Management system and method for multi-node servers

Abstract

This application discloses a management system and method for a multi-node server, relating to the field of server technology. The system designs a management system for a multi-node server that obtains and stores the configuration information of multiple servers through a controller to acquire register data from multiple servers. A data processing unit acts as the main management control unit for the multi-node server, reading the register data from multiple servers, configuring the network resources of multiple servers, and integrating and transmitting the network resources of multiple servers to a management switch through an onboard switch. This saves on the communication ports of the management switch and reduces the resource occupancy rate of the management switch.

Description

Technical Field

[0001] This application relates to the field of server technology, and in particular to a management system and method for a multi-node server. Background Technology

[0002] In high-performance computing scenarios, multi-node servers have become the mainstream hardware deployment solution due to their high density, modular architecture, and resource sharing characteristics. A multi-node server typically consists of multiple independent nodes, each with its own baseboard management controller.

[0003] In current related technologies, each node's baseboard management controller has an independent management network channel, and all nodes' management network channels are connected to a management switch. The management switch allocates independent resources for each node for management. However, the related technology requires the management switch to reserve multiple communication ports and to allocate independent management resources to each node, resulting in increased resource utilization of the management switch. Summary of the Invention

[0004] This application provides a management system and method for a multi-node server, which at least solves the problem of increased resource utilization of management switches in related technologies.

[0005] This application provides a management system for a multi-node server, including: a controller (10), a data processing unit (20), and an onboard switch (30).

[0006] The data processing unit (20) is communicatively connected to the controller (10) and the onboard switch (30);

[0007] The onboard switch (30) also communicates with the management switch;

[0008] The controller (10) is used to obtain the configuration information of multiple servers and store the configuration information of multiple servers into the register of the controller (10) to obtain the register data of multiple servers, and generate the firmware information of the onboard switch according to the register data. The firmware information is used to establish the communication path between the management system of multiple servers and the management switch.

[0009] The data processing unit (20) is used to read register data from multiple servers and configure network resources of multiple servers based on the register data from multiple servers.

[0010] The onboard switch (30) is used to integrate the network resources of multiple servers and transmit the integrated network resources to the management switch through the communication path so as to realize the management switch to manage multiple servers.

[0011] This application also provides a method for managing multi-node servers, including:

[0012] In response to the power-on operation of the server, obtain the configuration information of multiple servers;

[0013] Store configuration information for multiple servers to obtain register data from multiple servers;

[0014] Firmware information for the onboard switch is generated based on register data from multiple servers.

[0015] Read the firmware information of the onboard switch to establish a communication path between the management system and the management switch of the multi-node server;

[0016] Configure the network resources of multiple servers based on the register data of multiple servers, and integrate the network resources of multiple servers to obtain integrated network data;

[0017] The integrated network data is transmitted to the management switch via a communication path to enable the management switch to manage multiple servers.

[0018] This application also provides an electronic device, including: a memory for storing a computer program; and a processor for executing the computer program to implement the steps of any of the above-described multi-node server management methods.

[0019] This application also provides a computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the steps of any of the above-described multi-node server management methods.

[0020] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of any of the above-described multi-node server management methods.

[0021] This application provides a management system for a multi-node server. By acquiring and storing the configuration information of multiple servers through a controller, the system obtains the register data of multiple servers. A data processing unit serves as the main management control unit for the multi-node server, reads the register data of multiple servers, configures the network resources of multiple servers, and integrates and transmits the network resources of multiple servers to the management switch through an onboard switch. This saves the communication ports of the management switch and reduces the resource occupancy rate of the management switch. Attached Figure Description

[0022] To more clearly illustrate the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 A schematic diagram of the system architecture of the multi-node server management system provided in this application embodiment;

[0024] Figure 2 A flowchart illustrating the multi-node server management method provided in this application embodiment. Figure 1 ;

[0025] Figure 3 A flowchart illustrating the multi-node server management method provided in this application embodiment. Figure 2 ;

[0026] Figure 4 A flowchart illustrating the multi-node server management method provided in this application embodiment. Figure 3 ;

[0027] Figure 5 A flowchart illustrating the multi-node server management method provided in this application embodiment. Figure 4 ;

[0028] Figure 6 A flowchart illustrating the multi-node server management method provided in this application embodiment. Figure 5 ;

[0029] Figure 7 A schematic diagram of the structure of the electronic device provided in this application.

