JP2022068986A - Expansion device arbitration apparatus, expansion device arbitration method, failure recovery system apparatus, program, and recording media - Google Patents

Abstract

To provide an expansion device arbitration apparatus and method, a failure recovery system apparatus, a program, and a recording medium that detect and recover a fault for each expansion device in an expansion card including a plurality of expansion devices.SOLUTION: An arbitration apparatus 10 comprises a fault detection section, an expansion device cut-off section, an expansion device built-in section, and a recovery decision section. The fault detection section detects a fault occurred in multiple expansion devices that an expansion card connected to a main unit comprises. The expansion device cut-off section cuts off from the main unit an expansion device with a fault when a fault in the expansion device is detected. The expansion device built-in section integrates an expansion device after restoration processing after restoration processing of the expansion device with a fault into the main unit. The recovery decision section determines whether the integrated expansion device is recovered. The expansion device cut-off section cuts off the expansion device again in the case where the recovery decision section determines that the integrated expansion device is not recovered.SELECTED DRAWING: Figure 1

Description

The present invention relates to an extended device arbitration device, an extended device arbitration method, a disaster recovery system device, a program, and a recording medium.

AGP (Accelerated Graphics Port), SATA (Cerial ATA), as a standard for a bus or internal interface that connects a main unit such as a CPU (Central Processing Unit) and an I / O (Input / Output) device inside a computer. Various things such as PCI (Peripheral Component Interconnect) and PCI-e (Peripheral Component Interconnect-Express) are known.

When a failure occurs in an expansion card connected to the internal interface, a system that detects the failure and recovers from the failure is known (Patent Documents 1 and 2).

Japanese Unexamined Patent Publication No. 2011-128795 JP-A-2019-159439

In techniques such as Patent Documents 1 and 2, failure detection and recovery are performed on an expansion card basis. Therefore, when a plurality of expansion devices are mounted on the expansion card, there is a problem that not only the expansion device in which the failure has occurred but also all the expansion devices on the same card cannot be used temporarily.

Therefore, according to the present invention, in an expansion card provided with a plurality of expansion devices, an expansion device arbitration device, an arbitration method, a failure recovery system device, a program, and an expansion device arbitration device capable of detecting a failure of the expansion device and performing recovery in units of the expansion devices, and The purpose is to provide a recording medium.

In order to achieve the above object, the extended device arbitration device of the present invention includes a failure detection unit, an expansion device disconnection unit, an expansion device incorporation unit, and a recovery determination unit.
The failure detection unit detects failures in a plurality of expansion devices included in the expansion card connected to the main unit, and detects failures.
When a failure of the expansion device is detected, the expansion device disconnection unit disconnects the failed expansion device from the main unit.
After the recovery process of the failed expansion device, the expansion device embedded unit incorporates the expanded device after the recovery process into the main unit.
The recovery determination unit determines whether or not the incorporated expansion device has been restored, and determines whether or not the embedded expansion device has been restored.
The expansion device disconnection unit is a device characterized in that when the recovery determination unit determines that the incorporated expansion device has not been restored, the expansion device is disconnected again.

The arbitration method of the present invention includes a failure detection step, an expansion device disconnection step, an expansion device incorporation step, and a recovery determination step.
In the failure detection step, a failure is detected for a plurality of expansion devices included in the expansion card connected to the main unit.
In the expansion device disconnection step, when a failure of the expansion device is detected, the expansion device with the failure is disconnected from the main unit.
In the expansion device embedding step, after the recovery processing of the failed expansion device, the expansion device after the recovery processing is incorporated into the main unit.
The recovery determination step determines whether or not the incorporated expansion device has been restored, and determines whether or not the embedded expansion device has been restored.
The expansion device disconnection step is a method characterized by disconnecting the expansion device again when it is determined by the recovery determination step that the incorporated expansion device has not been restored.

The disaster recovery system apparatus of the present invention includes a main unit and an expansion card.
The main unit comprises an expansion device arbitrator.
The expansion card is equipped with a plurality of expansion devices.
The main unit, the expansion card, and the arbitration device of the expansion device can be connected to each other via their respective I / Fs.
The arbitration device for the expansion device is a system device that is the expansion device arbitration device of the present invention.

The program of the present invention is a program for causing a computer to execute a failure detection procedure, an extended device disconnection procedure, an extended device embedding procedure, and a recovery determination procedure.
The failure detection procedure detects failures for a plurality of expansion devices included in an expansion card connected to the main unit.
The expansion device disconnection procedure disconnects the failed expansion device from the main unit when a failure of the expansion device is detected.
In the expansion device embedding procedure, after the recovery process of the failed expansion device, the expansion device after the recovery process is incorporated into the main unit.
The recovery determination procedure determines whether or not the embedded extended device has been restored.
The expansion device disconnection procedure is a program characterized by disconnecting the expansion device again when it is determined by the recovery determination procedure that the incorporated expansion device has not been restored.

The recording medium of the present invention is a computer-readable recording medium on which the program of the present invention is recorded.

According to the present invention, in a system including an expansion card including a plurality of expansion devices, it is possible to detect and recover a failure in each expansion device.

FIG. 1 is a block diagram showing a configuration of an example of the arbitration device of the first embodiment. FIG. 2 is a block diagram showing an example of the hardware configuration of the arbitration device of the first embodiment. FIG. 3 is a flowchart showing an example of processing in the arbitration device of the first embodiment. FIG. 4 is a block diagram showing a configuration of an example of the arbitration device of the second embodiment. FIG. 5 is a flowchart showing an example of processing in the arbitration device of the second embodiment. FIG. 6 is a flowchart showing another example of the process in the arbitration device of the second embodiment. FIG. 7 is a schematic diagram showing a configuration of an example of a failure recovery system device including the arbitration device of the first embodiment.

