Multi-node server information management method and device, equipment, storage medium and product

Abstract

The invention relates to a multi-node server information management method and device, equipment, a storage medium and a product, and relates to the technical field of server firmware design. The method comprises the following steps: receiving node static information and node dynamic information sent by each server node; adding the node static information and the node dynamic information of each server node to a preset node information management table; in response to an information acquisition request sent by any server node for other server nodes, searching the node information management table to obtain target node information of other server nodes; the target node information comprises node static information and / or node dynamic information; and returning the target node information to any server node. By adopting the method, the information management cost of the multi-node server can be reduced.

Description

Technical Field

[0001] This application relates to the technical field of server firmware design, and in particular, to a method, device, equipment, storage medium, and product for managing multi-node server information. Background Art

[0002] In a common multi-node server architecture, each server node is equipped with independent processors, memory, storage, and network resources, and at the same time shares the chassis and the fans, power supplies, and management modules inside the chassis. In related technologies, a central hub is used to manage each server node, and each server node interacts with the central hub for data transmission, and the server nodes also interact with each other for data transmission accordingly. However, as the number of server nodes gradually increases, in a large-scale data interaction scenario, the data processing burden on the central hub increases, thereby increasing the costs of its hardware configurations such as chip processing capabilities and data caches, as well as software-level optimizations of related algorithms. Therefore, the multi-node server architecture in related technologies has a problem of high costs. Summary of the Invention

[0003] Based on this, it is necessary to provide a method, device, computer equipment, computer-readable storage medium, and computer program product for managing multi-node server information that can reduce costs in view of the above technical problems.

[0004] In a first aspect, this application provides a method for managing multi-node server information, which is applied to a management module in a multi-node server. The multi-node server is integrated by multiple server nodes, and includes:

[0005] Receiving node static information and node dynamic information sent by each server node;

[0006] Adding the node static information and the node dynamic information of each server node to a preset node information management table;

[0007] In response to an information acquisition request sent by any server node for other server nodes, searching the node information management table to obtain target node information of the other server nodes; the target node information includes node static information and / or node dynamic information;

[0008] Returning the target node information to the any server node.

[0009] In one of the embodiments, the adding the node static information and the node dynamic information of each server node to a preset node information management table includes:

[0010] Convert the node static information and the node dynamic information of each server node into a preset information format to obtain the converted static information and the converted dynamic information;

[0011] Add the converted static information and the converted dynamic information to a preset node information management table.

[0012] In one embodiment, the method further includes:

[0013] In response to an information acquisition request for the multi-node server sent by any one of the server nodes, search the node information management table to obtain the target whole-machine information of the multi-node server; the target whole-machine information includes at least one of the total number of all the server nodes, the node numbers of each server node, and the whole-machine dynamic information;

[0014] Return the target whole-machine information to the any one server node.

[0015] In one embodiment, the searching the node information management table in response to an information acquisition request for other server nodes sent by any one of the server nodes to obtain the target node information of the other server nodes includes:

[0016] In response to an information acquisition request for other server nodes sent by any one of the server nodes, determine the offset corresponding to the other server node according to the node number of the other server node;

[0017] Search the node information management table according to the offset corresponding to the other server node to obtain the target node information of the other server nodes.

[0018] In one embodiment, the adding the node static information and the node dynamic information of each server node to a preset node information management table includes:

[0019] After each power-on of the multi-node server, add the node static information of each server node to a preset node information management table;

[0020] Add the node dynamic information to a preset node information management table according to a preset period.

[0021] In one embodiment, the preset node information management table corresponds to each of the server nodes one by one.

[0022] In a second aspect, the present application further provides a multi-node server information management device, including:

[0023] An information receiving module, configured to receive node static information and node dynamic information sent by each server node;

[0024] An information writing module, configured to add the node static information and the node dynamic information of each server node to a preset node information management table;

[0025] An information locating module, configured to, in response to an information acquisition request sent by any server node for another server node, search the node information management table to obtain target node information of the other server node; the target node information includes node static information and / or node dynamic information;

[0026] An information sending module, configured to return the target node information to the any server node.

