JP6795782B1 - Information processing system, information processing device and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To realize appropriate use of an information processing device. The information processing system of the embodiment is an information processing system including a plurality of information processing devices and a relay device having a plurality of connection portions for connecting to the plurality of information processing devices. The first information processing system includes a power supply control unit that controls the supply of power to each of the plurality of information processing devices, and the information processing system is at least one of the plurality of information processing devices at the time of starting the information processing system. The first information processing is performed when the reception control unit that receives an abnormal signal indicating that the information processing device has failed to start and the first information processing device detects that the first information processing device has failed to start based on the abnormal signal. A transmission control unit for transmitting a request for a first instruction signal for stopping the supply of power to the device to the power supply control unit is provided. [Selection diagram] Fig. 3

Description

Embodiments of the present invention relate to information processing systems, information processing devices and programs.

There is an information processing system having a relay device having an expansion bus such as PCIe and a plurality of information processing devices (for example, a platform) connected to each other via the expansion bus.

Patent No. 6566158

However, in such an information processing system, when the entire system is started, at least one of the plurality of information processing devices may fail to start for some reason. If the start-up of the information processing device fails, the processing load is heavy to restart the entire information processing system. Therefore, it is preferable to appropriately control the information processing device whose startup has failed.

The information processing system according to the first aspect of the present invention is an information processing system including a plurality of information processing devices and a relay device having a plurality of connecting portions for connecting to the plurality of the information processing devices. The relay device includes a power supply control unit that controls the supply of power to each of the plurality of information processing devices, and any one of the plurality of information processing devices activates the information processing system. Occasionally, a reception control unit that receives an abnormal signal indicating that activation has failed in the first information processing device, which is at least one of the plurality of information processing devices, and first information based on the abnormal signal. If the boot processor detects a failure, and a transmission control unit for transmitting a request for first instruction signal for stopping the supply of power to the first information processing apparatus to the power supply controller The transmission control unit further requests a second instruction signal to start supplying power to the first information processing device after stopping the supply of the power to the first information processing device. The transmission is transmitted to the power supply control unit, and when the reception control unit transmits the second instruction signal and then receives an abnormal signal indicating that the first information processing apparatus has failed to start, the transmission is performed. The control unit does not transmit the request for the first instruction signal and the second instruction signal to the power supply control unit.

The information processing device according to the second aspect of the present invention is a first for connecting to a relay device having a plurality of first connection portions for connecting to the plurality of information processing devices via the first connection portion. Reception control for receiving an abnormal signal indicating that the first information processing device, which is at least one of the plurality of information processing devices, has failed to start when the two connection units and the plurality of information processing devices are started. When it is detected that the first information processing device has failed to start based on the abnormal signal , a request for a first instruction signal for stopping the power supply to the first information processing device is requested . and a transmission control unit that transmits to the relay apparatus, the transmission control unit further, after stopping the supply of the power to the first information processing apparatus, the power of the first information processing apparatus A request for a second instruction signal to start supply is transmitted to the relay device, and after the reception control unit transmits the second instruction signal, the first information processing device fails to start. When the indicated abnormal signal is received, the transmission control unit does not transmit the request for the first instruction signal and the second instruction signal to the relay device.

The program according to the third aspect of the present invention relates to a relay device having a plurality of first connection portions for connecting to a plurality of information processing devices, and a computer that can be connected via the first connection portion. Based on the reception step of receiving an abnormal signal indicating that the first information processing device, which is at least one of the plurality of information processing devices, has failed to start when the plurality of information processing devices are started, and the abnormal signal . When it is detected that the first information processing device has failed to start , the first information processing device transmits a request for a first instruction signal to stop the supply of power to the first information processing device . a transmission control step of, after stopping the supply of the power to the first information processing apparatus, a request for a second instruction signal to start the supply of power to the first information processing apparatus to the relay apparatus After transmitting the second transmission control step to be transmitted and the second instruction signal, the transmission control unit receives an abnormal signal indicating that the first information processing apparatus has failed to start. , A third transmission control step that does not transmit the request for the first instruction signal and the second instruction signal to the relay device .

According to the above aspect of the present invention, since the supply of electric power to the first information processing device can be stopped, appropriate use of the information processing device can be realized.