In the extended device arbitration device of the present invention, for example, the failure detection unit detects a failure of the extended device by at least one process selected from the group consisting of the following (1) to (3). There may be.
(1) Receive extended device failure information from the main unit.
(2) The failure detection unit accesses the expansion device to detect a failure.
(3) Receive extended device failure information from the extended device.

The extended device arbitration device of the present invention further includes, for example, a storage unit.
The storage unit stores the recovery threshold value for each expansion device, and stores the recovery threshold value.
The recovery threshold is the number of times the extended device is recovered.
The expansion device built-in unit may be in an embodiment in which the failure detection unit does not incorporate the expansion device that has detected a failure exceeding the recovery threshold into the main unit.

The expansion device arbitration device of the present invention includes, for example, an expansion card disconnection unit and an expansion card integration unit.
When all the plurality of expansion devices are separated by the expansion device disconnection unit, the expansion card disconnection unit disconnects the expansion card including the expansion device.
After the expansion card is restored, the expansion card incorporating unit incorporates the expanded card after the restoration process into the main unit.
The recovery determination unit may be in a mode of determining whether or not the incorporated expansion card has been restored.

The expansion device arbitration device of the present invention includes, for example, a storage unit, an expansion card disconnection unit, and an expansion card integration unit.
The storage unit stores the priority regarding the disconnection of the expansion card and the expansion card disconnection threshold value for each expansion device.
The expansion card disconnection threshold is a threshold for determining whether or not to disconnect an expansion card including an expansion device in which a failure has occurred.
When the priority of the expansion device determined to have failed in recovery by the recovery determination unit exceeds the expansion card disconnection threshold value, the expansion card disconnection unit disconnects the expansion card including the expansion device.
After the expansion card is restored, the expansion card incorporating unit incorporates the expanded card after the restoration process into the main unit.
The recovery determination unit may be in a mode of determining whether or not the incorporated expansion card has been restored.

The arbitration method of the present invention may be such that, for example, the failure detection step detects a failure of the extended device by at least one process selected from the group consisting of the following (1) to (3). good.
(1) Receive extended device failure information from the main unit;
(2) By the failure detection step, the extended device is accessed and a failure is detected;
(3) Receive extended device failure information from the extended device.

The arbitration method of the present invention uses, for example, a recovery threshold for each extended device.
The recovery threshold is the number of times the extended device is recovered.
The expansion device incorporation step may be an embodiment in which the expansion device that has detected a failure exceeding the recovery threshold value by the failure detection step is not incorporated into the main unit.

The arbitration method of the present invention includes, for example, an expansion card disconnection step and an expansion card incorporation step.
In the expansion card disconnection step, when all the plurality of expansion devices are detached by the expansion device disconnection step, the expansion card including the expansion device is detached.
In the expansion card incorporating step, after the expansion card is restored, the expanded card after the restoration process is incorporated into the main unit.
The recovery determination step may be in the form of determining whether or not the incorporated expansion card has been restored.

The arbitration method of the present invention includes, for example, an expansion card disconnection step and an expansion card incorporation step.
Using the expansion card detachment priority and the expansion card detachment threshold,
The expansion card disconnection threshold is a threshold for determining whether or not to disconnect an expansion card including an expansion device in which a failure has occurred.
In the expansion card disconnection step, when the priority of the expansion device determined to have failed in recovery by the recovery determination step exceeds the expansion card disconnection threshold value, the expansion card including the expansion device is detached.
In the expansion card incorporating step, after the expansion card is restored, the expanded card after the restoration process is incorporated into the main unit.
The recovery determination step may be in the form of determining whether or not the incorporated expansion card has been restored.

The program of the present invention may be in an embodiment in which, for example, the failure detection procedure detects a failure of the extended device by at least one process selected from the group consisting of the following (1) to (3). ..
(1) Receive extended device failure information from the main unit;
(2) By the failure detection procedure, the extended device is accessed to detect a failure;
(3) Receive extended device failure information from the extended device.

The program of the present invention uses, for example, a recovery threshold for each extended device.
The recovery threshold is the number of times the extended device is recovered.
The expansion device incorporation procedure may be an embodiment in which the expansion device that has detected a failure exceeding the recovery threshold value by the failure detection procedure is not incorporated into the main unit.

The program of the present invention includes, for example, an expansion card disconnection procedure and an expansion card installation procedure.
In the expansion card disconnection procedure, when all the plurality of expansion devices are detached by the expansion device disconnection procedure, the expansion card including the expansion device is detached.
In the expansion card incorporating procedure, after the expansion card is restored, the expanded card after the restoration process is incorporated into the main unit.
The recovery determination procedure may be in the form of determining whether or not the incorporated expansion card has been restored.

The program of the present invention includes, for example, an expansion card disconnection procedure and an expansion card installation procedure.
Using the expansion card detachment priority for each expansion device and the expansion card detachment threshold,
The expansion card disconnection threshold is a threshold for determining whether or not to disconnect an expansion card including an expansion device in which a failure has occurred.
In the expansion card disconnection procedure, when the priority of the expansion device determined to have failed in recovery by the recovery determination procedure exceeds the expansion card disconnection threshold value, the expansion card including the expansion device is detached.
In the expansion card incorporating procedure, after the expansion card is restored, the expanded card after the restoration process is incorporated into the main unit.
The recovery determination procedure may be in the form of determining whether or not the incorporated expansion card has been restored.

