Management apparatus, information processing system, and management method

The management device efficiently identifies failed devices in CDI server systems by associating device information with positional data, reducing maintenance time and improving server availability.

JP2024158926AActive Publication Date: 2024-11-08FSAS TECH INC
View PDF 11 Cites 0 Cited by

Patent Information

Application Number
JP2023074563
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Filing Date
2023-04-28
Publication Date
2024-11-08
Estimated Expiration
2043-04-28

AI Technical Summary

Technical Problem

In server systems with Composable Disaggregation Infrastructure (CDI) configurations, identifying a failed PCIe card can be time-consuming and challenging, especially when PCIe cards are stored in multiple PCIe boxes that can be dynamically changed, affecting the availability of the server system.

Method used

A management device with a storage unit and an identification unit that associates identification information with first and second position information of each device, allowing the system to quickly identify the location of a failed device by using management information to determine the device storage unit and its storage location based on received failed device information.

Benefits of technology

Enables rapid identification of failed devices, reducing maintenance time and improving server availability by minimizing the need to stop the entire system, thus enhancing operational efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2024158926000001_ABST
    Figure 2024158926000001_ABST
Patent Text Reader

Abstract

To specify easily a position of defective devices among a plurality of devices used by an information processing apparatus.SOLUTION: A storage unit stores management information associating identification information of each of a plurality of devices used by an information processing apparatus with a first positional information and a second positional information. The first positional information indicates a position of a device storing part for storing the plurality of devices. The second positional information indicates respective storage positions of the plurality of devices in the device storage part. A specifying unit receives, from the information processing apparatus, failure device information including identification information of failure devices among the plurality of devices. The specifying unit, from the identification information of the failure device included in the failure device information, based on the management information, specifies a position of the device storage part for storing the failure device and a storage position of the failure device in the device storage part.SELECTED DRAWING: Figure 2
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present invention relates to a management technique for identifying a failed device. [Background technology]

[0002] The server is equipped with a BMC (Baseboard Management Controller) that manages the server. The BMC stores a correspondence table that shows the correspondence between the slot numbers of PCIe (Peripheral Component Interconnect Express) slots and the BDFs (Bus Device Functions) of PCIe cards inserted in the PCIe slots.

[0003] The BDF is identification information of a PCIe card, and includes a combination of a bus number, a device number, and a function number. In the following description, a PCIe slot may be simply referred to as a slot.

[0004] When any of the PCIe cards fails, the BDF of the failed PCIe card is notified to the BMC via the PCIe bus. The BMC converts the notified BDF into a slot number based on the correspondence table, and notifies the user of the obtained slot number. The user can identify the installation location of the server from the ID lamp on the server, and identify the failed PCIe card from the notified slot number. The user is, for example, an operator who performs maintenance work on the server.

[0005] Regarding server failures, a method for maintaining the failure tolerance of storage devices in a composable infrastructure is known (see, for example, Patent Document 1). A method for identifying the physical location of a PCIe card on an I / O (Input / Output) drawer where a failure has occurred is also known (see, for example, Patent Document 2).

[0006] A technique for identifying an I / O faulty card in a computer system is also known (see, for example, Patent Document 3). A technique for improving fault tolerance in a virtualized computer system is also known (see, for example, Patent Document 4). [Prior art documents] [Patent documents]

[0007] [Patent Document 1] Special Publication No. 2022-517890 [Patent Document 2] JP 2011-197845 A [Patent Document 3] JP 2011-253332 A [Patent Document 4] JP 2012-160095 A Summary of the Invention [Problem to be solved by the invention]

[0008] In a server system with a CDI (Composable Disaggregation Infrastructure) configuration, PCIe cards used by the server are stored in multiple PCIe boxes outside the server, and the PCIe cards connected to the server can be changed dynamically. However, it may take a long time to identify a failed PCIe card.

[0009] This problem is not limited to server systems with a CDI configuration, but occurs in various information processing systems. Moreover, this problem is not limited to identifying a faulty PCIe card in a PCIe box, but occurs when identifying various faulty devices in various storage units.

[0010] In one aspect, an object of the present invention is to easily identify the location of a failed device among a plurality of devices used by an information processing device (computer). [Means for solving the problem]

[0011] In one scheme, the management device includes a storage unit and an identification unit.

[0012] The storage unit stores management information that associates identification information of each of a plurality of devices used by the information processing device with first location information and second location information. The first location information indicates a location of a device storage unit that stores the plurality of devices. The second location information indicates a storage location of each of the plurality of devices in the device storage unit.

