Control device, information processing device, information processing system, and control method
The control device addresses the challenge of maintaining server processing continuity during BMC failures by detecting and monitoring BMC failures, allowing for continued operation without duplicating BMC hardware, thus reducing costs.
Patent Information
- Application Number
- JP2024039701
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- Filing Date
- 2024-03-14
- Publication Date
- 2025-06-17
- Estimated Expiration
- 2044-03-14
AI Technical Summary
Existing server technologies face challenges in maintaining processing continuity when a Baseboard Management Controller (BMC) fails, while also striving to reduce costs associated with hardware duplication.
A control device is implemented on an information processing device, equipped with a detection unit to identify BMC failures, a monitoring unit to monitor target components in connected devices, and an output unit to notify abnormalities, thereby enabling continued processing without the need for BMC duplication.
This solution allows for continued BMC processing in devices experiencing BMC failures while maintaining cost efficiency, as it eliminates the need for duplicating BMC hardware.
Smart Images

Figure 0007693881000001_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to a control device, an information processing device, an information processing system, and a control method.
Background Art
[0002] Since it is required to store as many servers as possible in a limited area, in addition to cost reduction, high density is required for servers. However, in order to improve the fault tolerance of servers, generally, duplication of hardware including a BMC (Baseboard Management Controller) is performed. Duplication requires two equivalent devices, which is a factor hindering cost reduction.
[0003] Patent Document 1 describes a BMC including two independent processors.
Prior Art Documents
Patent Documents
[0004]
Patent Document 1
Summary of the Invention
Problems to be Solved by the Invention
[0005] In the technology of Patent Document 1, there is a possibility of cost reduction compared with duplication of the BMC. However, when a failure occurs in which the BMC itself cannot operate, the device including the BMC described in Patent Document 1 cannot continue the processing performed by the BMC.
[0006] One of the objects of the present disclosure is to provide a control device, an information processing device, an information processing system, and a control method that can continue the processing by the BMC for a device in which a failure of the BMC of the device occurs while suppressing the cost.
Means for Solving the Problems
[0007] A control device according to an aspect of the present disclosure is a control device mounted on an information processing device, and includes: a detection unit that detects a failure of a connection destination control device of a connection destination information processing device connected to the information processing device; a monitoring unit that monitors a connection destination monitoring target that is a monitoring target in the connection destination information processing device when a failure of the connection destination control device is detected; and an output unit that further outputs information indicating an abnormality of the connection destination monitoring target when an abnormality of the connection destination monitoring target is detected by monitoring the connection destination monitoring target.
[0008] A control method according to an aspect of the present disclosure is such that a control device mounted on an information processing device detects a failure of a connection destination control device of a connection destination information processing device connected to the information processing device, monitors a connection destination monitoring target that is a monitoring target in the connection destination information processing device when a failure of the connection destination control device is detected, and outputs information indicating an abnormality of the connection destination monitoring target when an abnormality of the connection destination monitoring target is detected by monitoring the connection destination monitoring target.
Effect of the Invention
[0009] The present disclosure has an effect that, while suppressing costs, processing by the BMC for a device in which a failure of the BMC of the device has occurred can be continued.
Brief Description of the Drawings
[0010]
Figure 1
Figure 2A
Figure 2B
Figure 3
Figure 4
Figure 5
Figure 6
Figure 7
Figure 8
Figure 9
Figure 10
Figure 11
Figure 12
Figure 13
Figure 14
Figure 15
Embodiments for Carrying Out the Invention
[0011] Next, embodiments of the present disclosure will be described in detail with reference to the drawings. In the drawings of the present disclosure, information is exchanged between components connected by lines. However, the combinations of components that exchange information are not necessarily limited to the combinations of components connected by lines.
[0012] <First Embodiment> First, the first embodiment of the present disclosure will be described in detail with reference to the drawings.
[0013] <Configuration> FIG. 1 is a block diagram showing an example of the configuration of a server according to the present disclosure.
[0014] Hereinafter, the configuration of the server according to the first embodiment of the present disclosure will be described in detail with reference to FIG. 1.
[0015] Server 101 has a reporting IF (Interface) 102, a BMC 103, a BMC monitoring device 104, an I2C (Inter-Integrated Circuit) switch 105, an I2C connector 106, a fan 107, and a temperature sensor 108.
[0016] Server 201 is a server of the same model as server 101. Similar to server 101, server 201 has a reporting IF 202, a BMC 203, a BMC monitoring device 204, an I2C switch 205, an I2C connector 206, a fan 207, and a temperature sensor 208.
[0017] The BMC, I2C switch, I2C connector, fan, and temperature sensor on server 101 and server 201 are each I2C-connected, and a unique I2C address is assigned to each server.
[0018] The I2C switch has an upstream pair and a downstream pair. An I2C bus of any downstream pair can be connected or disconnected from the upstream side of the I2C switch.
[0019] A bus to the BMC and the I2C connector is connected to the upstream pair of the I2C switch. Temperature sensors and fans are connected to the downstream pair of the I2C switch.
[0020] I2C connectors 106 and 206 are connected by an I2C bus, respectively.
[0021] FIG. 2A is a block diagram showing the functions of the BMC according to the present disclosure.
[0022] Figure 2B is a block diagram showing the functions of the BMC monitoring device according to the present disclosure.
[0023] Hereinafter, with reference to FIGS. 2A and 2B, the functions of the BMCs 103, 203, the BMC monitoring devices 104, and 204 in the present embodiment will be described.
[0024] The BMCs 103 and 203 have the same functions. In the following description, the BMCs 103 and 203 are collectively referred to as the BMC. The BMC monitoring devices 104 and 204 have the same functions. In the following description, the BMC monitoring devices 104 and 204 are collectively referred to as the BMC monitoring device.
[0025] The BMC has an external notification function 301 for notifying any content to the outside via a notification IF.
[0026] The BMC has a sensor monitoring function 302 for monitoring whether there is an abnormal temperature reading using the I2C address of the temperature sensor.
[0027] The BMC has an I2C access function 303 for accessing any I2C address.
[0028] The BMC has an I2C bus operation function 308 for accessing the I2C switch connected to the BMC using the I2C access function 303 and performing connection and disconnection of the I2C buses of any downstream pair of the connected I2C switches.
[0029] The BMC monitoring device has a failure monitoring function 304 for monitoring the failure of the BMC on its own server (i.e., the server on which the BMC monitoring device is mounted).
[0030] The BMC monitoring device has a BMC stop function 305 for making the BMC inoperable by continuously asserting a reset to the BMC.
[0031] The BMC monitoring device has a switch reset function 306 that resets the I2C switch.
