WO2012120635A1 - Procédé de gestion d'ordinateur, dispositif de gestion et système informatique - Google Patents

Procédé de gestion d'ordinateur, dispositif de gestion et système informatique Download PDF

Info

Publication number
WO2012120635A1
WO2012120635A1 PCT/JP2011/055339 JP2011055339W WO2012120635A1 WO 2012120635 A1 WO2012120635 A1 WO 2012120635A1 JP 2011055339 W JP2011055339 W JP 2011055339W WO 2012120635 A1 WO2012120635 A1 WO 2012120635A1
Authority
WO
WIPO (PCT)
Prior art keywords
computer
management
information
operation information
room
Prior art date
Application number
PCT/JP2011/055339
Other languages
English (en)
Japanese (ja)
Inventor
水野　和彦
敬太郎 上原
勇太 澤
直也 服部
上村　哲也
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/JP2011/055339 priority Critical patent/WO2012120635A1/fr
Publication of WO2012120635A1 publication Critical patent/WO2012120635A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/30—Monitoring
    • G06F11/3058—Monitoring arrangements for monitoring environmental properties or parameters of the computing system or of the computing system component, e.g. monitoring of power, currents, temperature, humidity, position, vibrations

Definitions

  • the present invention relates to a technique for managing computers in a computer system.
  • the present invention relates to a technique for detecting computer movement based on computer operation information.
  • Japanese Patent Application Laid-Open No. 2006-48482 discloses a technique for estimating physical costs such as wiring required for movement and placement of devices. Is disclosed.
  • Japanese Patent Laid-Open No. 2006-53695 discloses a technique for reflecting the layout information of the construction person in charge who actually performed the construction in the layout information created by the designer.
  • a service for associating a logical resource such as a virtual server and a physical resource such as a blade server is being provided.
  • the location of the physical resource in the virtual environment has been changed due to equipment expansion due to performance shortage or resource shortage, equipment replacement due to equipment replacement, or equipment movement due to work content change, etc.
  • the physical resource installation location cannot be easily followed.
  • it is difficult to manage where the physical resource on which the virtual resource is mounted is actually installed. This is because manual operation management is the mainstream when performing layout management in line with the introduction and movement of equipment at the beginning of equipment introduction or when starting up a new business. This is because there is a possibility that there is a difference between the current layout information and the managed layout information due to the reuse of previously used information.
  • a management apparatus acquires operating information that is information indicating an operating status of a computer, and the computer is based on the operating information. Judgment on movement of
  • the operation information of the computer determined to have moved is compared with the operation information of the other computers, The destination of the computer determined to have moved is determined.
  • the present invention it is possible to automatically detect the movement of a computer using the operation information of the computer, and layout management can be performed easily and accurately. Further, since the operation information of the computer is managed by the management server, the layout information can be managed at a low cost without preparing special equipment such as an RFID or a monitor.
  • FIG. 1A is a diagram showing the details of the server room 103 and 104 in the system configuration of the present embodiment
  • FIG. 1B is a diagram showing the system configuration of the present embodiment in detail for the operation management room 102.
  • the operation management server 105 and the layout management server 106 in the operation management room 102 are connected to the monitoring target devices 128, 129, 133 in the server rooms 103 and 104 through the business network 101.
  • the monitoring target devices 128, 129, 133, and 134 represent information processing apparatuses including physical resources such as blade servers and virtual resources such as virtual servers operating on the blade servers.
  • the operation information in this embodiment refers to the operation management server 105 and the monitored device 128 in addition to the behavior such as the CPU usage rate and the power consumption of the monitored devices 128, 129, 133, and 134 that are generally monitored. 129, 133, 134, and the communication information of the entrance / exit management servers 107, 108.
  • This communication information includes TTL that is information indicating the response time between devices and the timing of packet disappearance.
  • access information to the server rooms 103 and 104 in which the monitoring target devices 128, 129, 133, and 134 are installed is acquired, and this access information is also acquired as operation information. Is done.
  • the layout information in this embodiment represents the installation locations of the monitoring target devices 128, 129, 133, and 134, and the layout information is linked to the operation information of the monitoring target devices 128, 129, 133, and 134.
  • the layout information is linked to the operation information of the monitoring target devices 128, 129, 133, and 134.
  • an operation management server 105 and a layout management server 106 are installed in the operation management room 102.
  • the operation management server 105 the operation information of each monitored device 128, 129, 133, 134, and the administrator
  • the entry / exit situation of the server rooms 103 and 104 by a person such as the person is monitored, and the layout management server 106 detects movement of the monitored devices 128, 129, 133 and 134, notifies the movement destination, and manages layout information.
  • the server rooms 103 and 104 include monitoring target devices 128, 129, 133, and 134 that are used for normal business operations, and entrance / exit management for managing entry / exit to the server rooms 103 and 104 by a person such as an administrator.
  • Servers 107 and 108 are installed.
  • the operation management server 105 includes an operation information acquisition unit 109, a layout management table update unit 110, and an operation information transmission unit 111.
  • the operation information acquisition 109 the operation information of each monitoring target device 128, 129, 133, 134 and the operation information managed by the entry / exit management server 107, 108 are used as the monitoring target devices 128, 129, 133, 134, and , Collected from the entrance / exit management servers 107 and 108, respectively.
  • the layout management table update unit 110 acquires layout change information from the layout management server 106 when the layout management server 106 detects a layout change of the monitoring target devices 128, 129, 133, and 134.
  • the operation information transmission unit 111 transmits the operation information acquired by the operation management server 105 to the layout management server.
  • the layout management server 106 includes a management table creation unit 115, a device monitoring unit 114, an operation information management unit 113, and a position change notification unit 112.
  • the customer layout information is used by the layout management server 106 as existing layout information when the customer inputs it to the layout management server 106.
  • the management table creation unit 115 acquires the existing layout information provided by this customer.
  • the input content of the existing layout information in this embodiment is a content that matches the table created by the layout management server 106.