[0013] The identification unit receives failed device information including identification information of a failed device from the information processing device, and identifies the location of a device storage unit that stores the failed device and the storage location of the failed device within the device storage unit from the identification information of the failed device included in the failed device information based on management information. Effect of the Invention

[0014] According to one aspect, it is possible to easily identify the location of a failed device among a plurality of devices used by an information processing device. [Brief description of the drawings]

[0015] [Figure 1] FIG. 1 is a configuration diagram of a server system of a comparative example. [Diagram 2] FIG. 2 is a functional configuration diagram of a management apparatus according to the embodiment. [Diagram 3] 13 is a flowchart of a position identification process. [Figure 4] FIG. 2 is a hardware configuration diagram of the server system. [Diagram 5] FIG. 2 is a configuration diagram of a PCIe box. [Figure 6] FIG. 2 is a functional configuration diagram of a management server. [Figure 7] FIG. 13 illustrates a box information table. [Figure 8] FIG. 13 illustrates a device information table. [Figure 9] FIG. 13 is a diagram showing a device information table to which an entry has been added. [Figure 10] FIG. 13 is a diagram showing a device information table from which an entry has been deleted. [Figure 11] 13 is a flowchart of a box information table generating process. [Figure 12] 13 is a flowchart of a device information table update process. [Figure 13] 13 is a flowchart of a failure notification process. [Figure 14] FIG. 2 is a hardware configuration diagram of an information processing device. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0016] Hereinafter, the embodiments will be described in detail with reference to the drawings.

[0017] In a server system with a CDI configuration, the number and positions of PCIe boxes included in the logical system configuration may change depending on the PCIe cards connected to the server. Since the BDF of the PCIe card changes dynamically depending on the logical system configuration, the BMC in the server does not recognize the BDF of each PCIe card, nor does it recognize the position of the PCIe box that stores each PCIe card.

[0018] Fig. 1 shows an example of the configuration of a server system of a comparative example. The server system in Fig. 1 is a server system with a CDI configuration, and includes a server 101, a PCIe switch 102, a PCIe box 103-1, and a PCIe box 103-2.

[0019] The server 101 includes a BMC 111 and slots 112-1 to 112-3. A PCIe card is inserted into the slot 112-2. The PCIe box 103-1 includes slots 121-1 to 121-3. A PCIe card is inserted into each of the slots 121-i (i = 1 to 3). The PCIe box 103-2 includes slots 131-1 to 131-3. A PCIe card is inserted into each of the slots 131-i (i = 1 to 3).

[0020] The PCIe switch 102 is connected to a PCIe card inserted into the slot 112-2, and is also connected to the PCIe box 103-1 and the PCIe box 103-2. A user can configure a logical system configuration by connecting a desired slot 121-i or slot 131-i to the slot 112-2 via the PCIe switch 102.

[0021] For example, if a PCIe card inserted into the slot 131-2 fails during operation of a logical system configuration including the PCIe card, the BDF of the failed PCIe card is notified to the BMC 111 via the PCIe bus. However, the BMC 111 does not recognize the position of the PCIe box 103-2 and the BDF of the PCIe card inserted into the slot 131-2.

[0022] In this case, the BMC 111 displays error information indicating a server error on a management screen of a user terminal device (not shown). The user notices the occurrence of a failure in the server system by looking at the displayed error information, and performs an investigation to identify the failed PCIe card. This investigation is performed, for example, in the following procedure.

[0023] (P1) A user stops an application running on a server system.

[0024] (P2) If the user can log in to the server 101, the user logs in to the server 101 and analyzes the log to identify the failed PCIe card.

[0025] (P3) When it is impossible to log in to the server 101, the user constructs individual logical system configurations by separately connecting the PCIe cards inserted into the slots 121-i and 131-i to the slot 112-2. Then, the user checks whether or not each PCIe card is faulty, one by one, to identify the faulty PCIe card.

[0026] (P4) The user manually performs a task such as tracing the cable connections to identify the location of the PCIe box 103-j (j=1, 2) that contains the failed PCIe card.

[0027] However, when a user conducts an investigation, it takes a long time to identify the faulty PCIe card. In addition, since the user is required to have skills to determine the fault, it is difficult for an inexperienced user to identify the faulty PCIe card. Furthermore, since the scope of the stoppage of the server system is wide, the availability of the server system is impaired.

[0028] 2 illustrates an example of a functional configuration of a management device according to an embodiment. A management device 201 in FIG.

[0029] The storage unit 211 stores management information that associates identification information of each of a plurality of devices used by the information processing device with first location information and second location information. The first location information indicates the location of a device storage unit that stores the plurality of devices. The second location information indicates the storage location of each of the plurality of devices in the device storage unit.

[0030] Fig. 3 is a flowchart showing an example of a location specification process performed by the management device 201 in Fig. 2. First, the specification unit 212 receives faulty device information including identification information of a faulty device among a plurality of devices from an information processing device (step 301). Next, the specification unit 212 specifies the location of a device storage unit that stores the faulty device and the storage location of the faulty device in the device storage unit from the identification information of the faulty device included in the faulty device information based on management information (step 302).

[0031] According to the management device 201 in FIG. 2, it is possible to easily identify the location of a failed device among a plurality of devices used by an information processing device.

[0032] Fig. 4 shows an example of a hardware configuration of a server system including the management device 201 of Fig. 2. The server system of Fig. 4 includes a rack 401-1 and a rack 401-2. A rack 401-k (k=1, 2) is sometimes called a housing. The server system of Fig. 4 is an example of an information processing system.

[0033] The rack 401-1 includes a network switch 411-1, a management server 412, a PCIe switch 413-1, a server 414-1, a server 414-2, a PCIe box 415-1, and a PCIe box 415-2. These components are hardware. The management server 412 corresponds to the management device 201 in FIG.

[0034] The rack 401-2 includes a network switch 411-2, a PCIe switch 413-2, a server 414-3, a server 414-4, a PCIe box 415-3, and a PCIe box 415-4. These components are hardware.