[0032] The BMC monitoring device has an address change function 307 that changes the address of the I2C switch to a unique address A or address B. In other words, the address change function 307 switches the address of the I2C switch between the unique address A and address B. Address A and address B are addresses appropriately determined in advance. When no abnormality is detected in the BMC, the address change function 307 sets the address of the I2C switch to, for example, address A. When an abnormality is detected in the BMC, the address change function 307 sets the address of the I2C switch to, for example, address B. Address A and address B are also denoted as I2C address A and I2C address B, respectively.
[0033] The I2C switch has an upstream pair and a downstream pair. The downstream pair can be switched between connection and disconnection by the BMC.
[0034] The I2C switch is configured such that the I2C buses of all downstream pairs are in a disconnected state after reset.
[0035] <Operation> Next, the operation of the first embodiment of the present disclosure will be described in detail with reference to the drawings.
[0036] FIG. 3 is a flowchart showing an example of the operation when the power of the BMC monitoring device according to the present disclosure is turned on.
[0037] Hereinafter, the operation of the BMC monitoring device according to the first embodiment of the present disclosure will be described in detail with reference to FIG. 3. Hereinafter, as the operation of the BMC monitoring device, the operation of the BMC monitoring device 104 will be described. Note that the BMC monitoring device 204 also performs the same operation as the BMC monitoring device 104. The operation of the BMC monitoring device 204 is represented by the description in which the components of the server 101 and the corresponding components of the server 201 are interchanged in the following description.
[0038] After the AC (Alternating Current) is turned on (in other words, when the power supply of the server 101 is turned on), the BMC monitoring device 104 starts monitoring by the failure monitoring function 304 (step S11).
[0039] When the BMC monitoring device 104 has not detected a failure of the BMC 103 (NO in step S12), the BMC monitoring device 104 continues monitoring by the failure monitoring function 304 (step S11). When the BMC monitoring device 104 detects a failure of the BMC 103 (YES in step S12), the BMC monitoring device 104 stops the BMC 103 using the BMC stop function 305 so that the BMC 103 cannot operate (step S13). Next, the BMC monitoring device 104 changes the I2C address of the I2C switch 105 from address A to address B using the address change function 307 (step S14). Finally, the BMC monitoring device 104 resets the I2C switch 105 using the switch reset function 306 (step S15). By this operation, even when the downstream pair of the I2C switch 105 is in a connected state by the BMC 103, the downstream pair of the I2C switch 105 can be set to a disconnected state.
[0040] FIGS. 4 and 5 are flowcharts showing examples of the operation of the BMC according to the present disclosure.
[0041] Hereinafter, the operation of the BMC according to the first embodiment of the present disclosure will be described in detail with reference to FIGS. 4 and 5. Hereinafter, as the operation of the BMC, the operation of BMC203 will be described. Note that BMC103 also performs the same operation as that of BMC203. The operation of BMC103 is represented by the description in which the components of server 101 and the corresponding components of server 201 are interchanged in the following description.
[0042] After the AC of server 201 is turned on (in other words, when the power is turned on), BMC203 performs the following shown in FIG. 4.
[0043] BMC203 uses the sensor monitoring function 302 to monitor whether there is any abnormality in the temperature sensor 208 (step S21).
[0044] If there is an abnormality (YES in step S22), BMC203 uses the external notification function 301 to notify that a failure has occurred in server 201 via the notification IF202 (step S23). If there is no abnormality (NO in step S22), BMC203 then performs the operation of step S24.
[0045] BMC203 uses the I2C access function 303 to confirm whether it can access the I2C switch 105 using address B (step S24). If it cannot access (NO in step S24), the operation of BMC203 returns to step S21. If it can access (YES in step S24), BMC203 can indirectly detect that a failure has occurred in BMC103. In this case, BMC203 then performs the operation shown in FIG. 5.
[0046] When BMC203 detects a failure in BMC103, BMC203 performs the following operation shown in FIG. 5.
[0047] BMC203 uses the external notification function 301 to notify the outside that a failure has occurred in BMC103 via the notification IF202 (step S31).
[0048] Using the I2C address A, the BMC 203 disconnects the I2C downstream pair (i.e., the downstream switch of the I2C switch 205) from the fan 207 and the temperature sensor 208 through the I2C bus operation function 308 (step S32). Access to the I2C switch 205 is performed by accessing using the address A.
[0049] Using the I2C address B, the BMC 203 switches the connection of the downstream pair of the I2C switch 105 to the connection through the I2C bus operation function 308 via the I2C connector 206 and the I2C connector 106 (step S33). Access to the I2C switch 105 is performed by accessing using the I2C address B. By the operations of step S32 and step S33, the BMC 203 can access the temperature sensor 108 with the same I2C address as the temperature sensor 208.
[0050] The BMC 203 monitors the temperature sensor 108 through the sensor monitoring function 302 (step S34).
[0051] If there is an abnormality (YES in step S35), the BMC 203 takes necessary measures such as rotating the fan 107 at high speed, and then makes a notification using the notification IF102 through the external notification function 301 (step S36). If there is no abnormality (NO in step S35), the BMC 203 then performs the operation of step S37.
[0052] The BMC 203 switches the downstream pair of the I2C switch 105 to disconnection using the I2C address B through the I2C bus operation function 308 (step S37).
[0053] In step S37, the BMC 203 switches the downstream pair of the I2C switch 205 to connection using the I2C address A through the I2C bus operation function 308.
[0054] The BMC 203 monitors the temperature sensor 208 through the sensor monitoring function 302 (step S38).
[0055] Thereafter, BMC203 repeatedly executes the operations from step S33 to step S38.
[0056] By making the I2C addresses under the I2C switch of other servers connected to the I2C connector common, it becomes possible to access the sensors with the same I2C addresses as when accessing one's own server. This has the effect of reducing the manufacturing cost of HW (Hardware) and the modification and evaluation costs of BMC FW (Firmware).
[0057] In the above description, an example where BMC203 detects a failure of BMC103 is given. However, even when BMC203 fails, BMC103 can similarly detect the failure, report it, and monitor the sensors.
[0058] Figure 3 shows the operation of the BMC monitoring device 104 after AC ON. The BMC monitoring device 104 normally monitors BMC103. If there is an abnormality, it stops BMC103, changes the I2C switch 105 to address B, and resets the I2C switch.
[0059] Figure 4 shows the operation of BMC203 under normal conditions. BMC203 periodically monitors the temperature sensor 208. By monitoring the temperature sensor 208, it confirms that the temperature inside the server is normal. Also, by monitoring whether access is possible at address B, it indirectly monitors whether there is an abnormality in BMC103.
[0060] Figure 5 describes the processing after BMC203 detects a failure of BMC103. While switching the downstream pair of the I2C switch, BMC203 reports if there is an abnormality in the sensor.
[0061] <Effect> This embodiment has the effect that, while suppressing costs, the processing by the BMC for a device in which a failure of the BMC of the device (for example, a server) has occurred can be continued.
