Management system of multi-node server and multi-node server

Abstract

The application discloses a kind of management system and multi-node server of multi-node server, it is related to server technical field, including multiple server nodes, heat dissipation module, power module, operation panel and control module, multiple server nodes are connected with same control module;Through operation panel and control module, the management of multiple server nodes can be realized, user can obtain a platform for managing multiple server nodes, without setting independent management module to multiple server nodes, it is beneficial to simplify management maintenance process, improve management maintenance efficiency;Meanwhile, through control module, heat dissipation module and power module are managed, compared with arbitration management circuit designed for heat dissipation system and power system in the related art, the power module and heat dissipation module are managed by control module, and it is also beneficial to reduce R&D cost.The application can at least solve the problems that the management of server node is complicated, the efficiency is low, and the cost of management system is high in the related art.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of servers, and particularly relates to a management system of a multi-node server and the multi-node server. BACKGROUND

[0002] With the increasing computing demand of users on computers, multi-node servers emerge as the times require. The multi-node server includes multiple server nodes. In the related art, the management, heat dissipation, power supply and the like of the server nodes are complicatedly designed. Each server node is an independent system, and the management, heat dissipation, power supply and the like of the corresponding server node need to be considered in each system. This way is also relatively complex for users to operate, and the management efficiency is low. Meanwhile, the management of the heat dissipation system and the power supply system needs to be arbitrated among the multiple nodes, and multiple arbitration management circuits need to be designed, so the research and development cost and the product cost are high.

[0003] Therefore, how to improve the above problems has become one of the technical problems to be solved at present. SUMMARY

[0004] The present application provides a management system of a multi-node server and the multi-node server to at least solve the problems of complicated management, low efficiency and high cost of the management system of the server nodes in the related art.

[0005] The present application provides a management system of a multi-node server, including: multiple server nodes, a heat dissipation module, a power supply module, an operation panel and a control module.

[0006] The multiple server nodes, the heat dissipation module, the power supply module and the operation panel are connected with the same control module.

[0007] The operation panel is at least configured to receive a user operation and generate a control instruction in response to the user operation.

[0008] The control module is at least configured to adjust the running state of the server nodes according to the control instruction, and adjust the running of the power supply module and the heat dissipation module according to the running state of the server nodes.

[0009] The present application also provides a multi-node server including the above management system of the multi-node server.

[0010] The application provides a multi-node server management system and a multi-node server. The multi-node server management system is characterized in that a control module is arranged, and the control module is connected with a plurality of server nodes, a heat dissipation module, a power module and an operation panel. The control module is configured to adjust the running state of the server nodes according to a control instruction generated by the operation panel, and adjust the running of the power module and the heat dissipation module according to the running state of the server nodes. The application can realize the management of the plurality of server nodes by using one operation panel and one control module. A user can obtain a platform for managing the plurality of server nodes, and does not need to arrange independent management modules for the plurality of server nodes. The application is beneficial to simplifying the management and maintenance process and improving the management and maintenance efficiency. Meanwhile, the control module is used to manage the heat dissipation module and the power module. Compared with the arbitration management circuit designed for the heat dissipation system and the power system in the related art, the application is beneficial to reducing the research and development cost and the equipment cost. The application can at least solve the problems of complicated management, low efficiency and high cost of the management system of the server nodes in the related art. BRIEF DESCRIPTION OF DRAWINGS

[0011] In order to more clearly illustrate the embodiments of the application, the drawings needed in the embodiments will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the application, and other drawings can be obtained by those skilled in the art without creative labor.

[0012] Figure 1 Fig. 1 shows a schematic diagram of a multi-node server management system in the related art;

[0013] Figure 2 Fig. 2 shows a schematic diagram of a multi-node server management system provided by the embodiments of the application;

[0014] Figure 3 Fig. 3 shows a schematic diagram of power supply control of a power module provided by the embodiments of the application. DETAILED DESCRIPTION

[0015] The technical solutions in the embodiments of the application will be clearly and completely described in combination with the drawings in the embodiments of the application. Obviously, the described embodiments are only some of the embodiments of the application, but not all the embodiments of the application. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor are within the protection scope of the application.