[0035] The management server 412 includes a network interface controller (NIC) 421 and a host bus adapter (HBA) 422. The NIC 421 and the HBA 422 are hardware communication devices.

[0036] The servers 414-j (j=1 to 4) include a BMC 423-j and an HBA 424-j. The BMC 423-j is a hardware control device that manages the servers 414-j, and the HBA 424-j is a hardware communication device. The servers 414-j correspond to information processing devices.

[0037] The network switch 411-1 is connected to the NIC 421, the BMC 423-1, the BMC 423-2, and the network switch 411-2. The PCIe switch 413-1 is connected to the HBA 422, the HBA 424-1, the HBA 424-2, the PCIe box 415-1, the PCIe box 415-2, and the PCIe switch 413-2.

[0038] The network switch 411-2 is connected to the BMC 423-3, the BMC 423-4, and the network switch 411-1. The PCIe switch 413-2 is connected to the HBA 424-3, the HBA 424-4, the PCIe box 415-3, the PCIe box 415-4, and the PCIe switch 413-1.

[0039] The server 414-1 and the server 414-2 can access the PCIe box 415-1 and the PCIe box 415-2 via the PCIe switch 413-1. In addition, the server 414-1 and the server 414-2 can access the PCIe box 415-3 and the PCIe box 415-4 via the PCIe switch 413-1 and the PCIe switch 413-2.

[0040] The server 414-3 and the server 414-4 can access the PCIe box 415-3 and the PCIe box 415-4 via the PCIe switch 413-2. In addition, the server 414-3 and the server 414-4 can access the PCIe box 415-1 and the PCIe box 415-2 via the PCIe switch 413-2 and the PCIe switch 413-1.

[0041] The number of racks 401-k included in the server system may be one or more than three. The number of servers 414-j included in each rack 401-k may be one or more than three. The number of PCIe boxes 415-j included in each rack 401-k may be one or more than three.

[0042] Fig. 5 shows a configuration example of the PCIe box 415-j (j = 1 to 4) in Fig. 4. The PCIe box 415-j in Fig. 5 includes slots 511-1 to 511-N (N is an integer equal to or greater than 1). Removable devices 512-i such as PCIe cards are connected to the slots 511-i (i = 1 to N). The devices 512-i may be NICs, GPUs (Graphics Processing Units), or SSDs (Solid State Drives). The PCIe box 415-j corresponds to a device storage unit that stores devices.

[0043] A user can configure a logical system configuration for the server 414-j by connecting the slots 511-i in each PCIe box 415-j to the server 414-j via the PCIe switch 413-k.

[0044] The devices 512-i included in the logical system configuration for the server 414-j are devices 512-i that can be recognized by the operating system (OS) of the server 414-j. The PCIe box 415-j that stores the devices 512-i that can be recognized by the OS becomes the PCIe box 415-j to be managed. The devices 512-i that can be recognized by the OS correspond to devices used by the information processing device.

[0045] Fig. 6 shows an example of a functional configuration of the management server 412 in Fig. 4. The management server 412 in Fig. 6 includes a NIC 421, an HBA 422, an identification unit 611, a control unit 612, and a storage unit 613. The identification unit 611 and the storage unit 613 correspond to the identification unit 212 and the storage unit 211 in Fig. 2, respectively.

[0046] When constructing a logical system configuration, a user inputs box information of each PCIe box 415-j using a user terminal device (not shown) connected to the network switch 411-1. The NIC 421 receives the input box information via the network switch 411-1. The control unit 612 generates a box information table 621 including the received box information, and stores it in the storage unit 613.

[0047] Fig. 7 shows an example of the box information table 621. An entry of the box information table 621 in Fig. 7 includes Box#, Rack#, and U#. Box#, Rack#, and U# are associated with each other.

[0048] Box# is identification information of the PCIe box 415-j to be managed. Rack# is identification information of the rack 401-k including the PCIe box 415-j. U# is information indicating the position where the PCIe box 415-j is installed in the rack 401-k.

[0049] In this example, the PCIe boxes 415-j to be managed are the PCIe box 415-2 and the PCIe box 415-3.

[0050] Box# "2" indicates the PCIe box 415-2, and Rack# "1" indicates the rack 401-1. U# "10" indicates the height of the installation position of the PCIe box 415-2 in the rack 401-1. Box# "3" indicates the PCIe box 415-3, and Rack# "2" indicates the rack 401-2. U# "20" indicates the height of the installation position of the PCIe box 415-3 in the rack 401-2.

[0051] When the user adds a PCIe box 415-j to the logical system configuration, the user inputs box information of the added PCIe box 415-j using a user terminal device. The control unit 612 adds an entry including the input box information to the box information table 621.

[0052] When the user removes any of the PCIe boxes 415-j from the logical system configuration, the user inputs box information of the removed PCIe box 415-j using the user terminal device. The control unit 612 deletes the entry including the input box information from the box information table 621.

[0053] A user can dynamically change the devices 512-i to be included in the logical system configuration among the devices 512-i stored in the PCIe box 415-j to be managed. When the devices 512-i included in the logical system configuration are changed, configuration change information transferred via the PCIe bus is output from the PCIe switch 413-1 to the management server 412.

