Server configuration system and method

Abstract

The invention discloses a server configuration system and method, and relates to the technical field of server configuration. The first end of the first server node is connected with the substrate management controller; wherein under the condition that the server configuration mode of the server configuration system is a single-path server mode, the second end of the first server node is suspended; and under the condition that the server configuration mode of the server configuration system is a two-way server mode, the server configuration system further comprises a second server node, and the input end of the second server node is connected with the output end of the first server node. According to the invention, the use scene of server configuration is expanded.

Description

Technical Field

[0001] This application relates to the field of server configuration technology, and in particular to a server configuration system and method. Background Technology

[0002] As servers, such as CPUs (Central Processing Units), become increasingly prevalent in various usage scenarios, users are placing higher demands on server configuration methods.

[0003] Traditional server configuration methods use a single BMC (Baseboard Management Controller) to manage a single server node. This means that the server can only be configured as a single-processor server. This method has a significant drawback: because the server can only be configured as a single-processor server, it cannot be dynamically adjusted. In other words, this method limits the application scenarios of the server configuration.

[0004] The above content is only used to help understand the technical solution of this application and does not represent an admission that the above content is prior art. Summary of the Invention

[0005] The main purpose of this application is to provide a server configuration system and method, which aims to solve the technical problem of limited use cases for server configuration.

[0006] To achieve the above objectives, this application provides a server configuration system, the server configuration system comprising:

[0007] Baseboard management controller;

[0008] A first server node, wherein a first end of the first server node is connected to the baseboard management controller;

[0009] In the case where the server configuration mode of the server configuration system is a single-path server mode, the second end of the first server node is left unattended.

[0010] When the server configuration mode of the server configuration system is a dual-path server mode, the server configuration system further includes a second server node, and the second end of the second server node is connected to the second end of the first server node.

[0011] In one embodiment, the first server node includes:

[0012] A first programmable logic device, wherein a first terminal of the first programmable logic device is connected to the baseboard management controller;

[0013] A first central processing unit, wherein a first end of the first central processing unit is connected to a second end of the first programmable logic unit;

[0014] A first input connection unit, wherein a first end of the first input connection unit is connected to a third end of the first programmable logic device, and the first end of the first input connection unit is connected to the output connection unit of other server nodes to configure a dual-path server mode;

[0015] A first output connection unit, wherein a first end of the first output connection unit is connected to a fourth end of the first programmable logic device, and the first end of the first output connection unit is connected to an input connection unit of the second server node to configure a dual-path server mode.

[0016] In one embodiment, the first central processing unit includes:

[0017] The first switching transistor has its gate connected to the second terminal of the first programmable logic device, and its source is grounded.

[0018] The first resistor has its first end connected to the system power supply and its second end connected to the drain of the first switching transistor.

[0019] A first central processing unit is connected to the second end of the first resistor.

[0020] In one embodiment, the first input connection unit includes:

[0021] A first input connector, wherein a first end of the first input connector is connected to a third end of the first programmable logic device, and a second end of the first input connector is grounded;

[0022] The second resistor has its first end connected to the system power supply and its second end connected to the first end of the first input connector.

[0023] In one embodiment, the first output connection unit includes:

[0024] A first output connector, wherein a first end of the first output connector is connected to a fourth end of the first programmable logic device, and a second end of the first output connector is connected to a fourth end of the first programmable logic device;

[0025] The third resistor has its first end connected to the system power supply and its second end connected to the fourth end of the first programmable logic device.

[0026] In one embodiment, the server configuration system further includes:

[0027] The motherboard connector is used to connect the baseboard management controller to the first server node.

[0028] Furthermore, to achieve the above objectives, this application also provides a server configuration method, which is applied to the aforementioned server configuration system. The server configuration method includes:

[0029] Obtain the signal level information of the first programmable logic device in the first server node, and determine the server configuration mode based on the signal level information;

[0030] When the server is configured in dual-path server mode, the first server node and the second server node are configured according to the preset master-slave control rules.

[0031] In one embodiment, the step of determining the server configuration mode based on the signal level information includes:

[0032] Determine the first input level and the second input level in the signal level information;

[0033] When the values ​​of the first input level and the second input level are opposite, the server configuration mode is determined to be a dual-path server mode;

[0034] If the values ​​of the first input level and the second input level are the same and both are the first preset values, the server configuration mode is determined to be a single-channel server mode.