In the present invention, the expansion card is, for example, a member connected to the main unit by a bus to expand the function of the main unit. The connection standard is not particularly limited, and examples thereof include AGP, SATA, PCI, and PCIe. Further, in the present invention, the expansion device is a device that controls the function and is arranged on the expansion card. When the connection standard is, for example, PCI or PCIe, the expansion card is also referred to as a PCI card or PCIe card, and the expansion device is also referred to as a PCI device, a PCIe device, or an endpoint.

An embodiment of the present invention will be described with reference to the drawings. The present invention is not limited to the following embodiments. In each of the following figures, the same parts are designated by the same reference numerals. Further, the explanations of the respective embodiments can be referred to each other unless otherwise specified, and the configurations of the respective embodiments can be combined unless otherwise specified.

[Embodiment 1]
FIG. 1 is a block diagram showing a configuration of an example of the arbitration device 10 (hereinafter, also referred to as the present device 10) of the present embodiment. As shown in FIG. 1, the present apparatus 10 includes a failure detection unit 11, an expansion device disconnection unit 12, an expansion device incorporation unit 13, and a recovery determination unit 14. Further, the apparatus 10 may include a storage unit (not shown) as an arbitrary configuration, for example.

The device 10 may be, for example, one device including the above-mentioned parts, or may be a device in which the above-mentioned parts can be connected via a communication network. Further, the present device 10 can be connected to an external device described later via the communication network. The communication network is not particularly limited, and a known network can be used, and may be wired or wireless, for example. Examples of the communication line network include an Internet line, WWW (World Wide Web), a telephone line, a LAN (Local Area Network), a SAN (Storage Area Network), a DTN (Delay Traveler Network), and the like. Examples of wireless communication include WiFi (Wireless Fidelity), Bluetooth (registered trademark) and the like. The wireless communication may be either a form in which each device communicates directly (Ad Hoc communication) or an indirect communication via an access point. The apparatus 10 may be incorporated in the server as a system, for example.

FIG. 2 illustrates a block diagram of the hardware configuration of the present device 10. The apparatus 10 includes, for example, a central processing unit (CPU, GPU, etc.) 101, a memory 102, a bus 103, an input device 104, a display device 105, a communication device 106, a storage unit 107, and the like. Each part of the hardware configuration of the present apparatus 10 is connected to each other via the bus 103 by each interface (I / F).

The central processing unit (central processing unit) 101 is responsible for overall control of the apparatus 10. In the present device 10, for example, the program of the present invention and other programs are executed by the central processing unit 101, and various information is read and written. Specifically, for example, the central processing unit 101 functions as a failure detection unit 11, an expansion device disconnection unit 12, an expansion device incorporation unit 13, and a recovery determination unit 14.

The apparatus 10 can be connected to the main unit and the expansion card by, for example, the bus 103. The main unit and the expansion card will be described later. The bus 103 can also be connected to, for example, an external device. Examples of the external device include an external database and a printer. The device 10 can be connected to the communication network by, for example, a communication device 106 connected to the bus 103, and can also be connected to an external device via the communication network. Further, for example, when the failure recovery system device of the present invention described later includes a plurality of arbitration devices 10, the device 10 may be able to communicate with other arbitration devices 10 by, for example, a communication device 106. ..

The memory 102 may be, for example, a main memory (main storage device). When the central processing unit 101 performs processing, for example, the memory 102 reads various operation programs such as the program of the present invention stored in the storage unit 107 described later, and the central processing unit 101 reads from the memory 102. Receive the data and run the program. The main memory is, for example, a RAM (random access memory). Further, the memory 102 may be, for example, a ROM (read-only memory).

The storage unit 107 is also referred to as a so-called auxiliary storage device with respect to the main memory (main storage device), for example. As described above, the storage unit 107 stores an operation program including the program of the present invention. The storage unit 107 may be, for example, a combination of a recording medium and a drive for reading and writing to the recording medium. The recording medium is not particularly limited, and may be an internal type or an external type, and examples thereof include HD (hard disk), CD-ROM, CD-R, CD-RW, MO, DVD, flash memory, and memory card. Be done. The storage unit 107 may be, for example, a hard disk drive (HDD) in which a recording medium and a drive are integrated, and a solid state drive (SSD). When the apparatus 10 includes the storage unit, for example, the storage unit 107 functions as the storage unit. In this case, the storage unit 107 may store the recovery threshold value. The recovery threshold is, for example, the number of times the extended device is recovered. The recovery threshold value may be set to a different number of times for each of the extended devices, for example. In this case, the recovery threshold can be appropriately set according to, for example, the priority of the expansion device. Specifically, for example, the more important the device is, the higher the recovery threshold can be set.

In the apparatus 10, the memory 102 and the storage unit 107 can also store the access information and the log information from the administrator, and the information acquired from the external database (not shown).

The apparatus 10 further includes, for example, an input device 104 and a display device 105. The input device 104 is, for example, a touch panel, a keyboard, a mouse, or the like. Examples of the display device 105 include an LED display and a liquid crystal display.

FIG. 7 shows a configuration of an example of a failure recovery system device including the arbitration device 10 of the present embodiment. FIG. 7 is a schematic diagram showing an example of the configuration of the failure recovery system device 20 of the present embodiment. As shown in FIG. 7, the disaster recovery system apparatus 20 of the present embodiment includes a main unit 21, a bus 22, and a PCI card 23 as an expansion card. The main unit 21 and the PCI card 23 are connected to each other via the bus 22 via their respective I / Fs, and can communicate with each other. Although the main unit 21 is provided with the arbitration device 10 in FIG. 7, the arbitration device 10 may be connected to the bus 22 as a member independent of the main unit, for example. In this case, the arbitration device 10 can also communicate with the main unit 21 and the PCI card 23 via the bus 22 via its I / F. In FIG. 7, the system device 20 includes a PCI card as the expansion card and PCI devices A and B as the expansion device. In the system device of the present invention, the expansion card and the expansion device are , As mentioned above, it is not limited to the PCI standard.