  • device information, position information, and the like of the monitoring target devices 128, 129, 133, and 134 are input as existing layout information. In the present embodiment, the description has been given of inputting the existing layout information to the layout management server 106, but the existing layout information may be input to the operation management server 105.
  • the acquired existing layout information is managed as a model of a table for managing the position information and operation information of the monitoring target devices 128, 129, 133, and 134, and thereafter, the operation information and layout information are updated.
  • the device monitoring unit 114 manages the layout information created by the management table creation unit in association with the operation information transmitted from the operation management server 105 to the operation information management unit 113, and monitors the devices to be monitored 128, 129, 133, The movement detection of 134 and notification of the movement destination are performed.
  • the position change notification unit 112 notifies the operation management server 105 of a movement destination when the device monitoring unit 114 performs a movement destination notification.
  • the entrance / exit management servers 107 and 108 are configured by management information transmission units 118 and 121, communication monitoring units 116 and 119, and entrance / exit counting units 117 and 120.
  • the communication monitoring units 116 and 119 transmit / receive signals to / from the monitoring target devices 128, 129, 133, and 134, and transmit communication information between the entrance / exit management servers 107 and 108 and the monitoring target devices 128, 129, 133, and 134. get.
  • the entrance / exit counting sections 117 and 120 count the number of managers who entered and exited the server rooms 103 and 104.
  • the communication information and the number of persons entering and leaving the manager are transmitted from the room entry / exit management servers 107 and 108 to the operation management server 105 by the management information transmission units 118 and 121.
  • the operation information acquisition unit 109, the layout management table update unit 110, and the operation information transmission unit 111 of the operation management server 105 are stored in the memory 141 and executed by the CPU 123.
  • the location change notification unit 112, the operation information management unit 113, the device monitoring unit 114, and the management table creation unit 115 of the management server 106 are stored in the memory 142 and executed by the CPU 126.
  • the management information transmission unit 118, the communication monitoring unit 116, and the entrance / exit counting unit 117 of the server 107 are programs stored in the memory 143 and executed by the CPU 131, and the management information transmission unit of the entrance / exit management server 108 121, the communication monitoring unit 119, and the entrance / exit counting unit 120 Is stored in the memory 144, are programs executed by the CPU 136.
  • FIG. 2 shows the configuration of the management table creation unit 115 in the layout management server 106 and the logical relationship with the disk drive 127 in this embodiment.
  • the management table creation unit 115 includes a layout information acquisition unit 201, a table creation unit 202, and a table transmission unit 203.
  • the layout information acquisition unit 201 receives the existing layout information provided from the customer, and transmits this existing layout information to the table creation unit 202.
  • the existing layout information represents the position information of the monitoring target devices 128, 129, 133, and 134 arranged in the server rooms 103 and 104 of the customer environment. The method for inputting the existing layout information will be described later with reference to FIG.
  • the table creation unit 202 creates a provision information table 205, a layout management table 206, and a management device table 207 based on the received existing layout information.
  • the provided information table 205 records existing layout information.
  • the layout management table 206 the layout information of the monitoring target devices 128, 129, 133, and 134 is associated with the operation information used for detecting the layout change in each of the monitoring target devices 128, 129, 133, and 134 from the provided information table 205. Record.
  • the management device table 207 basic information such as the networks of the monitoring targets 128, 129, 133, and 134 is recorded.
  • the table creation unit 202 stores the generated provision information table 205, layout management table 206, and management device table 207 in the layout information DB 204 in the disk drive 204, and information via the table transmission unit 203.
  • the table information of the provision table 205, the layout management table 206, and the managed device table 207 is transmitted to the position change notification unit 112.
  • Fig. 3 shows an example of customer layout.
  • the layout state of the server room 103 will be described as an example.
  • a monitoring target device 128, a monitoring target device 129, and outlet boxes 303, 304, 305, 306, 307, and 308 are installed in the server room 103, and each of the set boxes 303, 304, 305, 306, 307, The power 308 is supplied from the breaker 302 through the power line 309.
  • the monitoring target devices 128 and 129 here correspond to blade servers, storages, and the like.
  • the server room 103 is divided into a mesh shape and is located in the outlet boxes 303, 304, 305, 306, 307, 308 installed in each division.
  • Define information For example, in the case of FIG. 3, the server room 103 is divided into A to G and 1 to 10, and the set box 303 is installed at the position “B2”. “B2” is defined as information.
  • the position information of each blade server can be grasped on the basis of the position information of the outlet boxes 303, 304, 305, 306, 307, and 308.
  • the granularity of the classification can be arbitrarily specified. By increasing the granularity of the classification, it is possible to accurately specify the position information of each blade server.
  • the information input here includes a file provision and a screen input method.
  • FIG. 4 shows an example of the provision information table 205.
  • the name 401 of the outlet boxes 303, 304, 305, 306, 307, 308 as the power supply information, the floor 402 and the room 403 of the installation location, and the outlet boxes 303, 304, 305, 306, 307, 308 position information 404 is recorded.
  • device type 405 and IP address 406, Subnet 407, and Gateway 408, which are network information of each device are recorded as device information.
  • the display example is based on the premise of a blade server. However, when the monitoring target devices 128, 129, 133, and 134 are mounted on a rack or chassis, the rack or chassis information is displayed.
  • FIG. 4 What is necessary is just to add to the kind 405 in FIG. 4, and when the virtual server is starting on each blade server, this virtual server is added to the kind 405 in FIG. 4, and the network information regarding each virtual server is illustrated. 4 may be added to the IP address 406, Subnet 407, and Gateway 408 in FIG.
  • the network information records information on the IP address 406, the subnet mask 407, and the gateway 408 that are necessary for the operation management server 105 and the entrance / exit management servers 107 and 108 to communicate.
  • 4 shows an example in which the layout information shown in FIG. 3 is also created for the server room 104.
  • FIG. 5A shows an example of the layout management table 206.
  • the layout management table 206 acquires the type and layout information in the device information recorded in the provision information table 205, and records the operation information of each device.