[0054] The configuration change information indicates, for example, the attachment or detachment of the device 512-i. The attachment of the device 512-i indicates a change to add the device 512-i to the logical system configuration for the server 414-j by connecting the device 512-i to the server 414-j. The detachment of the device 512-i indicates a change to remove the device 512-i from the logical system configuration for the server 414-j by disconnecting the device 512-i from the server 414-j.

[0055] The configuration change information indicating the attachment of the device 512-i can be written as, for example, "Attached Box:2 Slot:1 BDF:10:00.0." "Attached" indicates attachment.

[0056] "Box:2" indicates that the Box# of the PCIe box 415-j that stores the attached device 512-i is "2". "Slot:1" indicates that the Slot# of the slot 511-i to which the attached device 512-i is connected is "1". The Slot# is identification information of the slot 511-i. "BDF:10:00.0" indicates that the BDF of the attached device 512-i is "10:00.0".

[0057] The configuration change information indicating the attachment of the device 512-i is an example of device addition information. The attached device 512-i is an example of an added specific device, and the BDF of the device 512-i is an example of identification information of the specific device. The Box# of the PCIe box 415-j is an example of identification information of a device storage unit that stores the specific device, and the Slot# of the slot 511-i is an example of second position information indicating the storage position of the specific device in the device storage unit.

[0058] The configuration change information indicating the detachment of the device 512-i can be written as, for example, "Detached Box:2 Slot:1 BDF:10:00.0." "Detached" indicates detachment.

[0059] "Box:2" indicates that the Box# of the PCIe box 415-j that contained the detached device 512-i is "2." "Slot:1" indicates that the Slot# of the slot 511-i to which the detached device 512-i was connected is "1." "BDF:10:00.0" indicates that the BDF of the detached device 512-i is "10:00.0."

[0060] The configuration change information indicating the detachment of the device 512-i is an example of device removal information. The detached device 512-i is an example of a specific device that has been removed, and the BDF of the device 512-i is an example of identification information of the specific device. The Box# of the PCIe box 415-j is an example of identification information of a device storage unit that stores the specific device, and the Slot# of the slot 511-i is an example of second position information indicating the storage position of the specific device in the device storage unit.

[0061] The HBA 422 receives configuration change information from the PCIe switch 413-1. When constructing a logical system configuration, if configuration change information indicating the attachment of the device 512-i is received, the control unit 612 extracts the Box#, Slot#, and BDF from the received configuration change information. Then, the control unit 612 generates a device information table 622 including the extracted Box#, Slot#, and BDF, and stores the table in the storage unit 613.

[0062] Fig. 8 shows an example of the device information table 622. The entry of the device information table 622 in Fig. 8 includes a Box#, a Slot#, and a BDF extracted from "Attached Box: 2 Slot: 1 BDF: 10:00.0", which is configuration change information indicating an attachment. The Box#, the Slot#, and the BDF are associated with each other.

[0063] The Slot# and BDF included in the device information table 622 are associated via the Box# with the Rack# and U# included in the box information table 621. The box information table 621 and the device information table 622 correspond to management information.

[0064] The BDF included in the device information table 622 corresponds to the identification information of the device. The Rack# and U# included in the box information table 621 correspond to the first location information indicating the location of the device storage unit. The Slot# included in the device information table 622 corresponds to the second location information indicating the storage location of the device in the device storage unit.

[0065] When a server system includes multiple PCIe boxes 415-j, the Rack# and U# of each PCIe box 415-j are registered in the box information table 621. This makes it possible to identify the installation position of the PCIe box 415-j based on the BDF of the device 512-i.

[0066] After the device information table 622 is generated, if configuration change information indicating the attachment of the device 512-i is further received, the control unit 612 extracts the Box#, Slot#, and BDF from the received configuration change information. Then, the control unit 612 updates the device information table 622 by adding an entry including the extracted Box#, Slot#, and BDF to the device information table 622.

[0067] Fig. 9 shows an example of the device information table 622 to which an entry has been added. The device information table 622 in Fig. 9 is generated by adding an entry to the device information table 622 in Fig. 8. The second added entry includes the Box#, Slot#, and BDF extracted from "Attached Box:2 Slot:2 BDF:20:00.0", which is configuration change information indicating an attachment.

[0068] By adding an entry corresponding to the configuration change information indicating the attachment of the device 512-i, the change to add the device 512-i can be reflected in the device information table 622.

[0069] After the device information table 622 is generated, when configuration change information indicating detachment of the device 512-i is received, the control unit 612 extracts the Box#, Slot#, and BDF from the received configuration change information. Then, the control unit 612 updates the device information table 622 by deleting the entry including the extracted Box#, Slot#, and BDF from the device information table 622.

[0070] Fig. 10 shows an example of the device information table 622 from which an entry has been deleted. The device information table 622 in Fig. 10 is generated by deleting the first entry from the device information table 622 in Fig. 9. The deleted first entry includes the Box#, Slot#, and BDF extracted from "Detached Box:2 Slot:1 BDF:10:00.0", which is configuration change information indicating detachment.

[0071] By deleting the entry corresponding to the configuration change information indicating the detachment of the device 512-i, the change to exclude the device 512-i can be reflected in the device information table 622.