The main unit 21 is a unit that controls the main control of the system device 20, and has an OS / bus driver, an I / F, an arbitration device 10 of the present invention, and the like.

The PCI card (expansion card) 23 is connected to the main unit 21 through the bus 22. The PCI card 23 includes, for example, a PCI switch 231, a PCI device 232A, a PCI device 232B, and the like. The PCI switch 231 is a device for increasing the number of connectable PCI devices on the PCI card 23, for example. The PCI devices 232A and 232B are connected to the PCI switch 231 via the respective I / Fs and connected to the main unit 21 via the PCI switch 231, for example, on the PCI card 23. In FIG. 7, the number of PCI devices 232 included in the PCI card 23 is two, but the number is not limited to two, and the number may be two or more.

Next, an example of the arbitration method of the present invention will be described with reference to the flowchart of FIG. The arbitration method of the present embodiment is carried out as follows, for example, by using the system device 20 of FIG. 7 including the arbitration device 10 of FIGS. 1 and 2. The arbitration method of the present embodiment is not limited to the use of the system device 20 of FIG. 7, which includes the arbitration device 10 of FIGS. 1 and 2.

First, the failure detection unit 11 detects a failure of a plurality of expansion devices included in the expansion card connected to the main unit (S11, failure detection step). The failure can be detected by, for example, at least one process selected from the group consisting of the following (1) to (3). The selection and combination of the following processes (1) to (3) are not particularly limited, and for example, an appropriate one can be selected depending on the requirements and mounting method of the computer system provided with the arbitration device of the present invention. The failure detection method by the failure detection unit 11 is not limited to the processes (1) to (3) below, and is, for example, a known failure detection according to the requirements and mounting method of the computer system provided with the arbitration device of the present invention. The method can be adopted as appropriate.
(1) Receive extended device failure information from the main unit.
(2) The failure detection unit accesses the expansion device to detect a failure.
(3) Receive extended device failure information from the extended device.

The process (1) is, for example, a process in which the main unit detects a route failure to the expansion device via the expansion device I / F of the main unit. When the connection standard of the extended device is PCI or PCIe, the process of (1) can adopt, for example, a detection method compliant with PCI (e) Spec. When the main unit detects a path failure to the expansion device, the main unit transmits the expansion device failure information to the failure detection unit 11 of the arbitration device 10 of the present invention, and the failure detection unit of the arbitration device 10. 11 detects the failure of the extended device by receiving the extended device failure information. The extended device failure information is, for example, information meaning that a failure has occurred in the extended device.

In the process of (2), for example, the failure detection unit 11 periodically Read access to the expansion device via the I / F of the expansion device to the extent that the performance of the expansion device is not affected. Is a process to detect a read failure. In the process of (2), the failure detection unit 11 determines that the device that has detected the failure of the Read is an extended device in which a failure has occurred.

In the process of (3), for example, the driver of the extended device performs a failure detection process peculiar to the extended device and a recovery process, and when the recovery process fails, the driver uses the arbitration device 10 to perform the process. The extended device failure information is transmitted to the failure detection unit 11, and the failure detection unit 11 detects the failure of the extended device by receiving the extended device failure information. It is preferable that the process (3) is adopted, for example, when the driver of the expansion device can be changed.

Next, when the expansion device disconnection unit 12 detects a failure of the expansion device, the expansion device disconnection unit 12 disconnects the failed expansion device from the main unit (S12, expansion device disconnection step). The "disconnecting the expansion device" means, for example, removing the driver of the device from the main unit and invalidating the access route to the expansion device so that the expansion device cannot be accessed.

Then, the separated expansion device is restored by a known restoration processing means. Examples of the recovery process include a process of initializing or restarting the extended device according to an instruction from the main unit. Further, for example, when the expansion device itself is an expansion device having a recovery processing function, the expansion device itself may perform the recovery processing.

Next, the expansion device embedding unit 13 incorporates the expanded device after the recovery processing into the main unit after the recovery processing of the failed expansion device (S13, expansion device embedding step). The term "embedding the expansion device" means, for example, attaching the removed driver of the expansion device to the main unit and enabling the access route to the expansion device so that the expansion device can be accessed. ..

Next, the recovery determination unit 14 determines whether or not the incorporated expansion device has been restored (S14, restoration determination step). The recovery determination can be determined, for example, by whether or not Read access is possible (success or failure of Read access) and the success or failure of the driver installation (success or failure of driver installation) with respect to the embedded expansion device. Specifically, the recovery determination unit 14 first attempts Read access to the built-in expansion device. When the Read access fails, the recovery determination unit 14 determines that the built-in expansion device has failed to recover. When the Read access is successful, the recovery determination unit 14 next determines the success or failure of the driver installation. Then, when the driver installation fails, the recovery determination unit 14 determines that the expansion device has failed in recovery, and when the driver installation is successful, the recovery determination unit 14 determines that the expansion device has failed. Determine that the device has been successfully recovered. Further, when the recovery determination unit 14 determines that the driver installation is successful, for example, the recovery determination unit 14 may further confirm the normality of the expansion device. In this case, the recovery determination unit 14 determines that the expansion device has been successfully restored when the normality of the expansion device is confirmed in addition to the success of the Read access and the success of the driver installation. .. In the case of a driver whose operation does not confirm the normality of the extended device when the driver is installed, or when the failure detected in the failure detection process is restored by confirming the normality of the extended device when the driver is installed. If the failure is of a type that cannot be determined, for example, the recovery of the extended device may be determined by determining the success or failure of the Read access and the success or failure of the driver installation without checking the normality of the extended device. good.