[0062] The reason is that when the failure monitoring function of the BMC monitoring device of the server detects a failure of the BMC of that server, the address changing function 307 sets the address of the I2C switch of that server to the address set when a BMC failure is detected. The above-mentioned address B is the address set when a BMC failure is detected. And the BMCs of other servers connected to that server perform monitoring via the I2C switch to which address B is assigned in addition to monitoring via the I2C switch to which address A is assigned. Thereby, the processing by the BMC for the device in which the BMC failure has occurred is continued by the BMCs of other devices. Also, in this embodiment, there is no need to duplicate the BMC. Therefore, the cost is suppressed.
[0063] <Modification Example of the First Embodiment> In the first embodiment of the present disclosure, the BMC only monitored the temperature sensor, but in addition, the BMC may also monitor a fan rotation speed sensor, a voltage sensor, etc., and report an abnormality when there is an abnormality.
[0064] Also, in the first embodiment of the present disclosure, an example of two servers was shown, but the number of servers may be three or more. In that case, a plurality of I2C connectors (for example, the number of I2C connectors obtained by subtracting 1 from the number of servers) are prepared for each of the servers. And three or more servers are connected to each other via the I2C connectors. By doing so, it is also possible to monitor the failure of the BMC among a plurality of servers. In that case, the address of the I2C switch at the time of failure is determined in advance so as to be unique among the servers. And by monitoring the I2C address, it is possible to monitor the failure of the BMC among a plurality of servers. In this case, all the servers may monitor other servers. The server with the highest monitoring priority previously assigned to the servers among the normal servers may monitor other servers. The priority may be determined as appropriate. A unique priority may be determined for each of the plurality of servers. The priority of other servers may be determined for each server to be monitored.
[0065] The BMC may store the values obtained from the sensors of other servers in the memory and display the sensor values of other servers to the user by having an IF such as a Web UI (User Interface).
[0066] <Second Embodiment> Next, the second embodiment of the present disclosure will be described in detail with reference to the drawings. This embodiment is an embodiment that schematically represents the first embodiment.
[0067] <Configuration> FIG. 6 is a block diagram showing an example of the configuration of the information processing system according to the present disclosure.
[0068] Hereinafter, the configuration of the information processing system according to the second embodiment of the present disclosure will be described in detail with reference to FIG. 6.
[0069] In the example shown in FIG. 6, the information processing system 1 includes an information processing apparatus 10 and an information processing apparatus 20.
[0070] The information processing apparatus 10 includes a control apparatus 11, a control apparatus monitoring apparatus 12, a switch 13, a monitoring target 14, an interface unit 15, and an external interface unit 16.
[0071] The information processing apparatus 20 includes a control apparatus 21, a control apparatus monitoring apparatus 22, a switch 23, a monitoring target 24, an interface unit 25, and an external interface unit 26.
[0072] The information processing apparatus 10 corresponds to the server 101 of the first embodiment. The information processing apparatus 10 is the server 101 of the first embodiment described schematically. The information processing apparatus 20 corresponds to the server 201 of the first embodiment. The information processing apparatus 20 is the server 201 of the first embodiment described schematically.
[0073] The control device 11 and the control device monitoring device 12 will be described in detail later. The control device 11 corresponds to the BMC 103 of the first embodiment. The control device monitoring device 12 corresponds to the BMC monitoring device 104 of the first embodiment.
[0074] The switch 13 is a switch that switches the connection state between the control device 11 and the interface unit 15 and the monitoring target 14 between a connected state, which is a connected state, and a disconnected state, which is a disconnected state, by controlling the devices connected to the switch 13. The devices connected to the switch 13 that controls the switch 13 are, for example, the control device 11 and the control device 21. When the switch 13 is reset by, for example, the control device monitoring device 12, it enters the disconnected state.
[0075] The monitoring target 14 is the object of monitoring in the information processing device 10. Specifically, the monitoring target 14 is, for example, a sensor (such as a temperature sensor) that measures the state of the information processing device 10.
[0076] The interface unit 15 mediates communication (I2C communication) between the information processing device 10 and the information processing device 20.
[0077] The external interface unit 16 is an interface that mediates the output to the outside by the control device 11.
[0078] The switch 13 corresponds to the I2C switch 105 of the first embodiment. The monitoring target 14 corresponds to the fan 107 and the temperature sensor 108 of the first embodiment. The interface unit 15 corresponds to the I2C connector 106 of the first embodiment. The external interface unit 16 corresponds to the notification IF 102 of the first embodiment.
[0079] The control device 21 and the control device monitoring device 22 will be described in detail later. The control device 21 corresponds to the BMC 203 of the first embodiment. The control device monitoring device 22 corresponds to the BMC monitoring device 204 of the first embodiment.
[0080] Switch 23 is a switch that switches the connection state between the control device 21 and the interface unit 25 and the monitoring target 24 between a connected state (a connected state) and a disconnected state (a disconnected state) under the control of a device connected to the switch 23. The devices connected to the switch 23 that control the switch 23 are the control device 11 and the control device 21. When the switch 23 is reset by, for example, the control device monitoring device 22, it enters the disconnected state.
[0081] The monitoring target 24 is a target for monitoring in the information processing device 20. Specifically, the monitoring target 24 is, for example, a sensor (such as a temperature sensor) that measures the state of the information processing device 20.
[0082] The interface unit 25 mediates communication (I2C communication) between the information processing device 10 and the information processing device 20.
[0083] The external interface unit 26 is an interface that mediates the output to the outside by the control device 21.
[0084] The switch 23 corresponds to the I2C switch 205 of the first embodiment. The monitoring target 24 corresponds to the fan 207 and the temperature sensor 208 of the first embodiment. The interface unit 25 corresponds to the I2C connector 206 of the first embodiment. The external interface unit 26 corresponds to the reporting IF 202 of the first embodiment.
[0085] The control device 11, the switch 13, the monitoring target 14 (for example, the fan 107 and the temperature sensor 108), and the interface unit 15 are connected by, for example, an I2C bus. The control device 11, the switch 13, the monitoring target 14 (for example, the fan 107 and the temperature sensor 108), and the interface unit 15 are assigned I2C addresses (hereinafter, also simply referred to as addresses) that are unique in the information processing device 10.
[0086] The control device 21, the switch 23, the monitoring target 24 (for example, the fan 207 and the temperature sensor 208), and the interface unit 25 are connected by, for example, an I2C bus. An I2C address (hereinafter, also simply referred to as an address), which is unique in the information processing device 20, is assigned to the control device 21, the switch 23, the monitoring target 24 (for example, the fan 207 and the temperature sensor 208), and the interface unit 25.
