Operation and maintenance system, method, device, equipment and medium

Abstract

The embodiment of the invention provides an operation and maintenance system, method and device, equipment and a medium, and is used for solving the problem that in the prior art, when a HOST BMC crashes, problems occurring in a GPU BOX server cannot be reported. In the system, if other equipment receives a command packet and determines that the HOST BMC fails, an IP address of a target BOX BMC is obtained, connection with the target BOX BMC is established based on the IP address, and the command packet is sent to the target BOX BMC, so that execution result information reported by the target BOX BMC is obtained, the situation that the BOX BMC is strongly related to the operation condition of the HOST BMC and the situation that when the HOST BMC crashes, problems occurring in a GPU BOX server cannot be reported are avoided, and the execution efficiency of the GPU BOX server is improved. Therefore, the operation condition of the GPU BOX server where the BOX BMC is located can be monitored in time, and operation and maintenance services are provided for the GPU BOX server.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to an operation and maintenance system, method, device, equipment and medium. Background Art

[0002] The current graphics processing unit (GPU) node server baseboard management controller (Baseboard Management Controller, BMC), namely the GPU BOX baseboard management controller (BOX BMC), will set a static Internet Protocol (Internet Protocol, IP) address that is only in the same network segment as the baseboard management controller in the central processing unit (CPU) node server, namely the host baseboard management controller (HOST BMC), communicate with the HOST BMC through the external network port of the BOX BMC, and communicate with other devices through the HOST BMC. Specifically, the GPU BOX server where the BOX BMC is located can be provided with operation and maintenance services based on the HOST BMC. That is to say, when the BOX BMC is accessed externally, it can access other devices with the help of the HOST BMC.

[0003] However, in the above solution, BOX BMC is strongly related to the operation status of HOST BMC. If HOST BMC goes down, BOX BMC cannot provide operation and maintenance management for its GPUBOX server, which may cause some serious problems of GPU BOX server to fail to be reported, and operation and maintenance services cannot be provided for GPU BOX server in time. Summary of the invention

[0004] The embodiments of the present application provide an operation and maintenance system, method, apparatus, device and medium, which are used to solve the problem in the prior art that the HOST BMC is down and the problem of the GPU BOX server cannot be reported.

[0005] In a first aspect, an embodiment of the present application provides an operation and maintenance system, which includes a HOST BMC, a BOX BMC and other devices;

[0006] The other device is used to receive the command packet, obtain the identification information of the target BOX BMC carried in the command packet; send the first detection information to the HOST BMC connected to the target BOX BMC, and if it is determined that the HOST BMC is faulty, obtain the Internet Protocol IP address of the target BOX BMC, send the command packet to the target BOX BMC, and receive the execution result information of the target BOX BMC;

[0007] The target BOX BMC is used to receive the command packet sent by the other device, parse the command packet, obtain the command contained in the command packet and execute it, and return the execution result information to the other device.

[0008] Through the above method, if other devices receive the command packet and determine that the HOST BMC is faulty, they obtain the IP address of the target BOX BMC, establish a connection with the target BOX BMC based on the IP address, and send the command packet to the target BOX BMC, thereby obtaining the execution result information reported by the target BOX BMC, thereby avoiding the situation where the BOX BMC is strongly related to the operation status of the HOST BMC, and the problem of the GPU BOX server cannot be reported when the HOST BMC is down, so that the operation status of the GPU BOX server where the BOX BMC is located can be monitored in time, and operation and maintenance services can be provided for the GPU BOX server.

[0009] In a possible implementation manner, the other device is specifically configured to send a bridging property instruction to the HOST BMC;

[0010] The HOST BMC is used to obtain the IP address of any BOX BMC connected to the HOST BMC after receiving the bridge property instruction, and send the IP address of the BOX BMC and the identification information of the BOX BMC to the other device;

[0011] The other device is specifically used to receive the IP address and the identification information of the BOX BMC and store them accordingly.

[0012] In the above manner, other devices send a bridge command to the HOST BMC and obtain the IP address of any BOX BMC connected to the HOST BMC returned by the HOST BMC, thereby ensuring that other devices can subsequently establish a connection with the BOX BMC.

[0013] In a possible implementation manner, the HOST BMC is connected to the BOXBMC via a serial communication protocol I2C link;

[0014] The other device is further configured to send the command packet to the HOST BMC if it is determined that the HOST BMC is normal;

[0015] The HOST BMC is further configured to send the command packet to the target BOX BMC through an I2C link connected to the target BOX BMC according to the identification information of the target BOX BMC carried in the command packet.

[0016] Through the above method, if the HOST BMC fails, other devices can establish a communication connection with the target BOX BMC based on the IP address of the target BOX BMC102, so as to realize the independent management capability of the GPU BOX server; if the HOST BMC is normal, other devices forward the command packet to the BOX BMC connected to the HOST BMC through the HOST BMC, so as to realize the unified operation and maintenance management of each BOX BMC by the HOST BMC. Therefore, the operation and maintenance method provided in the embodiment of the present application is compatible with the ability of the CPU node server to manage multiple GPU BOX servers and the independent management capability of the GPU node server.

[0017] In a possible implementation, the HOST BMC is specifically used to determine a target HOST BMC BOX queue corresponding to the target BOX BMC; write the command packet into the target HOST BMC BOX queue; and send the command packet to the target BOX BMC through an I2C link connected to the target BOX BMC in a first-in-first-out order based on the target HOST BMC BOX queue.

[0018] Through the above method, there is a unique corresponding relationship between each HOST BMC BOX queue, I2C link and BOX BMC. Therefore, according to the identification information of the target BOX BMC carried in each command packet, the corresponding target HOST BMC BOX queue is determined, and each command packet is written into the corresponding target HOST BMC BOX queue, so that each target HOST BMC BOX queue is processed in parallel, and the command packet is sent to the corresponding target BOX BMC, thereby improving the transmission rate.

[0019] In a possible implementation manner, the HOST BMC is specifically configured to convert the command packet into an IPMB command packet according to a preset hardware management interface IPMB format; and write the IPMB command packet into the target HOST BMCBOX queue.

[0020] Through the above method, the command packet is converted into an IPMB command packet according to the preset IPMB format and written into the target HOST BMC BOX queue, which facilitates the combination of IPMB and I2C technology, ensures that the command packet can be transmitted smoothly, and ensures the stable operation of the server.