[0035] In one embodiment, after the step of determining that the server configuration mode is a dual-socket server mode, the following steps are included:

[0036] When the first input level is a first preset value and the second input level is a second preset value, the first server node is determined to be the master server node, wherein the first preset value and the second preset value are 0 and 1, respectively;

[0037] When the first input level is a second preset value and the second input level is a first preset value, the first server node is determined to be a slave server node.

[0038] In one embodiment, the step of configuring the first server node and the second server node according to preset master-slave control rules includes:

[0039] Determine the master server control level and slave server control level in the preset master-slave control rules;

[0040] The first server node is configured to perform master server settings based on the master server control level.

[0041] Based on the control level of the slave server, the second server node is configured as a slave server.

[0042] This application proposes a server configuration system, including a baseboard management controller; a first server node, the first end of which is connected to the baseboard management controller; wherein, when the server configuration mode of the server configuration system is a single-path server mode, the second end of the first server node is left unconnected; when the server configuration mode of the server configuration system is a dual-path server mode, the server configuration system further includes a second server node, the input end of which is connected to the output end of the first server node. This server configuration system, through its design, allows for dynamic adjustment of server configuration. In single-processor server mode, the second end of the first server node is left unconnected. In dual-processor server mode, a second server node is included, with its input connected to the output of the first server node. This avoids the problem in existing technologies where server configuration is limited to single-processor mode, preventing dynamic adjustment. This system achieves dual-processor server mode by connecting the first server node to a second server node, and single-processor server mode by leaving the second end of the first server node unconnected. This dynamic adjustment of server configuration between single-processor and dual-processor modes expands the application scenarios of server configuration. Attached Figure Description

[0043] Figure 1 A schematic diagram of a module of the server configuration system for this application;

[0044] Figure 2 A schematic diagram of the framework connection of the server configuration system of the first embodiment of this application;

[0045] Figure 3 A schematic diagram of the framework connection of the server configuration system of the second embodiment of this application;

[0046] Figure 4 A schematic diagram of the framework connection of the server configuration system of the third embodiment of this application;

[0047] Figure 5 A circuit connection diagram of the first embodiment of the server configuration system of this application;

[0048] Figure 6A circuit connection diagram of the second embodiment of the server configuration system of this application;

[0049] Figure 7 A circuit connection diagram of the third embodiment of the server configuration system of this application;

[0050] Figure 8 This is a flowchart illustrating the server configuration method for this application.

[0051] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings.

[0052] Explanation of icon numbers:

[0053] 100, Baseboard Management Controller; 10, First Server Node; 20, Second Server Node; 110, Management Motherboard; 120, First Motherboard; 130, First Motherboard Connector; 11, First Programmable Logic Controller; 12, First Central Processing Unit; 13, First Input Connection Unit; 14, First Output Connection Unit; 101, First Baseboard Management Controller; 111, First Management Motherboard; 112, Second Management Motherboard; 102, Second Baseboard Management Controller; 21, Second Programmable Logic Controller; 22, Second Central Processing Unit; 23, Second Input... Connection unit; 24, second output connection unit; 160, cascade cable; 140, second motherboard; 150, second motherboard connector; VCC, system power supply; 131, first input connector; 121, first central processing unit; 141, first output connector; Q1, first switching transistor; R1, first resistor; R2, second resistor; R3, third resistor; 231, second input connector; 221, second central processing unit; 241, second output connector; Q2, second switching transistor; R4, fourth resistor; R5, fifth resistor; R6, sixth resistor. Detailed Implementation

[0054] It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application.

[0055] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0056] With the continuous increase in CPU core count and performance improvements, single-socket servers (meaning the device occupies only one expansion slot on the motherboard) can now cover most application scenarios (such as cloud computing and regular data center workloads) in terms of computing power, bandwidth (BW), and capacity. Industry demands (such as cost optimization and simplified design) are driving the gradual popularization of single-socket server architectures, naturally shifting the market towards single-socket servers and gradually reducing reliance on multi-socket servers. Currently, traditional dual-socket servers still dominate the market. Dual-socket servers typically have two CPUs on the motherboard, requiring one CPU to be designated as the master and the other as the slave. While a single-socket server can also be configured, the entire server is pre-designed and fixed, making dynamic configuration as two single-socket servers or one dual-socket server impossible, thus failing to meet users' flexible configuration requirements (significantly limiting usage scenarios).