[0072] When any of the devices 512-i fails during operation of the logical system configuration for the server 414-j, the BDF of the failed device 512-i is notified to the BMC 423-j in the server 414-j via the PCIe bus. The BMC 423-j transmits failed device information including the notified BDF to the management server 412 via the network switch 411-k. The failed device 512-i corresponds to the failed device.

[0073] The identifying unit 611 of the management server 412 receives the failed device information via the NIC 421. Next, the identifying unit 611 extracts a BDF from the received failed device information, and uses a box information table 621 and a device information table 622 to identify a Rack#, a U#, and a Slot# associated with the extracted BDF.

[0074] First, the identification unit 611 searches the device information table 622 using the extracted BDF as a key, and acquires the Box# and Slot# associated with the BDF. Next, the identification unit 611 searches the box information table 621 using the acquired Box# as a key, and acquires the Rack# and U# associated with the Box#.

[0075] Then, the identifying unit 611 identifies the obtained Rack# and U# as the Rack# and U# of the PCIe box 415-j that stores the failed device 512-i. Furthermore, the identifying unit 611 identifies the obtained Slot# as the storage position of the failed device 512-i in the PCIe box 415-j.

[0076] Next, the identifying unit 611 generates failure notification information 623 including the identified Rack#, U#, and Slot#, and stores it in the storage unit 613. The NIC 421 transmits the failure notification information 623 to the user terminal device via the network switch 411-1. This allows the user to obtain the Rack#, U#, and Slot# that indicate the position of the failed device 512-i. The NIC 421 is an example of an output unit that outputs the failure notification information 623.

[0077] As an example, a case will be described in which the storage unit 613 stores the box information table 621 in FIG. 7 and the device information table 622 in FIG. 9, and the BDF included in the failed device information is "20:00.0".

[0078] In this case, the identifying unit 611 acquires Box# "2" and Slot# "2" associated with BDF "20:00.0" from the device information table 622 in Fig. 9. Next, the identifying unit 611 acquires Rack# "1" and U# "10" associated with Box# "2" from the box information table 621 in Fig. 7.

[0079] Then, the identifying unit 611 generates fault notification information 623 including Rack#“1”, U#“10”, and Slot#“2”, and transmits it to the user terminal device via the NIC 421. Rack#“1” indicates the rack 401-1, U#“10” indicates the installation position of the PCIe box 415-2, and Slot#“2” indicates the slot 511-2.

[0080] Therefore, the user can recognize from the failure notification information 623 that the device 512-2 connected to the slot 511-2 of the PCIe box 415-2 in the rack 401-1 has failed.

[0081] According to the server system of FIG. 4, when any of the devices 512-i fails, the location of the failed device 512-i can be easily identified from the BDF notified to the BMC 423-j.

[0082] Since the user can quickly obtain the location of the failed device 512-i from the failure notification information 623 indicating the location of the failed device 512-i, the time required for maintenance work can be shortened. When replacing the failed device 512-i, it is necessary to stop only the application operating in the rack 401-k that stores the device 512-i, which improves availability compared to the case where the entire server system is stopped.

[0083] Fig. 11 is a flowchart showing an example of a box information table generation process performed by the management server 412 in Fig. 6. First, the NIC 421 receives box information input by a user (step 1101), and the control unit 612 checks whether the received box information is box information at the time of constructing a logical system configuration (step 1102).

[0084] If the received box information is box information at the time of constructing a logical system configuration (step 1102, YES), the control unit 612 generates a box information table 621 including the received box information (step 1105).

[0085] If the received box information is not box information at the time of constructing the logical system configuration (step 1102, NO), the control unit 612 performs the process of step 1103. In step 1103, the control unit 612 checks whether the received box information is box information of the added PCIe box 415-j.

[0086] If the received box information is box information of the added PCIe box 415-j (step 1103, YES), the control unit 612 adds an entry including the received box information to the box information table 621 (step 1106).

[0087] If the received box information is not box information of the added PCIe box 415-j (step 1103, NO), the control unit 612 performs the process of step 1104. In step 1104, the control unit 612 checks whether the received box information is box information of the removed PCIe box 415-j.

[0088] If the received box information is box information of the excluded PCIe box 415-j (step 1104, YES), the control unit 612 deletes the entry including the received box information from the box information table 621 (step 1107).

[0089] If the received box information is not the box information of the excluded PCIe box 415-j (step 1104, NO), the control unit 612 ends the process.

[0090] Fig. 12 is a flowchart showing an example of a device information table update process performed by the management server 412 in Fig. 6. First, the HBA 422 receives configuration change information from the PCIe switch 413-1 (step 1201), and the control unit 612 checks whether the received configuration change information includes "Attached" (step 1202).

[0091] If the received configuration change information includes “Attached” (step 1202, YES), the control unit 612 extracts the Box#, Slot#, and BDF associated with “Attached” from the configuration change information (step 1203).Then, the control unit 612 adds an entry including the extracted Box#, Slot#, and BDF to the device information table 622 (step 1204).

[0092] Next, the control unit 612 checks whether the received configuration change information includes "Detached" (step 1205).

