源の供給を指示した場合、前記管理装置が、前記計算機に電源が供給されることによって通信可能となる接続を経由し、新たに通信可能となる経路を特定し、
    　前記管理装置が、前記特定した通信可能な経路上の計算機が新たに通信可能となるポートを特定し、
    　前記管理装置が、前記特定した計算機とポートとの関係を前記スイッチ情報に登録するよう前記ネットワークスイッチに指示することを特徴とする制御方法。     The control method according to claim 1, comprising:
    The internal network is connected to the external network via a port and a network switch;
    The port is connected to the computer;
    The network switch is
    Holds switch information that associates the computer that constructs the internal network with the port that outputs the data addressed to the computer,
    When receiving data from the external network, refer to the switch information, specify the port associated with the computer that is the destination of the received data,
    Transmitting the received data from the identified port to the internal network;
    The method
    When instructing the supply of power to a computer to which the power is not supplied, the management device uses a connection that enables communication when power is supplied to the computer to establish a new communication-enabled path. Identify,
    The management device identifies a port through which a computer on the identified communicable path can newly communicate,
    The control method, wherein the management apparatus instructs the network switch to register the relationship between the specified computer and port in the switch information.
  3. 　請求項１に記載の制御方法であって、
    　前記管理装置が、前記通信可能な経路が所定の条件を満たさないと判定された場合、前記内部ネットワークを構築する全ての計算機の接続関係に基づいて、前記利用可能な経路を特定することによって、前記利用可能経路情報を生成し、
    　前記管理装置が、前記利用可能経路情報を参照し、前記所定の条件を満たさない計算機から前記外部ネットワークに至る利用可能な経路から現在通信可能な経路以外の経路を特定することを特徴とする制御方法。     The control method according to claim 1, comprising:
    When the management device determines that the communicable route does not satisfy a predetermined condition, by specifying the available route based on the connection relationship of all the computers that construct the internal network, Generating the available route information;
    The control characterized in that the management device refers to the available route information and specifies a route other than a currently communicable route from available routes from a computer that does not satisfy the predetermined condition to the external network. Method.
  4. 　請求項１に記載の制御方法であって、
    　前記管理装置が、前記所定の条件を満たさない計算機から前記外部ネットワークに至る利用可能な経路から現在通信可能な経路以外の経路を特定できない場合、前記所定の条件を満たさない計算機から前記外部ネットワークに至る通信可能な経路が前記所定の条件を満たすことができない旨を管理者に報知することを特徴とする制御方法。     The control method according to claim 1, comprising:
    When the management device cannot identify a route other than the currently communicable route from the available route from the computer that does not satisfy the predetermined condition to the external network, the computer that does not satisfy the predetermined condition is transferred to the external network. A control method characterized by notifying an administrator that a reachable communication path cannot satisfy the predetermined condition.
  5. 　請求項１に記載の制御方法であって、
    　前記管理装置が、前記電源が供給されている各計算機から前記外部ネットワークに至る通信可能な経路の数が所定数未満である場合、及び前記電源が供給されている各計算機から前記外部ネットワークに至る通信可能な経路の帯域が所定の帯域を満たさない場合の少なくとも一方が成立した場合、前記通信可能な経路が前記所定の条件を満たさないと判定し、
    　前記通信可能な経路が前記所定の条件を満たさないと判定され、かつ、前記所定の条件を満たさない計算機が他の計算機への電源の供給が許可されている計算機である場合、前記管理装置が、前記利用可能経路情報を参照し、前記所定の条件を満たさない計算機から前記外部ネットワークに至る利用可能な経路から現在通信可能な経路以外の経路を特定することを特徴とする制御方法。     The control method according to claim 1, comprising:
    When the management apparatus has less than a predetermined number of communication paths from each computer to which the power is supplied to the external network, and from each computer to which the power is supplied to the external network If at least one of the cases where the bandwidth of the communicable route does not satisfy the predetermined bandwidth is determined, it is determined that the communicable route does not satisfy the predetermined condition;
    When it is determined that the communicable path does not satisfy the predetermined condition, and the computer that does not satisfy the predetermined condition is a computer that is permitted to supply power to another computer, the management device A control method is characterized in that, by referring to the available route information, a route other than a currently communicable route is identified from available routes from a computer that does not satisfy the predetermined condition to the external network.