[0016] It should be noted that in the description of the present application, the terms "comprising", "containing" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or equipment including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such a process, method, article or equipment. The terms "first", "second" and the like in the present application are used to distinguish similar objects, not to describe a specific order or sequence.

[0017] In order to enable those skilled in the art to better understand the present application, the present application will be further described in detail below in combination with the drawings and specific embodiments.

[0018] Figure 1 Fig. 1 shows a schematic diagram of a management system of a multi-node server in the related art, please refer to Figure 1 The inventor found in the research that in the related art, each server node 10' in the management system of the multi-node server is provided with a separate management module 50' for managing the server node 10', and when a user manages multiple server nodes 10', repeated operations are required to achieve the daily management of the multiple server nodes 10', which is relatively complicated and inefficient. At the same time, the multiple server nodes 10' share the same case, and the server nodes 10' have a shared cooling system 20' and a power supply system 30', so the cooling system 20' and the power supply system 30' need to be designed with a separate arbitration management circuit 60', which increases the research and development cost of the arbitration management circuit 60' and also increases the equipment cost.

[0019] Therefore, the present application provides a management system of a multi-node server and a multi-node server to at least solve the problems of complicated and inefficient management of server nodes and high cost of the management system in the related art.

[0020] Figure 2 Fig. 1 shows a schematic diagram of a management system of a multi-node server provided by an embodiment of the present application, please refer to Figure 2 The present application provides a management system 100 of a multi-node server, comprising: multiple server nodes 10, a cooling module 20, a power supply module 30, an operation panel 40 and a control module 50; the multiple server nodes 10, the cooling module 20, the power supply module 30 and the operation panel 40 are connected with the same control module 50; the operation panel 40 is at least configured to receive user operation and generate control instructions in response to the user operation; the control module 50 is at least configured to adjust the running state of the server nodes 10 according to the control instructions, and adjust the running of the power supply module 30 and the cooling module 20 according to the running state of the server nodes 10.

[0021] It should be noted that the accompanying drawings of the present application only show the connection relationship between the main components in the management system 100 of the multi-node server, and do not represent the actual structure of the management system 100 of the multi-node server. For example, the accompanying drawings of the present application only take two server nodes 10 in the management system 100 as an example for illustration, and are not limited thereto. In fact, more server nodes 10 can be included. The embodiments of the present application aim to illustrate that the same control module 50 can manage multiple server nodes 10, as well as the heat dissipation module 20 and the power module 30.

[0022] Specifically, the present application provides a management system 100 of a multi-node server, wherein the plurality of server nodes 10, the heat dissipation module 20, the power module 30 and the operation panel 40 are connected with the same control module 50. The heat dissipation module 20, the power module 30, the operation panel 40 and the control module 50 are modules shared between the plurality of server nodes 10.

[0023] The operation panel 40 is used to receive user operations and generate corresponding control instructions according to the user's operations on the operation panel 40, and then is used to adjust the running state of the server nodes 10. The control module 50 receives the control instructions transmitted by the operation panel 40 and adjusts the running of the server nodes 10 according to the control instructions. For example, the user issues an instruction to turn off one of the server nodes 10 through the operation panel 40. The operation panel 40 generates a corresponding control instruction and transmits the control instruction to the control module 50. The control module 50 receives the control instruction and controls the corresponding server node 10 to be turned off according to the control instruction. For another example, the user can issue an instruction to turn on all server nodes 10 through the operation panel 40. The operation panel 40 generates a corresponding control instruction and transmits the control instruction to the control module 50. The control module 50 receives the control instruction and controls the corresponding server node 10 to be turned on according to the control instruction. The present application can realize the management of multiple server nodes 10 through the operation panel 40 and the control module 50. The user can obtain a platform for managing multiple server nodes 10, without the need to manage multiple server nodes 10 respectively, which is conducive to simplifying the management and maintenance process and improving the management and maintenance efficiency.

[0024] The control module 50 is also connected with the power module 30, and can realize the management of the running of the power module 30. The control module 50 in the present application is connected with multiple server nodes 10. The control module 50 can monitor the running state of each server node 10 in real time, and can control the power module 30 to be powered on or powered off according to the running state of the server nodes 10, so as to control the server nodes 10 to be turned on and turned off, thereby realizing the management of the power module 30.