FIG. 1 is a diagram showing an example of the overall configuration of the information processing system according to the embodiment. FIG. 2 is a diagram showing an example of a hardware configuration of each device of the information processing system according to the embodiment. FIG. 3 is a diagram showing an example of a power supply configuration of the information processing system according to the embodiment. FIG. 4 is a sequence diagram showing processing at the time of starting the information processing system according to the embodiment. FIG. 5 is a flowchart showing the processing of the monitoring program of the main platform according to the embodiment. FIG. 6 is a flowchart showing a request generation process performed by the detection unit of the monitoring program according to the embodiment.

Hereinafter, examples of the information processing system, the information processing apparatus, and the program according to the present invention will be described in detail with reference to the drawings. The present invention is not limited to this embodiment.

FIG. 1 is a diagram showing an example of the overall configuration of the information processing system 1 according to the present embodiment. The information processing system 1 includes a main platform (an example of an information processing device) 10-1, a plurality of sub-platforms (an example of a plurality of information processing devices) 10-2 to 10-8, and a relay device 30. There is. The main platform 10-1 and the plurality of sub-platforms are communicably connected via the relay device 30. The combination of the main platform 10-1 and the plurality of sub-platforms 10-2 to 10-8 is referred to as a platform 10-1 to 10-8. Note that this embodiment is shown as an example, and the number of sub-platforms, slots, and endpoints may be changed as appropriate.

Platforms 10-1 to 10-8 are communicably connected via a relay device 30. Platforms 10-1 to 10-8 are inserted, for example, into slots on the board on which the relay device 30 is provided. Further, any of the plurality of slots may be in an empty state in which platforms 10-1 to 10-8 are not inserted. In the following description, it is not necessary to distinguish each platform 10-1 to 10-8, and when any platform 10-1 to 10-8 is indicated, it is described as platform 10.

Platform 10-1 is a main information processing device that manages platforms 10-2 to 10-8 and causes platforms 10-2 to 10-8 to execute various processes.

A monitor 21 and an input device 22 are connected to the platform 10-1. The monitor 21 displays various screens such as a liquid crystal display device. The input device 22 accepts various operations such as a keyboard and a mouse.

Platforms 10-2 to 10-8 are sub-information processing devices that execute, for example, AI (Artificial Intelligence) inference processing, image processing, and the like based on the requirements of platform 10-1. Further, the platforms 10-2 to 10-8 may have different functions.

Platforms 10-1 to 10-8 have a root complex (RC: Root Complex) 11-1 to 11-8 that can operate as a host side. Platforms 10-1 to 10-8 are an example of a second connection. In the following description, it is not necessary to distinguish each route complex 11-1 to 11-8, and when an arbitrary route complex 11-1 to 11-8 is indicated, it is described as the root complex 11.

The route complex 11 executes communication with each endpoint 31-1 to 1-31-8 of the relay device 30. That is, the platform 10 and the relay device 30 are communicably connected by a communication standard such as PCIe (Peripheral Component Interconnect Express). The platform 10 and the relay device 30 are not limited to PCIe and may be connected by other communication standards.

The relay device 30 has a plurality of endpoints (EPs: End Points) 31-1 to 1-31-8. The endpoints 31-1 to 1-31-8 are examples of the first connection. Further, the relay device 30 relays communication between a plurality of platforms 10 having a route complex 11 connected to endpoints 31-1 to 1-31-8.

Endpoints 31-1 to 1-31-8 perform communication with the root complex 11 of platform 10. In the following description, it is not necessary to distinguish each endpoint 31-1 to 1-31-8, and when an arbitrary endpoint 31-1 to 1-31-8 is indicated, it is described as endpoint 31.

Next, the hardware configuration of each device of the information processing system 1 will be described. FIG. 2 is a diagram showing an example of the hardware configuration of each device of the information processing system 1. The information processing system 1 includes a PSU (Power Supply Unit) 40 that supplies power to each unit.

The PSU 40 is, for example, an integrated circuit called a microcomputer or a microcontroller. The PSU 40 is connected to the processors 32 of the platforms 10-1 to 10-8 and the relay device 30.

The information processing system 1 includes platforms 10-1 to 10-8. Here, the hardware configuration of the platform 10-1 will be described as an example, and the description of the platforms 10-2 to 10-8 having the same configuration will be omitted.