  6. 　請求項１に記載の制御方法であって、
    　前記管理装置が、前記電源が供給されている計算機の電源の供給を停止する要求を受け付けた場合、前記電源の供給を停止する計算機の電源の供給を停止した場合の前記通信可能な経路を特定することによって、前記通信可能経路情報を更新し、
    　前記管理装置が、前記更新後の通信可能経路情報を参照し、前記電源の供給を停止する計算機以外の計算機から前記外部ネットワークに至る通信可能な経路が前記所定の条件を満たすか否かを判定し、
    　前記電源の供給を停止する計算機以外の計算機から前記外部ネットワークに至る通信可能な経路が前記所定の条件を満たさないと判定された場合、前記管理装置が、前記電源の供給を停止する計算機の電源の供給を停止せず、前記電源の供給の継続することを特徴とする制御方法。     The control method according to claim 1, comprising:
    When the management device receives a request to stop the power supply of the computer to which the power is supplied, the communication path when the power supply of the computer to stop the power supply is stopped is specified. To update the communicable route information,
    The management device refers to the updated communicable route information and determines whether a communicable route from a computer other than the computer that stops supplying power to the external network satisfies the predetermined condition. And
    When it is determined that a communicable path from a computer other than the computer that stops the power supply to the external network does not satisfy the predetermined condition, the management device supplies the power of the computer that stops the power supply The control method is characterized in that the supply of power is continued without stopping the supply of power.
  7. 　請求項６に記載の制御方法であって、
    　前記電源の供給を停止する計算機以外の計算機から前記外部ネットワークに至る通信可能な経路が前記所定の条件を満たすと判定された場合、前記管理装置が、前記電源の供給を停止する計算機への電源の供給の停止を指示することを特徴とする制御方法。     The control method according to claim 6, comprising:
    When it is determined that a communicable path from a computer other than the computer that stops supplying power to the external network satisfies the predetermined condition, the management device supplies power to the computer that stops supplying power The control method characterized by instruct | indicating the stop of supply.
  8. 　外部ネットワークに接続される内部ネットワークを構築する複数の計算機を管理し、前記計算機の電源状態を制御する管理装置であって、
    　電源が供給されている計算機同士の接続は通信可能であり、
    　電源が供給されていない計算機と当該計算機に接続された他の計算機との間の接続は通信不能であり、
    　前記管理装置は、
    　前記通信可能な接続のみを経由し、前記外部ネットワークに至る通信可能な経路を管理する通信可能経路情報と、
    　前記通信可能か前記通信不能かにかかわらずに前記計算機間の接続を経由し、前記外部ネットワークに至る利用可能な経路を管理する利用可能経路情報と、を保持し、
    　前記通信可能経路情報を参照し、前記電源が供給されている各計算機から前記外部ネットワークに至る通信可能な経路が所定の条件を満たすか否かを判定し、
    　前記通信可能な経路が所定の条件を満たさないと判定された場合、前記利用可能経路情報を参照し、前記所定の条件を満たさない計算機から前記外部ネットワークに至る利用可能な経路から現在通信可能な経路以外の経路を特定し、
    　前記特定した経路上の電源が供給されてない計算機への電源の供給を指示することを特徴とする管理装置。     A management device that manages a plurality of computers that construct an internal network connected to an external network and controls the power state of the computer,
    Connections between computers that are supplied with power are communicable,
    The connection between a computer that is not supplied with power and another computer connected to the computer is not possible.
    The management device
    Communicable route information for managing a communicable route to the external network only through the communicable connection;
    Regardless of whether the communication is possible or not possible, the available route information for managing the available route to the external network via the connection between the computers is held.
    Referencing the communicable route information, determining whether a communicable route from each computer to which the power is supplied to the external network satisfies a predetermined condition,
    If it is determined that the communicable route does not satisfy a predetermined condition, the available route information is referred to and communication is currently possible from an available route from a computer that does not satisfy the predetermined condition to the external network. Identify routes other than routes,
    A management apparatus for instructing power supply to a computer to which power on the specified path is not supplied.
  9. 　請求項８に記載の管理装置であって、
    　前記内部ネットワークはポート及びネットワークスイッチを介して前記外部ネットワークに接続され、
    　前記ポートは前記計算機に接続され、
    　前記ネットワークスイッチは、
    　前記内部ネットワークを構築する計算機と当該計算機宛のデータを出力するポートとを対応付けるスイッチ情報を保持し、
    　前記外部ネットワークからデータを受信した場合、前記スイッチ情報を参照し、前記受信したデータの宛先となる計算機に対応付けられたポートを特定し、
    　前記受信したデータを前記特定したポートから前記内部ネットワークに送信し、