[0025] The control module 50 is also connected with the heat dissipation module 20, and the operation of the heat dissipation module 20 can be managed. The control module 50 in the application is connected with multiple server nodes 10, and the control module 50 can monitor the actual operation state of each server node 10 in real time, such as the power-on / off state, power consumption, temperature and the like, so as to facilitate dynamic adjustment of the operation of the heat dissipation module 20 according to the actual operation state, and thus it is more conducive to server heat dissipation, providing a suitable working temperature for the server, and further improving the performance of the server.

[0026] In addition, compared with the arbitration management circuit designed for the heat dissipation system and the power supply system in the related art, the power supply module 30 and the heat dissipation module 20 are managed by the control module 50, avoiding the setting of a complex arbitration management circuit, and also facilitating the reduction of research and development costs and equipment costs.

[0027] It should be noted that the control module 50 is arranged to cooperatively manage the multiple server nodes 10 and the heat dissipation module 20 and the power supply module 30, and the originally isolated multiple subsystems are integrated, which on the one hand is conducive to user management of the multiple server nodes 10, simplifies the cumbersome management process and improves the management and maintenance efficiency, and on the other hand is conducive to simplifying the management of the power supply module 30 and the heat dissipation module 20, reducing research and development costs and equipment costs, and further improving the practicality and reliability of the multi-node server.

[0028] Please continue to refer to Figure 2 In an optional embodiment of the application, the control module 50 includes a switch 51, a processor state register 52 and a node state register 53; the switch 51 is used to switch the corresponding server node 10, the processor state register 52 is used to record the first state information of the server node 10, and the node state register 53 is used to record the second state information of the server node 10, the first state information at least including the power supply state of the server node 10, and the second state information at least including the physical environment data of the server node 10.

[0029] Specifically, the control module 50 is arranged to manage and maintain the multiple server nodes 10, wherein the switch 51 is used to select the server node 10 to be controlled, so that the control module 50 can interact with and control each server node 10 one by one and independently, rather than generally and globally, thus facilitating the implementation of differentiated management strategies for different server nodes 10.

[0030] The server node 10 comprises a processor 11 and a baseboard management controller 12, both of which are connected with a control module 50, the control module 50 can acquire relevant information of the processor 11 and the baseboard management controller 12 in the server node 10, the relevant information comprises first state information and second state information, the first state information comprises but is not limited to the power state of the server node 10, and the second state information comprises but is not limited to the physical environment data of the server node 10, wherein the power state comprises, for example, power switch, running or hibernation and the like, and the physical environment data comprises, for example, temperature, voltage, health state and the like. The control module 50 comprises a processor state register 52 and a node state register 53, and the processor state register 52 and the node state register 53 record the acquired first state information and second state information respectively. The processor state register 52 and the node state register 53 are hardware components, and the data stability thereof is much higher than that of a software variable stored in a memory. Recording the relevant information of the server node 10 in a dedicated register can effectively prevent the loss of state information caused by the software system crash or restart of the control module 50, and therefore, the embodiment is also beneficial to enhancing the robustness and reliability of the management system.

[0031] For the specific connection mode of the server node 10 and the control module 50, the application provides an optional embodiment that the ESPI bus (Enhanced Serial Peripheral Interface) of the processor 11 of the server node 10 and the I2C bus (Inter-Integrated Circuit) of the baseboard management controller 12 are respectively connected to the control module 50, for transmitting the first state information and the second state information. The application is only described by taking the above embodiment as an example, and is not limited thereto.

[0032] The embodiment realizes switching of different server nodes 10 to be controlled through the switch 51, so that the control module 50 can control different server nodes 10, and the processor state register 52 and the node state register 53 are used to record the relevant information of the server node 10, so as to know the state of different server nodes 10, which is beneficial to the management and maintenance of multiple server nodes 10 by the same control module 50, and further beneficial to improving the management efficiency and maintenance efficiency of the multi-node server.