[0027] In a third aspect, the present application further provides a computer device, including a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0028] Receive node static information and node dynamic information sent by each server node;

[0029] Add the node static information and the node dynamic information of each server node to a preset node information management table;

[0030] In response to an information acquisition request sent by any server node for another server node, search the node information management table to obtain target node information of the other server node; the target node information includes node static information and / or node dynamic information;

[0031] Return the target node information to the any server node.

[0032] In a fourth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0033] Receive node static information and node dynamic information sent by each server node;

[0034] Add the node static information and the node dynamic information of each server node to a preset node information management table;

[0035] In response to an information acquisition request sent by any server node for another server node, search the node information management table to obtain target node information of the other server node; the target node information includes node static information and / or node dynamic information;

[0036] Return the target node information to any one of the server nodes.

[0037] In a fifth aspect, the present application further provides a computer program product, including a computer program, which when executed by a processor implements the following steps:

[0038] Receive the node static information and node dynamic information sent by each server node;

[0039] Add the node static information and the node dynamic information of each server node to a preset node information management table;

[0040] In response to an information acquisition request sent by any one of the server nodes for other server nodes, search the node information management table to obtain the target node information of the other server nodes; the target node information includes node static information and / or node dynamic information;

[0041] Return the target node information to any one of the server nodes.

[0042] In the above multi-node server information management method, device, computer device, computer-readable storage medium, and computer program product, in this method, the management module receives the node static information and node dynamic information sent by each server node, adds the node static information and node dynamic information of each server node to a preset node information management table, and centrally manages the information of each server node; the management module also responds to an information acquisition request sent by any one of the server nodes for other server nodes, searches the node information management table to obtain the target node information of the other server nodes, where the target node information includes node static information and / or node dynamic information, and further returns the target node information to any one of the server nodes. The management module ensures the content synchronization and accuracy of the entire multi-node server in information management through centralized storage and information provision. In addition, no additional interaction paths need to be set between server nodes, and only the management module is used to implement information interaction between server nodes, reducing the design complexity of the multi-node server and also reducing the burden on the server nodes, thereby reducing the cost of information management. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required for use in the description of the embodiments of the present application or related technologies. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other related drawings can be obtained without creative efforts based on these drawings.

[0044] Figure 1Schematic diagram of the structure of a multi-node server architecture in related technologies in an embodiment;

[0045] Figure 2 Application environment diagram of a multi-node server information management method in an embodiment;

[0046] Figure 3 Flow schematic diagram of a multi-node server information management method in an embodiment;

[0047] Figure 4 Flow schematic diagram of a multi-node server information management method in another embodiment;

[0048] Figure 5 Schematic diagram of the structure of a multi-node server system in another embodiment;

[0049] Figure 6 Block diagram of the structure of a multi-node server information management device in an embodiment;

[0050] Figure 7 Internal structure diagram of a computer device in an embodiment. Detailed implementation manners