[0021] In a second aspect, the embodiment of the present application further provides an operation and maintenance method, which is applied to other devices. The beneficial effects of the operation and maintenance method can be found in the description of the first aspect and will not be repeated here. The method includes:

[0022] Receive a command packet, and obtain identification information of a target BOX BMC carried in the command packet; send first detection information to a HOST BMC connected to the target BOX BMC, and if it is determined that the HOST BMC is faulty, obtain the IP address of the target BOX BMC, send the command packet to the target BOX BMC, so that the target BOX BMC receives the command packet sent by the other device, parses the command packet, obtains the command contained in the command packet, and executes it; and receive execution result information of the target BOX BMC.

[0023] In a third aspect, an embodiment of the present application further provides an operation and maintenance method, which is applied to BOX BMC, and the method includes:

[0024] Receive a command packet sent by other devices; wherein the command packet is sent by the other device to the BOX BMC after sending first detection information to the HOST BMC connected to the BOX BMC, determining that the HOST BMC is faulty, and obtaining the Internet Protocol IP address of the BOX BMC; parse the command packet, obtain the command contained in the command packet and execute it; return execution result information to the other device.

[0025] In a fourth aspect, an embodiment of the present application further provides an operation and maintenance device, which is applied to other devices, and the operation and maintenance device includes:

[0026] A first receiving module is used to receive a command packet and obtain identification information of a target BOX BMC carried in the command packet;

[0027] a processing module, configured to send first detection information to a HOST BMC connected to the target BOX BMC, and if it is determined that the HOST BMC is faulty, obtain the IP address of the target BOX BMC, send the command packet to the target BOX BMC, so that the target BOX BMC receives the command packet sent by the other device, parses the command packet, obtains the command contained in the command packet, and executes the command;

[0028] The second receiving module is used to receive the execution result information of the target BOX BMC.

[0029] In a fifth aspect, an embodiment of the present application further provides an operation and maintenance device, which is applied to a BOX BMC. The operation and maintenance device includes:

[0030] a third receiving module, configured to receive a command packet sent by another device; wherein the command packet is sent by the other device to the BOX BMC after sending first detection information to the HOST BMC connected to the BOX BMC, determining that the HOST BMC is faulty, and obtaining the Internet Protocol IP address of the BOX BMC;

[0031] A parsing module, used to parse the command packet, obtain the command contained in the command packet and execute it;

[0032] The sending module is used to return the execution result information to the other device.

[0033] In a sixth aspect, an embodiment of the present application further provides an electronic device, which includes at least a processor and a memory, and the processor is used to implement the steps of the operation and maintenance method as described in any one of the above items when executing a computer program stored in the memory.

[0034] In a seventh aspect, an embodiment of the present application further provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the operation and maintenance method as described in any one of the above items.

[0035] In an eighth aspect, an embodiment of the present application provides a computer program product, which includes: a computer program code, which, when executed on a computer, enables the computer to execute the steps of the operation and maintenance method as described in any one of the first aspects. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0037] Figure 1 A schematic diagram of the structure of an operation and maintenance system provided in an embodiment of the present application;

[0038] Figure 2 A schematic diagram of a specific connection method between a HOST BMC and at least one BOX BMC provided in an embodiment of the present application;

[0039] Figure 3 A schematic diagram of an operation and maintenance process provided in an embodiment of the present application;

[0040] Figure 4 A schematic diagram of an operation and maintenance process for determining that the HOST BMC is normal provided in an embodiment of the present application;

[0041] Figure 5 A schematic diagram of an operation and maintenance process applied to other devices provided in an embodiment of the present application;

[0042] Figure 6 A schematic diagram of an operation and maintenance process applied to BOX BMC provided in an embodiment of the present application;

[0043] Figure 7 One of the structural schematic diagrams of an operation and maintenance device provided in an embodiment of the present application;

[0044] Figure 8 A second schematic diagram of the structure of an operation and maintenance device provided in an embodiment of the present application;

[0045] Fig. 9 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0046] In order to make the purpose and implementation method of the present application clearer, the exemplary implementation method of the present application will be clearly and completely described below in conjunction with the drawings in the exemplary embodiments of the present application. Obviously, the described exemplary embodiments are only part of the embodiments of the present application, rather than all the embodiments.

[0047] It should be noted that the brief description of terms in this application is only for the convenience of understanding the embodiments described below, and is not intended to limit the embodiments of this application. Unless otherwise specified, these terms should be understood according to their common and usual meanings.

[0048] The terms "first", "second", "third", etc. in the specification and claims of this application and the above drawings are used to distinguish similar or similar objects or entities, and do not necessarily mean to limit a specific order or sequence, unless otherwise noted. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances.

[0049] The terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover but not exclude inclusion, for example, a product or device comprising a list of components is not necessarily limited to all the components expressly listed but may include other components not expressly listed or inherent to such product or device.

[0050] The term "module" refers to any known or later developed hardware, software, firmware, artificial intelligence, fuzzy logic, or combination of hardware and / or software code that is capable of performing the functions associated with that element.

[0051] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0052] For the convenience of explanation, the above description has been made in conjunction with specific embodiments. However, the above exemplary discussion is not intended to be exhaustive or limit the embodiments to the specific forms disclosed above. Based on the above teachings, various modifications and variations can be obtained. The selection and description of the above embodiments are to better explain the principles and practical applications, so that those skilled in the art can better use the embodiments and various different variations of the embodiments suitable for specific use considerations.

[0053] The embodiment of the present application provides an operation and maintenance system, method, apparatus, device and medium, the system includes a HOST BMC, a BOX BMC and other devices; the other devices are used to receive a command packet, obtain identification information of a target BOX BMC carried in the command packet; send first detection information to the HOST BMC connected to the target BOX BMC, if it is determined that the HOST BMC is faulty, obtain the Internet Protocol IP address of the target BOX BMC, send the command packet to the target BOX BMC, and receive execution result information of the target BOX BMC; the target BOX BMC is used to receive the command packet sent by the other devices, parse the command packet, obtain the command contained in the command packet and execute it, and return the execution result information to the other devices. In the embodiment of the present application, if other devices receive the command packet and determine that the HOST BMC is faulty, the IP address of the target BOX BMC is obtained, a connection is established with the target BOX BMC based on the IP address, and the command packet is sent to the target BOX BMC, thereby obtaining the execution result information reported by the target BOX BMC, thereby avoiding the situation where the BOX BMC is strongly correlated with the operating status of the HOST BMC, and the problem of the GPUBOX server cannot be reported when the HOST BMC is down, so that the operating status of the GPU BOX server where the BOX BMC is located can be monitored in time, and operation and maintenance services can be provided for the GPU BOX server.