[0033] Please continue to refer to Figure 2In an optional embodiment of the present application, the operation panel 40 comprises a switch button 41, a unit identification button 42, a fault indicator 43, a display screen 44, and a universal asynchronous receiver-transmitter 45, the switch button 41, the unit identification button 42, the fault indicator 43, and the display screen 44 are connected with the control module 50. The display screen 44 cooperates with the switch button 41, the unit identification button 42, and the fault indicator 43 to control the working state of the corresponding server node 10 and display the relevant working information of the server node 10. The universal asynchronous receiver-transmitter 45 is connected with the switcher 51 and is used to switch the corresponding server node 10. The operation panel 40 is at least configured to generate a power-on / off control instruction according to the state of the switch button 41, generate a node switching control instruction according to the state of the unit identification button 42 and the universal asynchronous receiver-transmitter 45, obtain the fault state information of the server node 10 according to the state of the fault indicator 43, and transmit the power-on / off control instruction, the node switching control instruction, and the fault state information to the control module 50.

[0034] Specifically, the embodiment provides an operation panel 40, which comprises a switch button 41 and a unit identification button 42. The switch button 41 is used to respond to the power-on or power-off operation of a user, so that the operation panel 40 sends a power-on or power-off instruction to a corresponding server node 10. The unit identification button 42 is used to respond to the operation of selecting a server node 10 by a user. The unit identification button 42 comprises a button and an indicator lamp. When the user presses the unit identification button 42, the corresponding server node 10 is selected, and at the same time, the indicator lamp of the corresponding server node 10 is turned on. The operation panel 40 further comprises a fault indicator lamp 43, which is used to prompt that the corresponding server node 10 is in a fault state. The operation panel 40 further comprises a display screen 44, which can display multiple pages and multiple lines of information to display multiple kinds of related information of the server node 10. Exemplarily, the information displayed by the display screen 44 comprises but is not limited to the number, the power state, the selected state, the fault state, the IP address (Internet Protocol Address) of the baseboard management controller 12 and other node state information of any server node 10. An optional embodiment provided by the application is that the display screen 44 and the switch button 41 are combined to control the server node 10. For example, the display screen 44 displays the number of the server node 10, and the user specifies any server node 10 or multiple server nodes 10 to be powered on or powered off by pressing the corresponding switch button 41 of the server node 10. For another example, the combination of the fault indicator lamp 43 and the display screen 44 displays the number of the specific server node 10 in the fault state. The embodiment is intended to illustrate that the display screen 44 can cooperate with the switch button 41, the unit identification button 42 and the fault indicator lamp 43 to control the working state of the corresponding server node 10, and to display the related working information of the server node 10, and is not limited to the above-mentioned embodiments. Exemplarily, the specific operation process comprises: using the unit identification button 42 to switch to the target server node 10 in combination with the universal asynchronous receiver-transmitter 45; confirming the information and state of the server node 10 through the display screen 44; judging the health condition according to the fault indicator lamp 43; and performing the operation by using the switch button 41. In this way, the structured interaction mode is beneficial to reducing the operation complexity of management and maintenance.

[0035] It should be noted that the display screen 44 can intuitively display the relevant information of the server node 10, and the switch key 41 and the unit identification key 42 provide clear and specific physical touch keys, so that the visual degree of management and control is improved, and the operation complexity of management and maintenance is reduced. The user issues relevant instructions through the operation panel 40, and the operation panel 40 generates switch control instructions, node switching control instructions and fault state information in response to the user operation, which is further beneficial to realize the control of the control module 50 on the server node 10, thereby improving the management efficiency and maintenance efficiency of the server node 10.

[0036] For the connection mode of the operation panel 40, the server node 10 and the control module 50, an optional embodiment provided by the present application is that the signal connection of the switch key 41, the unit identification key 42 and the fault indicator 43 is connected to the GPIO interface (General Purpose Input / Output, general purpose input / output interface) of the control module 50, the display screen 44 is connected to the I2C slave interface of the control module 50 as an I2C master device through the I2C bus, and the GPIO interface and the I2C interface of the control module 50 can access the processor state register 52 and the node state register 53 in the control module 50 to obtain the current power supply state, access address and health state of the server node 10; the UART interface (Universal Asynchronous Receiver / Transmitter, asynchronous serial communication interface) of the processor 11 and the baseboard management controller 12 of different server nodes 10 is connected to different GPIO interfaces of the control module 50 respectively, and the switcher 51 in the control module 50 is connected to the UART interface of the operation panel 40. It should be noted that the above embodiment is only used for illustration, and is not limited thereto.