[0087] In the information processing device 10 and the information processing device 20, the same address is assigned to the corresponding components. That is, the address assigned to the control device 11 is the same as the address assigned to the control device 21. The address assigned to the switch 13 is the same as the address assigned to the switch 23. The address assigned to the monitoring target 14 is the same as the address assigned to the monitoring target 24. Specifically, the address assigned to the fan 107 is the same as the address assigned to the fan 207. The address assigned to the temperature sensor 108 is the same as the address assigned to the temperature sensor 208. The address assigned to the interface unit 15 is the same as the address assigned to the interface unit 25.
[0088] In the present disclosure, among these, the addresses assigned to the switch 13 and the switch 23 are referred to as switch addresses. The switch address corresponds to the address A in the first embodiment.
[0089] The information processing device 10 and the information processing device 20 are connected to each other via the interface unit 15 and the interface unit 25. The control device 11 can access the switch 23 via the I2C bus. The control device 21 can access the switch 13 via the I2C bus.
[0090] Note that the control device 11 can access a component (for example, the switch 13, the monitoring target 14 (for example, the fan 107 or the temperature sensor 108), or the interface unit 15) using the address assigned to the component. The control device 21 can access a component (for example, the switch 23, the monitoring target 24 (for example, the fan 207 or the temperature sensor 208), or the interface unit 25) using the address assigned to the component.
[0091] As described above, there may be a case where components to which the same address (hereinafter referred to as a common address) can be accessed via the I2C bus exist in both the information processing device 10 and the information processing device 20. In such a situation, in the information processing device 10, when the control device 11 accesses a component using the common address, the control device 11 is configured to access a component included in the information processing device 10 among the components to which the common address is assigned. In such a situation, in the information processing device 20, when the control device 21 accesses a component using the common address, the control device 21 is configured to access a component included in the information processing device 20 among the components to which the common address is assigned.
[0092] When either one of the components to which the common address is assigned in the information processing device 10 and the information processing device 20 is disconnected from the I2C bus by a switch (the switch 13 or the switch 23), only the component that is not disconnected is in a state where it can be accessed. In such a situation, in the information processing device 10, when the control device 11 accesses a component using the common address, the control device 11 is configured to access a component that is not disconnected among the components to which the common address is assigned. In such a situation, in the information processing device 20, when the control device 21 accesses a component using the common address, the control device 21 is configured to access a component that is not disconnected among the components to which the common address is assigned.
[0093] The access by the above-described control device 11 represents the access by the components of the control device 11, which will be described below. The access by the above-described control device 21 represents the access by the components of the control device 21, which will be described below.
[0094] <Control device> Next, the control device according to the second embodiment of the present disclosure will be described in detail with reference to the drawings.
[0095] FIG. 7 is a block diagram showing an example of the configuration of the control device according to the present disclosure.
[0096] Hereinafter, the control device according to the second embodiment of the present disclosure will be described in detail with reference to FIG. 7.
[0097] As shown in FIG. 7, the control device 11 and the control device 21 each include a detection unit 31, a monitoring unit 32, and an output unit 33.
[0098] <Control device monitoring device> Next, the control device monitoring device according to the second embodiment of the present disclosure will be described in detail with reference to the drawings.
[0099] FIG. 8 is a block diagram showing an example of the configuration of the control device monitoring device according to the present disclosure.
[0100] Hereinafter, the control device monitoring device according to the second embodiment of the present disclosure will be described in detail with reference to FIG. 8.
[0101] The control device monitoring device 12 and the control device monitoring device 22 each include a control device failure detection unit 34, a control device stop unit 35, an address change unit 36, and a reset unit 37.
[0102] In the following description, an information processing device including a component will be simply referred to as an information processing device. In addition, another information processing device connected to the information processing device including the component will be referred to as a connection destination information processing device.
[0103] The control device included in the information processing device containing the component is simply referred to as the control device. The control device included in another information processing device connected to the information processing device containing the component is referred to as the destination control device.
[0104] The control device monitoring device included in the information processing device containing the component is simply referred to as the control device monitoring device. The control device monitoring device included in another information processing device connected to the information processing device containing the component is referred to as the destination control device monitoring device.
[0105] The switch included in the information processing device containing the component is simply referred to as the switch. The switch included in another information processing device connected to the information processing device containing the component is referred to as the destination switch.
[0106] The monitoring target included in the information processing device containing the component is simply referred to as the monitoring target. The monitoring target included in another information processing device connected to the information processing device containing the component is referred to as the destination monitoring target.
[0107] For example, when the component is the detection unit 31 and the control device containing the detection unit 31 is the control device 11, the control device 11 is included in the information processing device 10. In such a case, the information processing device represents the information processing device 10. The destination information processing device represents the information processing device 20. The control device indicates the control device 11. The destination control device indicates the control device 21. The control device monitoring device indicates the control device monitoring device 12. The destination control device monitoring device indicates the control device monitoring device 22. The switch indicates the switch 13. The destination switch indicates the switch 23. The monitoring target indicates the monitoring target 14. The destination monitoring target indicates the monitoring target 24.
[0108] For example, when the component is the control device failure detection unit 34 and the control device monitoring device including the control device failure detection unit 34 is the control device monitoring device 22, the control device monitoring device 22 is included in the information processing device 20. In such a case, the information processing device represents the information processing device 20. The destination information processing device represents the information processing device 10. The control device indicates the control device 21. The destination control device indicates the control device 11. The control device monitoring device indicates the control device monitoring device 22. The destination control device monitoring device indicates the control device monitoring device 12. The switch indicates the switch 23. The destination switch indicates the switch 13. The monitoring target indicates the monitoring target 24. The destination monitoring target indicates the monitoring target 14.
[0109] However, when there is a description specifying the information processing device in which the component is included, it is not limited to the above description. For example, the description of the detection unit 31 included in the destination information processing device represents the detection unit 31 included in the information processing device that has been previously specified as the destination information processing device among the information processing device 10 and the information processing device 20.
[0110] <Control device failure detection unit 34> The control device failure detection unit 34 detects a failure of the control device of the information processing device in which the control device failure detection unit 34 is included.
[0111] The control device failure detection unit 34 corresponds to the failure monitoring function 304 of the first embodiment.
[0112] <Control device stop unit 35> When a failure of the control device is detected (in other words, when the control device fails), the control device stop unit 35 stops the control device.
[0113] The control device stop unit 35 corresponds to the BMC stop function 305 of the first embodiment.
[0114] <Address change unit 36> When a failure of the control device is detected (in other words, when the control device fails), the address change unit 36 changes the address of a switch (for example, switch 13 or switch 23) included in the information processing device that includes the address change unit 36 to the failure-time address.
[0115] The failure-time address is set as the address used for access from another information processing device connected to the information processing device that includes the control device to the information processing device that includes the control device when the control device fails. Specifically, the failure-time address is the address set as the address of the switch included in the information processing device that includes the failed control device when the control device fails. The address change unit 36 changes the address of the switch included in the information processing device that includes the address change unit 36 (that is, the information processing device that includes the failed control device) to the failure-time address when a failure of the control device is detected. Therefore, the failure-time address is an address that becomes available when the control device fails. The failure-time address is predetermined. The failure-time address corresponds to address B of the first embodiment.