[0051] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0052] As described in the background art, the multi-node server architecture of the related technology has the problem of relatively high costs. After research by the inventors, it is found that the reason for this problem is that in the common multi-node server architecture, each server node is equipped with independent processors, memories, storages, and network resources, and at the same time shares the chassis and the fans, power supplies, and management modules inside the chassis. In terms of the current design of the chassis management unit (CMU), the following problems are encountered in terms of cost and complexity: Problem 1: The data processing pressure causes the cost to climb - as the number of server nodes gradually increases, the amount of communication data and the communication frequency between the baseboard management controller (BMC) and the CMU continue to grow. This requires the CMU to continuously enhance its data processing performance and efficiency to ensure smooth cross-node communication and information synchronization. This requirement indirectly leads to a continuous increase in the design cost of the CMU. For example, in a large-scale data interaction scenario, the CMU needs to process a large amount of real-time data, which poses higher requirements for its hardware configurations such as chip processing capabilities and data caches, as well as software-level optimizations of related algorithms, thus driving up the cost. Problem 2: Fault detection and recovery further increase the complexity - in a multi-node server, the probability of a single node failing is relatively high. The CMU needs to have the ability to detect faults in a timely manner and take effective recovery measures, including operations such as quickly locating the faulty node, isolating the fault, and reassigning tasks. However, in actual complex application scenarios, the forms of faults are diverse, which greatly increases the difficulty of detection and recovery and the design complexity. For example, in a large-scale data processing scenario, a node may fail due to various reasons such as overheating, software hang, or hardware aging. In order to accurately determine the root cause of the fault, it is often necessary to additionally introduce the master-slave and interaction logic of the node BMC, as Figure 1 shown, which provides a schematic structural diagram of the multi-node server architecture in the related technology, and this poses extremely high requirements for aspects such as CMU algorithm design, logical judgment, and hardware cooperation.

[0053] For the above reasons, the present application provides a multi-node server information management method, aiming to reduce the information management cost of the multi-node server architecture.

[0054] The multi-node server information management method provided by the embodiments of the present application can be applied to, for example Figure 2In the application environment shown, the application scenario includes n server nodes 202, a management module 204, and a data storage system. The n server nodes are integrated to obtain a multi-node server. Among them, the server nodes 202 communicate with the management module 204 through a network. The data storage system can store the data that the management module 204 needs to process. The data storage system can be integrated on the server 204, or placed on the cloud or other network servers. The management module 204 receives the node static information and node dynamic information sent by each server node 202, and adds the node static information and node dynamic information of each server node 202 to a preset node information management table, and the node information management table is stored in the data storage system; in addition, the management module 204 responds to an information acquisition request sent by any server node 202 for other server nodes 202, searches the node information management table, and obtains the target node information of other server nodes 202, where the target node information includes node static information and / or node dynamic information. Further, the management module 204 returns the target node information to any server node.

[0055] In an exemplary embodiment, as Figure 3 shown, a multi-node server information management method is provided. Taking the management module 204 in Figure 2 as an example for description, the multi-node server is obtained by integrating multiple server nodes, and includes the following steps S302 to S308. Among them:

[0056] Step S302: Receive the node static information and node dynamic information sent by each server node.

[0057] Among them, the management module can be a CMU, which acts as the logical unit concept of the centralized management of the entire server in the multi-node server. In a specific implementation, it can be the MCU (Micro Controller Unit, microprocessor) that acts as the "management center" of the entire machine, or the CPLD (Complex Programmable Logic Device) can provide a read / write interface to the server BMC and act as the "information center" for the interaction of the entire machine management information. Among them, the CPLD is a digital integrated circuit in which users can construct logical functions according to their respective needs.

[0058] Among them, a multi-node server refers to integrating multiple independent server nodes in a physical server chassis. Each node has relatively independent processor, memory, storage, and network resources, just like multiple small servers integrated in a larger hardware system. Common multi-node servers mainly include: blade servers, rack-mounted multi-node servers, modular multi-node servers, etc.

[0059] Among them, the node static information can be the inherent configuration information of the server node, including: static asset information, including but not limited to BMC version, BIOS (Basic Input / Output System) version, firmware release date, system model, CPU Model (Central Processing Unit Model) name, memory capacity, motherboard SN / PN (Serial Number / Part Number), Raid (Redundant Array of Independent Disks) card manufacturer model, GPU (Graphics Processing Unit) card model, Riser card SN / PN, etc.); BMC management entry information, such as: BMC IP (Internet Protocol) address, SNMP (Simple Network Management Protocol) port, RMCP / RMCP+ (Remote Management Control Protocol / Remote Management Control Protocol Plus) port, etc.