[0037] Please continue to refer to Figure 2 In an optional embodiment of the present application, the control module 50 receives the switch control instructions, the node switching control instructions and the fault state information, and adjusts the operation of the server node 10 according to the switch control instructions, the node switching control instructions and the fault state information.

[0038] Specifically, the control module 50 controls the server nodes 10 according to the relevant instructions transmitted by the operation panel 40. The control module 50 does not blindly execute the instructions. The control module 50 can determine which server node 10 is the current operation target through the node switching control instruction. When the control module 50 receives the power-on / off control instruction, the control module 50 can make a comprehensive judgment in combination with the fault state information of the server node 10. In this way, it is beneficial to prevent system crashes and hardware damage caused by misoperation or forced operation in a fault state, thereby improving the reliability of the management system 100 and the operation safety of the server nodes 10. The present embodiment provides a way for the control module 50 to adjust the operation of the server nodes 10. The control module 50 adjusts the operation of the server nodes 10 according to the relevant control instructions transmitted by the operation panel 40 in combination with the current state of the server nodes 10 obtained by the control module 50. In this way, dynamic adjustment of the server nodes 10 can be achieved, which is beneficial to improve the reliability of the management system 100 and the operation safety of the server nodes 10.

[0039] Please continue to refer to Figure 2 In an optional embodiment of the present application, the control module 50 further includes a heat dissipation control module 54 and a power supply control module 55. The heat dissipation control module 54 is used to control the heat dissipation module 20, and the power supply control module 55 is used to control the power supply module 30.

[0040] Specifically, the present application sets the heat dissipation control module 54 and the power supply control module 55 in the control module 50 to manage the heat dissipation module 20 and the power supply module 30. The heat dissipation control module 54 and the power supply control module 55 can obtain the relevant information of the server nodes 10 recorded in the processor state register 52 and the node state register 53 in the control module 50, and adjust the working state of the heat dissipation module 20 and the power supply module 30 according to the relevant information. In this way, it is beneficial to achieve precise control and dynamic control of the server nodes 10, so as to keep the server nodes 10 in a healthy working state, thereby improving the performance of the server nodes 10.

[0041] Exemplarily, the power supply control module 55 can acquire the power supply state information of the server node 10, and when it is necessary to adjust the running state of the server node 10, the power supply control module 55 can adjust the power supply module 30 according to the real-time state of the server node 10, which is beneficial to avoid misoperation, for example, when it is necessary to turn off the power supply of a specified server node 10, and it is found that the server node 10 is already in the off state, secondary operation can be avoided. In this way, the reliability and management efficiency of the management system 100 can be improved. For another example, the heat dissipation control module 54 can acquire the temperature information of the server node 10, and can adjust the running power of the heat dissipation module 20 according to the temperature of the server node 10. When the temperature of the server node 10 is low, the running power of the heat dissipation module 20 is reduced, which is beneficial to reduce power consumption; when the temperature of the server node 10 is high, the running power of the heat dissipation module 20 is increased to improve the heat dissipation effect, so that the server node 10 works at an appropriate temperature, and thus the performance of the server node 10 can be improved.

[0042] Please continue to refer to Figure 2 In an optional embodiment of the present application, the power supply module 30 is connected with the power supply control module 55, the plurality of server nodes 10 and the heat dissipation module 20 respectively; the power supply module 30 supplies power to the server nodes 10 and the heat dissipation module 20 under the control of the power supply control module 55.