Platform 10-1 is a computer that performs arithmetic processing such as AI processing and image processing. Platform 10-1 includes a root complex 11-1, a processor 12-1, and a memory 13-1. Also, they are communicably connected via the bus.

Processor 12-1 controls the entire platform 10-1. Processor 12-1 may be a multiprocessor. Further, the processor 12-1 includes, for example, a CPU (Central Processing Unit), an MPU (Micro Processing Unit), a GPU (Graphics Processing Unit), a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), and a PLD (Programmable Logic Device). ), FPGA (Field Programmable Gate Array) may be one of them. Further, the processor 12 may be a combination of two or more types of elements of the CPU, MPU, GPU, DSP, ASIC, PLD, and FPGA. In the following description, it is not necessary to distinguish processors 12-1 to 12-8, and when any processor 12-1 to 12-8 is indicated, it is referred to as processor 12.

The memory 13-1 is a storage memory including a ROM (Read Only Memory) and a RAM (Random Access Memory). Various software programs and data for this program are written in the ROM of the memory 13-1. The software program on the memory 13-1 is appropriately read and executed by the processor 12. Further, the RAM of the memory 13-1 is used as a primary storage memory or a working memory. In the following description, it is not necessary to distinguish between the memories 13-1 to 13-8, and when an arbitrary memory 13-1 to 13-8 is indicated, it is described as the memory 13.

In the platform 10, various functions are realized by the processor 12 executing a software program stored in the memory 13.

The various software programs described above do not necessarily have to be stored in the memory 13. For example, the platform 10 may read and execute a program stored in a storage medium that can be read by a medium reader or the like. The storage medium that can be read by the platform 10 corresponds to, for example, a CD-ROM, a DVD disk, a portable recording medium such as a USB (Universal Serial Bus) memory, a semiconductor memory such as a flash memory, a hard disk drive, or the like. Further, the information processing program may be stored in a device connected to a public line, the Internet, a LAN, or the like, and the platform 10 may read and execute the information processing program from these.

Next, the relay device 30 will be described. The relay device 30 includes an endpoint 31-1 to 1-31-8 provided for each platform 10, a processor 32, a memory 33, a storage unit 34, an internal bus 35, a PCIe bus 36, and a power supply control unit 37. And. In the following description, it is not necessary to distinguish each endpoint 31-1 to 1-31-8, and when an arbitrary endpoint 31-1 to 1-31-8 is indicated, it is described as endpoint 31.

The endpoint 31 is provided for each platform 10 and executes data transmission / reception. For example, when the endpoint 31 receives data from the connected platform 10, it transmits the received data to the endpoint 31 connected to the destination platform 10 via the PCIe bus 36.

For example, the route complex 11 transmits data to another platform 10 by DMA (Direct Memory Access) transfer. Further, the endpoint 31 transmits the received data to the connected platform 10 when the data is received from the endpoint 31 connected to the platform 10 from which the data is transmitted via the PCIe bus 36.

The processor 32 controls the entire relay device 30. The processor 32 may be a multiprocessor. Further, the processor 32 may be any one of, for example, CPU, MPU, GPU, DSP, ASIC, PLD, and FPGA. Further, the processor 32 may be a combination of two or more types of elements of the CPU, MPU, GPU, DSP, ASIC, PLD, and FPGA.

The memory 33 is a storage device including a ROM and a RAM. Various software programs and data for this program are written in the ROM. The program stored in the memory 33 is read into the processor 32 and executed. In addition, RAM is used as a working memory.

The storage unit 34 is a storage device such as a hard disk drive, SSD, and storage class memory, and stores various data. For example, various software programs are stored in the storage unit 34.

The internal bus 35 communicatively connects the processor 32, the memory 33, the storage unit 34, and the PCIe bus 36.

The PCIe bus 36 communicatively connects a plurality of endpoints 31 and an internal bus 35. That is, the PCIe bus 36 connects the plurality of endpoints 31 so that data can be transferred. Further, the PCIe bus 36 is, for example, a bus conforming to the PCIe standard.

The power supply control unit 37 controls the PSU 40 and controls the supply of electric power to the platform 10. The power supply control unit 37 controls so that power supply to each of the platform 10 and the relay device 30 is started when the information processing system 1 is started. Further, power-off control and power-on control for the sub-platforms 10-2 to 10-8 are also performed according to the control from the main platform 10-1.