[0054] Embodiment 1:

[0055] Figure 1 A schematic diagram of the structure of an operation and maintenance system provided in an embodiment of the present application, the operation and maintenance system includes a HOST BMC 101, a BOX BMC 102 and other devices 103;

[0056] The other device 103 is used to receive the command packet, obtain the identification information of the target BOX BMC102 carried in the command packet; send the first detection information to the HOST BMC101 connected to the target BOX BMC102, and if it is determined that the HOST BMC101 is faulty, obtain the Internet Protocol IP address of the target BOX BMC102, send the command packet to the target BOX BMC102, and receive the execution result information of the target BOX BMC102;

[0057] The target BOX BMC 102 is used to receive the command packet sent by the other device, parse the command packet, obtain the command contained in the command packet and execute it, and return the execution result information to the other device.

[0058] In the operation and maintenance system provided in the embodiment of the present application, a HOST BMC 101 is connected to at least one BOX BMC 102 , and other devices 103 are connected to the HOST BMC 101 .

[0059] Among them, HOST BMC101 is deployed in the CPU node server; BOX BMC102 is deployed in the GPU BOX server; other devices 103 can be electronic devices in the same computer room environment as the CPU node server and the GPU BOX server, and the electronic devices can be servers, personal computers (Personal Computer, PC), etc., and no specific restrictions are made here.

[0060] In the embodiment of the present application, the other device 103 receives the command packet input by the user, parses the command packet, and determines the identification information of the target BOX BMC carried in the command packet. In one possible implementation, the other device 103 receives the parameters input by the user, and combines the command packet corresponding to the input parameters according to the command packet combination rule based on the parameters input by the user; the process of combining the command packet corresponding to the input parameters according to the command packet combination rule based on the parameters input by the user is a prior art and will not be described in detail here.

[0061] In order to determine whether the HOST BMC101 currently connected to the target BOX BMC102 is in normal operation, the other device 103 sends first detection information to the HOST BMC101 to determine whether the first detection information is successfully sent. If so, it is determined that the HOST BMC101 is normal, otherwise, it is determined that the HOST BMC101 is faulty.

[0062] Specifically, after sending the first detection information to the HOST BMC101, the other device 103 determines whether the return information of the HOST BMC101 is received within the preset time length, if not, it is determined that the HOST BMC101 is faulty; if yes, it continues to determine whether the return information of the HOST BMC101 is an error code (error), if yes, it is determined that the HOST BMC101 is faulty, if not, it is determined that the HOST BMC101 is normal. The first detection information can be a specific instruction or command, which is not specifically limited here.

[0063] In the embodiment of the present application, in order to ensure that when the HOST BMC101 fails, the other device 103 can still provide operation and maintenance management for the GPU BOX server where the BOXBMC102 is located and obtain the operation status information of the GPU BOX server, the other device 103 stores the correspondence between the identification information of each BOX BMC and the IP address. Therefore, if the other device 103 determines that the HOST BMC101 connected to the target BOX BMC102 fails, the IP address of the target BOX BMC102 is obtained according to the identification information of the target BOX BMC102 carried in the command packet and the correspondence between the identification information of each BOX BMC and the IP address, and based on the IP address, a connection is established with the target BOX BMC102, and the command packet is sent to the target BOXBMC102.

[0064] After receiving the command packet sent by other devices 103, the hardware management interface (Intelligent Platform Management Bus, IPMB) command processing queue in the target BOX BMC102 parses the command packet, obtains the command contained in the command packet and the target command type, and forwards the command to the corresponding processing module corresponding to the target command type in the target BOX BMC102 according to the saved correspondence between the command type and the processing module, so that the corresponding processing module provides corresponding operation and maintenance services for the GPU BOX server where the target BOX BMC is located.

[0065] For example, the commands include but are not limited to power on and off, heat dissipation, obtaining information, restarting, etc. The processing modules include but are not limited to power on and off modules, heat dissipation modules, information obtaining modules, restarting modules, etc.

[0066] After executing the command, the corresponding processing module in the target BOX BMC 102 returns the execution result information of the command to the IPMB command processing queue, and the IPMB command processing queue of the target BOX BMC 102 returns the execution result information to the other device 103 .

[0067] After receiving the execution result information returned by the target BOX BMC 102 , the other device 103 may display the execution result information for viewing by the operation and maintenance personnel.

[0068] In the embodiment of the present application, if other devices receive the command packet and determine that the HOST BMC is faulty, the IP address of the target BOX BMC is obtained, a connection is established with the target BOX BMC based on the IP address, and the command packet is sent to the target BOX BMC, thereby obtaining the execution result information reported by the target BOX BMC, thereby avoiding the situation where the BOX BMC is strongly correlated with the operating status of the HOST BMC, and the problem of the GPU BOX server cannot be reported when the HOST BMC is down, so that the operating status of the GPU BOX server where the BOX BMC is located can be monitored in time, and operation and maintenance services can be provided for the GPU BOX server.

[0069] Embodiment 2:

[0070] In order to ensure that other devices can establish a connection with the BOX BMC, based on the above embodiment, in the embodiment of the present application, the other device 103 is specifically used to send a bridge property instruction to the HOST BMC101;

[0071] The HOST BMC 101 is used to obtain the IP address of any BOX BMC 102 connected to the HOST BMC 101 after receiving the bridge property instruction, and send the IP address of the BOX BMC 102 and the identification information of the BOX BMC 102 to the other device 103;

[0072] The other device 103 is specifically used to receive the IP address and the identification information of the BOX BMC 102 and store them accordingly.

[0073] Since the BOX BMC's assigned IP address cannot be viewed in its network interface, and after the BOX BMC is connected to the HOST BMC, the HOST BMC can obtain the basic information of the BOX BMC, and the basic information includes the IP address of the BOX BMC, so in the embodiment of the present application, in order to obtain the IP address of the BOX BMC 102 connected to the HOST BMC 101, the other device 103 can send a bridging instruction to the HOST BMC 101 after establishing a connection with the HOST BMC 101. It can be understood that at this time, the HOST BMC 101 is in a normal operating state.