[0057] Therefore, based on the shortcomings of the above server configuration schemes, the server configuration system of this application is proposed. The main solution of the embodiments of this application is: through the design of the server configuration system, when the server configuration mode of the server configuration system is a single-path server mode, the second end of the first server node is left unattended. When the server configuration mode of the server configuration system is a dual-path server mode, the server configuration system also includes a second server node. The input end of the second server node is connected to the output end of the first server node, which realizes the dynamic adjustment of the server configuration. This avoids the problem in the prior art that the server configuration can only be configured as a single-path server, which prevents the dynamic adjustment of the server configuration. This server configuration system can realize the dual-path server mode by connecting the first server node to a second server node, and the single-path server mode by leaving the second end of the first server node unattended. This realizes the dynamic adjustment of the server configuration between the single-path server mode and the dual-path server mode, thereby expanding the application scenarios of the server configuration.

[0058] Based on this, embodiments of this application provide a server configuration system, referring to... Figure 1 , Figure 1 A schematic diagram of a module of the server configuration system for this application.

[0059] Reference Figure 1 This application provides a server configuration system, which includes:

[0060] Baseboard management controller 100;

[0061] First server node 10, the first end of the first server node 10 is connected to the baseboard management controller 100;

[0062] In the case where the server configuration mode of the server configuration system is single-path server mode, the second end of the first server node 10 is left unattended.

[0063] When the server configuration mode of the server configuration system is a dual-socket server mode, the server configuration system also includes a second server node 20, and the second end of the second server node 20 is connected to the second end of the first server node 10.

[0064] In this embodiment, the motherboard in dual-socket server mode includes two CPUs (i.e., one CPU in each of the first server node 10 and the second server node 20, forming a dual-socket server mode when the first server node 10 and the second server node 20 are connected). One CPU needs to be set as the master CPU and the other as the slave CPU. In this case, the input terminal of the second server node 20 can be connected to the output terminal of the first server node 10 to form the dual-socket server mode. When a single-socket server mode is needed, the second terminal of the first server node 10 can be left unconnected; that is, the first terminal of the first server node 10 is only connected to the baseboard management controller 100 to form a single-socket server. It is worth noting that a server node refers to a module composed of server-related devices, not a single point. The first end of the first server node 10 refers to the end connected to the baseboard management controller 100, and the second end of the first server node 10 refers to the port connected to other server nodes. It can include at least the input end and the output end of the first server node 10. The input end of one server node can be connected to the output end of another server node, and the output end of one server node can be connected to the input end of another server node, forming a dual-server mode. The connection state of the second end of the first server node 10 can be directly changed to dynamically switch between single-server and dual-server modes, thereby expanding the application scenarios of the server configuration.

[0065] In this embodiment, a server configuration system is provided, including a baseboard management controller 100; a first server node 10, the first end of which is connected to the baseboard management controller 100; wherein, when the server configuration mode of the server configuration system is a single-path server mode, the second end of the first server node 10 is left unconnected; when the server configuration mode of the server configuration system is a dual-path server mode, the server configuration system further includes a second server node 20, the input end of which is connected to the output end of the first server node 10. This server configuration system, through its design, allows for dynamic adjustment of the server configuration. In a single-processor server mode, the second end of the first server node 10 is left unconnected. In a dual-processor server mode, the system includes a second server node 20, whose input is connected to the output of the first server node 10. This avoids the problem in existing technologies where server configuration is limited to single-processor mode, preventing dynamic adjustment. This system achieves dual-processor mode by connecting the first server node 10 to a second server node 20, while leaving the second end of the first server node 10 unconnected enables single-processor mode. This dynamic adjustment between single-processor and dual-processor server modes expands the application scenarios of the server configuration.