[0030] The above figures include the following reference numerals:

[0031] 10-Controller;

[0032] 20 - Data processing unit;

[0033] 30 - Onboard switch;

[0034] 40-Expander;

[0035] 50 - Memory. Detailed Implementation

[0036] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the protection scope of this application.

[0037] It should be noted that, in the description of this application, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. The terms "first," "second," etc., in this application are used to distinguish similar objects and are not used to describe a specific order or sequence.

[0038] To address the issue of increased resource occupancy in management switches in related technologies, this application proposes the following technical concept: The inventors considered designing a management system for multi-node servers. This system obtains and stores the configuration information of multiple servers through a controller to acquire register data from the servers. A data processing unit, acting as the main management control unit for the multi-node servers, reads the register data from the servers, configures the network resources of the servers, and integrates and transmits the network resources of the servers to the management switch via an onboard switch. This saves communication ports on the management switch and reduces its resource occupancy.

[0039] To enable those skilled in the art to better understand the present application, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0040] Figure 1 This is a schematic diagram of the system architecture of the multi-node server management system provided in an embodiment of this application. Figure 1 As shown, it includes: controller 10, data processing unit 20 and onboard switch 30.

[0041] The data processing unit 20 is communicatively connected to the controller 10 and the onboard switch 30.

[0042] In this embodiment, the controller 10 is a programmable logic device.

[0043] In this embodiment, the baseboard management controller in the data processing unit 20 is connected to the controller 10 via a two-wire serial bus.

[0044] In this embodiment, the baseboard management controller in the data processing unit 20 is communicatively connected to the onboard switch 30 via an RGMII (Reduced Gigabit Media Independent Interface) line and an MDC (Management Data Clock) line.

[0045] In this embodiment, the data processing unit reserves an Ethernet management port to access the data center's management network. Operation and maintenance functions are completed directly or indirectly through the baseboard management controller of the data processing unit.

[0046] The onboard switch 30 also communicates with the management switch.

[0047] In this embodiment, the onboard switch 30 has only one reserved Ethernet management port for connecting to an external management switch, and is connected to the management switch via a network cable.

[0048] Controller 10 is used to obtain configuration information of multiple servers and store the configuration information of multiple servers in the register of controller 10 to obtain register data of multiple servers, and generate firmware information of onboard switch based on register data. Firmware information is used to establish communication path between the management system of multiple servers and the management switch.

[0049] In this embodiment, the controller 10 monitors the service configuration and node functions of different servers and flashes the firmware of the onboard switch 30 into the memory 50.

[0050] In this embodiment, when the server is powered on, the controller 10 collects register information, determines the node's presence status based on the extender 40, and determines the server's configuration information based on the identified server's service configuration.

[0051] The data processing unit 20 is used to read register data from multiple servers and configure network resources for multiple servers based on the register data from multiple servers.

[0052] In this embodiment, after the data processing unit 20 identifies the overall configuration information of the server through the controller 10, it writes the firmware information to the memory 50.

[0053] The onboard switch 30 is used to integrate the network resources of multiple servers and transmit the integrated network resources to the management switch through the communication path, so as to realize the management switch to manage multiple servers.

[0054] In this embodiment, the onboard switch 30 has a reserved network port for connecting to an external management switch.

[0055] In this embodiment, the MAC (Media Access Control Address) of the baseboard management controller in the data processing unit 20 is connected to the communication port of the onboard switch 30. The MACs of the baseboard management controllers of multiple servers are connected to multiple communication ports reserved in the onboard switch 30. Each communication port corresponds to the MAC of the baseboard management controller of one server, and an Ethernet module is provided between the MAC and the communication port.