[0116] The address change unit 36 corresponds to the address change function 307 of the first embodiment.
[0117] <Reset unit 37> When a failure of the control device is detected (in other words, when the control device fails), the reset unit 37 resets a switch (for example, switch 13 or switch 23) included in the information processing device that includes the reset unit 37.
[0118] In the present disclosure, when a switch is reset, the connection state between the control device to which the switch is connected and the monitoring target located at the end of the switch becomes a disconnected state, i.e., a cut-off state. Note that the control device to which the switch is connected is a control device connected to the switch by an I2C bus and a control device connected to the switch by an I2C bus via interface unit 15 and interface unit 25. The control device connected to the switch by an I2C bus is a control device included in the information processing device including the switch. The control device connected to the switch by an I2C bus via interface unit 15 and interface unit 25 is a control device included in another information processing device connected to the information processing device including the switch.
[0119] In other words, when a failure of the control device is detected (in other words, when the control device fails), the reset unit 37 sets the connection state between the monitoring target connected to the switch included in the information processing device including the reset unit 37 and the control device to a disconnected state. As described above, this control device is a control device of the information processing device including the reset unit 37 and a control device of another information processing device connected to the information processing device including the reset unit 37.
[0120] Thus, when the switch is reset, the control device cannot access the monitoring target connected to the reset switch.
[0121] The reset unit 37 corresponds to the switch reset function 306 of the first embodiment.
[0122] <Detection unit 31> The detection unit 31 detects a failure of the connection destination control device included in the connection destination information processing device.
[0123] As described above, when the connection destination control device included in the control device and the connection destination information processing device is not faulty, there is no device to which the failure-time address is assigned. In this case, access using the failure-time address (in other words, access to the device to which the failure-time address is assigned) fails. When the connection destination control device included in the connection destination information processing device fails, the address of the connection destination switch included in the connection destination information processing device is changed to the failure-time address. When the address of the connection destination switch is changed to the failure-time address, access using the failure-time address (in other words, access to the device to which the failure-time address is assigned) succeeds. The detection unit 31 detects a failure of the connection destination control device when access using the failure-time address succeeds.
[0124] The detection unit 31 corresponds to the I2C access function 303 of the first embodiment.
[0125] <Monitoring unit 32> When a failure of the connection destination control device is detected, the monitoring unit 32 monitors the connection destination monitoring target to be monitored in the connection destination information processing device.
[0126] Specifically, the monitoring unit 32 first sets the state of the switch indicated by the switch address (that is, the switch included in the information processing device including the monitoring unit 32) to a disconnected state in which the connection between the monitoring target connected to the switch and the control device is disconnected. Then, the monitoring unit 32 changes the state of the connection destination switch indicated by the failure-time address to a connected state in which the connection between the monitoring target connected to the connection destination switch and the control device is connected. Then, the monitoring unit 32 monitors the monitoring target connected to the connection destination switch.
[0127] The monitoring unit 32 determines, for example, whether there is any abnormality in the monitoring target connected to the destination switch. When the monitoring target is a temperature sensor, the monitoring unit 32 determines, for example, whether the value indicated by the temperature sensor of the destination information processing device is within the normal range. When the value indicated by the temperature sensor of the destination information processing device indicates an abnormality that is higher than the normal range, the monitoring unit 32 may increase the rotation speed of the fan of the destination information processing device. When the monitoring target is a fan, the monitoring unit 32 may determine whether the rotation speed of the fan is within the normal range. The normal range of the rotation speed of the fan may be, for example, a normal range determined according to the temperature indicated by the temperature sensor.
[0128] Note that the monitoring unit 32 also monitors the monitoring targets of the information processing device including the monitoring unit 32. When a failure of the destination control device is detected, the monitoring unit 32 may alternately perform the monitoring of the destination monitoring targets of the destination information processing device and the monitoring of the monitoring targets of the information processing device including the monitoring unit 32. When performing the monitoring of the destination monitoring targets of the destination information processing device, the monitoring unit 32 first sets the connection state of the switch to the disconnected state and sets the connection state of the destination switch to the connected state. Then, the monitoring unit 32 performs the monitoring of the destination monitoring targets of the destination information processing device. When performing the monitoring of the monitoring targets of the information processing device including the monitoring unit 32, the monitoring unit 32 sets the connection state of the destination switch to the connected state and sets the connection state of the switch of the information processing device including the monitoring unit 32 to the connected state. Then, the monitoring unit 32 performs the monitoring of the monitoring targets of the information processing device including the monitoring unit 32.
[0129] The monitoring unit 32 identifies the destination monitoring target in which an abnormality has been detected among the destination monitoring targets. The monitoring unit 32 may also identify the content of the abnormality detected in the destination monitoring target in which the abnormality has been detected.
[0130] The monitoring unit 32 identifies the monitoring target in which an abnormality has been detected among the monitoring targets. The monitoring unit 32 may also identify the content of the abnormality detected in the monitoring target in which the abnormality has been detected.
[0131] The monitoring unit 32 corresponds to the sensor monitoring function 302 and the I2C bus operation function 308 of the first embodiment.
[0132] <Output unit 33> When a failure of the connected control device is detected, the output unit 33 outputs information indicating the failure of the connected control device.
[0133] When an abnormality of a connection destination monitoring target that is a monitoring target in the connection destination information processing device is detected, the output unit 33 outputs information indicating the abnormality of the connection destination monitoring target. The information indicating the abnormality of the connection destination monitoring target includes, for example, information specifying the connection destination monitoring target in which the abnormality has been detected. The information indicating the abnormality of the connection destination monitoring target may include, for example, information representing the content of the abnormality detected in the connection destination monitoring target in which the abnormality has been detected.
[0134] When an abnormality of a monitoring target that is a monitoring target in the information processing device is detected, the output unit 33 outputs information indicating the abnormality of the monitoring target. The information indicating the abnormality of the monitoring target includes, for example, information specifying the monitoring target in which the abnormality has been detected. The information indicating the abnormality of the monitoring target may include, for example, information representing the content of the abnormality detected in the monitoring target in which the abnormality has been detected.
[0135] The output unit 33 corresponds to the external notification function 301 of the first embodiment.
[0136] <Operation> Next, the operation according to the second embodiment of the present disclosure will be described in detail with reference to the drawings.
[0137] FIG. 9 is a flowchart showing an example of the operation of the control device monitoring device according to the present disclosure.