[0060] Among them, the node dynamic information can be the running information of the server node, including the node health status (normal / slight / severe), the BMC running status of the node (normal / abnormal), and the sensor values of key temperatures, voltages, power consumptions, etc. of the node, including but not limited to: the temperatures of core devices that need to participate in heat dissipation speed control, such as CPU, GPU, memory, VR (Voltage Regulator) chips, etc.

[0061] It should be noted that each server node communicates with the management module through the Baseboard Management Controller BMC deployed on each server node. Among them, BMC is a hardware device used to monitor and manage various hardware and software components of a computer system. BMC is usually an independent chip, which is connected to the main processor and other hardware devices and can be accessed and controlled through a network or other remote management interfaces. The main functions of BMC include system monitoring, remote management, fault diagnosis, and security management, etc.

[0062] Optionally, the management module receives node static information and node dynamic information sent by the baseboard management controller of each server node as the basis for information management. It can be understood that the BMC of the server node collects node dynamic information in real time, but sends the node dynamic information to the management module periodically. The length of the cycle can be set according to actual needs and there is no specific limitation on this.

[0063] Step 304: Add the node static information and node dynamic information of each server node to a preset node information management table.

[0064] The preset node information management table may be a mapping table preset by a technician, which is provided with an identifier and used to store data. The preset node information management table is stored in a database, and the management module may read it through the identifier.

[0065] Optionally, the management module adds the node static information and node dynamic information of each server node to a preset node information management table for use as a basis for subsequent information review, such as when server node operation status detection or fault cause locating is required.

[0066] Step 306: In response to an information acquisition request sent by any server node for other server nodes, search the node information management table to obtain target node information of other server nodes.

[0067] The target node information includes node static information and / or node dynamic information.

[0068] The information acquisition request may be an information acquisition instruction sent by any server node and containing a node identifier or a node number of another server node.

[0069] Optionally, the management module responds to an information acquisition request sent by any server node to other server nodes, and searches the node information management table according to the node identifier or node number of the other server nodes in the information acquisition request to obtain the target node information and / or node dynamic information of the other server nodes.

[0070] Step S308, returning the target node information to any server node.

[0071] Optionally, the management module returns the target node information to any server node that initiates the information acquisition request, so that node information interaction between server nodes can be achieved.

[0072] In the above multi-node server information management method, in this method, the management module receives the node static information and node dynamic information sent by each server node, adds the node static information and node dynamic information of each server node to a preset node information management table, and centrally manages the information of each server node; the management module also responds to an information acquisition request sent by any server node for other server nodes, searches the node information management table, obtains the target node information of other server nodes, where the target node information includes node static information and / or node dynamic information, and further returns the target node information to any server node. The management module ensures content synchronization and accuracy in information management for the entire multi-node server through centralized storage and information provision. In addition, there is no need to set up an additional interaction path between server nodes, and information interaction between server nodes is only achieved through the management module, reducing the design complexity of the multi-node server and also alleviating the burden on server nodes, thereby reducing the cost of information management.

[0073] In an exemplary embodiment, step S304 adding the node static information and node dynamic information of each server node to a preset node information management table includes:

[0074] Converting the node static information and node dynamic information of each server node into a preset information format to obtain the converted static information and the converted dynamic information; adding the converted static information and the converted dynamic information to a preset node information management table.

[0075] Among them, the preset information format can be a data structure and specification preset by technicians, including data fields, coding methods, etc.

[0076] Optionally, the management module converts the node static information and node dynamic information of each server node into a preset information format to obtain the converted static information and the converted dynamic information, that is, manages the node static information and node dynamic information in a unified information format. It can be understood that, not limited to node static information and node dynamic information, other data managed by the management module can also be managed in a preset information format. Further, the management module adds the converted static information and the converted dynamic information to a preset node information management table.