  • FIG. 5A shows a management example of the layout management table 206 in a physical computer such as a blade server.
  • the response time (Response) 5105 in each device and the TTL 5106 which is information indicating the packet extinction timing, the power state 5107 of the device, the power consumption 5110, and the entry / exit of the server rooms 103 and 104
  • the operation information such as the number of times 5111, the layout information of the floor (Floor) 5108 and the room (Room) 5109 on which each device is installed, the device information 5102, the power source 5103, and the management server 5104 are recorded in association with each other. Thereby, it is possible to grasp the operating state and usage status of each device.
  • the response time records the response times of the operation management server 105 and the entrance / exit management servers 107 and 108 for each device.
  • the response time between the monitoring target device 128 and the operation management server 105 is 1 ms
  • the response time between the monitoring target device 128 and the entry / exit management server 107 is 0.5 ms.
  • the monitoring target device 128 and the entrance / exit management server 107 are installed in the server room 103 which is the same room.
  • the response time is assumed to be used for detecting movement of the device, and details will be described later.
  • the reflection time of the registration information of the provision information table 205 and the acquisition time of the operation information of each device are recorded in the acquisition time 5101. It is also possible to perform management using a layout management table for a physical computer such as a blade server on which a virtual server is mounted. Examples thereof will be described below with reference to FIGS. 5B, 5C, and 5D. Note that a part of the table shown in FIG. 5D is joined below a part of the table shown in FIG. 5C to form one table.
  • FIG. 5B, FIG. 5C, and FIG. 5D show examples of the layout management table when virtual server information is added to FIG. 5A.
  • the virtual server 5201 mounted in the layout management table 206 ′ is associated with the monitoring target device 5202
  • FIGS. 5C and 5D the virtual server mounted in the layout management table 206 ′′.
  • the operation information of each virtual server is registered.
  • the physical management computer on which the virtual server is mounted is arranged in the layout management table.
  • the movement detection process described later in FIG. 22 and the movement destination specifying process described later in FIG. 23 are performed.
  • the physical position can be grasped from the virtual server 5309, and analysis using the operation information and layout information (5103 to 5111) of the virtual server 5309 can be performed.
  • FIG. 6 shows an example of the management device table 207.
  • the management device table 207 information on the IP address 602, the subnet mask 603, and the gateway 604, which are network information of each device in the provided information table 205, is registered in association with the device information 601. This information is notified to the operation management server 105 and used for obtaining operation information.
  • the IP address of the monitoring target device 128 is acquired when the information is remotely acquired from the operation management server 105 using a command such as rsh or ssh. A command is issued to 11.111.111.11.
  • the device monitoring unit 114 includes an operation information acquisition unit 701, a fluctuation detection unit 702, and a detection information transmission unit 703.
  • the operation information acquisition unit 701 the operation information recorded in the layout management table 206 stored in the layout information DB 204 is acquired by the table creation unit 202 in the management table creation unit 115, and this operation information is stored in the fluctuation detection unit 702. Send.
  • the change detection unit 702 performs a movement detection process and a movement destination identification process for the monitoring target devices 128, 129, 133, and 134 using the evaluation table 704 based on each operation information recorded in the layout management table 206.
  • this evaluation table 704 parameters such as response time are recorded, and operation information relating to these parameters is used for the movement detection process and the movement destination specifying process.
  • the fluctuation detection unit 702 determines that the movement of the monitoring target devices 128, 129, 133, and 134 is detected or the movement destination is specified, the movement detection or the movement destination specification is notified to the detection information transmission unit 703.
  • the detection information transmission unit 703 transmits the notification to the position change notification unit 112.
  • the specific process of movement detection will be described later with reference to FIG. 22, and the specific process of specifying the movement destination will be described later with reference to FIG.
  • FIG. 8 shows an example of the evaluation table 704.
  • the evaluation table 704 records the parameters 801 that serve as specific detection criteria for the movement detection of the monitoring target devices 128, 129, 133, and 134, or the movement destination.
  • a parameter 801 (Parameter) serving as a criterion
  • a monitoring target (Unit) 802 targets (Destination 803, Source 804) specified when acquiring information between monitoring targets
  • an evaluation value calculation method ( (Value) 805 is registered.
  • a response time (Response), a power state (Power Status), a TTL representing information on the life of the packet, the number of times of entering and leaving, power consumption, and the like are set.
  • the In Destination 803 and Source 804, a target device is set when acquiring operation information between the devices.
  • a device that issues a command for acquiring operation information is set.
  • a command from Destination 803 is set. Set each device that accepts.
  • the operation management server 105 or the entry / exit management servers 107 and 108 are set in the Destination 803, and the monitoring target devices 128, 129, 133, and 134 are set in the Source 804. ing.
  • the response times of the operation management server 105, the monitoring target devices 128, 129, 133, and 134, and the entrance / exit management servers 107 and 108 are set. And for the destination identification process. For example, in the response time measured by the operation management server 105, a delay occurs depending on the number of routers through which the device moves, and a difference occurs in the response time before and after the device moves. Further, in the response time measured by the entrance / exit management servers 107 and 108, when the device moves to another room, at least one of the devices passes through the router, resulting in a delay in the response time.
  • the movement detection process and the movement destination specifying process can be performed by using a response time in which a delay occurs due to the movement of the device to another room.
  • the value 805 indicating a method of counting values related to the response time and other operation information “Ave” for acquiring an average value, “Status” for acquiring a state, and “Count” for acquiring a total value are set.
  • the set value here is only an example, and an arbitrary parameter may be registered. For example, by adding a TTL that indicates the packet lifetime to the evaluation parameter, the TTL has a constant value unless the installation location or system configuration changes, so that the movement detection process and the destination identification can be performed with higher accuracy. Processing can be performed.