Next, the power supply control in the information processing system 1 will be described. FIG. 3 is a diagram showing an example of the power supply configuration of the information processing system 1 according to the present embodiment.

The information processing system 1 includes a power button 50 that accepts an operation of changing the power state of the information processing system 1. The power button 50 is an operation unit that accepts an operation of starting the information processing system 1, an operation of shutting down, and an operation of forcibly shutting down. For example, the power button 50 accepts pressing while the information processing system 1 is shut down as an operation for starting the information processing system 1. Further, the power button 50 accepts pressing while the information processing system 1 is running as an operation for shutting down the information processing system 1.

Further, the information processing system 1 is not limited to the power button 50, and may accept an operation of shutting down the information processing system 1 by another method. For example, the information processing system 1 may accept an operation of shutting down the information processing system 1 on the screen of the OS (Operating System) of the main platform 10-1.

The relay device 30 includes a power supply control unit 37 that controls the PSU 40 that supplies power to the information processing system 1.

The power supply control unit 37 controls the supply of electric power using the PSU 40 to each of the main platform 10-1 and the sub-platforms 10-2 to 10-8. The power supply control unit 37 is, for example, a microcomputer.

Further, the power supply control unit 37 is not limited to the microcomputer, and may be any one of, for example, CPU, MPU, GPU, DSP, ASIC, PLD, and FPGA. Further, the power supply control unit 37 may be a combination of two or more types of elements of the CPU, MPU, GPU, DSP, ASIC, PLD, and FPGA.

The power supply control unit 37 realizes the function shown in FIG. 3 by executing a software program stored in the memory of the power supply control unit 37 by a processor such as a CPU or MPU. Specifically, the power supply control unit 37 realizes an operation input unit 311, a monitoring unit 312, a display processing unit 313, and a signal control unit 314.

The operation input unit 311 receives a power SW input signal indicating an operation received by the power button (not shown) of the information processing system 1. For example, the operation input unit 311 determines that an operation for starting the information processing system 1 has been input when the power switch input signal is in the High state. On the other hand, when the Low state is reached, it is determined that an operation for shutting down the information processing system 1 has been input.

The monitoring unit 312 monitors the status of the main platform 10-1 and the sub-platforms 10-2 to 10-8.

For example, the monitoring unit 312 monitors the power supply states of the main platform 10-1 and the sub-platforms 10-2 to 10-8. Further, the monitoring unit 312 monitors whether or not the main platform 10-1 and the sub-platforms 10-2 to 10-8 have normally completed the OS startup.

Further, the monitoring unit 312 notifies the main platform 10-1 of the operating state of the sub-platforms 10-2 to 10-8. For example, the monitoring unit 312 of the present embodiment provides boot status information including whether or not each of the sub-platforms 10-2 to 10-8 has failed to start, via the signal control unit 314 described later, to the main platform 10. Send to -1. The boot status information shall include information such as whether or not each of the sub-platforms 10-2 to 10-8 has failed to start, as well as information such as the completion of booting in the information processing system 1.

The display processing unit 313 displays error information on the display unit 41 provided in the information processing system 1 according to the monitoring result by the monitoring unit 312. The display unit 41 may be a display unit that lights up in the event of an error, or may be a liquid crystal panel or the like for displaying a character string indicating an error.

The signal control unit 314 controls the transmission and reception of signals. For example, the signal control unit 314 controls a signal transmitted or received to the PSU 40 or the platform 10 in response to a request from the monitoring unit 312 and a notification from the main platform 10-1.

For example, the signal control unit 314 transmits the monitoring result of the monitoring unit 312 as system status information at predetermined time intervals.

For example, the signal control unit 314 transmits and receives a signal such as a power on / off signal to and from the sub-platforms 10-2 to 10-8, and transmits and receives a signal such as a PS_ON_PMU # signal to and from the PSU 40.

The power on / off signal is a signal for switching the power state of the sub-platforms 10-2 to 10-8. More specifically, the power on / off signal is a signal for switching between the power ON state and the OFF state of the sub-platforms 10-2 to 10-8. Sub-platforms 10-2 to 10-8 are in the power-on state when the power-on / off signal is in the high state. On the other hand, the sub-platforms 10-2 to 10-8 are in the power-off state when the power-on / off signal is in the Low state. In the present embodiment, when the power on / off signal is in the High state, it is referred to as a power on signal, and when the power on / off signal is in the Low state, it is referred to as a power off signal.