[0066] Furthermore, based on the first embodiment of this application described above, a second embodiment of the server configuration system of this application is proposed. In this embodiment, reference is made to... Figure 2 , Figure 2 This is a schematic diagram of the framework connection of the first embodiment of the server configuration system of this application. The first server node 10 includes:

[0067] The first programmable logic device 11, the first terminal of the first programmable logic device 11 is connected to the baseboard management controller 100;

[0068] The first central processing unit 12, the first end of the first central processing unit 12 is connected to the second end of the first programmable logic device 11;

[0069] The first input connection unit 13 has a first end connected to the third end of the first programmable logic device 11. The first end of the first input connection unit 13 is connected to the output connection unit of other server nodes to configure a dual-path server mode.

[0070] The first output connection unit 14 has its first end connected to the fourth end of the first programmable logic device 11. The first end of the first output connection unit 14 is connected to the input connection unit of the second server node 20 to configure a dual-path server mode.

[0071] In one embodiment, the server configuration system further includes:

[0072] The motherboard connector and the baseboard management controller 100 are connected to the first server node 10 via the motherboard connector.

[0073] In this embodiment, taking the first server node 10 (the second server node 20 has the same composition as the first server node 10, and will not be repeated here) as an example, the first server node 10 has a first programmable logic device 11, such as a CPLD (Complex Programmable Logic Device), a first central processing unit 12, such as a CPU, a first input connection unit 13, and a first output connection unit 14. When the first server node 10 is designed to support a single-path working mode, forming a single-path server mode, the CPU is automatically set to the main CPU mode, and the first input connection unit 13 and the first output connection unit 14 are not connected to the input connection units and output connection units of other server nodes. It is worth noting that the composition of other server nodes is the same as that of the first server node 10. Therefore, the input connection units of other server nodes can be connected to the first output connection unit 14 of the first server node 10 to form a dual-processor server. Alternatively, the output connection units of other server nodes can be connected to the first input connection unit 13 of the first server node 10 to form a dual-processor server. In the dual-processor server mode, the CPU on the first server node 10 can be automatically set as the master CPU and the CPU on the second server node 20 can be set as the slave CPU. Of course, adaptive settings can also be made according to the actual situation, which are not limited here.

[0074] In one embodiment, the entire server configuration system can be configured based on the following server modes, which can be referred to... Figure 2 The entire server configuration system is configured as a single-processor server. The first end of the first server node 10 is connected to the baseboard management controller 100, and the CPU in the first server node 10 operates in main CPU mode. Further details can be found in [reference needed]. Figure 3 , Figure 3This is a schematic diagram of the framework connection of the second embodiment of the server configuration system of this application. The entire server configuration system is configured with two single-processor servers. The first end of the first server node 10 is connected to the first baseboard management controller 101, and the first end of the second server node 20 is connected to the second baseboard management controller 102. At this time, the CPU in the first server node 10 operates in the main CPU mode, and the CPU in the second server node 20 operates in the main CPU mode. Further, refer to... Figure 4 , Figure 4 This is a schematic diagram of the framework connection of the server configuration system according to the third embodiment of this application. The entire server configuration system is configured as a dual-processor server. The first end of the first server node 10 is connected to the first baseboard management controller 101, and the second end of the second server node 20 is connected to the second end of the first server node 10. The CPU in the first server node 10 can be configured to operate in master CPU mode, and the CPU in the second server node 20 can operate in slave CPU mode, or vice versa. It is worth noting that the baseboard management controller 100 can be located on the management motherboard 110, the first server node 10 can be located on the first motherboard 120, and the second server node 20 can be located on the second motherboard 150. The baseboard management controller 100 is connected to the first server node 10 via a motherboard connector, which can be a DC-SCM connector, and the management motherboard 110 can be a DC-SCM motherboard.

[0075] Furthermore, based on the first and / or second embodiments of this application described above, a third embodiment of the server configuration system of this application is proposed. In this embodiment, reference can be made to... Figure 5 , Figure 5 This is a circuit connection diagram of the first embodiment of the server configuration system of this application. The first central processing unit 12 includes:

[0076] The first switch Q1 has its gate connected to the second terminal of the first programmable logic device 11, and its source is grounded.

[0077] The first resistor R1 has its first end connected to the system power supply VCC, and its second end connected to the drain of the first switching transistor Q1.

[0078] The first central processing unit 121 is connected to the second end of the first resistor R1.

[0079] In one embodiment, the first input connection unit 13 includes:

[0080] The first input connector 131 has its first end connected to the third end of the first programmable logic device 11, and its second end grounded.