Then, when it is determined in the recovery determination step that the incorporated expansion device has not been recovered (S14, No), the expansion device disconnection unit 12 disconnects the expansion device again, and the steps S12 to S14 are repeated. At this time, when the recovery threshold value is stored in the storage unit of the present device 10, the failure is detected in the failure detection step in excess of the recovery threshold value, that is, the recovery threshold value is exceeded in the steps S12 to S14. For the expansion device in which the processing is repeated, the processing may be terminated without performing the expansion device incorporating step. On the other hand, when it is determined in the recovery determination that the extended device has been restored (S14, Yes), the process ends (END).

According to the expansion device arbitration method of the present embodiment, in a system including an expansion card including a plurality of expansion devices, it is possible to detect and recover a failure in each expansion device. Therefore, according to the present invention, for example, the influence on the entire system due to the occurrence of a failure of the expansion device can be more localized, so that the availability of the system can be improved.

[Embodiment 2]
The arbitration device of the present embodiment is the same as that of the first embodiment except that it further includes, for example, an expansion card disconnection unit and an expansion card incorporation unit.

FIG. 4 is a block diagram showing an example of the configuration of the arbitration device 10A of the present embodiment. As shown in FIG. 4, the arbitration device 10A further includes an expansion card disconnection unit 15 and an expansion card incorporation unit 16 in addition to the arbitration device 10 of the embodiment. The hardware configuration of the arbitration device 10A is the same except that the central processing unit 101 functions as an expansion card disconnection unit 15 and an expansion card incorporation unit 16 in addition to the configuration of the arbitration device 10 of FIG.

Next, the arbitration method of the second embodiment will be described with reference to the flowchart of FIG. The arbitration method of the second embodiment can be carried out by using, for example, the arbitration device 10A of the second embodiment shown in FIG. The arbitration method of the second embodiment is not limited to the use of the arbitration device 10A.

First, S11 to S13 are carried out in the same manner as S11 to S13 in the arbitration method of the first embodiment.

Next, the recovery determination unit 14 determines whether or not the incorporated expansion device has been restored (S114). When the embedded expansion device is restored (S14, Yes), the process ends (END). On the other hand, when the incorporated expansion device has not been restored (S14, No), the expansion device disconnection unit 12 disconnects the expansion device again (S12', expansion device disconnection step).

Next, the expansion card disconnection unit 15 determines whether or not all of the plurality of expansion devices included in the expansion card have been detached (S15A), and if there is an expansion device that has not been detached (S15A, No), S11 to S14. Repeat the process of. On the other hand, when all of the plurality of expansion devices included in the expansion card are disconnected (S15A, Yes), the expansion card disconnection unit 15 disconnects the expansion card (S15B, expansion card disconnection step).

Then, the separated expansion card is restored by a known restoration processing means. Examples of the recovery process include a process of initializing or restarting the expansion card according to an instruction from the main unit. Further, for example, when the expansion card itself is an expansion card having a recovery processing function, the expansion card itself may perform the recovery processing.

Next, the expansion card incorporating unit 16 incorporates the expanded card after the restoration process into the main unit after the restoration process of the expansion card (S16, expansion card incorporating step). The term "incorporating an expansion card" means, for example, attaching the driver of the removed expansion card to the main unit and activating the access route to the expansion card so that the expansion card can be accessed. ..

Next, the recovery determination unit 14 determines whether or not the incorporated expansion card has been restored (S17, restoration determination step). The determination of recovery is determined by, for example, whether or not the expansion device included in the expansion card has been restored. Specifically, for example, in S17, the determination as to whether or not the expansion card has been restored may be determined even if it is determined that the expansion card has been restored when it is determined that all the expansion devices included in the expansion card have been restored. Alternatively, when it is determined that at least one expansion device among the expansion devices included in the expansion card has been restored, it may be determined that the expansion card has been restored, but the former is preferable. In the latter case, when the priority and the disconnection threshold value described later are set for each expansion device, for example, when it is determined that the device whose priority exceeds the disconnection threshold value has been restored. It may be determined that the expansion card has been restored. In S17, whether or not each of the extended devices has been restored may be determined in the same manner as in S14, for example.

Then, when it is determined in the recovery determination step that the incorporated expansion card has not been restored (S17, No), the expansion card is detached again by the expansion card disconnection 15, and the steps S15B to S17 are repeated. At this time, as in the S14 step, when the recovery threshold value is stored in the storage unit of the apparatus 10 for each expansion card, the expansion card that exceeds the recovery threshold value and repeats the processes of the steps S15B to S17 is used. The process may be completed without performing the expansion card incorporating step. On the other hand, when it is determined in the recovery determination step that the expansion card has been restored (S17, Yes), the process ends (END).

According to the expansion device arbitration method of the present embodiment, in a system including an expansion card including a plurality of expansion devices, it is possible to detect and recover a failure in each expansion device. Then, when it is impossible to recover all the expansion devices included in the expansion card, the recovery process can be performed for each expansion card. Therefore, according to the arbitration method of the present embodiment, for example, the system recovery process due to the occurrence of a failure of the expansion device can be multi-staged, so that the influence on the entire system can be reduced and the availability of the system can be improved.

[Modification example]
The processing by the expansion card disconnection unit 15 and the expansion card integration unit 16 is not limited to the above example, and may be performed, for example, according to the priority of the expansion device in which the failure is detected.