    　前記管理装置は、
    　前記電源が供給されていない計算機への電源の供給を指示した場合、前記計算機に電源が供給されることによって通信可能となる接続を経由し、新たに通信可能となる経路を特定し、
    　前記特定した通信可能な経路上の計算機が新たに通信可能となるポートを特定し、
    　前記特定した計算機とポートとの関係を前記スイッチ情報に登録するよう前記ネットワークスイッチに指示することを特徴とする管理装置。     The management device according to claim 8,
    The internal network is connected to the external network via a port and a network switch;
    The port is connected to the computer;
    The network switch is
    Holds switch information that associates the computer that constructs the internal network with the port that outputs the data addressed to the computer,
    When receiving data from the external network, refer to the switch information, specify the port associated with the computer that is the destination of the received data,
    Transmitting the received data from the identified port to the internal network;
    The management device
    When instructing the supply of power to a computer that is not supplied with power, a connection that enables communication by supplying power to the computer is specified, and a path that can be newly communicated is specified.
    Identify a port on which the computer on the identified communicable path can newly communicate,
    A management apparatus that instructs the network switch to register the relationship between the specified computer and port in the switch information.
  10. 　請求項８に記載の管理装置であって、
    　記通信可能な経路が所定の条件を満たさないと判定された場合、前記内部ネットワークを構築する全ての計算機の接続関係に基づいて、前記利用可能な経路を特定することによって、前記利用可能経路情報を生成し、
    　前記利用可能経路情報を参照し、前記所定の条件を満たさない計算機から前記外部ネットワークに至る利用可能な経路から現在通信可能な経路以外の経路を特定することを特徴とする管理装置。     The management device according to claim 8,
    When it is determined that the communicable route does not satisfy a predetermined condition, the usable route information is determined by specifying the usable route based on the connection relation of all the computers constituting the internal network. Produces
    A management apparatus that refers to the available route information and identifies a route other than a currently communicable route from available routes from a computer that does not satisfy the predetermined condition to the external network.
  11. 　請求項８に記載の管理装置であって、
    　前記所定の条件を満たさない計算機から前記外部ネットワークに至る利用可能な経路から現在通信可能な経路以外の経路を特定できない場合、前記所定の条件を満たさない計算機から前記外部ネットワークに至る通信可能な経路が前記所定の条件を満たすことができない旨を管理者に報知することを特徴とする管理装置。     The management device according to claim 8,
    When a route other than the currently communicable route cannot be specified from the available routes from the computer that does not satisfy the predetermined condition to the external network, the communicable route from the computer that does not satisfy the predetermined condition to the external network A management device that notifies the administrator that the predetermined condition cannot be satisfied.
  12. 　請求項８に記載の管理装置であって、
    　前記電源が供給されている各計算機から前記外部ネットワークに至る通信可能な経路の数が所定数未満である場合、及び前記電源が供給されている各計算機から前記外部ネットワークに至る通信可能な経路の帯域が所定の帯域を満たさない場合の少なくとも一方が成立した場合、前記通信可能な経路が前記所定の条件を満たさないと判定し、
    　前記通信可能な経路が前記所定の条件を満たさないと判定され、かつ、前記所定の条件を満たさない計算機が他の計算機への電源の供給が許可されている計算機である場合、前記利用可能経路情報を参照し、前記所定の条件を満たさない計算機から前記外部ネットワークに至る利用可能な経路から現在通信可能な経路以外の経路を特定することを特徴とする管理装置。     The management device according to claim 8,
    When the number of communicable paths from each computer to which the power is supplied to the external network is less than a predetermined number, and a communicable path from each computer to which the power is supplied to the external network If at least one of the cases where the band does not satisfy the predetermined band is established, it is determined that the communicable route does not satisfy the predetermined condition;
    When it is determined that the communicable path does not satisfy the predetermined condition, and the computer that does not satisfy the predetermined condition is a computer that is permitted to supply power to another computer, the usable path A management apparatus that refers to information and identifies a route other than a currently communicable route from available routes from a computer that does not satisfy the predetermined condition to the external network.
  13. 　請求項８に記載の管理装置であって、
    　前記管理装置が、前記電源が供給されている計算機の電源の供給を停止する要求を受け付けた場合、前記管理装置が、前記電源の供給を停止する計算機の電源の供給を停止した場合の前記通信可能な経路を特定することによって、前記通信可能経路情報を更新し、