[0093] If the received configuration change information includes "Detached" (step 1205, YES), the control unit 612 extracts the Box#, Slot#, and BDF associated with "Detached" from the configuration change information (step 1206). Next, the control unit 612 deletes the entry including the extracted Box#, Slot#, and BDF from the device information table 622 (step 1207). Then, the management server 412 repeats the processes from step 1201 onwards.

[0094] If the received configuration change information does not include "Attached" (step 1202, NO), the control unit 612 performs the processes from step 1205 onwards. If the received configuration change information does not include "Detached" (step 1205, NO), the management server 412 repeats the processes from step 1201 onwards.

[0095] Fig. 13 is a flowchart showing an example of a failure notification process performed by the server system of Fig. 4. First, the BMC 423-j checks whether or not a BDF of the failed device 512-i has been received via the PCIe bus (step 1301).

[0096] When the BDF of the failed device 512-i is received (step 1301, YES), the BMC 423-j transmits failed device information including the received BDF to the management server 412 (step 1302). The NIC 421 of the management server 412 receives the failed device information.

[0097] Next, the identifying unit 611 extracts a BDF from the received failed device information, and identifies the Rack#, U#, and Slot# associated with the extracted BDF using the box information table 621 and the device information table 622 (step 1303).

[0098] Next, the identifying unit 611 generates failure notification information 623 including the identified Rack#, U#, and Slot#, and transmits it to the user terminal device via the NIC 421 (step 1304). Then, the server system repeats the processes from step 1301 onwards.

[0099] If the BDF of the failed device 512-i has not been received (step 1301, NO), the server system repeats the process from step 1301 onwards.

[0100] The configurations of the server systems in FIGS. 1 and 4 are merely examples, and some of the components may be omitted or changed depending on the purpose or conditions of the server system.

[0101] The configuration of the management device 201 in FIG. 2 is merely an example, and some of the components may be omitted or changed depending on the application or conditions of the management device 201.

[0102] The configuration of the PCIe box 415-j in Fig. 5 is merely an example, and some of the components may be omitted or changed depending on the purpose or conditions of the server system. The configuration of the management server 412 in Fig. 6 is merely an example, and some of the components may be omitted or changed depending on the purpose or conditions of the server system.

[0103] The flowcharts in FIG. 3 and FIG. 11 to FIG. 13 are merely examples, and some of the processes may be omitted or changed depending on the configuration or conditions of the management device 201 or the server system.

[0104] The box information table 621 shown in FIG. 7 and the device information table 622 shown in FIGS. 8 to 10 are merely examples, and the box information table 621 and the device information table 622 change according to the configuration of the server system.

[0105] Fig. 14 shows an example of the hardware configuration of an information processing device used as the management server 412 in Fig. 6. The information processing device in Fig. 14 includes a CPU (Central Processing Unit) 1401, a memory 1402, an auxiliary storage device 1403, a media drive device 1404, a NIC 421, and an HBA 422. These components are hardware, and are connected to each other via a bus 1405.

[0106] The memory 1402 is, for example, a semiconductor memory such as a Read Only Memory (ROM) or a Random Access Memory (RAM), and stores programs and data used in processing. The memory 1402 may operate as the storage unit 211 in FIG. 2 or the storage unit 613 in FIG. 6.

[0107] 2 by executing a program using the memory 1402. The CPU 1401 also operates as the identification unit 611 and the control unit 612 in FIG. 6 by executing a program using the memory 1402.

[0108] The auxiliary storage device 1403 is, for example, a magnetic disk device, an optical disk device, a magneto-optical disk device, a tape device, or the like. The auxiliary storage device 1403 may be a hard disk drive or an SSD. The information processing device can store programs and data in the auxiliary storage device 1403 and use them by loading them into the memory 1402. The auxiliary storage device 1403 may operate as the storage unit 211 in FIG. 2 or the storage unit 613 in FIG. 6.

[0109] The medium drive device 1404 drives the portable recording medium 1406 and accesses the recorded contents. The portable recording medium 1406 is a memory device, a flexible disk, an optical disk, a magneto-optical disk, etc. The portable recording medium 1406 may be a CD-ROM (Compact Disk Read Only Memory), a DVD (Digital Versatile Disk), a USB (Universal Serial Bus) memory, etc. A user can store programs and data in the portable recording medium 1406 and load them into the memory 1402 for use.

[0110] Thus, the computer-readable recording medium that stores the program and data used in the processing is a physical (non-transitory) recording medium such as the memory 1402, the auxiliary storage device 1403, or the portable recording medium 1406.

[0111] 14, some of the components may be omitted or changed depending on the purpose or conditions of the information processing device. For example, when the auxiliary storage device 1403 or the portable recording medium 1406 is not used, the auxiliary storage device 1403 or the medium drive device 1404 can be omitted.

[0112] Although the disclosed embodiments and their advantages have been described in detail, it will be appreciated that those skilled in the art may make various modifications, additions and omissions therein without departing from the scope of the invention as clearly set forth in the claims.