[0056] In one embodiment of this application, the management system for the multi-node server further includes: an extender 40.

[0057] The extender 40 communicates with multiple servers and controllers 10 respectively.

[0058] In this embodiment, the extender 40 and the controller 10 are connected via a two-wire serial bus.

[0059] Extender 40 is used to acquire server level data from multiple servers and determine the configuration information of multiple servers based on the server level data.

[0060] In this embodiment, the GPIO (General Purpose Input / Output) port of the extender 40 monitors the node server.

[0061] For example, the GPIO ports 0, 1, 2, and 3 of the extender 40 monitor the in-situ status of the node server, and the GPIO ports 4, 5, 6, and 7 monitor the service configuration type of the node server.

[0062] In one embodiment of this application, the management system for the multi-node server further includes a memory 50.

[0063] The memory 50 is communicatively connected to the data processing unit 20 and the onboard switch 30.

[0064] In this embodiment, the memory 50 and the baseboard management controller in the data processing unit 20 are connected via a two-wire serial bus.

[0065] In this embodiment, the memory 50 is connected to the onboard switch via a communication bus.

[0066] The memory 50 is used to store the firmware information of the onboard switch 30 generated by the data processing unit 20.

[0067] In this embodiment, the memory 50 can be flashed with a pre-compiled bin (binary) file as the firmware of the onboard switch 30, enabling the onboard switch 30 to perform network switching functions.

[0068] Figure 2A flowchart illustrating the multi-node server management method provided in this application embodiment. Figure 1 ,like Figure 2 As shown, embodiments of this application provide a management method for a multi-node server. The method is described in detail below:

[0069] S201: In response to the power-on operation of the server, obtain the configuration information of multiple servers.

[0070] Specifically, the in-situ status data and server type data of multiple servers are determined based on the server level data, and the configuration information of multiple servers is obtained through encoding conversion.

[0071] The presence status indicates whether the server can be detected at the location where the server is set.

[0072] For example, a server with two nodes is set up, and the positions of the servers are set as position A and position B. If server a is detected at position A, a high level of 1 indicates that server a is detected at position A, and the presence state of server a is 1. If server b is not detected at position B, a low level of 0 indicates that server b is not detected at position B, and the presence state of server b is 0.

[0073] S202: Stores configuration information for multiple servers to obtain register data from multiple servers.

[0074] In this embodiment, the configuration information of multiple servers records, but is not limited to, the server's on-site status and business data.

[0075] In this embodiment, the register data is data in which configuration information is stored according to the controller's register data storage format.

[0076] S203: Generate firmware information for the onboard switch based on register data from multiple servers.

[0077] Specifically, the data mapping file is parsed, the data is traversed and parsed based on the register data to obtain the firmware path, the firmware of the onboard switch is obtained, and the firmware information is determined.

[0078] S204: Read the firmware information of the onboard switch to establish a communication path between the management system and the management switch of the multi-node server.

[0079] Specifically, the baseboard management controller of the data processing unit acquires write access to the memory and write permission, writes the firmware into the memory via a two-wire serial bus, and releases the write permission.

[0080] Specifically, after the firmware is written, the baseboard management controller of the data processing unit controls the onboard switch to reset through the management data input / output interface. The onboard switch loads the firmware in the memory and establishes a communication path between the management system of the multi-node server and the management switch.

[0081] S205: Configure the network resources of multiple servers based on the register data of multiple servers, and integrate the network resources of multiple servers to obtain integrated network data.

[0082] In this embodiment, network resources include, but are not limited to, network type and network IP address.

[0083] In this embodiment, the integrated network data is the data obtained by classifying and integrating the network resources of multiple servers according to network type and network IP address.

[0084] S206: The integrated network data is transmitted to the management switch through the communication path to enable the management switch to manage multiple servers.