    　前記管理装置が、前記更新後の通信可能経路情報を参照し、前記電源の供給を停止する計算機以外の計算機から前記外部ネットワークに至る通信可能な経路が前記所定の条件を満たすか否かを判定し、
    　前記電源の供給を停止する計算機以外の計算機から前記外部ネットワークに至る通信可能な経路が前記所定の条件を満たさないと判定された場合、前記電源の供給を停止する計算機の電源の供給を停止せず、前記電源の供給の継続することを特徴とする管理装置。     The management device according to claim 8,
    When the management device receives a request to stop the power supply of the computer to which the power is supplied, the communication when the management device stops the power supply of the computer that stops the power supply Updating the communicable route information by specifying a possible route;
    The management device refers to the updated communicable route information and determines whether a communicable route from a computer other than the computer that stops supplying power to the external network satisfies the predetermined condition. And
    When it is determined that a communicable path from a computer other than the computer that stops the power supply to the external network does not satisfy the predetermined condition, stop the power supply of the computer that stops the power supply. The management apparatus characterized in that the supply of power is continued.
  14. 　請求項１３に記載の管理装置であって、
    　前記電源の供給を停止する計算機以外の計算機から前記外部ネットワークに至る通信可能な経路が前記所定の条件を満たすと判定された場合、前記電源の供給を停止する計算機への電源の供給の停止を指示することを特徴とする管理装置。     The management device according to claim 13,
    When it is determined that a communicable path from a computer other than the computer that stops the power supply to the external network satisfies the predetermined condition, the power supply to the computer that stops the power supply is stopped. A management device characterized by instructing.
  15. 　外部ネットワークに接続される内部ネットワークを構築する複数の計算機と、
    　前記複数の計算機を管理し、前記計算機の電源状態を制御する管理装置と、を備える計算機システムであって、
    　電源が供給されている計算機同士の接続は通信可能であり、
    　電源が供給されていない計算機と当該計算機に接続された他の計算機との間の接続は通信不能であり、
    　前記管理装置は、
    　前記通信可能な接続のみを経由し、前記外部ネットワークに至る通信可能な経路を管理する通信可能経路情報と、
    　前記通信可能か前記通信不能かにかかわらずに前記計算機間の接続を経由し、前記外部ネットワークに至る利用可能な経路を管理する利用可能経路情報と、を保持し、
    　前記通信可能経路情報を参照し、前記電源が供給されている各計算機から前記外部ネットワークに至る通信可能な経路が所定の条件を満たすか否かを判定し、
    　前記通信可能な経路が所定の条件を満たさないと判定された場合、前記利用可能経路情報を参照し、前記所定の条件を満たさない計算機から前記外部ネットワークに至る利用可能な経路から現在通信可能な経路以外の経路を特定し、
    　前記特定した経路上の電源が供給されてない計算機への電源の供給を指示し、
    　前記計算機は、前記管理計算機からの指示に基づいて、前記電源の供給の開始することを特徴とする計算機システム。     A plurality of computers that build an internal network connected to an external network;
    A management system that manages the plurality of computers and controls a power state of the computers,
    Connections between computers that are supplied with power are communicable,
    The connection between a computer that is not supplied with power and another computer connected to the computer is not possible.
    The management device
    Communicable route information for managing a communicable route to the external network only through the communicable connection;
    Regardless of whether the communication is possible or not possible, the available route information for managing the available route to the external network via the connection between the computers is held.
    Referencing the communicable route information, determining whether a communicable route from each computer to which the power is supplied to the external network satisfies a predetermined condition,
    If it is determined that the communicable route does not satisfy a predetermined condition, the available route information is referred to and communication is currently possible from an available route from a computer that does not satisfy the predetermined condition to the external network. Identify routes other than routes,
    Instructing the supply of power to a computer that is not supplied with power on the specified path,
    The computer system starts supplying the power based on an instruction from the management computer.
PCT/JP2014/057647 2014-03-20 2014-03-20 Computer control method, management apparatus, and computer system WO2015140973A1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/JP2014/057647 WO2015140973A1 (en) 2014-03-20 2014-03-20 Computer control method, management apparatus, and computer system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2014/057647 WO2015140973A1 (en) 2014-03-20 2014-03-20 Computer control method, management apparatus, and computer system