[0077] In this embodiment, information is managed in a unified preset information format. Whether the server node BMC writes information to the management module CMU or reads information from the management module CMU, the definition of its information format remains consistent according to the preset information format. The unified information format standard helps to improve the stability and efficiency of information interaction, reduce parsing errors and data conversion costs caused by format differences, thereby further reducing the cost of information management.

[0078] In an exemplary embodiment, the multi-node server information management method described in the above embodiment further includes:

[0079] In response to an information acquisition request for the multi-node server sent by any server node, search the node information management table to obtain the target overall machine information of the multi-node server; return the target overall machine information to any server node.

[0080] Among them, the target overall machine information includes at least one of the total number of all server nodes, the node numbers of each server node, and the overall machine dynamic information. Among them, the overall machine dynamic information is the dynamic information of the chassis, which may include real-time readings such as the rotation speed / power consumption of the chassis fan FAN (fan), and the voltage / current / power consumption of the power supply unit PSU (Power Supply Unit).

[0081] It can be understood that the preset node information management table managed by the management module has been pre-written by technicians with the total number of server nodes and the node numbers of each server node. During the operation of the multi-node server, the management module will collect the overall machine dynamic information in real time and write it into or update the node information management table. Optionally, in response to an information acquisition request for the multi-node server sent by any server node, the management module searches the node information management table and returns the target overall machine information to any server node. The information acquisition request includes a request for obtaining at least one of the total number of server nodes, the node numbers of each server node, and the overall machine dynamic information.

[0082] In this embodiment, in the node information management table managed by the management module, there are not only the node static information and node dynamic information of each server node, but also the overall machine information. Whether it is dynamic data such as fan rotation speed and power output voltage and current, or static parameters such as component models and specifications, they are all recorded in detail, forming a comprehensive server node resource and status information library, thereby improving the comprehensiveness of the information management of the multi-node server.

[0083] In an exemplary embodiment, step S306, in response to an information acquisition request for other server nodes sent by any server node, searches the node information management table to obtain the target node information of other server nodes, including:

[0084] In response to an information acquisition request for other server nodes sent by any server node, determine the offset corresponding to the other server node according to the node number of the other server node; search the node information management table according to the offset corresponding to the other server node to obtain the target node information of the other server node.

[0085] The preset node information management table corresponds to each server node one by one, that is, each server node corresponds to a node information management table.

[0086] Among them, the offset is an address index or position offset value used to quickly locate the target server node information, usually an integer, which represents the displacement of the storage location of the target node information in the node information management table relative to the table start address (such as byte offset or record sequence number). The offset is uniquely determined by the node number of the server node (such as physical slot number, logical ID) and is generated through predefined rules (such as hashing, array indexing), similar to the "base address + offset" mode in memory addressing. The management module directly accesses the target data through the base address (table start address) and offset.

[0087] Optionally, the management module responds to the information acquisition request sent by any server node for other server nodes, calculates its offset according to the node number of other server nodes and predefined mapping rules, thereby determining the offset corresponding to other server nodes, and the management module searches for the corresponding entry in the node information management table according to the offset corresponding to other server nodes, reads the target node information of other server nodes, and returns the target node information to any server node. It should be noted that any server node that initiates the information acquisition request for other server nodes can obtain the node information of other server nodes one by one, or select at least one server node among other server nodes to obtain the node information, and after the management module returns the target node information, any server node uniformly parses the target node information. The BMC of each server node can obtain the information of other server nodes from the management module CMU, and use the same set of parsing logic to process and store relevant information, which means that in a multi-node server system, the information processing process is simplified and unified, and the efficiency of data processing is improved.