  • FIG. 9 shows the configuration of the operation information management unit 113 in the layout management server 106 in this embodiment and the logical relationship with the disk drive 127.
  • the operation information management unit 113 includes an operation information reception unit 901 and an operation information update unit 902.
  • the operation information receiving unit 901 receives operation information on the monitoring target devices 128, 129, 133, and 134 from the operation management server 105, and transmits the received information to the operation information update unit 902.
  • the operation information update unit 902 acquires the layout management table 206 stored in the layout information DB 204 by the table creation unit 202, and updates the acquired layout management table 206 based on the operation information acquired by the operation information reception unit 901.
  • the layout management table 206 is updated by storing the updated layout management table 206 in the layout information DB 204.
  • FIG. 10 shows the configuration of the position change notification unit 112 in the layout management server 106 in this embodiment.
  • the position change notification unit 112 includes a change detection reception unit 1001 and an update information transmission unit 1002.
  • the position change notifying unit 112 receives the layout management table 206 transmitted from the management table creating unit 115 to the change detection receiving unit 1001, and the movement detection process and the movement destination specifying process transmitted from the device monitoring unit 114.
  • the destination information of the monitoring target devices 128, 129, 133, and 134 is received, and the information is transmitted to the update information transmission unit 1002 and transmitted to the operation management server 105.
  • the information received by the location change notification unit 112 is only transmitted to the operation management server 105, but the transmission history to the operation management server 105 is stored and only the difference is transmitted to the operation management server 105. You may do it.
  • FIG. 11 shows the configuration of the layout management table update unit 110 in the operation management server 105 and the logical relationship with the disk drive 124 in this embodiment.
  • the layout management table update unit 110 includes an update information reception unit 1101 and a management table update unit 1102.
  • the layout management server 206 receives and manages the layout management table 206 stored and managed in the disk drive 127 and transmits the information to the management table update unit 1102.
  • the management table update unit 1102 acquires the layout management table 1103 managed by the operation management server 105 and uses the information in the layout management table 206 updated by the operation information update unit 902 of the layout management server 106 as the management table update unit.
  • the data is updated and reflected in the layout management table 1103 held and managed in the layout information DB 1104 in 1102.
  • the update to the layout management table 1103 here includes position information (Floor 5108 and Room 5109 in FIGS. 5A to 5D) and power supply information (power supply 5103 of A to 5D in FIG. 5) registered in the layout management table 206.
  • the layout management tables 206 and 1103 are updated by the operation management server 105 and the layout management server 106, respectively, but the layout management tables 206 and 1103 are integrated into one, and the operation management server 105 or
  • the layout management servers 106 may manage the layout management tables 106 and 1103 by integrating the operation management server 105 and the layout management server 106 into one.
  • the layout management table 1103 of the operation management server 105 is created by first duplicating the layout management table 206 that has received the layout management table 1103 from the layout management server 106. Thereafter, for the created layout management table 206, the operation information (the power state 5107, the power consumption 5110, and the number of entry / exit times 5111 in FIGS. 5A to 5D) is updated with the information acquired by the operation management server 105, and the layout information (Floor 5108, Room 5109, and power source 5103 in FIGS. 5A to 5D) are updated by the information received from the layout management server 106.
  • the operation information the power state 5107, the power consumption 5110, and the number of entry / exit times 5111 in FIGS. 5A to 5D
  • the layout information Floor 5108, Room 5109, and power source 5103 in FIGS. 5A to 5D
  • FIG. 12 shows the configuration of the operation information transmission unit 111 in the operation management server 105 in this embodiment.
  • the operation information transmission unit 111 includes a table transmission unit 1201 and a table acquisition unit 1202, and the table acquisition unit 1202 acquires operation information held in the layout information DB 1104 and managed by the layout management table 1103.
  • the acquired information is transmitted to the table transmission unit 1201, and the operation information is transmitted to the layout management server 106.
  • FIG. 13 shows the configuration of the operation information acquisition unit 109 in the operation management server 105 and the logical relationship with the disk drive 124 in this embodiment.
  • the operation information acquisition unit 109 includes an operation information reception unit 1301 and an operation information registration unit 1302.
  • the operation information acquisition unit 109 receives the operation information of the monitoring target devices 128, 129, 133, and 134 and the operation information acquired by the entrance / exit management servers 107 and 108, and stores the operation information in the operation information registration unit 1302. Send.
  • the layout management table 1103 is updated by reflecting the received operation information, and is stored in the layout information DB 1004.
  • FIG. 14 shows the configuration of the entrance / exit totaling unit 117 in the entrance / exit management servers 107 and 108 in this embodiment, and the logical relationship with the disk drive 132.
  • the entry / exit counting unit 117 includes an entry / exit detection unit 1401 and a counter unit 1402.
  • the entry / exit detection unit 1401 detects the entry / exit of a person such as an administrator in the server rooms 103 and 104, and transmits detection information to the counter unit 1402 when it is detected.
  • the counter unit 1402 counts the number of times of entering and leaving the room, and records the total number of times of entering and leaving the room in the counting DB 1403 in the disk drive 132.
  • the entry / exit detection method in this embodiment is based on the assumption that the entrance / exit management servers 107 and 108 manage entrance / exit of an administrator or the like.
  • entrance / exit management servers 107 and 108 are installed at the entrances and exits of the server rooms 103 and 104, and an entrance / exit authentication interface for controlling opening and closing of the entrances and exits of the server rooms 103 and 104 using an ID card, and an entrance / exit management server 107, 108 entry / exit detection unit 1401 is connected, receives information registered in an ID card for authentication of an entry / exit from the entry / exit authentication interface, and verifies it by the entry / exit management servers 107, 108, Whether to enter / exit 103 and 104 is determined, and the determination result is notified to the entrance / exit interface. At this time, when entry / exit is permitted, entry / exit is detected.