[0138] Hereinafter, the operation of the control device monitoring device according to the second embodiment of the present disclosure will be described in detail with reference to FIG. 9. When the control device is the control device 11, FIG. 9 shows the operation of the control device monitoring device 12. When the control device is the control device 21, FIG. 9 shows the operation of the control device monitoring device 22.
[0139] In the example shown in FIG. 9, the control device failure detection unit 34 detects a failure of the control device (step S101). If no failure is detected (NO in step S102), the control device monitoring device repeats the operation of step S101.
[0140] If a failure is detected (YES in step S102), the control device stop unit 35 stops the operation of the control device (step S103).
[0141] The reset unit 37 sets the state of the switch to the disconnected state (step S104). Then, the address change unit 36 changes the address of the switch to the failure-time address (step S105). Note that the operation of step S104 may be performed after the operation of step S105. The operation of step S104 may be performed in parallel with the operation of step S105.
[0142] FIG. 10 is a flowchart showing an example of the operation of the control device according to the present disclosure.
[0143] Hereinafter, the operation of the control device according to the second embodiment of the present disclosure will be described in detail with reference to FIG. 10. When the control device is the control device 11, the destination control device is the control device 21. The information processing device is the information processing device 10. The destination information processing device is the information processing device 20. When the control device is the control device 21, the destination control device is the control device 11. The information processing device is the information processing device 20. The destination information processing device is the information processing device 10.
[0144] In the example shown in FIG. 10, first, the control device executes an abnormality detection process, which is a process of monitoring a monitoring target that is the target of monitoring in the information processing device (step S201). The abnormality detection process will be described in detail later.
[0145] Next, the detection unit 31 detects a failure of the destination control device by accessing the failure-time address (step S202). If no failure is detected (NO in step S203), the control device repeats the operation in step S201.
[0146] If a failure is detected (YES in step S203), the output unit 33 outputs information indicating the failure of the destination control device (step S204). The information indicating the failure of the destination control device may include information identifying the destination information processing device including the destination control device and information indicating that the destination control device of the destination information processing device has failed.
[0147] Then, the control device executes a destination monitoring process (step S205), which is a process of monitoring a destination monitoring target that is a target of monitoring in the destination information processing device, and a monitoring process (step S206). The destination monitoring process will be described in detail later. The monitoring process in step S201 and the monitoring process in step S206 are the same process.
[0148] FIG. 11 is a flowchart showing an example of the operation of the monitoring process of the control device according to the present disclosure.
[0149] Hereinafter, the operation of the monitoring process of the control device according to the second embodiment of the present disclosure will be described in detail with reference to FIG. 11.
[0150] In the example shown in FIG. 11, the monitoring unit 32 detects an abnormality of the monitoring target (step S211). If no abnormality is detected (NO in step S212), the control device ends the operation shown in FIG. 11.
[0151] If an abnormality is detected (YES in step S212), the output unit 33 outputs information indicating the abnormality of the monitoring target (step S213). Then, the control device ends the operation shown in FIG. 11.
[0152] FIG. 12 is a flowchart showing an example of the operation of the destination monitoring process of the control device according to the present disclosure.
[0153] Hereinafter, the operation of the connection destination monitoring process of the control device according to the second embodiment of the present disclosure will be described in detail with reference to FIG. 12.
[0154] When the destination control device fails, the address of the destination switch is changed to the failure-time address.
[0155] First, the monitoring unit 32 sets the state of the switch indicated by the switch address to the disconnected state (step S221). Next, the monitoring unit 32 sets the state of the destination switch indicated by the failure-time address to the connected state (step S222). The address assigned to the destination monitoring target that is the monitoring target in the destination information processing device is the same as the address assigned to the monitoring target that is the monitoring target in the information processing device. By steps S221 and S222, the monitoring target that the monitoring unit 32 can access using the address assigned to the monitoring target becomes the destination monitoring target that is the monitoring target in the destination information processing device.
[0156] Then, the monitoring unit 32 uses the address assigned to the monitoring target to detect an abnormality in the destination monitoring target (step S223). If no abnormality is detected (NO in step S224), the control device then performs the operations from step S226 onward.
[0157] If an abnormality is detected (YES in step S224), the output unit 33 outputs information indicating the abnormality of the destination monitoring target (step S225). The control device then performs the operations from step S226 onward.
[0158] Next, the monitoring unit 32 sets the state of the destination switch indicated by the failure-time address to the disconnected state (step S226). Then, the monitoring unit 32 sets the state of the switch indicated by the switch address to Set to the connected state (step S227). Through step S226 and step S227, the monitoring target that the monitoring unit 32 can access using the address assigned to the monitoring target becomes the monitoring target that is the monitoring target in the information processing device.
[0159] <Effect> This embodiment has the same effect as the first embodiment. The reason is the same as the reason for the effect of the first embodiment.
[0160] <Third Embodiment> Next, the third embodiment of the present disclosure will be described in detail with reference to the drawings. This embodiment represents the main part of the second embodiment of the present disclosure.
[0161] <Configuration> FIG. 13 is a block diagram showing an example of the configuration of a control device according to the present disclosure.
[0162] Hereinafter, the configuration of the control device according to the third embodiment of the present disclosure will be described in detail with reference to FIG. 13.
[0163] In the example shown in FIG. 13, the control device 30 includes a detection unit 31, a monitoring unit 32, and an output unit 33.
[0164] The detection unit 31 is a control device mounted on the information processing device, and detects a failure of the connection destination control device of the connection destination information processing device connected to the information processing device.
[0165] When a failure of the connection destination control device is detected, the monitoring unit 32 monitors the connection destination monitoring target that is the monitoring target in the connection destination information processing device.
[0166] When an abnormality of the connection destination monitoring target is detected by monitoring the connection destination monitoring target, the output unit 33 further outputs information indicating the abnormality of the connection destination monitoring target.
[0167] <Operation> FIG. 14 is a flowchart showing an example of the operation of the control device according to the present disclosure.
[0168] Hereinafter, the operation of the control device 30 according to the third embodiment of the present disclosure will be described in detail with reference to FIG. 14.
[0169] In the example shown in FIG. 14, first, the detection unit 31 detects a failure of the destination control device (step S301). If no failure is detected (NO in step S302), the control device 30 ends the operation shown in FIG. 14.
[0170] If a failure is detected (YES in step S302), the monitoring unit 32 monitors the destination to be monitored of the destination information processing device (step S303). If no abnormality is detected (NO in step S304), the control device 30 ends the operation shown in FIG. 14.
[0171] If an abnormality is detected (YES in step S304), the output unit 33 outputs information indicating the abnormality of the destination to be monitored (step S305).
[0172] <Effect> This embodiment has the same effect as the first embodiment. The reason is the same as the reason for the effect of the first embodiment.