[0085] Specifically, the baseboard management controller of the data processing unit configures port forwarding instructions to forward the integrated network data to the onboard switch, and the onboard switch transmits the integrated network data to the management switch through the communication path.

[0086] As can be seen from the above embodiments, server level data of the server is obtained through the extender, the controller aggregates the server level data of multiple servers and sends it to the data processing unit. The data processing unit manages the servers of multiple nodes and establishes a connection between the server and the management switch using the onboard switch, thereby reducing the resource occupancy of the management switch.

[0087] In one embodiment of this application, step S201 includes:

[0088] S201a: Determine the in-situ status data and service type data of multiple servers based on the server level data of multiple servers.

[0089] For example, if there are 4 servers, the first 4 bits of the extender's GPIO port represent the server's presence status, and the combination of the high and low levels of the last 4 bits represent the server's service type.

[0090] In this embodiment, the high and low levels of the extender represent the in-situ status data of multiple servers.

[0091] For example, a low level indicates that the server is not in place, and a high level indicates that the server is in place.

[0092] In this embodiment, business type data includes, but is not limited to, file storage type, application storage type, and database type.

[0093] S201b: Encodes and converts the on-premises status data and business type data of multiple servers to generate digital codes.

[0094] Specifically, the status data and business type data obtained by the extender are concatenated, and the concatenated data is encoded into binary numbers to obtain a digital code.

[0095] In this embodiment, the numbers are encoded as a structured sequence of numbers.

[0096] S201c: Standardizes the digital encoding to obtain configuration information for multiple servers.

[0097] Specifically, the length and field order of the numeric codes on each server are standardized, and the processed numeric code sequences are integrated into a structured data object.

[0098] In this embodiment, the server's configuration information records the server's in-situ status and the server's service type.

[0099] As can be seen from the above embodiments, by reading the physical status register through the extender, determining the in-situ status and service type based on the server level data, converting the encoding to obtain digital encoding, and using the digital encoding to drive firmware writing, the efficiency of information writing is improved.

[0100] In one embodiment of this application, step S203 includes:

[0101] S203a: Parse the pre-stored data mapping file to generate parsed data.

[0102] In this embodiment, a data mapping file is pre-stored in the image in the baseboard manager of the data processing unit.

[0103] The data mapping file is a mapping file between server configuration information and the firmware path of the onboard switch.

[0104] The data parsed includes, but is not limited to, register values, descriptive information, and bin file paths.

[0105] S203b: Obtain the firmware path by traversing and parsing the register data of multiple servers.

[0106] Specifically, the baseboard management controller in the data processing unit loads register data, saves the contents of the parsed data to the data bus interface, traverses the register values ​​in the parsed data, and obtains the firmware path of the server based on the register values.

[0107] S203c: Obtain the firmware of the onboard switch based on the firmware path, and determine the firmware information of the onboard switch.

[0108] Specifically, the baseboard management controller in the data processing unit obtains the firmware of the onboard switch according to the firmware path and writes the firmware into the memory.

[0109] As can be seen from the above embodiments, by parsing the pre-stored data mapping file to obtain parsed data, traversing the parsed data to obtain the firmware path, and automatically writing the firmware according to the firmware path, the efficiency of firmware writing is improved.

[0110] Figure 3 A flowchart illustrating the multi-node server management method provided in this application embodiment. Figure 2 ,like Figure 3 As shown, in one embodiment of this application, after step S204, the method further includes:

[0111] S301: In response to the operation of adding a target server, obtain the server level data of the target server.

[0112] Specifically, the baseboard management controller of the data processing unit receives the instruction to add a new server sent by the data center, and obtains the level data of the server to be added according to the instruction.

[0113] S302: Generates a data configuration file and target firmware information based on the server level data of the target server.

[0114] Specifically, the server's service type is determined based on the voltage level data, a structured data configuration file is generated, and the appropriate firmware is matched based on the data configuration file.