The PS_ON_PMU # signal is a signal for switching the power supply of 12V. More specifically, the PSU 40 supplies a 12V power supply when the PS_ON_PMU # signal is in the Low state. On the other hand, the PSU 40 shuts off the 12V power supply when the PS_ON_PMU # signal is in the High state.

When the PS_ON_PMU # signal is in the Low state, 12 V of power is supplied to each of the main platform 10-1 and the sub-platforms 10-2 to 10-8.

The processor 12-1 of the main platform 10-1 controls the entire information processing system 1. The processor 12-1 realizes the function shown in FIG. 3 by executing the monitoring program 350 stored in the memory 13-1. Specifically, the processor 12-1 realizes the reception control unit 351, the detection unit 352, and the transmission control unit 353 as the monitoring program 350. Then, the monitoring program 350 receives information on the activation state of the sub-platforms 10-2 to 10-8, and based on the information, controls the sub-platforms 10-2 to 10-8 via the relay device 30. Do.

When the information processing system 1 is started, the reception control unit 351 receives boot status information regarding the startup state of the sub-platforms 10-2 to 10-8 from the relay device 30. The boot status information indicates the boot status of each of the sub-platforms 10-2 to 10-8. For example, the boot status information indicates whether or not the boot has failed in each of the sub-platforms 10-2 to 10-8. Is included.

The detection unit 352 detects whether or not to restart the power supply of the sub-platforms 10-2 to 10-8 based on the boot status information.

In the present embodiment, when the information processing system 1 is started, the sub-platforms 10-2 to 10-8 (hereinafter, the sub-platforms 10-2 to 10-8 that failed to start are referred to as the start-up failure sub-platforms. It may fail to boot on any one or more of the platforms). The failure of the activation occurs rarely, and it may be unknown whether or not an abnormality has occurred in the first place. In such a case, since the OS of the boot failure sub-platform has not started, it is difficult to restart according to the request from the main platform 10-1. Therefore, in the present embodiment, the startup failure sub-platform is forcibly terminated, the power supply is turned off, and then the power supply is restarted to prompt the startup failure sub-platform to start normally. did.

Further, in the present embodiment, after turning off the power supply of the startup failure sub-platform, the control to restart the power supply is performed only once. This is based on the idea that if the control is performed twice, the time until the information processing system 1 can start using is delayed, and the startup failure sub-platform that fails to start twice is clearly abnormal. It is based on.

In this way, when the detection unit 352 detects that any one of the sub-platforms 10-2 to 10-8 has failed to start based on the boot status information, the start failure is the first time. Instructs the transmission control unit 353 to make a power off / on request.

The transmission control unit 353 transmits a request for a power-off signal (an example of the first instruction signal) for stopping the power supply of the startup failure subplatform to the power supply control unit 37 in accordance with the instruction from the detection unit 352. Further, the transmission control unit 353 controls the power supply of a power-on signal (an example of a second instruction signal) for starting the power supply to the start-up failure sub-platform after stopping the power supply to the start-up failure sub-platform. It is transmitted to the unit 37.

Further, when the transmission control unit 353 transmits a power-on signal to the boot failure subplatform and then the reception control unit 351 receives boot status information indicating that the boot has failed again on the boot failure subplatform. Is controlled so as not to transmit the power off signal and the power on signal request to the power supply control unit 37 as described above.

Next, the processing at the time of starting the entire information processing system 1 of the present embodiment will be described. FIG. 4 is a sequence diagram showing the processing at the time of starting the information processing system 1 according to the present embodiment. In the sequence diagram shown in FIG. 4, it is assumed that the startup fails on the sub-platform 10-2.

The power control unit 37 receives a power SW input signal indicating an operation received by the power button (not shown) of the information processing system 1 (S401). Then, the power supply control unit 37 confirms the power supply state of the information processing system 1 (S402). In the example shown in FIG. 4, it is determined that the power of 12V is not supplied to the entire information processing system 1.