[0113] The following supplementary notes are further disclosed regarding the embodiment described with reference to FIGS. (Appendix 1) a storage unit that stores management information that associates identification information of each of a plurality of devices used by the information processing device with first location information indicating a location of a device storage unit that stores the plurality of devices, and second location information indicating a storage location of each of the plurality of devices within the device storage unit; an identification unit that receives failed device information including identification information of a failed device among the plurality of devices from the information processing device, and identifies a location of the device storage unit that stores the failed device and a storage location of the failed device within the device storage unit from the identification information of the failed device included in the failed device information based on the management information; A management device comprising: (Appendix 2) the information processing device is capable of accessing a plurality of device storage units; each of the plurality of device storage units stores a plurality of devices; the device storage unit storing the failed device is one of the plurality of device storage units, The management device described in Appendix 1, characterized in that the management information corresponds, with each of the multiple device storage units as a managed device storage unit, identification information of each of the multiple devices stored in the managed device storage unit, first location information indicating a location of the managed device storage unit, and second location information indicating a storage location of each of the multiple devices within the managed device storage unit. (Appendix 3) a receiving unit that receives device addition information when a specific device in any one of the plurality of device storage units is added to a plurality of devices used by the information processing device, the device addition information including identification information of the any one of the device storage units, identification information of the specific device, and second location information indicating a storage location of the specific device in the any one of the device storage units; a control unit that adds, to the management information, the identification information of the specific device included in the device addition information and second location information indicating a storage location of the specific device, in association with first location information indicating a location of the device storage unit, based on the identification information of any of the device storage units; 3. The management device according to claim 2, further comprising: (Appendix 4) a receiving unit that receives device removal information when a specific device in any one of the plurality of device storage units is removed from the plurality of devices used by the information processing device, the device removal information including identification information of the any one of the device storage units, identification information of the specific device, and second location information indicating a storage location of the specific device in the any one of the device storage units; a control unit that deletes, from the management information, identification information of the specific device and second location information indicating a storage location of the specific device, which are included in the device deletion information; 3. The management device according to claim 2, further comprising: (Appendix 5) 5. The management device according to claim 1, further comprising an output unit that outputs failure notification information including a location of the device storage unit that stores the failed device and a storage location of the failed device. (Appendix 6) An information processing device; a device storage unit for storing a plurality of devices used by the information processing device; a storage unit configured to store management information that associates identification information of each of the plurality of devices with first location information indicating a location of the device storage unit, and second location information indicating a storage location of each of the plurality of devices within the device storage unit; an identification unit that receives failed device information including identification information of a failed device among the plurality of devices from the information processing device, and identifies a location of the device storage unit that stores the failed device and a storage location of the failed device within the device storage unit from the identification information of the failed device included in the failed device information based on the management information; An information processing system comprising: (Appendix 7) The information processing system includes a plurality of device storage units, each of the plurality of device storage units stores a plurality of devices; the device storage unit storing the failed device is one of the plurality of device storage units, The information processing system of claim 6, wherein the management information corresponds, with each of the plurality of device storage units as a device storage unit to be managed, identification information of each of the plurality of devices stored in the device storage unit to be managed, first location information indicating a location of the device storage unit to be managed, and second location information indicating a storage location of each of the plurality of devices within the device storage unit to be managed. (Appendix 8) a receiving unit that receives device addition information when a specific device in any one of the plurality of device storage units is added to a plurality of devices used by the information processing device, the device addition information including identification information of the any one of the device storage units, identification information of the specific device, and second location information indicating a storage location of the specific device in the any one of the device storage units; a control unit that adds, to the management information, the identification information of the specific device included in the device addition information and second location information indicating a storage location of the specific device, in association with first location information indicating a location of the device storage unit, based on the identification information of any of the device storage units; 8. The information processing system according to claim 7, further comprising: (Appendix 9) a receiving unit that receives device removal information when a specific device in any one of the plurality of device storage units is removed from the plurality of devices used by the information processing device, the device removal information including identification information of the any one of the device storage units, identification information of the specific device, and second location information indicating a storage location of the specific device in the any one of the device storage units; a control unit that deletes, from the management information, identification information of the specific device and second location information indicating a storage location of the specific device, which are included in the device deletion information; 8. The information processing system according to claim 7, further comprising: (Appendix 10) 10. The information processing system according to any one of claims 6 to 9, further comprising an output unit that outputs failure notification information including the location of the device storage unit that stores the failed device and the storage location of the failed device. (Appendix 11) receiving faulty device information from the information processing device, the faulty device information including identification information of a faulty device among a plurality of devices used by the information processing device; identifying the location of the device storage unit that stores the failed device and the storage location of the failed device within the device storage unit from the identification information of the failed device included in the failed device information, based on management information that associates identification information of each of the multiple devices with first location information indicating the location of a device storage unit that stores the multiple devices, and second location information indicating the storage location of each of the multiple devices within the device storage unit; A management method characterized in that processing is executed by a computer. (Appendix 12) the information processing device is capable of accessing a plurality of device storage units; each of the plurality of device storage units stores a plurality of devices; the device storage unit storing the failed device is one of the plurality of device storage units, The management method according to claim 11, characterized in that the management information corresponds, with each of the plurality of device storage units as a device storage unit to be managed, identification information of each of the plurality of devices stored in the device storage unit to be managed, first location information indicating a location of the device storage unit to be managed, and second location information indicating a storage location of each of the plurality of devices within the device storage unit to be managed. (Appendix 13) receiving device addition information including identification information of the device storage unit, identification information of the specific device, and second location information indicating a storage location of the specific device in the device storage unit when a specific device in any one of the device storage units is added to a plurality of devices used by the information processing device; adding, to the management information, the identification information of the specific device included in the device addition information and second location information indicating a storage location of the specific device, in association with first location information indicating a location of the device storage unit, based on the identification information of any one of the device storage units; 13. The management method according to claim 12, further comprising the steps of: (Appendix 14) receiving device removal information including identification information of the device storage unit, identification information of the specific device, and second location information indicating a storage location of the specific device in the device storage unit when a specific device in any one of the device storage units is removed from the multiple devices used by the information processing device; deleting, from the management information, the identification information of the specific device and second location information indicating a storage location of the specific device, which are included in the device deletion information; 13. The management method according to claim 12, further comprising the steps of: (Appendix 15) The management method described in any one of appendices 11 to 14, characterized in that the computer further executes a process of outputting failure notification information including the location of the device storage section that stores the failed device and the storage location of the failed device. [Explanation of symbols]