The arbitration method of the modified example will be described with reference to the flowchart of FIG. The arbitration method of the modified example can be carried out by using, for example, the arbitration device 10A of the second embodiment shown in FIG. The arbitration method of the modified example is not limited to the use of the arbitration device 10A.

First, S11 to S13 are carried out in the same manner as S11 to S13 in the arbitration method of the first embodiment.

Next, the recovery determination unit 14 determines whether or not the incorporated expansion device has been restored (S114). When the embedded expansion device is restored (S14, Yes), the process ends (END). On the other hand, when the incorporated expansion device has not been restored (S14, No), in the expansion card disconnection unit 15, the priority set for the expansion device determined to have failed the restoration exceeds the expansion card disconnection threshold value. Whether or not it is determined (S15A'). The priority is, for example, a value indicating the importance in a plurality of expansion devices included in the expansion card. The priority may be defined as high or low for each expansion device, or even if an arbitrary value set for each expansion device is stored in the storage unit of the apparatus 10A as the priority. good. The expansion card disconnection threshold is a threshold for determining whether or not to disconnect an expansion card including the expansion device in which the failure has occurred, and can be appropriately set according to, for example, the function of the expansion device included in each expansion card. .. Then, when the priority set for the expansion device that failed to recover does not exceed the expansion card disconnection threshold value (S15A', No), the recovery processing of S12 to S14 is repeated. On the other hand, when the priority set for the expansion device that failed to recover exceeds the expansion card disconnection threshold value (S15A', YES), the expansion card disconnection unit 15 disconnects the expansion card including the expansion device (S15A', YES). S15B, expansion card disconnection process).

After that, S16 to S17 are carried out in the same manner as in S16 to S17 of the second embodiment, and the process is terminated (END).

According to the arbitration method of the modified example, for example, the recovery process is switched to each expansion card according to the priority of the expansion device on the expansion card in which the failure occurred, so that the expansion device having an important function fails. If so, the recovery process for each expansion card can be performed promptly.

[Embodiment 3]
The program of this embodiment is a program for causing a computer to execute each step of the method of each of the above-described embodiments as a procedure. In the present invention, "procedure" may be read as "processing". Further, the program of the present embodiment may be recorded on a computer-readable recording medium, for example. The recording medium is, for example, a non-transitory computer-readable storage medium. The recording medium is not particularly limited, and for example, HD (hard disk), CD-ROM, CD-R, CD-RW, MO, DVD, floppy (registered trademark) disk (FD), flash memory, memory card and the like. Can be mentioned.

Although the present invention has been described above with reference to the embodiments, the present invention is not limited to the above embodiments. Various modifications that can be understood by those skilled in the art can be made to the structure and details of the present invention within the scope of the present invention.