  • a dedicated sensor for detecting the entrance / exit of a person such as an administrator is prepared inside or outside the server room 103, 104, and information on the entrance / exit is obtained from the sensor. Such an implementation may be used.
  • FIG. 15 shows the configuration of the communication monitoring unit 116 in the entry / exit management servers 107 and 108 in this embodiment and the logical relationship with the disk drive 132.
  • the communication monitoring unit 116 includes a signal transmission / reception unit 1501 and a communication measurement unit 1502.
  • the signal transmission / reception unit 1501 transmits / receives a signal to / from each of the monitoring target devices 128, 129, 133, 134, and notifies the communication measurement unit 1502 of the signal transmission / reception status.
  • the communication measurement unit 1502 measures the response times of the entry / exit management servers 107 and 108 and the monitoring target devices 128, 129, 133, and 134 from the transmission / reception status, and holds the measurement results in the summary DB 1403.
  • the measurement of the response time here can be obtained, for example, by using the execution result by the ping command or calculating the difference between the times when small-scale IP packets are transmitted / received.
  • the acquisition timing is arbitrary, but by acquiring the acquisition interval at a constant value, it is possible to grasp the fluctuation of the response time.
  • FIG. 16 shows the configuration of the management information transmitting unit 118 in the entrance / exit management servers 107 and 108 in this embodiment and the logical relationship with the disk drive 132.
  • the management information transmission unit 118 takes the operation information held in the summary DB 1403 into the management information acquisition unit 1602, notifies the information transmission unit 1601 of the operation information, and transmits the operation information to the operation management server 105.
  • all the operation information managed by the entry / exit management servers 107 and 108 may be transmitted, or only the updated information excluding the previously transmitted operation information may be transmitted.
  • the layout management server 106 based on the operation information of the monitoring target devices 128, 129, 133, and 134, the movement detection of the monitoring target devices 128, 129, 133, and 134 and the movement destination specifying process are performed. A method for analyzing operation information in this process will be described with reference to FIGS. 17, 18, and 19.
  • FIG. 17 shows a change example of the operation information of the monitoring target devices 128, 129, 133, and 134 and the entry / exit information of the server rooms 103 and 104.
  • the response time 1702 between the operation management server 105 and the monitoring target devices 128, 129, 133, 134, and the entry / exit management server 107, 108 between the monitoring target devices 128, 129, 133, and 134 is shown in the example of FIG. 17, the response time 1702 between the operation management server 105 and the monitoring target devices 128, 129, 133, 134, and the entry / exit management server 107, 108 between the monitoring target devices 128, 129, 133, and 134.
  • Response time 1703 number of times of entering / leaving the server room 103, 104, power status 1704 of the monitored devices 128, 129, 133, 134, between the operation management server 105 and the monitored devices 128, 129, 133, 134 TTL 1704, which is information representing the packet life of the user, and TTL 1706, which is information representing the packet life between the entry / exit management servers 107, 108 and the monitored devices 128, 129, 133, 134, are shown.
  • the monitored devices 128, 129, 133, and 134 are moved when the behavior of the monitor changes from the steady state. Performing movement detection by the determined and.
  • response times 1702 and 1703 and TTLs 1705 and 1706 between the operation management server 106 and the entrance / exit management server 107 and the monitoring target device 128 change.
  • the TTL is calculated based on the time until the operation management server 106 or the entrance / exit management server 107 transmits a packet to the monitored device and the packet disappears, for example.
  • the behaviors of response times 1702, 1703 and TTLs 1705, 1706 are changed between times T1 and T2, thereby detecting that the monitored device 128 has moved.
  • the process of turning off the power of the target device with respect to the number of times of entry 1700 of a person such as an administrator in the server rooms 103 and 104 and the power status 1704, which are work contents when moving the device. Is added to the criteria.
  • the number of times of entry / exit 1700 for example, it is determined that the monitored device has been moved to a room larger than a predetermined number of times. It can also be determined that the monitored device has been moved to a room with the largest number of entry / exit 1700s.
  • this movement detection detection is performed based on a difference that varies from the steady state, but it is assumed that a criterion for this difference is set in advance by an administrator. Further, specific processing of movement detection will be described later with reference to FIG.
  • FIG. 18 shows an outline of processing for specifying the movement destinations of the monitoring target devices 128, 129, 133, and 134 from the operation information. For example, when the movement of the monitoring target device 128 is detected, the behavior of the other monitoring target devices 129, 133, and 134 is confirmed, and the server rooms 104 and 105 that are the same as the monitoring target devices 129, 133, and 134 that have similar behaviors. It is determined that it has moved to.
  • the monitoring target device 128 is set as a movement detection target will be described as an example. Further, in the example of FIG.
  • the response time between the operation management server 105 and the monitoring target devices 128, 129, 133, and 134 is a graph 1800, the operation management server 105 and the monitoring target devices 128, 129, 133, and 134
  • a graph 1810 shows a TTL that is information representing a packet life between the server rooms 103 and a graph 1820 shows a transition of power consumption in the server rooms 103 and 104.
  • the response time of the monitoring target device 128 is indicated by 1804 (solid line)
  • the response times of the monitoring target devices 129, 133, and 134 are indicated by 1801, 1802, and 1803 (both broken lines), respectively.
  • the TTL of the monitored device 128 is indicated by 1813 (solid line), the TTL of the monitored device 129 is indicated by 1811 (broken line), and the TTL of the monitored devices 133 and 134 is indicated by 1812 (broken line). Further, in the graph 1820 regarding the transition of the power consumption, the transition of the power consumption in the server room 103 is represented by 1821 and the transition of the power consumption in the server room 104 is represented by 1822. Since the monitoring target devices 133 and 134 are installed in the same room, the response time shows similar behavior and the TTL shows the same behavior.
  • FIG. 18 shows a case where the monitoring target device 128 moves between times T1 and T2, and the response time 1804 and TTL 1813 of the monitoring target device 128 are the same as or similar to those of the monitoring target devices 133 and 134. Therefore, it is estimated that the monitoring target device 133 or 134 has moved to the server room 104 in which it is installed.
  • the power consumption 1820 since the power consumption 1821 of the server room 103 decreases and the power consumption 1822 of the server room 104 increases during the time T1 to T2 when the monitoring target device 128 moves, monitoring is performed. It is determined that the target device 128 has moved from the server room 103 to the server room 104.