[0114] 101, 414-1 to 414-4 servers 102, 413-1, 413-2 PCIe Switch 103-1, 103-2, 415-1~415-4 PCIe Box 111, 423-1~423-4 BMC 112-1~112-3, 121-1~121-3, 131-1~131-3 slots 201 Management device 211, 613 Storage section 212, 611 Specific part 401-1, 401-2 rack 411-1, 411-2 Network Switch 412 Management Server 421NIC 422, 424-1 to 424-4 HBAs 511-1~511-N Slots 512-1~512-N Devices 612 Control section 621 Box Information Table 622 Device Information Table 623 Failure notification information 1401 CPU 1402 Memory 1403 Auxiliary storage device 1404 Media drive unit 1405 Bus 1406 Portable recording media

Claims

1. a storage unit that stores management information that associates identification information of each of a plurality of devices used by the information processing device with first location information indicating a location of a device storage unit that stores the plurality of devices, and second location information indicating a storage location of each of the plurality of devices within the device storage unit; an identification unit that receives failed device information including identification information of a failed device among the plurality of devices from the information processing device, and identifies a location of the device storage unit that stores the failed device and a storage location of the failed device within the device storage unit from the identification information of the failed device included in the failed device information based on the management information; A management device comprising:

2. the information processing device is capable of accessing a plurality of device storage units; each of the plurality of device storage units stores a plurality of devices; the device storage unit storing the failed device is one of the plurality of device storage units, The management device described in claim 1, characterized in that the management information corresponds, with each of the multiple device storage units as a managed device storage unit, identification information of each of the multiple devices stored in the managed device storage unit, first location information indicating the location of the managed device storage unit, and second location information indicating the storage location of each of the multiple devices within the managed device storage unit.

3. a receiving unit that receives device addition information when a specific device in any one of the plurality of device storage units is added to a plurality of devices used by the information processing device, the device addition information including identification information of the any one of the device storage units, identification information of the specific device, and second location information indicating a storage location of the specific device in the any one of the device storage units; a control unit that adds, to the management information, the identification information of the specific device included in the device addition information and second location information indicating a storage location of the specific device, in association with first location information indicating a location of the device storage unit, based on the identification information of any of the device storage units; The management device according to claim 2, further comprising:

4. a receiving unit that, when a specific device in any one of the plurality of device storage units is removed from the plurality of devices used by the information processing device, receives device removal information including identification information of the any one of the device storage units, identification information of the specific device, and second location information indicating a storage location of the specific device in the any one of the device storage units; a control unit that deletes, from the management information, identification information of the specific device and second location information indicating a storage location of the specific device, which are included in the device deletion information; The management device according to claim 2, further comprising:

5. 5. The management apparatus according to claim 1, further comprising an output unit that outputs failure notification information including a location of the device storage unit that stores the failed device and a storage location of the failed device.

6. An information processing device; a device storage unit for storing a plurality of devices used by the information processing device; a storage unit configured to store management information that associates identification information of each of the plurality of devices, first location information indicating a location of the device storage unit, and second location information indicating a storage location of each of the plurality of devices within the device storage unit; an identification unit that receives failed device information including identification information of a failed device among the plurality of devices from the information processing device, and identifies a location of the device storage unit that stores the failed device and a storage location of the failed device within the device storage unit from the identification information of the failed device included in the failed device information based on the management information; An information processing system comprising:

7. receiving faulty device information from the information processing device, the faulty device information including identification information of a faulty device among a plurality of devices used by the information processing device; identifying the location of the device storage unit that stores the failed device and the storage location of the failed device within the device storage unit from the identification information of the failed device included in the failed device information, based on management information that associates identification information of each of the multiple devices with first location information indicating the location of a device storage unit that stores the multiple devices, and second location information indicating the storage location of each of the multiple devices within the device storage unit; A management method characterized in that processing is executed by a computer.

Citation Information

Patent Citations

  • System bus diagnostic device

    JP1995325731A

  • Disk array device and failure restoration control method

    JP2004272527A

  • Device recognition method for computer system

    JP2006276975A

  • Storage control device and discrete type storage device

    JP2007065984A

  • Method and apparatus for identifying enclosures and devices

    JP2010518513A