[0074] After receiving the bridge property instruction sent by the other device 103, the HOST BMC 101 obtains the IP address of any BOX BMC 102 connected to the HOST BMC 101 based on the bridge property instruction, and sends the IP address of the BOX BMC 102 and the identification information of the BOX BMC 102 to the other device 103. The process of obtaining the IP address based on the bridge property instruction is a prior art and will not be repeated here.

[0075] The other device 103 receives the IP address and identification information of any BOX BMC connected to the HOST BMC 101 sent by the HOST BMC 101, and saves the correspondence between the IP address and identification information of the BOX BMC, so that the other device 103 can establish a communication connection with the corresponding BOX BMC based on the saved IP address.

[0076] In the embodiment of the present application, other devices send a bridge property instruction to the HOST BMC, and obtain the IP address of any BOX BMC connected to the HOST BMC returned by the HOST BMC, thereby ensuring that other devices can subsequently establish a connection with the BOX BMC.

[0077] Embodiment 3:

[0078] In order to be compatible with the CPU node server's ability to manage multiple GPU BOX servers and the GPU node server's independent management capabilities, based on the above embodiments, in the embodiment of the present application, the HOST BMC101 is connected to the BOX BMC102 via a serial communication protocol (Inter-Integrated Circui, I2C) link;

[0079] The other device 103 is further configured to send the command packet to the HOST BMC 101 if it is determined that the HOST BMC 101 is normal;

[0080] The HOST BMC101 is further configured to send the command packet to the target BOX BMC102 through the I2C link connected to the target BOX BMC102 according to the identification information of the target BOX BMC102 carried in the command packet.

[0081] In order to ensure that BOX BMC102 can communicate with devices other than HOST BOX101, in the embodiment of the present application, Figure 2 The schematic diagram of the specific connection between the HOST BMC and at least one BOX BMC is shown. The HOST BMC101 deployed in the CPU node server is connected via an I2C link (ie Figure 2 The IPMB over I2C) shown in the figure is connected to any BOX BMC102 deployed in the GPU BOX server, so that the external network port of BOX BMC102 is not occupied, that is, the external network port of BOXBMC102 is released, so that BOX BMC102 can communicate with any device except HOST BOX101 based on the external network port, and then can flexibly adapt to the combination of CPU node servers and GPU BOX servers in more scenarios.

[0082] In the embodiment of the present application, if the other device 103 determines that the HOST BMC 101 connected to the target BOX BMC 102 is normal, the command packet is sent to the HOST BMC 101 connected to the target BOX BMC 102 .

[0083] After receiving the command packet sent by the other device 103 , the HOST BMC 101 writes the command packet into the buffer of the HOST BMC 101 .

[0084] In a possible implementation, if a command packet is stored in the buffer of HOST BMC101, the command packet is forwarded to the message processing queue; the command packet stored in the message processing queue can be directly parsed to determine the message type contained in the command packet, and the target command category of the command packet is determined according to the correspondence between the saved message type and the command category, and the target priority corresponding to the command packet is determined according to the target command category and the correspondence between the saved command category and the priority, and the command packet is written into the classification queue corresponding to the target priority; when processing the classification queue corresponding to the target priority, the command packet stored in the classification queue can be directly written into the IPMB command processing queue of HOSTBMC101; the command packet stored in the IPMB command processing queue can be parsed to obtain the identification information of the target BOX BMC102 carried in the command packet.

[0085] Among them, the priority includes high priority, medium priority, low priority, etc. The correspondence between command classification and priority includes: if the command classification is power on / off, heat dissipation, etc., then the priority corresponding to the command classification is high priority; if the command classification is information acquisition, etc., then the priority corresponding to the command classification is medium priority; if the command classification is restart, etc., then the priority corresponding to the command classification is low priority. The classification queues corresponding to the corresponding priorities include high priority command queue, medium priority command queue, and low priority command queue.

[0086] Since the HOST BMC101 is connected to any BOX BMC connected to the HOST BMC101 through an I2C link, and the HOST BMC101 stores the correspondence between the identification information of the BOX BMC and the identification information of the I2C link, in the embodiment of the present application, the I2C link connected to the target BOX BMC102 can be determined according to the identification information of the target BOX BMC102, and the command packet can be sent to the target BOX BMC102 through the I2C link connected to the target BOX BMC102, so that the target BOX BMC102 writes the command packet into its own IPMB command processing queue.

[0087] After the command packet is written into the IPMB command processing queue of the target BOX BMC102, the command packet can be parsed to obtain the command and target command type contained in the command packet, and the command is forwarded to the corresponding processing module corresponding to the target command type in the target BOX BMC102 according to the correspondence between the saved command type and the processing module, so that the corresponding processing module provides corresponding operation and maintenance services for the GPU BOX server where the target BMC is located. After the corresponding processing module in the target BOXBMC102 completes the execution of the command, the execution result information of the command is written into the IPMB command processing queue, and the execution result information is returned to the HOST BMC101 based on the IPMB command processing queue of the target BOX BMC102, and the HOST BMC101 sends the execution result information to other devices 103.

[0088] In another possible implementation, if a plurality of command packets are stored in the buffer of HOST BMC101, the plurality of command packets are sequentially written into the message processing queue in a first-in-first-out order; after the message processing queue receives the plurality of command packets, each command packet is parsed to determine the message type contained in the command packet, a target command classification of the command packet is determined according to the correspondence between the saved message type and the command classification, and a target priority corresponding to the command packet is determined according to the target command classification and the correspondence between the saved command classification and the priority; after determining the target priority corresponding to each command packet, each command packet is sequentially written into the target priority command queue corresponding to the command packet in a first-in-first-out order; after each priority command queue receives the command packet belonging to the priority, each command packet is sequentially written into the IPMB command processing queue of HOST BMC101 in accordance with a preset writing rule; after the IPMB command processing queue receives each command packet, each command packet is parsed to determine the identification information of the target BOX BMC102 carried in each command packet.

[0089] The preset write rule includes processing the command packets stored in the high priority command queue, the medium priority command queue, and the low priority command queue in sequence according to the preset ratio, wherein each priority command queue processes the command packets stored in the priority command queue in the first-in-first-out order. For example, the preset ratio may be 3:2:1 for high priority: medium priority: low priority, that is, 3 high priority commands are processed first, then 2 medium priority commands are processed, then 1 low priority command is processed, and so on.