[0043] Specifically, the power supply module 30 is a shared module of the plurality of server nodes 10 and the heat dissipation module 20, and the power supply module 30 uniformly supplies power to the server nodes 10 and the heat dissipation module 20, and places the server nodes 10 and the heat dissipation module 20 under the centralized management of the power supply control module 55, which is beneficial to the power supply control module 55 to adjust the running strategy according to the overall state and dynamically and cooperatively allocate the power supply of each module. Exemplarily, the power supply control module 55 can adjust the power supply state of the heat dissipation module 20 according to the running state of the plurality of server nodes 10, and when there is a server node 10 that is turned on, the power supply control module 55 controls the power supply module 30 to provide power to the corresponding server node 10, and also controls the power supply module 30 to provide power to the heat dissipation module 20, so that the heat dissipation module 20 plays a heat dissipation function. This embodiment tightly couples the energy supply of the server nodes 10 and the heat dissipation module 20 together by establishing a power supply control center with the power supply control module 55 as the core, which is beneficial to realize energy efficiency collaborative optimization, and compared with the related art in which an arbitration management circuit is arranged for the heat dissipation system and the power supply system, the present application is also beneficial to reduce the hardware complexity and equipment cost.

[0044] Figure 3 Fig. 1 shows a schematic diagram of power supply control of the power supply module provided by the embodiment of the present application, please refer to Figure 2 and Figure 3Optionally, the power module 30 comprises a plurality of first sub-modules 31 and a second sub-module 32, the plurality of first sub-modules 31 supply power to the plurality of server nodes 10 respectively, and the second sub-module 32 is used to supply power to the heat dissipation module 20.

[0045] When any server node 10 is powered on, the enable signal of the corresponding first sub-module 31 of the server node 10 is an effective signal, and the enable signal of the second sub-module 32 is an effective signal; when all server nodes 10 are powered off, the enable signal of the first sub-module 31 is an invalid signal, and the enable signal of the second sub-module 32 is an invalid signal.

[0046] Specifically, the first sub-module 31 and the second sub-module 32 in the power module 30 are respectively used to supply power to the server nodes 10 and the heat dissipation module 20, wherein the first sub-module 31 corresponds to the server nodes 10 one by one. The power control module 55 can obtain the relevant information of the server nodes 10 through the processor state register 52 and the node state register 53, and generate the enable signals of the first sub-module 31 and the second sub-module 32 according to the power-on and power-off control instructions of the operation panel 40. In an optional embodiment of the present application, when at least one server node 10 in the plurality of server nodes 10 is powered on, the enable signal of the corresponding first sub-module 31 of the server node 10 is an effective signal, thereby supplying power to the corresponding server node 10, and as long as there is a server node 10 powered on, the heat dissipation module 20 is needed to dissipate heat for it, therefore, the enable signal of the second sub-module 32 is also an effective signal, thereby supplying power to the heat dissipation module 20, and the heat dissipation module 20 works to dissipate heat for the server nodes 10. In another optional embodiment of the present application, when all server nodes 10 are powered off, at this time, the server nodes 10 and the heat dissipation module 20 are both not needed to work, and the enable signals of the first sub-module 31 and the second sub-module 32 are both invalid signals.

[0047] It should be noted that, by setting independent first sub-modules 31 and second sub-modules 32 to supply power to each server node 10 and heat dissipation module 20, the working states of each server node 10 and heat dissipation module 20 can be accurately controlled, which is conducive to the management of different devices by the control module 50, and is also conducive to the statistics of energy consumption, thereby being conducive to the realization of energy management.

[0048] Please refer to Figure 2 In an optional embodiment of the present application, the heat dissipation module 20 comprises a fan, and the heat dissipation control module 54 adjusts the rotating speed of the fan according to the power-on and power-off states of the server nodes 10 and the working state of the baseboard management controller 12 of the server nodes 10.

[0049] Specifically, the heat dissipation module 20 is connected with the control module 50, the control module 50 can obtain the rotating speed information of the fan in the heat dissipation module 20, and the baseboard management controller 12 of the server node 10 is also connected with the control module 50, so that when the server node 10 is powered on, the baseboard management controller 12 can obtain the rotating speed information of the fan in the heat dissipation module 20, and the baseboard management controller 12 can adjust the rotating speed of the fan in combination with the temperature of the server node 10.

[0050] Please continue to refer to Figure 2 Optionally, when any server node 10 is powered on and the baseboard management controller 12 of the server node 10 is working normally, the corresponding baseboard management controller 12 controls the rotating speed of the corresponding fan;

[0051] When the server node 10 is powered off, or the server node 10 is powered on and the baseboard management controller 12 is abnormal, the control module 50 controls the rotating speed of the corresponding fan.