Therefore, the power supply control unit 37 gives an instruction to the PSU 40 to switch the PS_ON_PMU # signal to the Low state and start the power supply (S403).

The PSU 40 starts supplying 12V power to the relay device 30, the main platform 10-1, and the power control unit 37 according to the PS_ON_PMU # signal (S404 to S406).

After that, the signal control unit 314 of the power supply control unit 37 inquires about the activation state to the relay device 30 (S407). Then, the signal control unit 314 receives the response in the activated state from the relay device 30 (S408). In the sequence diagram shown in FIG. 4, it is assumed that the relay device 30 has been normally started.

The monitoring unit 312 confirms the connection status of the main platform 10-1 (S409). When the monitoring unit 312 determines that the main platform 10-1 is normally connected, the signal control unit 314 notifies the main platform 10-1 of the activation start instruction (S410).

The main platform 10-1 controls to turn on the power according to the start-up start instruction (S411). After that, the main platform 10-1 notifies the power supply control unit 37 of a response that the power supply has been normally turned on (S412).

Further, the main platform 10-1 starts the startup process (S413). According to the boot process, the BIOS and the OS are booted. At that time, the monitoring program 350 of the main platform 10-1 is also started. After that, the startup process of the main platform 10-1 is completed (S414). Then, the main platform 10-1 notifies the power supply control unit 37 of a response that the startup process is completed (S415).

The monitoring unit 312 confirms the connection status of the sub-platforms 10-2 to 10-8 (S416). When the monitoring unit 312 determines that the sub-platforms 10-2 to 10-8 are normally connected, the signal control unit 314 notifies the sub-platforms 10-2 to 10-8 of the power-on signal. (S417).

The monitoring unit 312 further confirms the operation of the sub-platforms 10-2 to 10-8 (S418). The confirmation of the operation includes, for example, confirming whether or not the fans of the sub-platforms 10-2 to 10-8 are operating normally.

When the monitoring unit 312 determines that the operation of the sub-platforms 10-2 to 10-8 is normal, the signal control unit 314 notifies the sub-platforms 10-2 to 10-8 of the activation start instruction. (S419).

After that, the information processing system 1 waits for a predetermined time to receive the activation completion notification from the sub-platforms 10-2 to 10-8 (S420). Then, the power supply control unit 37 waits for a predetermined time, and when there are sub-platforms 10-2 to 10-8 that have not transmitted the start-up completion notification, it indicates that there is a sub-platform that has failed to start up. X ”is detected (S421). In the example shown in FIG. 4, the power supply control unit 37 considers the sub-platform 10-2 that did not transmit the start-up completion notification as the start-up failure sub-platform 10-2.

Then, the signal control unit 314 transmits boot status information (notification of boot failure) indicating that the boot failure sub-platform 10-2 has been detected to the main platform 10-1 (S422).

Then, when the reception control unit 351 of the monitoring program 350 of the main platform 10-1 receives the boot status information indicating the boot failure, the abnormality detection process according to the boot status information is performed (S423). The specific processing will be described later.

Then, the transmission control unit 353 transmits a power off / on request (a request to transmit the power on signal after transmitting the power off signal) to the power supply control unit 37 (S424). ).

Then, the signal control unit 314 of the power supply control unit 37 continues to transmit the power off signal for a predetermined time to the start failure subplatform 10-2 based on the power off / on request from the main platform 10-1 (S425). ).

In the startup failure sub-platform 10-2, forced termination is performed (S426). In this way, when the power off signal is received for a predetermined time in the sub-platform, the forced termination is executed.

Then, the monitoring unit 312 confirms the power supply status of the startup failure sub-platform 10-2 (S427). Then, after the monitoring unit 312 confirms that the forced termination of the startup failure sub-platform 10-2 is completed based on the power supply state, the signal control unit 314 sends a power-on signal to the startup failure sub-platform 10-. It is transmitted to 2 (S428). Further, the signal control unit 314 also transmits a start-up start instruction as needed.

After that, in the boot failure sub-platform 10-2, the driver is loaded (S430) after the OS is booted (S429).

After that, the sub-platform 10-2 transmits a start-up completion notification indicating that the start-up is completed to the power supply control unit 37 (S431).

Then, the signal control unit 314 of the power supply control unit 37 transmits a startup completion notification indicating that the startup failure sub-platform has normally completed startup to the main platform 10-1 (S432).