[0081] The second resistor R2 has its first end connected to the system power supply VCC and its second end connected to the first end of the first input connector 131.

[0082] In one embodiment, the first output connection unit 14 includes:

[0083] The first output connector 141 has a first end connected to the fourth end of the first programmable logic device 11, and a second end connected to the fourth end of the first programmable logic device 11.

[0084] The third resistor R3 has its first end connected to the system power supply VCC and its second end connected to the fourth end of the first programmable logic device 11.

[0085] In this embodiment, the first central processing unit 12 consists of a first switching transistor Q1, a first resistor R1, and a first central processing unit 121. The entire logic for setting up the master-slave CPU can be defined in advance, such as by controlling the second terminal of the first programmable logic device 11 (defined as the switching transistor control terminal) to achieve the master-slave CPU configuration. The configuration principle is shown in the table below:

[0086] Switch control terminal CPU working mode 1 Main CPU mode 0 From CPU mode

[0087] Table 1

[0088] Of course, it can also be set according to the actual situation. For example, when the control terminal of the switching transistor is at a low level, it is in main CPU mode.

[0089] In one embodiment, the first input connection unit 13 includes a first input connector 131 and a second resistor R2. Based on the connection relationship of the first input connection unit 13, it can be determined that when the first input connector 131 is connected to the output connector of other server nodes, a connection is established between the first end of the first input connector 131 and the second end of the first input connector 131. At this time, the third end of the first programmable logic device 11 connected to the first end of the first input connector 131 will be directly grounded, thus exhibiting a low level. It can be determined that the first input connector 131 is connected to the output connector of other server nodes based on the low level of the third end of the first programmable logic device 11. Conversely, when the third end of the first programmable logic device 11 is high, the first input connector 131 is not connected to the output connector of other server nodes. In one embodiment, the first output connection unit 14 includes a first output connector 141 and a third resistor R3. Based on the connection relationship of the first output connection unit 14, it can be determined that when the first output connector 141 is connected to the input connector of another server node, a connection is established between the first end and the second end of the first output connector 141. At this time, the fourth end of the first programmable logic device 11 connected to the first end of the first output connector 141 will be connected to the system power supply VCC, thus exhibiting a high level. It can be determined that the first output connector 141 is not connected to the input connector of another server node based on the high level of the fourth end of the first programmable logic device 11. Conversely, when the fourth end of the first programmable logic device 11 is low, the first output connector 141 is connected to the input connector of another server node. Simultaneously, the master-slave CPU configuration of the server nodes in the entire server configuration system is performed in conjunction with the configuration principles in Table 1 above. Assuming that the fourth end of the first programmable logic device 11 is the second input level end and the third end of the first programmable logic device 11 is the first input level end, the following control exists:

[0090]

[0091]

[0092] Table 2

[0093] like Figure 4As shown, if both the first and second input level signals are high, the CPLD can determine that neither the motherboard before or after the CPLD (i.e., the first input connector 131 and the first output connector 141) has a cascaded motherboard (i.e., a server node). The system should operate in single-path mode, and the CPU should operate in main CPU mode. Therefore, based on Table 1, the CPLD control switch terminal is set to high. After inversion by the first switch Q1, the CPU input is low, and the CPU is set to main CPU mode. If the first input level signal is high and the second input level signal is low, the CPLD determines that there is no cascaded motherboard before the CPLD's motherboard, but there is a cascaded motherboard after the CPLD's motherboard. The system should operate in dual-path mode, and the motherboard where the CPLD is located is the first motherboard. The CPU should operate in main CPU mode (i.e., directly outputting a high level based on the control switch terminal in Table 1). If the first input signal is low and the second input signal is high, the CPLD determines that the motherboard before the CPLD has a cascaded motherboard, but the motherboard after it does not. The system should operate in dual-processor mode, and the motherboard where the CPLD is located should be the second motherboard. The CPU should operate in slave CPU mode. If both the first and second input signals are low, the system does not support this operating mode. (Based on Table 2 above...) Figure 5 As can be seen from the records, the circuits of the first output connection unit 14 and the first input connection unit 13 can be directly designed to achieve level output under different connection states, thereby determining whether the first output connection unit 14 and the first input connection unit 13 are connected to other server nodes, so as to configure the server nodes. This can expand the server's usage scenarios and accurately configure the server to ensure the accuracy of the server's operation.