[0090] In the embodiment of the present application, the I2C link corresponding to each command packet can be determined according to the identification information of the target BOX BMC102 carried in each command packet; each command packet is sent to the target BOX BMC102 corresponding to the command packet through the I2C link corresponding to the command packet in a first-in-first-out order, so that the target BOX BMC102 writes the command packet into its own IPMB command processing queue.

[0091] For each target BOX BMC102, after writing at least one command packet into the IPMB command processing queue in the target BOX BMC102, the written command packets are parsed in turn in a first-in-first-out order to determine the commands contained in each command packet and the target command type, and the parsed commands are forwarded to the corresponding processing module corresponding to the target command type to which the command belongs, so that the corresponding processing module provides corresponding operation and maintenance services for the GPU BOX server where the target BOX BMC is located. After executing the command, the corresponding processing module returns the execution result information of the command to the IPMB command processing queue, and returns the execution result information to the HOST BMC101 based on the IPMB command processing queue of the target BOX BMC102. After receiving the execution result information sent by any target BOX BMC102, the HOSTBMC101 forwards the execution result information to other devices 103.

[0092] In addition, when it is determined that the HOST BMC101 is normal, in addition to the above-mentioned method of sending the command packet to the target BOX BMC102 through the HOST BMC101, in a possible implementation, since the IP address of each BOX BMC102 is stored in the other device 103, the other device 103 can establish a communication connection with the target BOX BMC102 based on the IP address of the target BOX BMC102, and directly forward the command packet to the target BOX BMC102, so that the target BOX BMC102 writes the command packet into its own IPMB command processing queue, thereby realizing the independent management capability of the GPU BOX server.

[0093] Furthermore, it is understandable that, in order to achieve unified management of multiple BOX BMCs, when the HOST BMC101 is normal, the above-mentioned method of sending the command packet to the target BOX BMC102 through the HOST BMC101 is usually adopted, so as to ensure that after the HOST BMC101 receives the information of each BOX BMC102 connected to the HOST BMC101, the information is backed up and stored in the HOST BMC101, so as to facilitate unified management of multiple BOX BMCs connected to the HOST BMC101.

[0094] In the embodiment of the present application, if the HOST BMC fails, other devices can establish a communication connection with the target BOX BMC based on the IP address of the target BOX BMC102, so as to realize the independent management capability of the GPU BOX server; if the HOST BMC is normal, other devices forward the command packet to the BOX BMC connected to the HOST BMC through the HOST BMC, so as to realize the unified operation and maintenance management of each BOX BMC by the HOST BMC. Therefore, the operation and maintenance method provided in the embodiment of the present application is compatible with the ability of the CPU node server to manage multiple GPU BOX servers and the independent management capability of the GPU node server.

[0095] Embodiment 4:

[0096] In order to improve the transmission rate, on the basis of the above embodiments, in the embodiment of the present application, the HOSTBMC101 is specifically used to determine the target HOST BMC BOX queue corresponding to the target BOX BMC102; write the command packet into the target HOST BMC BOX queue; based on the target HOST BMC BOX queue, in a first-in-first-out order, send the command packet to the target BOX BMC102 through the I2C link connected to the target BOX BMC102.

[0097] In the embodiment of the present application, a HOST BMC BOX queue corresponding to the BOX BMC is set in the HOST BMC 101 for any BOX BMC connected to the HOST BMC 101. Therefore, after the IPMB command processing queue of the HOST BMC 101 obtains the identification information of the target BOX BMC 102 carried in the command packet, the target HOST BMC BOX queue corresponding to the target BOX BMC 102 is determined according to the identification information of the target BOX BMC 102; and the command packet is written into the target HOST BMC BOX queue corresponding to the target BOX BMC 102.

[0098] Among them, if there are multiple command packets in the IPMB command processing queue of HOST BMC101, after obtaining the identification information of the target BOX BMC102 carried in each command packet, the target HOST BMC BOX queue corresponding to each command packet is determined according to the identification information of the target BOX BMC102 carried in each command packet; for each target HOST BMC BOX queue, at least one command packet corresponding to the target HOST BMC BOX queue is written into the target HOST BMC BOX queue in a first-in-first-out order.

[0099] In the embodiment of the present application, there is a unique correspondence between each HOST BMC BOX queue, the I2C link and the BOX BMC. Therefore, after the command packet is written to the target HOST BMC BOX queue, the target HOST BMCBOX queue of HOST BMC101 sends at least one command packet existing in the target HOST BMC BOX queue to the target BOX BMC102 through the I2C link connected to the target BOX BMC102 in a first-in-first-out order.

[0100] In the embodiment of the present application, there is a unique correspondence between each HOST BMC BOX queue, I2C link and BOX BMC. Therefore, according to the identification information of the target BOX BMC carried in each command packet, the corresponding target HOST BMCBOX queue is determined, and each command packet is written into the corresponding target HOST BMC BOX queue, so as to facilitate parallel processing of each target HOST BMC BOX queue, and send the command packet to the corresponding target BOX BMC, thereby improving the transmission rate.

[0101] Embodiment 5:

[0102] To ensure that the command packet can be transmitted smoothly, based on the above embodiments, in the embodiment of the present application, the HOST BMC101 is specifically used to convert the command packet into an IPMB command packet according to a preset IPMB format; and write the IPMB command packet into the target HOST BMC BOX queue.

[0103] Since the combined use of IPMB and I2C technologies can achieve comprehensive monitoring and management of server hardware, for example, IPMB can monitor the temperature and voltage of the server in real time, promptly discover and handle potential hardware failures, and ensure the stable operation of the server, and the implementation of the IPMB protocol relies on the technology of the I2C bus, and data is transmitted and equipment is controlled through the I2C bus, thereby realizing remote management and monitoring of the server platform. Therefore, in an embodiment of the present application, in order to realize the combination of IPMB and I2C technologies, the IPMB command processing queue in the HOST BMC101 receives the command packet written by the classification queue, and after parsing the command packet, determines the fields contained in the command packet, combines the fields according to the preset IPMB format requirements, obtains the converted IPMB command packet, and writes the IPMB command packet into the target HOST BMC BOX queue corresponding to the identification information of the target BOX BMC.

[0104] In the embodiment of the present application, the command packet is converted into an IPMB command packet according to the preset IPMB format and written into the target HOST BMC BOX queue, so as to facilitate the combination of IPMB and I2C technology, ensure that the command packet can be transmitted smoothly, and ensure the stable operation of the server.