<Additional notes>
Some or all of the above embodiments may be described as, but not limited to, the following appendixes.
(Appendix 1)
Includes a failure detection unit, an expansion device disconnection unit, an expansion device integration unit, and a recovery determination unit.
The failure detection unit detects failures in a plurality of expansion devices included in the expansion card connected to the main unit, and detects failures.
When a failure of the expansion device is detected, the expansion device disconnection unit disconnects the failed expansion device from the main unit.
After the recovery process of the failed expansion device, the expansion device embedded unit incorporates the expanded device after the recovery process into the main unit.
The recovery determination unit determines whether or not the incorporated expansion device has been restored, and determines whether or not the embedded expansion device has been restored.
The expansion device arbitration device is characterized in that the expansion device disconnection unit disconnects the expansion device again when the recovery determination unit determines that the incorporated expansion device has not been restored.
(Appendix 2)
The extended device arbitration device according to Appendix 1, wherein the failure detection unit detects a failure of the extended device by at least one process selected from the group consisting of the following (1) to (3).
(1) Receive extended device failure information from the main unit;
(2) The failure detection unit accesses the expansion device to detect a failure;
(3) Receive extended device failure information from the extended device.
(Appendix 3)
In addition, it includes a storage unit
The storage unit stores the recovery threshold value for each expansion device, and stores the recovery threshold value.
The recovery threshold is the number of times the extended device is recovered.
The expansion device arbitration device according to Appendix 1 or 2, wherein the expansion device incorporating unit does not incorporate the expansion device that has detected a failure exceeding the recovery threshold into the main unit by the failure detection unit.
(Appendix 4)
Includes expansion card disconnection section and expansion card integration section
When all the plurality of expansion devices are separated by the expansion device disconnection unit, the expansion card disconnection unit disconnects the expansion card including the expansion device.
After the expansion card is restored, the expansion card incorporating unit incorporates the expanded card after the restoration process into the main unit.
The expansion device arbitration device according to any one of Supplementary note 1 to 3, wherein the recovery determination unit determines whether or not the incorporated expansion card has been restored.
(Appendix 5)
Includes storage, expansion card detachment, and expansion card integration
The storage unit stores the priority regarding the disconnection of the expansion card and the expansion card disconnection threshold value for each expansion device.
The expansion card disconnection threshold is a threshold for determining whether or not to disconnect an expansion card including an expansion device in which a failure has occurred.
When the priority of the expansion device determined to have failed in recovery by the recovery determination unit exceeds the expansion card disconnection threshold value, the expansion card disconnection unit disconnects the expansion card including the expansion device.
After the expansion card is restored, the expansion card incorporating unit incorporates the expanded card after the restoration process into the main unit.
The expansion device arbitration device according to any one of Supplementary note 1 to 4, wherein the recovery determination unit determines whether or not the incorporated expansion card has been restored.
(Appendix 6)
Including main unit and expansion card
The main unit comprises an expansion device arbitrator.
The expansion card is equipped with a plurality of expansion devices.
The main unit, the expansion card, and the arbitration device of the expansion device can be connected to each other via their respective I / Fs.
The expansion device arbitration device is a failure recovery system device, which is the expansion device arbitration device according to any one of Supplementary note 1 to 5.
(Appendix 7)
Includes failure detection process, expansion device disconnection process, expansion device installation process, and recovery determination process.
In the failure detection step, a failure is detected for a plurality of expansion devices included in the expansion card connected to the main unit.
In the expansion device disconnection step, when a failure of the expansion device is detected, the expansion device with the failure is disconnected from the main unit.
In the expansion device embedding step, after the recovery processing of the failed expansion device, the expansion device after the recovery processing is incorporated into the main unit.
The recovery determination step determines whether or not the incorporated expansion device has been restored, and determines whether or not the embedded expansion device has been restored.
The expansion device arbitration method is characterized in that, when it is determined by the recovery determination step that the incorporated expansion device has not been restored, the expansion device disconnection step disconnects the expansion device again.
(Appendix 8)
The extended device arbitration method according to Appendix 7, wherein the failure detection step detects a failure of the extended device by at least one process selected from the group consisting of the following (1) to (3).
(1) Receive extended device failure information from the main unit;
(2) By the failure detection step, the extended device is accessed and a failure is detected;
(3) Receive extended device failure information from the extended device.
(Appendix 9)
Using the recovery threshold for each expansion device,
The recovery threshold is the number of times the extended device is recovered.
The expansion device arbitration method according to Supplementary note 7 or 8, wherein the expansion device incorporation step does not incorporate the expansion device that has detected a failure exceeding the recovery threshold value into the main unit by the failure detection step.
(Appendix 10)
Including expansion card disconnection process and expansion card installation process
In the expansion card disconnection step, when all the plurality of expansion devices are detached by the expansion device disconnection step, the expansion card including the expansion device is detached.
In the expansion card incorporating step, after the expansion card is restored, the expanded card after the restoration process is incorporated into the main unit.
The expansion device arbitration method according to any one of Supplementary note 7 to 9, wherein the recovery determination step determines whether or not the incorporated expansion card has been restored.
(Appendix 11)
Including expansion card disconnection process and expansion card installation process
Using the expansion card detachment priority and the expansion card detachment threshold,
The expansion card disconnection threshold is a threshold for determining whether or not to disconnect an expansion card including an expansion device in which a failure has occurred.
In the expansion card disconnection step, when the priority of the expansion device determined to have failed in recovery by the recovery determination step exceeds the expansion card disconnection threshold value, the expansion card including the expansion device is detached.
In the expansion card incorporating step, after the expansion card is restored, the expanded card after the restoration process is incorporated into the main unit.
The expansion device arbitration method according to any one of Supplementary note 7 to 9, wherein the recovery determination step determines whether or not the incorporated expansion card has been restored.
(Appendix 12)
A program for causing a computer to perform a failure detection procedure, an extended device disconnection procedure, an extended device installation procedure, and a recovery determination procedure.
The failure detection procedure detects failures for a plurality of expansion devices included in an expansion card connected to the main unit.
The expansion device disconnection procedure disconnects the failed expansion device from the main unit when a failure of the expansion device is detected.
In the expansion device embedding procedure, after the recovery process of the failed expansion device, the expansion device after the recovery process is incorporated into the main unit.
The recovery determination procedure determines whether or not the embedded extended device has been restored.
The expansion device disconnection procedure is a program comprising disconnecting the expansion device again when it is determined by the recovery determination procedure that the incorporated expansion device has not been restored.
(Appendix 13)
The program according to Appendix 12, wherein the failure detection procedure detects a failure of the extended device by at least one process selected from the group consisting of the following (1) to (3).
(1) Receive extended device failure information from the main unit;
(2) By the failure detection procedure, the extended device is accessed to detect a failure;
(3) Receive extended device failure information from the extended device.
(Appendix 14)
Using the recovery threshold for each expansion device,
The recovery threshold is the number of times the extended device is recovered.
The program according to Appendix 12 or 13, wherein the expansion device incorporation procedure does not incorporate the expansion device that has detected a failure exceeding the recovery threshold value into the main unit by the failure detection procedure.
(Appendix 15)
Including expansion card disconnection procedure and expansion card installation procedure
In the expansion card disconnection procedure, when all the plurality of expansion devices are detached by the expansion device disconnection procedure, the expansion card including the expansion device is detached.
In the expansion card incorporating procedure, after the expansion card is restored, the expanded card after the restoration process is incorporated into the main unit.
The recovery determination procedure is the program according to any one of Supplementary note 12 to 14, which determines whether or not the incorporated expansion card has been restored.
(Appendix 16)
Including expansion card disconnection procedure and expansion card installation procedure
Using the expansion card detachment priority for each expansion device and the expansion card detachment threshold,
The expansion card disconnection threshold is a threshold for determining whether or not to disconnect an expansion card including an expansion device in which a failure has occurred.
In the expansion card disconnection procedure, when the priority of the expansion device determined to have failed in recovery by the recovery determination procedure exceeds the expansion card disconnection threshold value, the expansion card including the expansion device is detached.
In the expansion card incorporating procedure, after the expansion card is restored, the expanded card after the restoration process is incorporated into the main unit.
The recovery determination procedure is the program according to any one of Supplementary note 12 to 15, which determines whether or not the incorporated expansion card has been restored.
(Appendix 17)
A computer-readable recording medium recording the program according to any one of Supplementary Notes 12 to 16.