[0052] Specifically, the application provides an optional embodiment that when at least two server nodes 10 are powered on and the baseboard management controllers 12 of the server nodes 10 are all normal, the baseboard management controller 12 can issue a fan speed control signal in combination with the temperature of the corresponding server node 10 and transmit it to the node state register 53 in the control module 50, and the heat dissipation control module 54 calculates the average value of the fan speed control signals issued by the baseboard management controllers 12 of the various powered-on server nodes 10 after reading the fan speed control signals, and sends it to the corresponding fan, and the corresponding fan adjusts the speed. The application provides another optional embodiment that when only one server node 10 is powered on and its baseboard management controller 12 is normal, the baseboard management controller 12 of the server node 10 controls the speed of the corresponding fan, and the baseboard management controller 12 issues a fan speed control signal in combination with the temperature of the server node 10 and transmits it to the node state register 53 in the control module 50, and the heat dissipation control module 54 reads the fan speed control signal and sends it to the corresponding fan, and the corresponding fan adjusts the speed. The application provides still another optional embodiment that the server nodes 10 are all powered off, or the baseboard management controllers 12 of the server nodes 10 are all abnormal, at this time, there is no baseboard management controller 12 that can adjust the fan speed, and the fan speed is adjusted by the heat dissipation control module 54, at this time, the heat dissipation control module 54 can adjust the fan speed in stages. Illustratively, when the server nodes 10 are all powered off, the heat dissipation control module 54 adjusts the fan speed to 0%; when the number of powered-on server nodes 10 is less than the number of powered-off server nodes 10, the heat dissipation control module 54 adjusts the fan speed to 30%; when the number of powered-on server nodes 10 is equal to the number of powered-off server nodes 10, the heat dissipation control module 54 adjusts the fan speed to 50%; and when the number of powered-on servers is greater than the number of powered-off servers, the heat dissipation control module 54 adjusts the fan speed to 80%; the application is only described by the above examples, and is not limited thereto.

[0053] It should be noted that for the adjustment of the speed of the fan in the heat dissipation module 20, when the baseboard management controllers 12 are normal, the baseboard management controllers 12 adjust the fan speed in combination with the temperature of the server nodes 10, and when the baseboard management controllers 12 are all abnormal, the heat dissipation control module 54 adjusts the fan speed. In this way, the fan speed can be adjusted according to the real-time temperature of the server nodes 10, which is beneficial to improve the accurate control of the fan speed and improve the heat dissipation performance, so that the server nodes 10 work at an appropriate temperature, and thus the performance of the server nodes 10 is improved.

[0054] Please continue to refer to Figure 2In an optional embodiment of the present application, the plurality of server nodes 10 and the control module 50 are arranged on the same mainboard. In another optional embodiment of the present application, the plurality of server nodes 10 and the control module 50 are arranged on a plurality of independent boards. The control module 50 is connected to the plurality of server nodes 10, the operation panel 40, the heat dissipation module 20 and the power module 30 through connectors and cables. The power module 30 can also directly supply power to the control module 50 through the cables. The design of the independent control module 50 and the cable connection is suitable for a plurality of arrangement modes of the plurality of server nodes 10 in the server case, for example, the plurality of server nodes 10 are arranged on the same mainboard, or the plurality of server nodes 10 are arranged on different mainboards, the plurality of mainboards are arranged side by side in the case, the plurality of mainboards are arranged in layers in the server case, etc. Only the structure for fixing the control module 50 and the length of the cable need to be redesigned.

[0055] It should be noted that the above embodiments of the present application only illustrate that the server node 10 and the control module 50 can be arranged on different boards or on the same board. Such arrangement is beneficial to improving the practicability of the management system of the multi-node server. The specific design can be made according to the actual needs, and the present application is not limited in this regard.

[0056] Based on the same inventive concept, the present application also provides a multi-node server, which is described in detail in the following. Figure 2 The multi-node server comprises the management system 100 of the multi-node server, and the management system 100 of the multi-node server is any one of the management systems 100 of the multi-node server provided in the embodiments of the present application.

[0057] It should be noted that the embodiments of the multi-node server can refer to the embodiments of the management system 100 of the multi-node server provided in the present application, and the repeated parts will not be described herein.