[0105] Embodiment 6:

[0106] Based on the above embodiments, the present application embodiment provides a schematic diagram of an operation and maintenance process, such as Figure 3 As shown, the process includes:

[0107] S301: other devices receive the command packet, obtain identification information of the target BOX BMC carried in the command packet, and send first detection information to the HOST BMC connected to the target BOX BMC.

[0108] S302: Other devices determine whether the first detection information is sent successfully, and if so, execute S303; if not, execute S308.

[0109] S303: Other devices send command packets to the HOST BMC.

[0110] S304: The HOST BMC sends the command packet to the target BOX BMC through the I2C link connected to the target BOX BMC according to the identification information of the target BOX BMC carried in the command packet.

[0111] S305: After receiving the command packet, the target BOX BMC parses the command packet, obtains the command contained in the command packet, and provides corresponding operation and maintenance services for the GPU BOX server where the target BOX BMC is located based on the command; after executing the command, the execution result information of the command is sent to the HOST BMC.

[0112] S306: The HOST BMC sends the received execution result information to other devices.

[0113] S307: Other devices receive the execution result information and display it.

[0114] S308: The other device obtains the IP address of the target BOX BMC stored in itself according to the identification information of the target BOX BMC, establishes a connection with the target BOX BMC based on the IP address, and sends a command packet to the target BOX BMC.

[0115] S309: The target BOX BMC parses the command packet, obtains the command contained in the command packet, executes it, and returns the execution result information to other devices.

[0116] S310: Other devices receive the execution result information of the target BOX BMC.

[0117] Based on the above embodiments, the embodiment of the present application also provides a schematic diagram of an operation and maintenance process for determining that the HOST BMC is normal, such as Figure 4 As shown, the process includes:

[0118] Step 1: Other devices send at least one command packet to the HOST BMC.

[0119] Step 2: The HOST BMC stores the received at least one command packet in the buffer of the HOST BMC, and writes each command packet into the message processing queue in sequence according to the first-in-first-out order.

[0120] Step three, when processing the command packets in the message processing queue, parse each command packet in turn to determine the message type contained in the command packet, determine the target command category of the command packet based on the correspondence between the saved message type and the command category, and determine the target priority corresponding to the command packet based on the target command category and the correspondence between the saved command category and the priority; write each command packet in turn into the target priority command queue corresponding to the command packet in a first-in-first-out order.

[0121] Among them, the priority command queue includes a high priority command queue, a medium priority command queue, and a low priority command queue.

[0122] Step 4: After each priority command queue receives the command packet belonging to the priority, the classification queue processes the command packets stored in the high priority command queue, the medium priority command queue, and the low priority command queue in turn according to the preset ratio, and writes each command packet into the IPMB command processing queue of the HOST BMC in turn.

[0123] Step 5: When processing each command packet in the IPMB command processing queue of the HOST BMC, parse each command packet to determine the identification information of the target BOX BMC carried in each command packet; determine the target HOST BMC BOX queue corresponding to each command packet according to the identification information of the target BOX BMC102 carried in each command packet; for each target HOST BMC BOX queue, write at least one command packet corresponding to the target HOST BMC BOX queue into the target HOST BMC BOX queue in a first-in-first-out order; determine the I2C link corresponding to each command packet according to the correspondence between the HOST BMC BOX queue, the I2C link and the BOX BMC; for each target HOST BMC BOX queue, send at least one command packet stored in the target HOST BMC BOX queue to the target BOX BMC through the I2C link corresponding to the target HOST BMC BOX queue (i.e., the I2C link connected to the target BOX BMC) in a first-in-first-out order, so that the target BOX BMC writes the command packet into its own IPMB command processing queue.

[0124] Step 6: For each target BOX BMC, after the IPMB command processing queue in the target BOX BMC receives at least one command packet, it parses each received command packet in turn according to the first-in-first-out order, determines the command contained in each command packet and the target command type, and forwards each parsed command to the corresponding processing module corresponding to the target command type to which the command belongs, so that the corresponding processing module provides corresponding operation and maintenance services for the GPU BOX server where the target BOX BMC is located; after executing the command, the corresponding processing module returns the execution result information of the command to the IPMB command processing queue, and the IPMB command processing queue of the target BOX BMC returns the execution result information to the HOST BMC.

[0125] Step 7: After receiving the execution result information sent by any target BOX BMC, the HOST BMC forwards the execution result information to other devices.

[0126] Embodiment 7:

[0127] Based on the same concept, on the basis of the above embodiments, the present application provides an operation and maintenance method, which is applied to other devices. Figure 5 A schematic diagram of an operation and maintenance process applied to other devices provided in an embodiment of the present application includes:

[0128] S501: Receive a command packet, and obtain identification information of a target BOX BMC carried in the command packet.

[0129] The operation and maintenance method provided in the embodiments of the present application is applied to other devices shown in the above embodiments.

[0130] The other devices receive the command packet input by the user, parse the command packet, and determine the identification information of the target BOX BMC carried in the command packet.

[0131] S502: Send first detection information to the HOST BMC connected to the target BOX BMC. If it is determined that the HOST BMC is faulty, obtain the IP address of the target BOX BMC, send the command packet to the target BOX BMC, so that the target BOX BMC receives the command packet sent by the other device, parses the command packet, obtains the command contained in the command packet, and executes it.

[0132] In order to determine whether the HOST BMC currently connected to the target BOX BMC is in normal operation, other devices send first detection information to the HOST BMC to determine whether the first detection information is successfully sent. If so, it is determined that the HOST BMC is normal, otherwise, it is determined that the HOST BMC is faulty.

[0133] Specifically, after sending the first detection information to the HOST BMC, the other devices determine whether the return information of the HOST BMC is received within a preset time period, if not, the HOST BMC is determined to be faulty; if yes, it continues to determine whether the return information of the HOST BMC is an error code (error), if yes, the HOST BMC is determined to be faulty, if not, the HOST BMC is determined to be normal. The first detection information can be a specific instruction or command, which is not specifically limited here.

[0134] In the embodiment of the present application, in order to ensure that when the HOST BMC fails, other devices can still provide operation and maintenance management for the GPU BOX server where the BOX BMC is located and obtain the operating status information of the GPU BOX server, the other devices store the corresponding relationship between the identification information of each BOX BMC and the IP address. Therefore, if the other devices determine that the HOST BMC connected to the target BOX BMC is faulty, the IP address of the target BOX BMC is obtained according to the identification information of the target BOX BMC carried in the command packet and the corresponding relationship between the identification information of each BOX BMC and the IP address, and based on the IP address, a connection is established with the target BOX BMC, and the command packet is sent to the target BOX BMC.