[0115] S303: Writes the data configuration file and target firmware information to the extender to add the target server.

[0116] Specifically, the baseboard management controller of the data processing unit writes the data configuration file and target firmware information into the memory via a two-wire serial bus, updates the firmware of the onboard switch, and enables the addition of the server.

[0117] As can be seen from the above embodiments, when a new server is added, the data processing unit obtains the server level data to be added, generates a data configuration file and target firmware information based on the server level data to be added, and writes the data configuration file and target firmware information corresponding to the new server into the extender to realize the addition of the server, thereby improving the convenience of adding new server nodes in a multi-node server.

[0118] Figure 4 A flowchart illustrating the multi-node server management method provided in this application embodiment. Figure 3 ,like Figure 4 As shown, in one embodiment of this application, before step S301, the following steps are further included:

[0119] S401: Obtain access permissions to the target server.

[0120] In this embodiment, the target server's access permissions are encrypted digital certificates or digital tokens.

[0121] S402: Decrypt the access permissions of the target server to obtain the decrypted permission data, and verify the decrypted permission data.

[0122] Specifically, the baseboard management controller of the data processing unit uses a private key to decrypt the encrypted access permissions using an asymmetric decryption algorithm, and verifies the decrypted access data to check whether the digital signature has expired.

[0123] S403: If the decrypted permission data passes verification, create an add instruction for the target server to execute the add operation for the target server.

[0124] In this embodiment, the information recorded in the addition instruction includes, but is not limited to, the target server's network IP address, server service type, and priority.

[0125] As can be seen from the above embodiments, by verifying the access permissions of the target server, the security of the server node to be added is determined. If the verification is successful, the addition is allowed, which improves the security of multi-node servers.

[0126] Figure 5 A flowchart illustrating the multi-node server management method provided in this application embodiment. Figure 4 ,like Figure 5 As shown, in one embodiment of this application, after step S204, the method further includes:

[0127] S501: Receives network resource utilization rate data sent by the management switch.

[0128] Specifically, the onboard switch acquires the network resource utilization rate sent by the management switch through a preset collection period.

[0129] S502: Determine if there are servers in the network resource utilization rate that exceed the resource utilization rate threshold.

[0130] Specifically, the network resource utilization rate is compared with a preset resource utilization rate threshold to identify servers that exceed the limit.

[0131] S503: If there are servers that exceed the resource utilization threshold, the network address of the server exceeding the threshold shall be determined based on the network resource utilization.

[0132] Specifically, the network address mapping table is queried for servers that exceed the resource utilization threshold to determine the network address of the overloaded servers.

[0133] S504: Determine the over-limit server based on its network address and generate alarm information based on the over-limit server.

[0134] Specifically, the baseboard management controller of the data processing unit determines the over-limit server based on the network address, generates an alarm command, and sends the alarm information to the data center through the onboard switch.

[0135] In this embodiment, the alarm information records, but is not limited to, the identifier of the server that exceeded the limit, the time of exceeding the limit, and the network address of the server that exceeded the limit.

[0136] As can be seen from the above embodiments, the network resource utilization rate sent by the management switch is obtained through the onboard switching module, the data processing unit determines whether there is a server with excessive resource utilization, identifies the server with excessive utilization based on the network address and generates alarm information, thereby avoiding long-term occupation of the network resources of the management switch.

[0137] Figure 6 A flowchart illustrating the multi-node server management method provided in this application embodiment. Figure 5 ,like Figure 6 As shown, in one embodiment of this application, before step S206, the following steps are further included:

[0138] S601: The integrated network data is encrypted in layers using a preset encryption algorithm to generate encrypted data.

[0139] Specifically, the baseboard management controller of the data processing unit uses a symmetric session key to perform layered encryption on the integrated network data, generating encrypted data.

[0140] S602: Generate a feature verification code based on the public key of the management switch.