[0058] The management system of the multi-node server and the multi-node server provided in the present application are described in detail above. The principles and implementation modes of the present application are described by applying specific examples. The above description of the embodiments is only used to help understand the method of the present application and its core idea. It should be noted that those skilled in the art can make some improvements and modifications to the present application without departing from the principles of the present application. These improvements and modifications also fall within the protection scope of the claims of the present application.

Claims

1. A multi-node server management system, characterized in that: include: Multiple server nodes, cooling modules, power modules, operation panels, and control modules; A plurality of the server nodes, heat dissipation modules, power supply modules and operation panels are all connected to the same control module; The operation panel is at least configured to receive a user operation and generate a control instruction in response to the user operation; The control module is at least configured to adjust the operating state of the server node according to the control instruction, and adjust the operation of the power module and the heat dissipation module according to the operating state of the server node; The server node includes a processor and a baseboard management controller, the control module includes a switch and multiple general input and output interfaces, and the operation panel includes a universal asynchronous receiver and transmitter, a unit identification button, and a display screen; the universal asynchronous receiver and transmitter is connected to the switch, and the unit identification button and the display screen are both connected to the control module; The operation panel is at least configured to generate a node switching control instruction according to the unit identification button and the state of the universal asynchronous receiver and transmitter, and transmit the node switching control information to the control module, and the switch and the universal asynchronous receiver and transmitter are used to switch the corresponding server node; The processors and baseboard management controllers of different server nodes are respectively connected to different general input and output interfaces of the control module.

2. The multi-node server management system according to claim 1, characterized in that: The control module also includes a processor status register and a node status register; The processor status register is used to record the first status information of the server node, and the node status register is used to record the second status information of the server node. The first status information includes at least the power status of the server node, and the second status information includes at least the physical environment data of the server node.

3. The multi-node server management system according to claim 2, characterized in that: The operation panel further includes a switch button and a fault indicator light, and the switch button, the fault indicator light and the display screen are all connected to the control module; The display screen cooperates with the switch button, the unit identification button and the fault indicator light to control the working status of the corresponding server node and display relevant working information of the server node; The operation panel is at least configured to generate a power on / off control instruction according to the state of the switch button, obtain the fault status information of the server node according to the state of the fault indicator light, and transmit the power on / off control instruction and the fault status information to the control module.

4. The multi-node server management system according to claim 3, characterized in that: The control module receives the power on / off control instruction, the node switching control instruction and the fault status information, and adjusts the operation of the server node according to the power on / off control instruction, the node switching control instruction and the fault status information.

5. The multi-node server management system according to claim 2, characterized in that: The control module further includes a heat dissipation control module and a power supply control module. The heat dissipation control module is used to control the heat dissipation module, and the power supply control module is used to control the power supply module.

6. The multi-node server management system according to claim 5, characterized in that: The power supply module is respectively connected to the power supply control module, the plurality of server nodes and the heat dissipation module; The power supply module supplies power to the server node and the heat dissipation module under the control of the power supply control module.

7. The multi-node server management system according to claim 6, characterized in that: The power supply module includes a plurality of first submodules and a second submodule, wherein the plurality of first submodules respectively supply power to the plurality of server nodes, and the second submodule is used to supply power to the heat dissipation module; When any of the server nodes is powered on, the enable signal of the first submodule corresponding to the server node is a valid signal, and the enable signal of the second submodule is a valid signal; When all the server nodes are powered off, the enable signal of the first submodule is an invalid signal, and the enable signal of the second submodule is an invalid signal.

8. The multi-node server management system according to claim 5, characterized in that: The heat dissipation module includes a fan, and the heat dissipation control module adjusts the rotation speed of the fan according to the power on / off state of the server node and the working state of the baseboard management controller of the server node.

9. The multi-node server management system according to claim 8, characterized in that: When any of the server nodes is powered on and the baseboard management controller of the server node is working normally, the corresponding baseboard management controller controls the speed of the corresponding fan; When the server node is shut down, or when the server node is turned on and the baseboard management controller works abnormally, the control module controls the rotation speed of the corresponding fan.

10. A multi-node server, characterized in that: A management system comprising a multi-node server according to any one of claims 1 to 9.

Images