[0135] S503: Receive the execution result information of the target BOX BMC.

[0136] After receiving the execution result information returned by the target BOX BMC, other devices can display the execution result information for operation and maintenance personnel to view.

[0137] In the embodiment of the present application, if other devices receive the command packet and determine that the HOST BMC is faulty, the IP address of the target BOX BMC is obtained, a connection is established with the target BOX BMC based on the IP address, and the command packet is sent to the target BOX BMC, thereby obtaining the execution result information reported by the target BOX BMC, thereby avoiding the situation where the BOX BMC is strongly correlated with the operating status of the HOST BMC, and the problem of the GPU BOX server cannot be reported when the HOST BMC is down, so that the operating status of the GPU BOX server where the BOX BMC is located can be monitored in time, and operation and maintenance services can be provided for the GPU BOX server.

[0138] In order to ensure that other devices can establish a connection with the BOX BMC, based on the above embodiments, in the embodiment of the present application, the step of obtaining the IP address of the target BOX BMC includes:

[0139] Acquire the IP address of the target BOX BMC according to the identification information of the target BOX BMC and the stored correspondence between the identification information of the BOX BMC and the IP address;

[0140] The process of determining the correspondence between the identification information of the BOX BMC and the IP address includes:

[0141] Sending a bridge property instruction to the HOST BMC, so that the HOST BMC obtains the IP address of any BOX BMC connected to the HOST BMC after receiving the bridge property instruction, and sends the IP address of the BOX BMC and the identification information of the BOX BMC to the other device;

[0142] The IP address and the identification information of the BOX BMC are received and stored accordingly.

[0143] In order to be compatible with the ability of the CPU node server to manage multiple GPU BOX servers and the independent management ability of the GPU node server, based on the above embodiments, in the embodiment of the present application, if it is determined that the HOST BMC is normal, the method further includes:

[0144] The command packet is sent to the HOST BMC, so that the HOST BMC sends the command packet to the target BOX BMC through an I2C link connected to the target BOX BMC according to the identification information of the target BOX BMC carried in the command packet; wherein the HOST BMC is connected to the BOX BMC through the I2C link.

[0145] Embodiment 8:

[0146] Based on the same concept, on the basis of the above embodiments, this application provides an operation and maintenance method, which is applied to BOX BMC. Figure 6 A schematic diagram of an operation and maintenance process applied to a BOX BMC provided in an embodiment of the present application includes:

[0147] S601: receiving a command packet sent by another device; wherein the command packet is sent by the other device to the BOX BMC after sending first detection information to the HOST BMC connected to the BOX BMC, determining that the HOST BMC is faulty, and obtaining the Internet Protocol IP address of the BOX BMC.

[0148] The operation and maintenance method provided in the embodiments of the present application is applied to the target BOX BMC shown in the above embodiments.

[0149] S602: Parse the command packet, obtain the commands contained in the command packet, and execute them.

[0150] S603: Return execution result information to the other device.

[0151] The process of BOX BMC processing the command packet can refer to the above embodiments, which will not be described in detail here.

[0152] In the embodiment of the present application, if other devices receive the command packet and determine that the HOST BMC is faulty, the IP address of the target BOX BMC is obtained, a connection is established with the target BOX BMC based on the IP address, and the command packet is sent to the target BOX BMC, thereby obtaining the execution result information reported by the target BOX BMC, thereby avoiding the situation where the BOX BMC is strongly correlated with the operating status of the HOST BMC, and the problem of the GPU BOX server cannot be reported when the HOST BMC is down, so that the operating status of the GPU BOX server where the BOX BMC is located can be monitored in time, and operation and maintenance services can be provided for the GPU BOX server.

[0153] Embodiment 9:

[0154] Based on the same technical concept, on the basis of the above embodiments, the present application provides an operation and maintenance device, which is applied to other equipment. Figure 7 This is one of the schematic diagrams of the structure of an operation and maintenance device provided in an embodiment of the present application, such as Figure 7 As shown, the device comprises:

[0155] The first receiving module 701 is used to receive a command packet and obtain identification information of a target BOX BMC carried in the command packet;

[0156] The processing module 702 is used to send the first detection information to the HOST BMC connected to the target BOX BMC, and if it is determined that the HOST BMC is faulty, obtain the IP address of the target BOX BMC, send the command packet to the target BOX BMC, so that the target BOX BMC receives the command packet sent by the other device, parses the command packet, obtains the command contained in the command packet, and executes it;

[0157] The second receiving module 703 is used to receive the execution result information of the target BOX BMC.

[0158] In a possible implementation manner, the processing module 702 is specifically configured to obtain the IP address of the target BOX BMC according to the identification information of the target BOX BMC and the stored correspondence between the identification information of the BOX BMC and the IP address;

[0159] The processing module 702 is specifically configured to send a bridge property instruction to the HOST BMC, so that the HOST BMC obtains the IP address of any BOX BMC connected to the HOST BMC after receiving the bridge property instruction, and sends the IP address of the BOX BMC and the identification information of the BOX BMC to the other device;

[0160] The IP address and the identification information of the BOX BMC are received and stored accordingly.

[0161] In a possible implementation, the processing module 702 is further configured to, if it is determined that the HOST BMC is normal, send the command packet to the HOST BMC, so that the HOST BMC sends the command packet to the target BOX BMC through an I2C link connected to the target BOX BMC according to the identification information of the target BOX BMC carried in the command packet; wherein the HOST BMC is connected to the BOX BMC through the I2C link.

[0162] Embodiment 10:

[0163] Based on the same technical concept, on the basis of the above embodiments, the present application provides an operation and maintenance device, which is applied to BOX BMC. Figure 8 The second schematic diagram of the structure of an operation and maintenance device provided in the embodiment of the present application is as follows: Figure 8 As shown, the device comprises:

[0164] The third receiving module 801 is used to receive a command packet sent by other devices; wherein the command packet is sent by the other device to the BOX BMC after sending first detection information to the HOST BMC connected to the BOX BMC, determining that the HOST BMC is faulty, and obtaining the Internet Protocol IP address of the BOX BMC;

[0165] The parsing module 802 is used to parse the command packet, obtain the command contained in the command packet and execute it;

[0166] The sending module 803 is used to return the execution result information to the other device.