[0094] In one embodiment, reference is made to Figure 6 , Figure 6 The diagram below shows the circuit connection of the server configuration system according to a second embodiment of this application. Two server nodes can be directly connected via a cascade cable 160, thereby fulfilling the configuration requirements of the server nodes. Further details can be found in the following... Figure 7 , Figure 7 This is a circuit connection diagram of the third embodiment of the server configuration system of this application. In this case, it shows the connection between the baseboard management controller 100 and two server nodes, and the entire server configuration system is operating in dual-server mode. For example, in... Figure 5Because there is no cascaded second motherboard, the second input level signal is pulled up to VCC by the third resistor R3, so the CPLD detects a high level signal at the second input level. Conversely, when the second input level signal is pulled up to VCC by the third resistor R3, it is also connected to ground via the cascade cable 160 to the second input connector 231, so the CPLD detects a low level signal at the second input level. The same principle applies to the second input level, so it will not be repeated here. Then, the CPLDs in the first and second motherboards respectively set the CPU operating modes of the first and second motherboards to master and slave CPU modes, respectively. This achieves cascading of the two motherboards and automatic CPU configuration, enabling the system to operate in dual-processor mode, thus expanding the application scenarios of the server configuration system.

[0095] In one embodiment, the CPLD on the first motherboard is simultaneously connected to and communicates with the BMC via I2C, SPI, or other buses. The CPLD reports the system topology, i.e., the current cascading status (single-socket or dual-socket mode), to the BMC through this bus to ensure the accuracy of subsequent management of the two server nodes. The entire server configuration system automatically detects the system topology and automatically sets the CPU operating mode by detecting signals on the input and output connectors through the CPLD. This automates the configuration of single-socket and dual-socket servers, breaking through the limitations of traditional server architectures and enabling adaptive single / dual-socket architectures. It provides a cost-effective and scalable hardware connectivity solution for data centers, edge computing, and other scenarios, demonstrating significant technological innovation and commercial value.

[0096] Based on the above-described embodiments of the server configuration system of this application, a first embodiment of the server configuration method of this application is proposed. In this embodiment, the server configuration method is applied to the above-described server configuration system, referring to... Figure 8 , Figure 8 This is a flowchart illustrating the server configuration method of this application. The server configuration method includes:

[0097] Step S10: Obtain the signal level information of the first programmable logic device 11 in the first server node 10, and determine the server configuration mode based on the signal level information;

[0098] Step S20: When the server configuration mode is dual-path server mode, configure the first server node 10 and the second server node 20 according to the preset master-slave control rules.

[0099] In this embodiment, based on the above server configuration system, after obtaining the signal level information of the first programmable logic device 11 in the first server node 10, the server configuration mode is determined based on the signal level information. The signal level information refers to the level received by each port of the first programmable logic device 11 in the server configuration system, generally the level of the input / output connection unit. The server configuration mode refers to the mode of the server node, including at least a dual-processor server mode and a single-processor server mode. When the server configuration mode is determined to be a dual-processor server mode, the first server node 10 and the second server node 20 are configured according to preset master-slave control rules. Specifically, the preset master-slave control rules specify which server node's CPU is configured as the master CPU and which server node's CPU is configured as the slave CPU. This expands the application scenarios of the server configuration while simultaneously configuring the master and slave CPUs, facilitating accurate management of the configured master and slave CPUs in the future.

[0100] It is worth noting that when the server is configured as a single-processor server, the CPU in that server node can be directly configured as the primary CPU without any further control.

[0101] Based on the first embodiment of the server configuration method, a second embodiment of the server configuration method of this application is proposed. In one embodiment, the step of determining the server configuration mode based on signal level information includes:

[0102] Step S11: Determine the first input level and the second input level in the signal level information;

[0103] Step S12: If the values ​​of the first input level and the second input level are opposite, determine that the server configuration mode is a dual-path server mode.

[0104] Step S13: If the values ​​of the first input level and the second input level are the same and both are the first preset values, determine that the server configuration mode is a single-channel server mode.