Publications (1)

Publication Number Publication Date
WO2015140973A1 true WO2015140973A1 (en) 2015-09-24

Family

ID=54143978

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2014/057647 WO2015140973A1 (en) 2014-03-20 2014-03-20 Computer control method, management apparatus, and computer system

Country Status (1)

Country Link
WO (1) WO2015140973A1 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPWO2020016920A1 (en) * 2018-07-17 2020-07-27 三菱電機株式会社 Monitor control screen creation support device

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2012164651A1 (en) * 2011-05-27 2012-12-06 株式会社日立製作所 Interface device, computer system, and computer control method
JP2013070200A (en) * 2011-09-22 2013-04-18 Fujitsu Ltd Communication device and path establishment method
WO2013145255A1 (en) * 2012-03-30 2013-10-03 富士通株式会社 Power supplying control device, relay node device, wired ad hoc network system, and power supplying control method

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2012164651A1 (en) * 2011-05-27 2012-12-06 株式会社日立製作所 Interface device, computer system, and computer control method
JP2013070200A (en) * 2011-09-22 2013-04-18 Fujitsu Ltd Communication device and path establishment method
WO2013145255A1 (en) * 2012-03-30 2013-10-03 富士通株式会社 Power supplying control device, relay node device, wired ad hoc network system, and power supplying control method

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPWO2020016920A1 (en) * 2018-07-17 2020-07-27 三菱電機株式会社 Monitor control screen creation support device

Similar Documents

Publication Publication Date Title
JP5637873B2 (en) HBA identifier takeover method for computer system and PCI card
US9178808B2 (en) Distributing functions in a distributed and embedded environment
CN111427827B (en) CPU and multi-CPU system management method
KR20090082242A (en) Transparent replacement of a system processor
TW201339969A (en) Management method and system for start servers in data center
JP2018506236A (en) Method, apparatus and system for determining VNF processing policy
JP2016053855A (en) Storage device, firmware update method, and firmware update program
US11405455B2 (en) Elastic scaling in a storage network environment
JP2005251188A (en) Redundant path control apparatus and redundant path control method
JP6053637B2 (en) Method for upgrading virtual host and network device
US20160103714A1 (en) System, method of controlling a system including a load balancer and a plurality of apparatuses, and apparatus
JP5282569B2 (en) Management device, management system, management method, and management program
US20200364073A1 (en) Management apparatus, host apparatus, management method, and program
US20100235549A1 (en) Computer and input/output control method
CN104219061B (en) Request the method and device of power consumption state variation
WO2015140973A1 (en) Computer control method, management apparatus, and computer system
JP6228318B2 (en) Computer and computer system
US9146849B2 (en) Apparatus and method for controlling power supply of control device that controls access to data
US10838479B2 (en) Information processing system, management device, and method of controlling information processing system
JP6200707B2 (en) Switch and control method
JP2013242739A (en) Load distribution system
JP2017054416A (en) Control apparatus, information processing system, and control program
US20180150336A1 (en) Management system and control method
JP2013168743A (en) Communication system, transfer device controller, and transfer device control method
WO2014045610A1 (en) Rule setting method and relay system

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 14886474

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 14886474

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: JP