[0167] Embodiment 11:

[0168] Based on the same technical concept, the present application also provides an electronic device, Fig. 9 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application is shown in FIG. Fig. 9 As shown, it includes: a processor 901, a communication interface 902, a memory 903 and a communication bus 904, wherein the processor 901, the communication interface 902, and the memory 903 communicate with each other through the communication bus 904;

[0169] The memory 903 stores a computer program, and when the program is executed by the processor 901, the processor 901 implements any of the above embodiments. Since the principle of solving problems by electronic devices is similar to the operation and maintenance method, the implementation of the electronic device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0170] The communication bus mentioned in the above electronic device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0171] The communication interface 902 is used for communication between the electronic device and other devices.

[0172] The memory may include a random access memory (RAM) or a non-volatile memory (NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0173] The above-mentioned processor can be a general-purpose processor, including a central processing unit, a network processor (Network Processor, NP), etc.; it can also be a digital signal processing processor (Digital Signal Processing, DSP), an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, etc.

[0174] Embodiment 12:

[0175] Based on the same technical concept, the embodiment of the present application provides a computer-readable storage medium, in which a computer program executable by an electronic device is stored, and when the program is run on the electronic device, the electronic device implements any of the above embodiments when executing. Since the principle of solving the problem by the computer-readable storage medium is similar to the operation and maintenance method, the implementation of the computer-readable storage medium can refer to the implementation of the method, and the repeated parts will not be repeated.

[0176] The above-mentioned computer-readable storage medium can be any available medium or data storage device that can be accessed by the processor in the electronic device, including but not limited to magnetic storage such as floppy disks, hard disks, magnetic tapes, magneto-optical disks (MO), etc., optical storage such as CD, DVD, BD, HVD, etc., and semiconductor storage such as ROM, EPROM, EEPROM, non-volatile memory (NANDFLASH), solid-state drive (SSD), etc.

[0177] Based on the same technical concept, the embodiment of the present application also provides a computer program product, which includes: computer program code, when the computer program code is run on a computer, the computer executes any of the above embodiments. Since the principle of solving the problem by the above computer program product is similar to that of the data transmission method, the implementation of the above computer program product can refer to the implementation of the method, and the repeated parts will not be repeated.

[0178] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0179] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0180] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0181] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0182] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. An operation and maintenance system, characterized in that: The system includes a host baseboard management controller HOST BMC, a graphics processing unit node server baseboard management controller BOX BMC and other devices; The other device is used to receive the command packet, obtain the identification information of the target BOX BMC carried in the command packet; send the first detection information to the HOST BMC connected to the target BOX BMC, and if it is determined that the HOST BMC is faulty, obtain the Internet Protocol IP address of the target BOX BMC, send the command packet to the target BOX BMC, and receive the execution result information of the target BOX BMC; The target BOX BMC is used to receive the command packet sent by the other device, parse the command packet, obtain the command contained in the command packet and execute it, and return the execution result information to the other device.

2. The system according to claim 1, characterized in that The other device is specifically used to send a bridge property instruction to the HOST BMC; The HOST BMC is used to obtain the IP address of any BOX BMC connected to the HOST BMC after receiving the bridge property instruction, and send the IP address of the BOX BMC and the identification information of the BOX BMC to the other device; The other device is specifically used to receive the IP address and the identification information of the BOX BMC and store them accordingly.

3. The system according to claim 1, characterized in that The HOST BMC is connected to the BOX BMC via a serial communication protocol I2C link; The other device is further configured to send the command packet to the HOST BMC if it is determined that the HOST BMC is normal; The HOST BMC is further configured to send the command packet to the target BOX BMC through an I2C link connected to the target BOX BMC according to the identification information of the target BOX BMC carried in the command packet.

4. The system according to claim 3, characterized in that The HOST BMC is specifically used to determine a target HOST BMC BOX queue corresponding to the target BOXBMC; write the command packet into the target HOST BMC BOX queue; and send the command packet to the target BOX BMC through an I2C link connected to the target BOX BMC in a first-in-first-out order based on the target HOST BMC BOX queue.

5. The system according to claim 4, characterized in that The HOST BMC is specifically used to convert the command packet into an IPMB command packet according to a preset hardware management interface IPMB format; and write the IPMB command packet into the target HOST BMC BOX queue.

6. An operation and maintenance method, characterized in that: Applied to other devices, the method includes: Receive a command packet, and obtain identification information of the target BOX BMC carried in the command packet; Sending first detection information to a HOST BMC connected to the target BOX BMC, if determining that the HOST BMC is faulty, obtaining the IP address of the target BOX BMC, sending the command packet to the target BOX BMC, so that the target BOX BMC receives the command packet sent by the other device, parses the command packet, obtains the command contained in the command packet, and executes the command; Receive the execution result information of the target BOX BMC.

7. An operation and maintenance method, characterized in that: Applied to BOX BMC, the method comprises: receiving a command packet sent by another device; wherein the command packet is sent by the other device to the BOX BMC after sending first detection information to the HOST BMC connected to the BOX BMC, determining that the HOST BMC is faulty, and obtaining the Internet Protocol IP address of the BOX BMC; Parsing the command packet, obtaining the command contained in the command packet and executing it; Return the execution result information to the other device.

8. An operation and maintenance device, characterized in that: Applied to other equipment, the device comprises: A first receiving module is used to receive a command packet and obtain identification information of a target BOX BMC carried in the command packet; a processing module, configured to send first detection information to a HOST BMC connected to the target BOX BMC, and if it is determined that the HOST BMC is faulty, obtain the IP address of the target BOX BMC, send the command packet to the target BOX BMC, so that the target BOX BMC receives the command packet sent by the other device, parses the command packet, obtains the command contained in the command packet, and executes the command; The second receiving module is used to receive the execution result information of the target BOX BMC.

9. An operation and maintenance device, characterized in that: Applied to BOX BMC, the device comprises: a third receiving module, configured to receive a command packet sent by another device; wherein the command packet is sent by the other device to the BOX BMC after sending first detection information to the HOST BMC connected to the BOX BMC, determining that the HOST BMC is faulty, and obtaining the Internet Protocol IP address of the BOX BMC; A parsing module, used to parse the command packet, obtain the command contained in the command packet and execute it; The sending module is used to return the execution result information to the other device.

10. An electronic device, characterized in that: The electronic device includes at least a processor and a memory, and the processor is used to implement the steps of the operation and maintenance method as claimed in claim 6 or 7 when executing the computer program stored in the memory.

Images