[0088] In addition, in one embodiment, if a multi-node server has a fault, it is necessary to locate the fault for the multi-node server. After the management module and the BMC of each server node are connected and communicate normally, the node information management table of the management module stores information of all server nodes, including whole machine static information, whole machine dynamic information, node static information and node dynamic information, etc. Therefore, when troubleshooting, the technician can access the management module CMU through any server node BMC, or directly access the management module CMU, read the failed server node from the node number of each server node, or read the abnormal common parts of the whole machine from the whole machine dynamic information and the node dynamic information, or the abnormal module in the abnormal server node, thereby helping the technician to locate and attribute the fault, facilitate timely maintenance of the multi-node server, and improve the stability of the multi-node server.

[0089] In this embodiment, the interaction process between the management module CMU and the BMCs of each server node in the traditional multi-node server is optimized. The complex cross-communication method between the BMCs of each server node, the management module CMU, and between each server node and the BMCs of each server node is simplified into a pure interaction solution between the BMCs of the server nodes and the management module CMU. On the one hand, the probability of communication conflicts can be reduced. On the other hand, since the intermediate transfer links are reduced, the data transfer between the BMC and the CMU is more direct, so the communication efficiency can be improved and the design cost can be saved.

[0090] In an exemplary embodiment, step S308 adds the node static information and node dynamic information of each server node to a preset node information management table, including:

[0091] After each power-on of the multi-node server, the node static information of each server node is added to a preset node information management table; according to a preset period, the node dynamic information is added to the preset node information management table.

[0092] Among them, the preset period can be set according to the actual information acquisition requirements.

[0093] Optionally, after each power-on of the multi-node server, the management module adds the node static information of each server node to a preset node information management table, and according to a preset period, adds the node dynamic information of each server node to the preset node information management table. It can be understood that it can also be that the BMCs of each server node periodically send their respective node dynamic information to the management module according to a preset period, and the management module stores it in the node information management table after receiving it.

[0094] In this embodiment, after each power-on of the multi-node server, the static information is automatically written into the management table to ensure the latest and accurate information, which is beneficial to subsequent management and maintenance. By periodically collecting the node dynamic information of each server node, the server status can be continuously tracked, enhancing the real-time monitoring ability of the system. In addition, the continuous collection of dynamic information helps to detect potential faults or anomalies in advance, improving the overall reliability and stability of the system.

[0095] In an exemplary embodiment, as Figure 4 shown, a flowchart of another information management method for a multi-node server is provided. This method is applied to a multi-node server system as Figure 5 shown, including:

[0096] In this embodiment, a CMU logic unit concept as a multi-node server integrated management module is provided. In terms of actual implementation, it can either be the hardware subsystem composed of MCUs that undertakes the key role of the "management center", or the CPLD can provide read and write interfaces to the node BMCs and act as the "information center" for the integrated management information interaction. In the following description, the second CPLD solution will be used as the core of the CMU, and its own hardware resources will be used to provide read and write support for the BMCs and a detailed introduction will be carried out.

[0097] Step 1: The BMC of Node 1 (Server Node 1) obtains the node number (Node ID) of this node and the total number of nodes in the whole machine from the CMU.

[0098] Step 2: The BMC of Node 1 writes the node static information, such as BMC version, BIOS version, firmware release date, system model, CPU Model name, memory capacity, motherboard SN / PN, Raid card manufacturer model, GPU card model, Riser card SN / PN, BMC IP address, etc. into the integrated management module (management module) CMU, and the CMU records the node static information in "Table 1" in real time.

[0099] Step 3: The BMC of Node 1 periodically writes the node dynamic information, such as: node system health status, node BMC running status, read values of node key temperature / voltage / power sensors, etc. into the integrated management module CMU, and the CMU records the node dynamic information in "Table 1" (node information management table) in real time.

[0100] Among them, as shown in Table 1, the specific content of the node information management table is provided.

[0101] Table 1

[0102]

[0103] Step 4: The BMC of Node 1 periodically reads the dynamic information of the whole machine from the integrated management module CMU, such as: real-time read values of chassis fan speed / power consumption, power module voltage / current / power consumption, etc., to expand its own monitoring scope and capabilities.