[0173] <Other Embodiments> The control device and the control device monitoring device according to the present disclosure can be realized by a computer including a memory loaded with a program read from a storage medium and a processor that executes the program. The control device and the control device monitoring device according to the present disclosure can also be realized by dedicated hardware. The control device and the control device monitoring device according to the present disclosure can also be realized by a combination of the aforementioned computer and dedicated hardware.
[0174] FIG. 15 is a diagram showing an example of the hardware configuration of a computer 1000 that can implement the control device and the control device monitoring device according to the present disclosure. In the example shown in FIG. 15, the computer 1000 includes a processor 1001, a memory 1002, a storage device 1003, and an I / O (Input / Output) interface 1004. Further, the computer 1000 can access a storage medium 1005. The memory 1002 and the storage device 1003 are storage devices such as a RAM (Random Access Memory) and a hard disk, for example. The storage medium 1005 is a storage device such as a RAM, a hard disk, a ROM (Read Only Memory), or a removable storage medium, for example. The storage device 1003 may be the storage medium 1005. The processor 1001 can read and write data and programs to and from the memory 1002 and the storage device 1003. The processor 1001 can access, via the I / O interface 1004, for example, other components included in the information processing device and other information processing devices. The processor 1001 can access the storage medium 1005.
[0175] A program for operating the computer 1000 as the control device according to the embodiment of the present disclosure is stored in the storage medium 1005.
[0176] The processor 1001 loads, into the memory 1002, the program for operating the computer 1000 as the control device according to the embodiment of the present disclosure, which is stored in the storage medium 1005. Then, by executing the program loaded into the memory 1002, the computer 1000 operates as the control device according to the embodiment of the present disclosure.
[0177] A program for operating the computer 1000 as the control device monitoring device according to the embodiment of the present disclosure may be stored in the storage medium 1005.
[0178] In that case, the processor 1001 loads, into the memory 1002, a program that causes the computer 1000 stored in the storage medium 1005 to operate as the control device monitoring device according to the embodiment of the present disclosure. Then, by executing the program loaded into the memory 1002 by the processor 1001, the computer 1000 operates as the control device monitoring device according to the embodiment of the present disclosure.
[0179] The detection unit 31, the monitoring unit 32, and the output unit 33 can be realized, for example, by the processor 1001 that executes a program loaded into the memory 1002. Part or all of the detection unit 31, the monitoring unit 32, and the output unit 33 can be realized by dedicated circuits that realize the functions of the respective units.
[0180] The control device failure detection unit 34, the control device stop unit 35, the address change unit 36, and the reset unit 37 can be realized, for example, by the processor 1001 that executes a program loaded into the memory 1002. Part or all of the control device failure detection unit 34, the control device stop unit 35, the address change unit 36, and the reset unit 37 can be realized by dedicated circuits that realize the functions of the respective units.
[0181] Also, part or all of the above embodiments can be described as follows in the following supplementary notes, but are not limited thereto.
[0182] (Supplementary Note 1) A control device mounted on an information processing device, detection means for detecting a failure of a connection destination control device of a connection destination information processing device connected to the information processing device; monitoring means for monitoring a connection destination monitoring target that is a monitoring target in the connection destination information processing device when a failure of the connection destination control device is detected; output means for further outputting information indicating an abnormality of the connection destination monitoring target when an abnormality of the connection destination monitoring target is detected by monitoring the connection destination monitoring target; A control device comprising:
[0183] (Supplementary Note 2) When the connection destination control device fails, the monitoring means monitors the connection destination information processing device using a failure address set as an address that can be used for access to the connection destination information processing device. The control device according to Supplementary Note 1.
[0184] (Supplementary Note 3) When the connection destination control device fails, the connection destination information processing device sets the address of a connection destination switch that switches between a connected state (connection state) and a disconnected state (disconnection state), which is the state between the bus of the connection destination information processing device and the connection destination monitoring target, to the failure address. After setting the state of the connection destination switch indicated by the failure address to the connected state, the monitoring means monitors the connection destination monitoring target. The control device according to Supplementary Note 2.
[0185] (Supplementary Note 4) The monitoring means sets the switch state indicated by a switch address set as an address for accessing a switch that switches the switch state, which is the state between the control device and the monitoring target to be monitored in the information processing device, between the connected state and the disconnected state to the disconnected state, sets the connection destination switch state indicated by the failure address to the connected state, and then monitors the connection destination monitoring target. The control device according to Supplementary Note 3.
[0186] (Supplementary Note 5) The address of the monitoring target and the address of the connection destination monitoring target are set to a predetermined monitoring target address. The monitoring means sets the switch state to the disconnected state and the connection destination switch state to the connected state, then monitors the connection destination monitoring target using the monitoring target address, sets the switch state to the connected state using the switch address, sets the connection destination switch state to the connected state using the failure address, and then monitors the monitoring target using the monitoring target address. The control device described in Supplementary Note 4.
[0187] (Supplementary Note 6) When the destination control device fails, the destination information processing device changes the state of the destination switch from the connected state to the disconnected state. The control device according to any one of Supplementary Notes 3 to 5.
[0188] (Supplementary Note 7) When access using the failure-time address is successful, the detection means detects a failure of the destination control device. The control device according to Supplementary Note 2 or 3.
[0189] (Supplementary Note 8) An information processing device including a control device monitoring device and the control device according to Supplementary Note 4 or 5, wherein the control device monitoring device has control device failure detection means for detecting a failure of the control device, and address change means for changing the address of the switch from the switch address to the failure-time address when a failure of the control device is detected.
[0190] (Supplementary Note 9) The information processing device including the control device according to Supplementary Note 3, the destination information processing device, including wherein the destination information processing device has the destination control device, destination control device failure detection means for detecting a failure of the destination control device, and destination address change means for changing the address of the destination switch from the switch address, which is the address used by the destination control device to access the destination switch, to the failure-time address when a failure of the destination control device is detected. When a failure of the destination control device is detected, the output means outputs information indicating the failure of the destination control device. Information processing system.
[0191] (Appendix 10) A control device mounted on an information processing device detects a failure of a connection destination control device of a connection destination information processing device connected to the information processing device, when the failure of the connection destination control device is detected, monitors a connection destination monitoring target that is a monitoring target in the connection destination information processing device, when an abnormality of the connection destination monitoring target is detected by monitoring the connection destination monitoring target, outputs information indicating the abnormality of the connection destination monitoring target. Control method.
[0192] (Appendix 11) When the connection destination control device fails, the control device monitors the connection destination information processing device using a failure address set as an address that can be used for access to the connection destination information processing device. The control method according to Appendix 10.
[0193] (Appendix 12) When the connection destination control device fails, the connection destination information processing device sets the address of a connection destination switch that switches between a connected state (connection state) and a disconnected state (disconnection state), which is the state between the bus of the connection destination information processing device and the connection destination monitoring target, to the failure address. The control device monitors the connection destination monitoring target after setting the state of the connection destination switch indicated by the failure address to the connected state. The control method according to Appendix 11.