  • the increase in the power consumption 1822 is greater than or equal to a predetermined value, it may be determined that the monitoring target device 128 has moved from the server room 103 to the server room 104.
  • the number of rooms to be managed becomes large, for example, when managing large-scale equipment such as a data center. Since it is possible to narrow down the destination server room from the behavior of the movement detection target in the environment, each behavior can be easily analyzed. The specific process for specifying the destination will be described later with reference to FIG.
  • FIG. 19 shows a procedure for acquiring response times from the monitored devices 128, 129, 133, and 134 by the entry / exit management server 107
  • FIG. 20 shows an acquisition procedure from the entry / exit management server 107 by the operation management server 105.
  • the procedure for updating the layout management table 1103 for the response time is shown.
  • the communication monitoring unit 116 of the entrance / exit management server 107 first issues a ping command to the monitoring target devices 128, 129, 133, and 134 (1900). This ping command is issued periodically, and the acquisition timing is arbitrarily set by the administrator. Next, the communication monitoring unit 116 acquires the response time from the execution result of the ping command (1901), and the management information transmitting unit 118 transmits the acquired response time to the operation management server 105 (1902).
  • the operation management server 105 receives the response time transmitted from the entry / exit management server 107 by the operation information acquisition unit 109 (2000).
  • the moving average is calculated from the response time and the response time acquired until the previous time (2001), and the calculated moving average is registered in the layout management table 1103 as the response time between the entrance / exit management server 107 and the monitoring target device 128.
  • the moving average here is the average value of the response time acquired in a certain period. For example, even if the response time acquired suddenly increases, it is more stable than the average of the response time up to that time. This value is used as movement information for movement detection and movement destination search. As a result, sudden behavior other than the movement of the monitored device can be excluded as a determination criterion for movement detection and destination search, and the accuracy of movement detection and destination search can be improved.
  • the management table creation unit 115 acquires existing layout information from the customer (2100). As shown in FIG. 3, the customer's server rooms 103 and 104 are divided into meshes, and information defining the position is input by the customer. A provision information table 205 as shown in FIG. 4 is generated from the existing layout information (2101), and the evaluation table 704 as shown in FIG. The parameter 801 is added to create the layout management table 206 shown in FIGS. 5A to 5D (2102). As for the IP address, subnet mask, and gateway information registered in the provided information table 205, the information used when the operation management server 105 remotely acquires the operation information of the monitored devices 128, 129, 133, and 134.
  • an IP address, subnet mask, and gateway information may be added. Then, the created layout management table 206 is transmitted to the operation management server 105 (2103).
  • the operation management server 105 creates a layout management table 1103 by duplicating the layout management table 206.
  • the operation management server 105 updates the operation information in the layout management table 1103.
  • the movement detection process and the movement destination specifying process are performed by the device monitoring unit 114 of the layout management server 106, and the movement destination notification to the operation management server 105 is notified by the position change notification unit 112.
  • FIG. 22 shows the procedure of the movement detection process performed by the device monitoring unit 114
  • FIG. 23 shows the procedure of the movement destination specifying process for investigating the movement destination after the device monitoring unit 114 detects the movement in the movement detection process.
  • the processing in FIG. 22 may be periodically performed by the device monitoring unit 114 of the layout management server 106 or may be performed when an administrator inputs an execution command to the layout management server 106.
  • 23 may be triggered by the completion of the process of FIG. 22, or separately from the process of FIG. 22, such as when an administrator inputs an execution command to the layout management server 106. You may go.
  • the variation detection unit 702 of the device monitoring unit 114 illustrated in FIG. 7 acquires the layout management table 206 illustrated in FIGS. 5A to 5D from the layout information DB 204, and the monitoring target devices 128, 129, and 133 from the layout information DB 204. , 134 (2200), and based on the evaluation table 704, an evaluation parameter 801 used for movement detection processing is acquired from the layout management table 206 (2201).
  • the device monitoring unit 114 uses the acquired operation information, and uses the operation information acquired, the operation information totaling method associated with the target operation information (Parameter) in the evaluation table 704.
  • the values aggregated according to (Value 805) are used.
  • the behavior of the monitored devices 128, 129, 133, and 134 is different from the steady state for the acquired evaluation parameter (2202).
  • a parameter acquired with the value 805 of the evaluation table 704 as an average (Ave) such as response time and power consumption
  • a predetermined time for the operation information acquired at each time An average value is calculated based on the width, a difference is calculated by comparing the calculated average values, and a determination is made as to whether or not each difference increases.
  • a threshold value which judges whether this difference becomes large, an administrator sets in advance, and when a difference is larger than the set threshold value, it determines with the monitoring object apparatus having moved.
  • behavior determination is performed based on a change from a constant value.
  • the behavior of the evaluation parameter is the same as in the steady state, it is determined that the monitored devices 128, 129, 133, and 134 are not moved (2204).
  • the movement target is specified from the monitoring target devices 128, 129, 133, and 134 based on the evaluation parameters for the monitoring target devices 128, 129, 133, and 134 (2205). ). Since the evaluation parameter is acquired from each of the monitoring target devices 128, 129, 133, and 134, the monitoring target devices 128, 129, 133, and 134 different from the steady state can be identified from the evaluation parameters.
  • the monitoring target device 128 here is a blade server as an example, and it is assumed that the monitoring target device 128 is mounted in a rack.
  • the behavior of the operation information of other monitoring target devices mounted in the same rack as the monitoring target device 128 is confirmed (2206). If the behavior of other monitored devices is all different from the steady state, it is determined that the rack itself has been moved, and all monitored devices including the monitored devices 128 that are mounted on the rack are detected (2209). In addition, when the behavior of any other monitoring target device other than the movement detection target monitoring device 128 mounted in the rack is different, the monitoring target device other than the movement detection target monitoring device 128 If any of the devices other than the monitoring target device 128 is the same as in the steady state, it is determined that only the monitoring target device 128 that has first detected movement has moved (2211). .