By performing the above-mentioned processing, it is possible to realize normal startup for the sub-platform that has failed to start.

Next, the processing of the monitoring program 350 of the main platform 10-1 will be described. FIG. 5 is a flowchart showing the processing of the monitoring program 350 of the main platform 10-1 according to the present embodiment.

The reception control unit 351 of the monitoring program 350 stores the received boot status information in the registry of the main platform 10-1 as the system status information of the information processing system 1. The storage is performed every time the boot status information is received.

Then, the detection unit 352 refers to the system state information of the information processing system 1 in the registry (S501). Then, the detection unit 352 determines whether or not the activation monitoring is possible because the system status information includes the activation status of each of the sub-platforms 10-2 to 10-8 (S502). When it is determined that the start monitoring cannot be performed (S502: No), the process ends.

When the detection unit 352 determines that the startup monitoring is possible (S502: Yes), the detection unit 352 acquires the system state from the system state information (S503). Then, the detection unit 352 determines what kind of state the system state is (S504). When the detection unit 352 determines that "system startup is completed", the detection unit 352 ends the process. Further, when the detection unit 352 determines that "the system startup process is in progress or the main platform is being restarted", the detection unit 352 shifts to the process of S506.

Further, when the detection unit 352 determines that "startup has failed", the detection unit 352 performs a request generation process for the power supply control unit 37 (S505). In the present embodiment, for example, when a predetermined time has elapsed from the start of the start of the information processing system 1, the start completion notification is not received from any one or more of the sub-platforms 10-2 to 10-8. If this is the case, the detection unit 352 determines that the startup has failed.

The process of generating a request for the power supply control unit 37 will be described. FIG. 6 is a flowchart showing a request generation process performed by the detection unit 352 according to the present embodiment.

The detection unit 352 acquires the power state of each of the sub-platforms 10-2 to 10-8 from the system state information (S601). Next, the detection unit 352 acquires each activation state of the sub-platforms 10-2 to 10-8 from the system state information (S602). As a result, the detection unit 352 can identify the startup failure subplatform.

The detection unit 352 generates information indicating a power off / on request for the boot failure subplatform (S603).

Further, the detection unit 352 updates the system status information to "restart the sub board" (S604). As a result, the system status information is updated from "boot failure" to "subboard restart".

Returning to FIG. 5, the detection unit 352 sets the start monitoring 10-second timer (S506). That is, in the present embodiment, whether or not the system startup is completed is monitored at 10-second intervals.

Then, the detection unit 352 waits for a timer event according to the set timer (S507).

After that, the detection unit 352 starts processing according to the timer event (S508). Then, the detection unit 352 refers to the system state information (S509).

Then, the detection unit 352 determines what kind of state the system state is (S510). If the system status is "abnormal parameter", the process ends.

On the other hand, when the system state is "system startup processing or main platform restarting", the detection unit 352 acquires the latest boot status information received by the reception control unit 351 (S511). Then, the detection unit 352 updates the system state information based on the boot status information (S512).

Then, the detection unit 352 determines what kind of state the system state is after the update (S513). When the detection unit 352 determines that "system startup is completed", the detection unit 352 ends the process. Further, when the detection unit 352 determines that "the system startup process is in progress or the main platform 10-1 is being restarted", the detection unit 352 shifts to the process of S515.

In S513, when the detection unit 352 determines that "starting failure", the detection unit 352 performs a request generation process for the power supply control unit 37 (S514). The process of generating the request is the same as that of S505, and the description thereof will be omitted.

After that, the detection unit 352 sets a start monitoring 10-second timer (S515). Then, the detection unit 352 waits for a timer event according to the set timer (S516). After that, the process is performed again from S508.

On the other hand, in S510, when the system state is "subboard restart", the transmission control unit 353 transmits a power off / on request for the startup failure subplatform generated in S505 or S514 to the power control unit 37. (S517), the process is terminated.

In the present embodiment, by performing the above-mentioned control, it is possible to realize the control of turning on the power after turning off the power for the startup failure sub-platform. As described above, after the power off / on request for the startup failure subplatform is transmitted to the power control unit 37, the process is terminated. This allows a one-time power off / on request to the failed boot subplatform.