[0104] Step 5: The BMC of Node 1 periodically reads the dynamic information of other nodes from the integrated management module CMU, such as: health status, BMC running status, and read values of key temperature / voltage / power sensors of Node 2 / 3 / 4, etc., to enhance the perception ability of adjacent nodes.

[0105] Step 6: Repeat the work of Step 3 to Step 5 at a certain period in a loop to complete a complete round of interaction between Node 1 and the CMU.

[0106] Step 7 to Step 12: Repeat the process of Step 1 to Step 6 to complete the information exchange between the BMC and CMU of Node 2;

[0107] Step 13 to Step 18: Repeat the process of Step 1 to Step 6 to complete the information exchange between BMC and CMU of Node 3;

[0108] Step 19 to Step 20: Repeat the process of Step 1 to Step 6 to complete the information exchange between the BMC and CMU of node 4.

[0109] Among them, there is no time coupling or logic dependency in the interaction between the BMC and CMU of each node, so their respective steps can be synchronized and parallelized.

[0110] When CPLD is used as the CMU core, dedicated read / write registers can be used to implement the storage and reading and writing of the contents of tables #1 to #4.

[0111] In this embodiment, the information management method of the multi-node server achieves comprehensive information coverage, and the table content fully includes all static and dynamic information of the common components of the whole machine (such as fans, power supplies) and the key components of each node. Whether it is dynamic data such as fan speed, power supply output voltage and current, or static parameters such as component models and specifications, detailed records are recorded to form a comprehensive server node resource and status information library. Unified information format, whether BMC writes information to CMU or reads information from CMU, the definition of its information format remains consistent (as shown in the red box). This unified format standard helps to improve the stability and efficiency of information interaction and reduce parsing errors and data conversion costs caused by format differences. Consistent parsing logic, BMC can obtain information from other nodes from CMU, and use the same set of parsing logic to process and store relevant information. This means that in a multi-node server system, the information processing process has been simplified and unified, and the efficiency of data processing has been improved. Clear definition of CMU responsibilities, CMU is mainly responsible for storing all node information, and is also responsible for providing real-time information such as fan readings and power consumption of common components. Through centralized storage and information provision, CMU ensures the synchronization and accuracy of information management in the entire server system, reducing the complexity of CMU design while also alleviating the burden on BMC.

[0112] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0113] Based on the same inventive concept, an embodiment of the present application further provides a multi-node server information management device for implementing the multi-node server information management method described above. The solution provided by this device to solve the problem is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the multi-node server information management device provided below can refer to the limitations on the multi-node server information management method in the above text, and will not be repeated here.

[0114] In an exemplary embodiment, as Figure 6 shown, a multi-node server information management device 600 is provided, including: an information receiving module 601, an information writing module 602, an information positioning module 603, and an information sending module 604, where:

[0115] The information receiving module 601 is configured to receive node static information and node dynamic information sent by each server node;

[0116] The information writing module 602 is configured to add the node static information and node dynamic information of each server node to a preset node information management table;

[0117] The information positioning module 603 is configured to, in response to an information acquisition request sent by any server node for other server nodes, search the node information management table to obtain the target node information of other server nodes; the target node information includes node static information and / or node dynamic information;

[0118] The information sending module 604 is configured to return the target node information to any server node.

[0119] Further, in one embodiment, the information writing module 602 is further configured to convert the static information and the node dynamic information of each server node into a preset information format to obtain the converted static information and the converted dynamic information; and add the converted static information and the converted dynamic information to a preset node information management table.

[0120] Further, in one embodiment, the information locating module 603 is further configured to, in response to an information acquisition request for a multi-node server sent by any server node, search the node information management table to obtain the target whole-machine information of the multi-node server; the target whole-machine information includes at least one of the total number of all server nodes, the node numbers of each server node, and the whole-machine dynamic information; and return the target whole-machine information to any server node.