  • the behavior different from the steady state is determined based on a threshold set in advance by the administrator for the moving average such as response time.
  • a threshold set in advance by the administrator for the moving average such as response time.
  • the response time or the like need not be specialized for moving average, and the acquired value may be used as it is as an evaluation parameter.
  • the movement detection unit 114 identifies the server room 103 or 104 to which the movement has been performed by the movement destination identification process.
  • the procedure of the movement destination specifying process will be described with reference to FIG.
  • the device monitoring unit 114 first acquires the layout management table 206 from the layout information DB 204, and acquires the operation information of the monitoring target devices 128, 129, 133, and 134 from the layout management table 206 (2300).
  • the operation information is acquired here, but since it has already been acquired in the movement detection process, there is no problem even if this process is not provided.
  • Other monitoring target devices 129, 133, and 134 whose response time and TTL exhibit the same behavior as the monitoring target device 128 determined to be a movement target are selected (2301).
  • the behavior determination here is the same as the processing performed in the movement detection process, and the difference from the movement detection process is that the comparison target is not the steady state of the operation information in the monitored device 128 but the operation of other monitored devices.
  • the information is in a steady state.
  • the average value of the response time between times T1 and T2 in FIG. 18 is calculated for each of the monitoring target device 128 that is the movement detection target and the other monitoring target devices, and the calculated average value of the response time is compared.
  • the difference from the average response time of the monitoring target device 128 is less than a preset threshold, it is determined that the monitoring target device exhibits the same behavior as the movement detection target monitoring target device 128.
  • the average value was compared here, you may calculate the difference by comparing the value of operation information for every predetermined acquisition time.
  • the server rooms 103 and 104 whose behavior varies according to the movement time of the monitoring target device 128 determined as the movement target from the acquired power consumption are identified (2303). If the server rooms 103 and 104 to be moved are specified, the monitoring unit 128 to be moved and the server rooms 103 and 104 to be moved are notified to the location change notification unit 112 (2304).
  • the notification information is transmitted from the position change notification unit 112 to the operation management server 105, and the operation management server 105 notifies the administrator of the screen on the screen.
  • the process of specifying the server rooms 103 and 104 serving as the movement destinations has been described.
  • the outlet box 303 in the item of the power supply 5103 registered in the layout management table 206 is described.
  • 304, 305, 306, 307, 308 and the position 404 registered in the provision information table 205 it is possible to specify a more detailed position.
  • the power consumption registered in the layout management table 206 is aggregated for each outlet box 303, 304, 305, 306, 307, 308, and the increase in the power consumption 1822 is greater than or equal to a predetermined value or the largest outlet.
  • step 2302 of FIG. 23 the number of times of entry / exit 511 in the room such as the server rooms 103, 104 may be obtained instead of the power consumption 510.
  • step 2303 it is determined that the monitoring target device has been moved to a room such as the server rooms 103 and 104 in which the increase in the number of entry / exit is greater than the predetermined number in accordance with the movement time. It can also be determined that the monitored device has been moved to the room with the largest number of entry / exit 511 among the rooms such as the server rooms 103 and 104.
  • FIG. 24 shows a screen configuration example 2400 for notifying the administrator of a layout change.
  • This screen is displayed on the operation management server 105 assuming that the administrator is performing operation management on the operation management server 105.
  • this represents that the blade C of 2F has moved to 1F (2401).
  • a layout display (2402) of the room in which the blade C was operating before the movement of the blade C and a layout display (2403) of the room in which the blade C was operating before the movement of the blade C are displayed.
  • the administrator determines the position of the blade C by determining the position (2403) of the blade C after the movement in FIG.
  • the position information determined by the administrator is notified from the operation management server 105 to the layout management server 106, and the layout information in the layout management table 206 is updated. Further, the layout information in the layout management table 206 may be automatically updated without going through the administrator's decision.
  • the operation information and usage information of the monitoring target devices 128, 129, 133, and 134 in the virtual environment are monitored by the operation management server 105, and the operation of the monitoring target devices 128, 129, 133, and 134 is monitored.
  • the movement of the monitoring target devices 128, 129, 133, and 134 is detected by detecting the behavior that the information and the usage information are different from those during normal operation, and the movement of the monitoring target devices 128, 129, 133, and 134 is detected.
  • the monitored devices 128, 129, 133, and 134 whose movement has been detected are the same as the monitored devices 128, 129, 133, and 134 that exhibit the same behavior. It is possible to identify that it has moved to the server room 103 and 104.
  • the present embodiment it is possible to indicate the difference between the layout information managed in advance by the administrator and the current layout information.
  • the output format can be changed according to the intended use. For example, it is possible to easily notify the difference between the existing layout information and the current layout information by matching the output format with the format of the existing layout information managed in advance by the administrator.
  • a user such as an administrator reflects the layout information of the actually installed monitoring target devices 128, 129, 133, and 134 in the existing layout information managed by the user, and performs more accurate device management. It becomes possible.
  • the operation management server 105 that performs operation management of the monitoring target devices 128, 129, 133, and 134 and the layout management server 106 that performs movement detection processing and movement destination identification processing are described separately.
  • operation management including layout management can be performed only by the operation management server 105.
  • the operation management server 105 and the layout management server 106 can be combined into one server.
  • the layout management tables 206 and 1103 are recorded on the shared disk, so that the layout management server 206 transfers to the operation management server 105. The notification of the layout management table 206 can be made unnecessary.