[0141] Specifically, the baseboard management controller of the data processing unit calculates the digital digest of the encrypted data, obtains the system private key based on the public key of the management switch, signs and encapsulates the digital digest using the system private key, and obtains the feature verification code.

[0142] S603: Compress the signature verification code and encrypted data to generate a network data packet to be transmitted.

[0143] Specifically, the baseboard management controller of the data processing unit uses the feature verification code and encrypted data as the payload, compresses them according to a predefined communication protocol format, and generates network data packets to be transmitted.

[0144] As can be seen from the above embodiments, by using a symmetric encryption algorithm and layered encryption technology to encrypt the transmitted network data, and creating a feature verification code based on the public key of the management switch, the feature verification code and encrypted data are compressed to obtain a network data packet and transmitted to the management switch, thereby improving the security of the transmitted data.

[0145] In one embodiment of this application, step S602 includes:

[0146] S602a: Calculate the digital digest of the encrypted data to obtain the hash value of the encrypted data.

[0147] Specifically, a digital digest of the encrypted data is calculated using a preset hash algorithm to obtain a hash value.

[0148] S602b: Asymmetric encryption is performed on the hash value of the encrypted data using the system private key to obtain a digital signature.

[0149] Specifically, the hash value is signed using an asymmetric encryption algorithm based on the system's private key to obtain a digital signature.

[0150] In this embodiment, the system private key and the management switch public key are asymmetric key pairs.

[0151] S602c: Encapsulates the digital signature and generates a feature verification code.

[0152] Specifically, the digital signature is assembled and encoded according to a predefined encoding format to generate a structured feature verification code.

[0153] As can be seen from the above embodiments, the integrity and security of the feature verification code can be achieved by calculating the digital digest of the encrypted data packet, performing digital signature using the system private key, and standardizing and encapsulating the signature result.

[0154] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method.

[0155] Figure 7 A schematic diagram of the structure of the electronic device provided in this application. Figure 7 As shown, the electronic device 70 provided in this embodiment includes at least one processor 701 and a memory 702. Optionally, the electronic device 70 further includes a communication component 703. The processor 701, memory 702, and communication component 703 are connected via a bus.

[0156] In a specific implementation, at least one processor 701 executes computer execution instructions stored in memory 702, causing at least one processor 701 to execute the above-described multi-node server management method embodiment.

[0157] The specific implementation process of processor 701 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0158] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the application can be directly manifested as being executed by a hardware processor, or executed by a combination of hardware and software modules within the processor.

[0159] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0160] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0161] Embodiments of this application also provide a computer-readable storage medium storing a computer program, wherein the computer program is configured to execute the steps in any of the above embodiments of the multi-node server management method when running.

[0162] In one exemplary embodiment, the aforementioned computer-readable storage medium may include, but is not limited to, various media capable of storing computer programs, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard disk, magnetic disk, or optical disk.

[0163] The embodiments of this application also provide a computer program product, which includes a computer program that, when executed by a processor, implements the steps in any of the above embodiments of the multi-node server management method.

[0164] Embodiments of this application also provide another computer program product, including a non-volatile computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps in any of the above-described multi-node server management method embodiments.

[0165] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0166] The above provides a detailed description of a multi-node server management system and method provided in this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the embodiments above are only intended to help understand the method and core ideas of this application. It should be noted that those skilled in the art can make various improvements and modifications to this application without departing from its principles, and these improvements and modifications also fall within the protection scope of the claims of this application.

Claims

1. A management system of a multi-node server, characterized by, The application relates to a multi-node server management system, which comprises a controller (10), a data processing unit (20) and an on-board switch (30). The data processing unit (20) is in communication connection with the controller (10) and the on-board switch (30) respectively. The on-board switch (30) is also in communication connection with a management switch. The controller (10) is used for obtaining configuration information of multiple servers and storing the configuration information of the multiple servers into a register of the controller (10), so as to obtain register data of the multiple servers and generate firmware information of the on-board switch according to the register data, wherein the firmware information is used for establishing a communication path between a management system of the multiple servers and the management switch. The data processing unit (20) is used for reading the register data of the multiple servers and configuring network resources of the multiple servers according to the register data of the multiple servers. The on-board switch (30) is used for integrating the network resources of the multiple servers and transmitting the integrated network resources to the management switch through the communication path, so as to realize management of the multiple servers by the management switch. The multi-node server management system further comprises an extender (40).