[0121] Further, in one embodiment, the information locating module 603 is further configured to, in response to an information acquisition request for other server nodes sent by any server node, determine the offset corresponding to the other server nodes according to the node numbers of the other server nodes; and search the node information management table according to the offset corresponding to the other server nodes to obtain the target node information of the other server nodes.

[0122] Further, in one embodiment, the information writing module 602 is further configured to, after each power-on of the multi-node server, add the node static information of each server node to a preset node information management table; and add the node dynamic information to the preset node information management table according to a preset period.

[0123] Each module in the above multi-node server information management device 600 can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in the processor in the computer device in the form of hardware or be independent of it, or can be stored in the memory in the computer device in the form of software, so as to facilitate the processor to call and execute the operations corresponding to the above respective modules.

[0124] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as Figure 7As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data such as node static information, node dynamic information, and whole machine information. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals through a network connection. When the computer program is executed by the processor, it implements a multi-node server information management method.

[0125] Those skilled in the art can understand that Figure 7 the structure shown in is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0126] In one embodiment, a computer device is further provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in the above method embodiments are implemented.

[0127] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by the processor, the steps in the above method embodiments are implemented.

[0128] In one embodiment, a computer program product is provided, including a computer program. When the computer program is executed by the processor, the steps in the above method embodiments are implemented.

[0129] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in this application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in this application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logic devices, data processing logics based on quantum computing, artificial intelligence (AI) processors, etc., without limitation.

[0130] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered to be within the scope recorded in this application.

[0131] The above-described embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all fall within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. A multi-node server information management method, characterized in that, A management module applied to a multi-node server, where the multi-node server is integrated by multiple server nodes, and the method includes: Receiving node static information and node dynamic information sent by each server node; Adding the node static information and the node dynamic information of each server node to a preset node information management table; In response to an information acquisition request sent by any one server node for other server nodes, searching the node information management table to obtain target node information of the other server nodes; the target node information includes node static information and / or node dynamic information; Returning the target node information to the any one server node.

2. The method according to claim 1, characterized in that, The adding the node static information and the node dynamic information of each server node to a preset node information management table includes: Converting the node static information and the node dynamic information of each server node into a preset information format to obtain converted static information and converted dynamic information; Adding the converted static information and the converted dynamic information to a preset node information management table.

3. The method according to claim 1, characterized in that, The method further includes: In response to an information acquisition request sent by any one server node for the multi-node server, searching the node information management table to obtain target whole-machine information of the multi-node server; the target whole-machine information includes at least one of the total number of all the server nodes, the node numbers of each server node, and the whole-machine dynamic information; Returning the target whole-machine information to the any one server node.

4. The method according to claim 3, wherein The searching the node information management table to obtain the target node information of the other server nodes in response to an information acquisition request sent by any one server node for other server nodes includes: In response to an information acquisition request sent by any one server node for other server nodes, determining an offset corresponding to the other server nodes according to the node numbers of the other server nodes; Searching the node information management table according to the offset corresponding to the other server nodes to obtain the target node information of the other server nodes.

5. The method according to claim 1, wherein The adding the node static information and the node dynamic information of each server node to a preset node information management table includes: After each power-on of the multi-node server, adding the node static information of each server node to a preset node information management table; Adding the node dynamic information to a preset node information management table according to a preset period.

6. The method according to any one of claims 1-5, characterized in that, The preset node information management table corresponds to each of the server nodes one by one.

7. A multi-node server information management device, characterized in that, The device includes: An information receiving module, configured to receive node static information and node dynamic information sent by each server node; An information writing module, configured to add the node static information and the node dynamic information of each server node to a preset node information management table; An information location module, configured to respond to an information acquisition request sent by any server node for other server nodes, search the node information management table, and obtain the target node information of the other server nodes; the target node information includes node static information and / or node dynamic information; An information sending module, configured to return the target node information to the any server node.

8. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images