In the present embodiment, if the information processing system 1 has the above-described configuration, the power is turned off by forcibly terminating the startup failure sub-platform, so that unnecessary power supply can be suppressed. Furthermore, appropriate use of the sub-platform can be realized.

Further, in the present embodiment, since the information processing system 1 is provided with the above-described configuration, an error may occur at startup in rare cases when the power is turned on after the power is turned off by forcibly terminating the startup failure sub-platform. Appropriate use of various sub-platforms can be realized.

In the present embodiment, the information processing system 1 is provided with the above-described configuration, and information processing is performed by controlling the power-on after the power is turned off by forcibly terminating the startup failure sub-platform. It is possible to prevent the waiting time until the system 1 can be used from becoming long.

Although some embodiments of the present invention have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These novel embodiments can be implemented in various other embodiments, and various omissions, replacements, and changes can be made without departing from the gist of the invention. These embodiments and modifications thereof are included in the scope and gist of the invention, and are also included in the scope of the invention described in the claims and the equivalent scope thereof.

1 ... Information processing system, 10-1 ... Main platform, 10-2 to 10-8 ... Sub-platform, 11 ... Route complex, 30 ... Relay device, 31 ... Endpoint, 37 ... Power control unit, 311 ... Operation input unit 312 ... Monitoring unit, 313 ... Display processing unit, 314 ... Signal control unit, 350 ... Monitoring program, 351 ... Reception control unit, 352 ... Detection unit, 353 ... Transmission control unit.

Claims (3)

An information processing system including a plurality of information processing devices and a relay device having a plurality of connecting portions for connecting to the plurality of the information processing devices.
The relay device
A power supply control unit that controls the supply of electric power to each of the plurality of information processing devices is provided.
The information processing device of any one of the plurality of information processing devices
When the information processing system is started, a reception control unit that receives an abnormal signal indicating that the first information processing device, which is at least one of the plurality of information processing devices, has failed to start.
When it is detected that the first information processing apparatus fails to start based on the abnormal signal, the power supply control unit requests a first instruction signal to stop the power supply to the first information processing apparatus. and a transmission control section for transmitting to,
The transmission control unit further requests the power supply for a second instruction signal to start supplying electric power to the first information processing apparatus after stopping the supply of electric power to the first information processing apparatus. Send to the control unit
After the reception control unit transmits the second instruction signal, when the first information processing apparatus receives an abnormal signal indicating that the activation has failed, the transmission control unit receives the first instruction signal. The instruction signal of the above and the request of the second instruction signal are not transmitted to the power supply control unit.
Information processing system. A relay device having a plurality of first connection portions for connecting to a plurality of information processing devices, and a second connection portion for connecting via the first connection portion.
A reception control unit that receives an abnormal signal indicating that the first information processing device, which is at least one of the plurality of information processing devices, has failed to start when the plurality of information processing devices are started.
When it is detected that the first information processing device has failed to start based on the abnormal signal , the relay device requests a first instruction signal to stop the power supply to the first information processing device. and a transmission control section for transmitting to,
The transmission control unit further relays a request for a second instruction signal to start supplying electric power to the first information processing apparatus after stopping the supply of electric power to the first information processing apparatus. Send to device,
When the reception control unit receives an abnormal signal indicating that the first information processing apparatus has failed to start after transmitting the second instruction signal, the transmission control unit receives the first instruction signal. And the request for the second instruction signal are not transmitted to the relay device.
Information processing apparatus. A relay device having a plurality of first connection portions for connecting to a plurality of information processing devices, and a computer that can be connected via the first connection portion.
At the time of starting the plurality of information processing devices, a receiving step of receiving an abnormal signal indicating that the first information processing device, which is at least one of the plurality of information processing devices, has failed to start.
When it is detected that the first information processing device has failed to start based on the abnormal signal , the relay device requests a first instruction signal to stop the power supply to the first information processing device. The first transmission control step to transmit to
A second transmission for transmitting a request for a second instruction signal to start supplying electric power to the first information processing apparatus to the relay device after stopping the supply of the electric power to the first information processing apparatus. Control steps and
After transmitting the second instruction signal, when the first information processing apparatus receives an abnormal signal indicating that the activation has failed, the request for the first instruction signal and the second instruction signal is made. A third transmission control step that does not transmit to the relay device, and
A program to execute.

Images