[0105] In this embodiment, the server configuration mode is determined primarily based on the first and second input levels in the signal level information. Furthermore, based on the design of the input / output connection unit, the server configuration mode is determined to be a dual-path server mode when the values ​​of the first and second input levels are opposite. Conversely, when the values ​​of the first and second input levels are the same and both are the first preset value, the server configuration mode is determined to be a single-path server mode. In this case, the first and second input levels are 0 and 1 respectively, with the first input level being the level at the first input level terminal and the second input level being the level at the second input level terminal. It is worth noting that due to the design of the input / output connection unit, as shown in Table 2, there will not be a situation where both the first and second input levels are 0. If both the first and second input levels are 0, it would indicate a situation where three server nodes are connected in series. This situation is not considered in this application. In this case, the server mode can be determined based on the first and second input levels to configure different server modes specifically, ensuring the accuracy of the server configuration. Simultaneously, a server configuration system can be used to achieve dynamic configuration of the server mode, expanding the application scenarios of server configuration.

[0106] Further steps after determining the server configuration mode to be a dual-socket server mode include:

[0107] Step S121: When the first input level is a first preset value and the second input level is a second preset value, the first server node 10 is determined to be the master server node, wherein the first preset value and the second preset value are 0 and 1 respectively;

[0108] Step S122: When the first input level is the second preset value and the second input level is the first preset value, determine that the first server node 10 is the slave server node.

[0109] In this embodiment, determining the server configuration mode as a dual-path server mode also allows for the determination of master and slave server nodes. This is achieved by determining the first input level and the second input level. When the first input level is a first preset value and the second input level is a second preset value, the first server node 10 is determined to be the master server node, where the first and second preset values ​​are 0 and 1, respectively. Conversely, when the first input level is the second preset value and the second input level is the first preset value, the first server node 10 is determined to be the slave server node. The master and slave server nodes can be varied according to the design of the input / output connection unit, as shown in Table 2. For example, the design of the input / output connection unit is as follows... Figure 5When the first input level and the second input level are 10, the first server node 10 is the master server node; conversely, when the first input level and the second input level are 01, the first server node 10 is the slave server node. By determining the master and slave server nodes, it is known which programmable logic device in the server node is used to implement the detection. Based on the connection of the baseboard management controller 100, it is determined which server node the baseboard management controller 100 is directly connected to (the baseboard management controller 100 generally prioritizes directly controlling the programmable logic device in the connected server node to implement the detection). At the same time, the master and slave server nodes can be used to synchronize and determine the master and slave CPUs to ensure the consistency of subsequent server node management.

[0110] Based on the first and / or second embodiments of the server configuration method, a third embodiment of the server configuration method of this application is proposed. In one embodiment, the step of configuring the first server node 10 and the second server node 20 according to preset master-slave control rules includes:

[0111] Step S21: Determine the master server control level and slave server control level in the preset master-slave control rules;

[0112] Step S22: Configure the master server by controlling the first server node 10 based on the master server control level.

[0113] Step S23: Configure the second server node 20 as a slave server based on the slave server control level.

[0114] In this embodiment, when configuring two server nodes, the master server control level and slave server control level in the preset master-slave control rules can be directly used. The first server node 10 can be configured as a master server based on the master server control level, and the second server node 20 can be configured as a slave server based on the slave server control level. Here, the master server control level refers to the level at which the CPU in the server node is configured as the master CPU, and master server configuration means configuring the CPU in that server as the master CPU. The slave server control level refers to the level at which the CPU in the server node is configured as the slave CPU, and slave server configuration means configuring the CPU in that server as the slave CPU. It is worth noting that, in this case, adaptively selecting which server node's CPU to configure as the master CPU simply requires the server node to output the master server control level. Alternatively, the master server node's CPU can be synchronously configured as the master CPU in combination with the above method of determining master and slave server nodes to ensure the synchronization of subsequent server management.

[0115] Furthermore, based on the above embodiments, this application also provides a server, which includes the server configuration system described above, and a server configurator in the server configuration system (which can be directly controlled by the baseboard management controller) for the server configuration method described above.