[0194] (Appendix 13) The control device sets the switch state indicated by the switch address, which is set as an address for accessing a switch that switches the switch state, which is the state between the control device and the monitoring target in the information processing device, between the connected state and the disconnected state to the disconnected state, sets the connection destination switch state indicated by the failure address to the connected state, and then monitors the connection destination monitoring target. The control method according to Supplementary Note 12.
[0195] (Supplementary Note 14) The addresses of the monitoring target and the connection destination monitoring target are set to a predetermined monitoring target address. The control device sets the switch state to the disconnected state, sets the connection destination switch state to the connected state, then monitors the connection destination monitoring target using the monitoring target address, sets the switch state to the connected state using the switch address, sets the connection destination switch state to the connected state using the failure address, and then monitors the monitoring target using the monitoring target address. The control method according to Supplementary Note 13.
[0196] (Supplementary Note 15) When the connection destination control device fails, the connection destination information processing device changes the state of the connection destination switch from the connected state to the disconnected state. The control method according to any one of Supplementary Notes 12 to 14.
[0197] (Supplementary Note 16) When access using the failure address is successful, the control device detects a failure of the connection destination control device. The control method according to Supplementary Note 11 or 12.
[0198] (Supplementary Note 17) In the information processing device including a control device monitoring device and the control device controlled by the control method according to Supplementary Note 13 or 14, The control device monitoring device Detect a failure of the control device, When a failure of the control device is detected, change the address of the switch from the switch address to the failure-time address, Information processing apparatus control method.
[0199] (Appendix 18) The information processing apparatus including the control device controlled by the control method described in Appendix 12, The destination information processing apparatus including the destination control device, In an information processing system including, The destination information processing apparatus, Detect a failure of the destination control device, When a failure of the destination control device is detected, change the address of the destination switch from the switch address, which is the address used by the destination control device to access the destination switch, to the failure-time address, The control device, When a failure of the destination control device is detected, output information indicating the failure of the destination control device Information processing system control method.
[0200] As described above, the present disclosure has been described with reference to the embodiments, but the present disclosure is not limited to the above embodiments. Various changes that can be understood by those skilled in the art can be made to the configuration and details of the present disclosure within the scope of the present disclosure.
Description of Signs
[0201] 1 Information processing system 10 Information processing apparatus 11 Control device 12 Control device monitoring device 13 Switch 14 Monitoring target 15 Interface unit 16 External interface unit 20 Information processing apparatus 21 Control device 22 Control device monitoring device 23 Switch 24 Monitored Object 25 Interface Unit 26 External Interface Unit 30 Control Device 31 Detection Unit 32 Monitoring Unit 33 Output Unit 34 Control Device Failure Detection Unit 35 Control Device Stop Unit 36 Address Change Unit 37 Reset Unit 101 Server 102 Notification IF 103 BMC 104 BMC Monitoring Device 105 I2C Switch 106 I2C Connector 107 Fan 108 Temperature Sensor 201 Server 202 Notification IF 203 BMC 204 BMC Monitoring Device 205 I2C Switch 206 I2C Connector 207 Fan 208 Temperature Sensor 301 External Notification Function 302 Sensor Monitoring Function 303 I2C Access Function 304 Failure Monitoring Function 305 BMC Stop Function 306 Switch Reset Function 307 Address Change Function 308 I2C Bus Operation Function 1000 Computer 1001 Processor 1002 Memory 1003 Storage Device 1004 I / O Interface 1005 Storage Medium
Claims
1. A control device mounted on an information processing device, a detection means for detecting a failure of a destination control device of a destination information processing device connected to the information processing device; a monitoring means for monitoring a destination monitoring target which is a monitoring target in the destination information processing device when a failure of the destination control device is detected; an output means for, when an abnormality in the connection destination monitoring target is detected by monitoring the connection destination monitoring target, further outputting information indicating the abnormality in the connection destination monitoring target; A control device comprising:
2. The monitoring means monitors the destination information processing device by using a failure time address that is set as an address that can be used to access the destination information processing device when the destination control device fails. The control device according to claim 1 .
3. the destination information processing device, when the destination control device fails, sets an address of a destination switch that switches a destination switch state, which is a state between the bus of the destination information processing device and the destination monitoring target, between a connected state, which is a connected state, and a disconnected state, which is a disconnected state, to the failure address; The monitoring means sets the state of the connection destination switch indicated by the failure address to a connected state, and then monitors the connection destination monitoring target. The control device according to claim 2.
4. The monitoring means sets the switch state indicated by a switch address set as an address for accessing a switch that switches a switch state between the control device and a monitoring target that is a monitoring target in the information processing device between the connected state and the disconnected state to the disconnected state, sets the connection destination switch state indicated by the failure time address to the connected state, and then monitors the connection destination monitoring target. The control device according to claim 3.
5. The address of the monitoring target and the address of the connection destination monitoring target are set to a predetermined monitoring target address, The monitoring means sets the switch state to the disconnected state, sets the connected switch state to the connected state, then monitors the connected monitoring target using the monitoring target address, sets the switch state to the connected state using the switch address, sets the connected switch state to the connected state using the failure address, and then monitors the monitoring target using the monitoring target address. The control device according to claim 4.
6. When the destination control device fails, the destination information processing device changes the state of the destination switch from the connected state to the disconnected state. A control device according to any one of claims 3 to 5.
7. The detection means detects a failure of the destination control device when access using the failure address is successful. The control device according to claim 2 or 3.
8. A control device monitoring device and the control device according to claim 4 or 5, The control device monitoring device A control device failure detection means for detecting a failure of the control device; an address change means for changing an address of the switch from the switch address to the failure address when a failure of the control device is detected; An information processing device comprising:
9. The information processing device including the control device according to claim 3; The destination information processing device; Including, The destination information processing device includes: The destination control device; a connection destination control device failure detection means for detecting a failure of the connection destination control device; a destination address change means for changing an address of the destination switch from a switch address, which is an address used by the destination control device to access the destination switch, to the failure address when a failure of the destination control device is detected; Equipped with The output means outputs information indicating a failure of the connection destination control device when a failure of the connection destination control device is detected. Information processing system.
10. A control device mounted on the information processing device, Detecting a failure of a destination control device of a destination information processing device connected to the information processing device; When a failure of the connection destination control device is detected, monitoring of a connection destination monitoring target that is a monitoring target in the connection destination information processing device is performed; when an abnormality in the connection destination monitoring target is detected by monitoring the connection destination monitoring target, outputting information indicating the abnormality in the connection destination monitoring target. Control methods.
Citation Information
Patent Citations
Computer system
JP2015230720A
Information processing system and information processing device
JP2020086805A
Baseboard management controller, information processing system, and baseboard management controller processing execution method
JP6540142B2