2. The management system of a multi-node server according to claim 1, wherein The extender (40) is in communication connection with the multiple servers and the controller (10) respectively. The extender (40) is used for obtaining server level data of the multiple servers and determining the configuration information of the multiple servers according to the server level data of the multiple servers. The multi-node server management system further comprises a memory (50).

3. The management system of a multi-node server according to claim 1, wherein The memory (50) is in communication connection with the data processing unit (20) and the on-board switch (30) respectively. The memory (50) is used for storing the firmware information of the on-board switch (30) generated by the data processing unit (20). The application further relates to a method for managing multiple servers.

4. A management method of a multi-node server, characterized by, The method comprises the following steps: obtaining configuration information of multiple servers in response to a power-on operation of the servers; storing the configuration information of the multiple servers to obtain register data of the multiple servers; generating firmware information of an on-board switch according to the register data of the multiple servers; reading the firmware information of the on-board switch to establish a communication path between a management system of the multiple servers and a management switch; configuring network resources of the multiple servers according to the register data of the multiple servers and integrating the network resources of the multiple servers to obtain integrated network data; transmitting the integrated network data to the management switch through the communication path to realize management of the multiple servers by the management switch.

5. The management method of a multi-node server according to claim 4, characterized by, The step of obtaining the configuration information of the multiple servers comprises the following steps: determining in-place state data and service type data of the multiple servers according to server level data of the multiple servers; encoding and converting the in-place state data and the service type data of the multiple servers to generate digital codes; standardizing the digital codes to obtain the configuration information of the multiple servers.

6. The management method of a multi-node server according to claim 4, characterized by, The step of generating the firmware information of the on-board switch according to the register data of the multiple servers comprises the following steps: analyzing a pre-stored data mapping file to generate analysis data; According to the register data of the plurality of servers, the parsing data is traversed to obtain a firmware path; According to the firmware path, firmware of the on-board switch is acquired, and firmware information of the on-board switch is determined.

7. The management method of a multi-node server according to claim 4, characterized by, After the firmware information of the on-board switch is read, the method further comprises: In response to an operation of adding a target server, server level data of the target server is acquired; According to the server level data of the target server, data configuration files and target firmware information are generated; The data configuration files and the target firmware information are written into an extender to implement addition of the target server.

8. The management method of a multi-node server according to claim 7, characterized by, Before the operation of adding the target server, the server level data of the target server is acquired, the method further comprises: Access authority of the target server is acquired; The access authority of the target server is decrypted to obtain decrypted authority data, and the decrypted authority data is verified; If the decrypted authority data is verified, an addition instruction of the target server is created to execute the addition operation of the target server.

9. The management method of a multi-node server according to claim 4, characterized by, After the firmware information of the on-board switch is read, the method further comprises: A network resource usage rate sent by a management switch is received; It is judged whether there is a server exceeding a resource usage rate threshold in the network resource usage rate; If there is a server exceeding the resource usage rate threshold, a network address of an out-of-limit server is determined according to the network resource usage rate; The out-of-limit server is determined according to the network address of the out-of-limit server, and alarm information is generated according to the out-of-limit server.

10. The management method of a multi-node server according to claim 4, characterized by, Before the integrated network data is transmitted to the management switch through the communication path, the method further comprises: The integrated network data is hierarchically encrypted by a preset encryption algorithm to generate encrypted data; A feature verification code is generated according to a public key of the management switch; The feature verification code and the encrypted data are compressed to generate a network data packet to be transmitted.

Images