[0116] The server configuration system within the server is designed to allow for dynamic adjustment of the server configuration. In a single-processor server configuration mode, the second end of the first server node 10 is left floating. In a dual-processor server configuration mode, the system includes a second server node 20, whose input is connected to the output of the first server node 10. This avoids the limitation in existing technologies where server configuration is limited to single-processor mode, preventing dynamic adjustments. This system achieves dual-processor mode by connecting the first server node 10 to the second server node 20, while leaving the second end of the first server node 10 floating represents single-processor mode. This dynamic adjustment between single-processor and dual-processor server modes expands the application scenarios of the server configuration. Of course, the server can also include other components, which will not be detailed here.

[0117] The above are merely preferred embodiments of this application and do not limit the scope of the patent application. Any equivalent structural transformations made based on the inventive concept of this application and the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included within the scope of patent protection of this application.

Claims

1. A server configuration system, characterized in that, The server configuration system includes: Baseboard management controller; A first server node, wherein a first end of the first server node is connected to the baseboard management controller; In the case where the server configuration mode of the server configuration system is a single-path server mode, the second end of the first server node is left unattended. When the server configuration mode of the server configuration system is a dual-path server mode, the server configuration system further includes a second server node, and the second end of the second server node is connected to the second end of the first server node.

2. The server configuration system as described in claim 1, characterized in that, The first server node includes: A first programmable logic device, wherein a first terminal of the first programmable logic device is connected to the baseboard management controller; A first central processing unit, wherein a first end of the first central processing unit is connected to a second end of the first programmable logic unit; A first input connection unit, wherein a first end of the first input connection unit is connected to a third end of the first programmable logic device, and the first end of the first input connection unit is connected to the output connection unit of other server nodes to configure a dual-path server mode; A first output connection unit, wherein a first end of the first output connection unit is connected to a fourth end of the first programmable logic device, and the first end of the first output connection unit is connected to an input connection unit of the second server node to configure a dual-path server mode.

3. The server configuration system as described in claim 2, characterized in that, The first central processing unit includes: The first switching transistor has its gate connected to the second terminal of the first programmable logic device, and its source is grounded. The first resistor has its first end connected to the system power supply and its second end connected to the drain of the first switching transistor. A first central processing unit is connected to the second end of the first resistor.

4. The server configuration system as described in claim 2, characterized in that, The first input connection unit includes: A first input connector, wherein a first end of the first input connector is connected to a third end of the first programmable logic device, and a second end of the first input connector is grounded; The second resistor has its first end connected to the system power supply and its second end connected to the first end of the first input connector.

5. The server configuration system as described in claim 2, characterized in that, The first output connection unit includes: A first output connector, wherein a first end of the first output connector is connected to a fourth end of the first programmable logic device, and a second end of the first output connector is connected to a fourth end of the first programmable logic device; The third resistor has its first end connected to the system power supply and its second end connected to the fourth end of the first programmable logic device.

6. The server configuration system as described in any one of claims 1 to 5, characterized in that, The server configuration system also includes: The motherboard connector is used to connect the baseboard management controller to the first server node.

7. A server configuration method, characterized in that, The server configuration method is applied to the server configuration system as described in any one of claims 1 to 6, and the server configuration method includes: Obtain the signal level information of the first programmable logic device in the first server node, and determine the server configuration mode based on the signal level information; When the server is configured in dual-path server mode, the first server node and the second server node are configured according to the preset master-slave control rules.

8. The server configuration method as described in claim 7, characterized in that, The step of determining the server configuration mode based on the signal level information includes: Determine the first input level and the second input level in the signal level information; When the values ​​of the first input level and the second input level are opposite, the server configuration mode is determined to be a dual-path server mode; If the values ​​of the first input level and the second input level are the same and both are the first preset values, the server configuration mode is determined to be a single-channel server mode.

9. The server configuration method as described in claim 8, characterized in that, After determining that the server configuration mode is a dual-socket server mode, the following steps are included: When the first input level is a first preset value and the second input level is a second preset value, the first server node is determined to be the master server node, wherein the first preset value and the second preset value are 0 and 1, respectively; When the first input level is a second preset value and the second input level is a first preset value, the first server node is determined to be a slave server node.

10. The server configuration method as described in claim 7, characterized in that, The step of configuring the first server node and the second server node according to the preset master-slave control rules includes: Determine the master server control level and slave server control level in the preset master-slave control rules; The first server node is configured to perform master server settings based on the master server control level. Based on the control level of the slave server, the second server node is configured as a slave server.

Images