Abstract

L'invention concerne un procédé de gestion d'ordinateur dans un système informatique qui comprend des processus dans lesquels un dispositif de gestion : obtient des premières et secondes informations opérationnelles qui sont des valeurs indiquant l'état de fonctionnement d'un premier et d'un second ordinateur ; détermine que le premier ordinateur s'est déplacé si la quantité de changements apportés aux premières informations opérationnelles est supérieure à une première valeur seuil prescrite ; et, après le déplacement du premier ordinateur, détermine que le premier ordinateur s'est déplacé vers un emplacement où fonctionne le second ordinateur pour lequel la différence est inférieure à second seuil, si la différence entre les premières informations opérationnelles et les secondes informations opérationnelles est inférieure à la seconde valeur seuil prescrite.
PCT/JP2011/055339 2011-03-08 2011-03-08 Procédé de gestion d'ordinateur, dispositif de gestion et système informatique WO2012120635A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/JP2011/055339 WO2012120635A1 (fr) 2011-03-08 2011-03-08 Procédé de gestion d'ordinateur, dispositif de gestion et système informatique

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2011/055339 WO2012120635A1 (fr) 2011-03-08 2011-03-08 Procédé de gestion d'ordinateur, dispositif de gestion et système informatique

Publications (1)

Publication Number Publication Date
WO2012120635A1 true WO2012120635A1 (fr) 2012-09-13

Family

ID=46797638

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2011/055339 WO2012120635A1 (fr) 2011-03-08 2011-03-08 Procédé de gestion d'ordinateur, dispositif de gestion et système informatique

Country Status (1)

Country Link
WO (1) WO2012120635A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2014132400A (ja) * 2013-01-07 2014-07-17 Nec Fielding Ltd 管理サーバ、管理システム、部品管理方法及びプログラム

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH07311744A (ja) * 1994-05-17 1995-11-28 Mitsubishi Electric Corp 資源所在位置検出方式
JP2002118568A (ja) * 2000-10-10 2002-04-19 Kddi Research & Development Laboratories Inc 分散サーバシステム
WO2008126163A1 (fr) * 2007-03-08 2008-10-23 Fujitsu Limited Programme, procédé et dispositif de définition d'autorité d'accès
JP2010277595A (ja) * 2010-06-22 2010-12-09 Nec Corp 仮想サーバ管理システムおよびその方法ならびに管理サーバ装置

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH07311744A (ja) * 1994-05-17 1995-11-28 Mitsubishi Electric Corp 資源所在位置検出方式
JP2002118568A (ja) * 2000-10-10 2002-04-19 Kddi Research & Development Laboratories Inc 分散サーバシステム
WO2008126163A1 (fr) * 2007-03-08 2008-10-23 Fujitsu Limited Programme, procédé et dispositif de définition d'autorité d'accès
JP2010277595A (ja) * 2010-06-22 2010-12-09 Nec Corp 仮想サーバ管理システムおよびその方法ならびに管理サーバ装置

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2014132400A (ja) * 2013-01-07 2014-07-17 Nec Fielding Ltd 管理サーバ、管理システム、部品管理方法及びプログラム

Similar Documents

Publication Publication Date Title
EP3570494B1 (fr) Cadre d'opérations automatisées intelligentes pour gestion de réseau, de service et d'expérience client
CA2816469C (fr) Prediction de problemes de performance et de defaillances
US20170364818A1 (en) Automatic condition monitoring and anomaly detection for predictive maintenance
US9203894B1 (en) Methods and systems for building an application execution map
US9246777B2 (en) Computer program and monitoring apparatus
US10613504B2 (en) Methods and systems for determining occupancy of a zone in a building
US20130190095A1 (en) Faults and Performance Issue Prediction
CN106844165A (zh) 告警方法及装置
US10540886B2 (en) Network diagnostic tool for testing and commissioning building systems
CN102752142A (zh) 一种基于多维建模的信息系统的监控方法及监控系统
CN105933176B (zh) 一种检测主机状态的方法及装置
JP2010009411A (ja) 仮想化環境運用支援システム及び仮想環境運用支援プログラム
CN103475511A (zh) 用于网络维护的方法及装置
WO2012120635A1 (fr) Procédé de gestion d'ordinateur, dispositif de gestion et système informatique
CN105162639B (zh) 一种kvm下的虚拟网络故障定位装置
JP6223380B2 (ja) 中継装置及びプログラム
KR101079036B1 (ko) 제어망 이상 징후 탐지 장치 및 방법
US20180060987A1 (en) Identification of abnormal behavior in human activity based on internet of things collected data
JP2007228421A (ja) Ｉｐネットワーク経路診断装置およびｉｐネットワーク経路診断システム
JP2018519753A (ja) マルチテナント型データセンタにおけるｖｍからｖｍのトラフィック推定
JP5973362B2 (ja) 監視装置、監視システム、監視方法およびプログラム
JP2020035297A (ja) 機器状態監視装置及びプログラム
JP2012037991A (ja) 予測装置、予測システム及びプログラム
KR20160126609A (ko) 건물 에너지 분석 시스템 및 방법
CN108319535A (zh) 计算机终端运维辅助系统

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: 11860247

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: 11860247

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: JP