According to the present invention, in a system including an expansion card including a plurality of expansion devices, it is possible to detect and recover a failure in each expansion device. Therefore, according to the present invention, for example, the influence on the entire system due to the occurrence of a failure of the expansion device can be more localized, so that the availability of the system can be improved. Therefore, the present invention can be suitably used in a wide range of fields related to computer systems, for example.

10, 10A Mediation device 11 Failure detection unit 12 Expansion device disconnection unit 13 Expansion device integration unit 14 Recovery judgment unit 15 Expansion card disconnection unit 16 Expansion card installation unit 20 Failure recovery system device 21 Main unit 22 Bus 23 Expansion card (PCI card)
101 Central processing unit (CPU)
102 Memory 103 Bus 104 Input device 105 Display device 106 Communication device 107 Storage device (storage unit)

Claims (10)

Includes a failure detection unit, an expansion device disconnection unit, an expansion device integration unit, and a recovery determination unit.
The failure detection unit detects failures in a plurality of expansion devices included in the expansion card connected to the main unit, and detects failures.
When a failure of the expansion device is detected, the expansion device disconnection unit disconnects the failed expansion device from the main unit.
After the recovery process of the failed expansion device, the expansion device embedded unit incorporates the expanded device after the recovery process into the main unit.
The recovery determination unit determines whether or not the incorporated expansion device has been restored, and determines whether or not the embedded expansion device has been restored.
The expansion device arbitration device is characterized in that the expansion device disconnection unit disconnects the expansion device again when the recovery determination unit determines that the incorporated expansion device has not been restored. The extended device arbitration device according to claim 1, wherein the failure detection unit detects a failure of the extended device by at least one process selected from the group consisting of the following (1) to (3).
(1) Receive extended device failure information from the main unit;
(2) The failure detection unit accesses the expansion device to detect a failure;
(3) Receive extended device failure information from the extended device. In addition, it includes a storage unit
The storage unit stores the recovery threshold value for each expansion device, and stores the recovery threshold value.
The recovery threshold is the number of times the extended device is recovered.
The extended device arbitration device according to claim 1 or 2, wherein the extended device built-in unit does not incorporate the extended device that has detected a failure exceeding the recovery threshold into the main unit by the failure detection unit. Includes expansion card disconnection section and expansion card integration section
When all the plurality of expansion devices are separated by the expansion device disconnection unit, the expansion card disconnection unit disconnects the expansion card including the expansion device.
After the expansion card is restored, the expansion card incorporating unit incorporates the expanded card after the restoration process into the main unit.
The expansion device arbitration device according to any one of claims 1 to 3, wherein the recovery determination unit determines whether or not the incorporated expansion card has been restored. Includes storage, expansion card detachment, and expansion card integration
The storage unit stores the priority regarding the disconnection of the expansion card and the expansion card disconnection threshold value for each expansion device.
The expansion card disconnection threshold is a threshold for determining whether or not to disconnect an expansion card including an expansion device in which a failure has occurred.
When the priority of the expansion device determined to have failed in recovery by the recovery determination unit exceeds the expansion card disconnection threshold value, the expansion card disconnection unit disconnects the expansion card including the expansion device.
After the expansion card is restored, the expansion card incorporating unit incorporates the expanded card after the restoration process into the main unit.
The expansion device arbitration device according to any one of claims 1 to 4, wherein the recovery determination unit determines whether or not the incorporated expansion card has been restored. Including main unit and expansion card
The main unit comprises an expansion device arbitrator.
The expansion card is equipped with a plurality of expansion devices.
The main unit, the expansion card, and the arbitration device of the expansion device can be connected to each other via their respective I / Fs.
The expansion device arbitration device is a failure recovery system device, which is the expansion device arbitration device according to any one of claims 1 to 5. Includes failure detection process, expansion device disconnection process, expansion device installation process, and recovery determination process.
In the failure detection step, a failure is detected for a plurality of expansion devices included in the expansion card connected to the main unit.
In the expansion device disconnection step, when a failure of the expansion device is detected, the expansion device with the failure is disconnected from the main unit.
In the expansion device embedding step, after the recovery processing of the failed expansion device, the expansion device after the recovery processing is incorporated into the main unit.
The recovery determination step determines whether or not the incorporated expansion device has been restored, and determines whether or not the embedded expansion device has been restored.
The expansion device arbitration method is characterized in that, when it is determined by the recovery determination step that the incorporated expansion device has not been restored, the expansion device disconnection step disconnects the expansion device again. The extended device arbitration method according to claim 7, wherein the failure detection step detects a failure of the extended device by at least one process selected from the group consisting of the following (1) to (3).
(1) Receive extended device failure information from the main unit;
(2) By the failure detection step, the extended device is accessed and a failure is detected;
(3) Receive extended device failure information from the extended device. A program for causing a computer to perform a failure detection procedure, an extended device disconnection procedure, an extended device installation procedure, and a recovery determination procedure.
The failure detection procedure detects failures for a plurality of expansion devices included in an expansion card connected to the main unit.
The expansion device disconnection procedure disconnects the failed expansion device from the main unit when a failure of the expansion device is detected.
In the expansion device embedding procedure, after the recovery process of the failed expansion device, the expansion device after the recovery process is incorporated into the main unit.
The recovery determination procedure determines whether or not the embedded extended device has been restored.
The expansion device disconnection procedure is a program comprising disconnecting the expansion device again when it is determined by the recovery determination procedure that the incorporated expansion device has not been restored. A computer-readable recording medium on which the program according to claim 9 is recorded.

Images