Information processing method, baseboard management controller and switch

The network rate information is obtained through the switch's substrate management controller and communicates with the management system, which solves the problem of the port connection information that cannot be viewed due to IB network exceptions, improves the exception handling efficiency, and realizes rapid identification and resolution of abnormal conditions.

CN118972720APending Publication Date: 2024-11-15XFUSION DIGITAL TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410815495.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-06-21
Publication Date
2024-11-15

AI Technical Summary

Technical Problem

IB network connection abnormality causes the switch to be unable to report port exception information, reducing the efficiency of exception handling.

Method used

The substrate management controller (BMC) in the switch obtains network rate information of external nodes from the switch chip, identifies the port connection status, and communicates with the management system through the Gigabit Ethernet port to send port connection information to avoid reliance on the IB network to transmit abnormal information. .

Benefits of technology

Administrators can view and manage abnormal conditions of switches and external nodes through the management system, which improves the efficiency of exception handling and can quickly identify and resolve abnormal problems.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118972720A_ABST
    Figure CN118972720A_ABST
Patent Text Reader

Abstract

The embodiment of the invention provides an information processing method, a baseboard management controller and a switch, and relates to the technical field of switches. The method is applied to a switch, and a BMC of the switch obtains network rate information of an external node accessing the switch from a switch chip, identifies port connection information of the switch according to the network rate information, and sends the port connection information to a management system. Therefore, the switch does not need to be accessed to an IB network, an administrator can check and manage the switch, the external node connected with the switch and the abnormal condition of the port through a nano-management system, abnormal information transmission does not need to be carried out by depending on the IB network, the problem that the connection information of the switch port cannot be checked due to the IB network abnormity is solved, the abnormity processing efficiency is improved, and the user experience is improved. And an administrator can identify and solve abnormal conditions more quickly.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of switches, and in particular to an information processing method, a baseboard management controller and a switch. Background Art

[0002] After an external node (such as an optical module) is connected to an InfiniBand (IB) switch, the IB switch can communicate with the external node. In addition, the IB switch can send the current status of the port connected to the external node and network connection information (such as network transmission rate, etc.) to the management node through the IB network, so that the administrator or management node can understand the operating status and network connection of the IB switch in real time.

[0003] However, this communication mechanism is highly dependent on the stability of the IB network connection between the IB switch and the management node. If the IB network connection itself is abnormal, the IB switch cannot report the abnormal information of the abnormal port to the management node through the IB network, thereby reducing the efficiency of abnormal processing. Summary of the invention

[0004] In order to solve the above problems, the embodiments of the present application provide an information processing method, a baseboard management controller and a switch, which can improve the efficiency of exception processing.

[0005] In the first aspect, the embodiment of the present application discloses an information processing method, which is applied to a switch, wherein the switch includes a baseboard management controller BMC and a switch chip, and the method includes: the BMC obtains the network rate information of the external node connected to the switch from the switch chip; the BMC identifies the port connection information of the switch based on the network rate information of the external node; the BMC sends the port connection information of the switch to the management system. As a result, the switch does not need to be connected to the IB network, and the administrator can view and manage the switch and its connected external nodes, as well as the abnormal conditions of the port through the management system, without relying on the IB network for abnormal information transmission, which solves the problem that the switch port connection information cannot be viewed due to IB network abnormalities, improves the efficiency of abnormal processing, and enables administrators to identify and resolve abnormal conditions more quickly.

[0006] In some specific implementations, the switch further includes an embedded processor, and the BMC obtains network rate information of external nodes accessing the switch from the switch chip, including: the BMC receives the network rate information of the external nodes accessing the switch sent by the embedded processor, and the network rate information is obtained by the embedded processor from the switch chip.

[0007] In some specific implementations, the port at which the external node is connected to the switch includes a first sub-port and a second sub-port, and the BMC identifies the port connection information of the switch based on the network rate information of the external node, including: when the sum of the network rate of the first sub-port and the network rate of the second sub-port is a first value, if the first sub-port is in a connected state and the second sub-port is in an unconnected state or an unidentified state, the BMC determines that the switch is connected to the first sub-port at a first network rate, and the first network rate is less than the first value.

[0008] In some specific implementations, the port at which the external node is connected to the switch includes a first sub-port and a second sub-port, and the BMC identifies the port connection information of the switch based on the network rate information of the external node, including: when the sum of the network rate of the first sub-port and the network rate of the second sub-port is a first value, if the first sub-port and the second sub-port are both in an unconnected state or an unrecognized state, then the BMC determines that the port connection information of the switch is unconnected or unrecognized.

[0009] In some specific implementations, the port connecting the external node to the switch includes a first sub-port and a second sub-port, and the BMC identifies the port connection information of the switch based on the network rate information of the external node, including: when the sum of the network rate of the first sub-port and the network rate of the second sub-port is a first value, if the first sub-port and the second sub-port are both in a connected state, the BMC determines that the switch is connected to the first sub-port and the second sub-port at a first network rate, and the first network rate is less than the first value.

[0010] In some specific implementations, the method further includes: the BMC obtains node presence information and / or node power information of the external node from the switch chip; and the BMC sends the node presence information and / or node power information of the external node to the management system.

[0011] In some specific implementations, the external node includes an optical module, an electrical port module, an optical-to-electrical module, an electrical-to-optical module, or a server.

[0012] In the second aspect, an embodiment of the present application discloses a baseboard management controller, which includes: a memory and a controller; the memory is used to store programs; the controller is used to execute programs to implement the various steps of the information processing method disclosed in the first aspect. As a result, the switch does not need to be connected to the IB network, and the administrator can view and manage the switch and the external nodes connected to it through the management system. In addition, when an abnormality occurs in the port connected to the switch and the external node, the administrator can directly view the abnormal condition of the port through the management system without relying on the IB network for abnormal information transmission, which solves the problem of being unable to view the switch port connection information due to IB network abnormalities, improves the efficiency of exception handling, and enables administrators to identify and resolve abnormal conditions more quickly.

[0013] In the third aspect, an embodiment of the present application discloses a switch, which includes: a baseboard management controller BMC, a switch chip, a first port and a second port, the switch chip is connected between the second port and the BMC, the BMC is connected to the first port, the first port is a Gigabit Ethernet port, the first port is used to communicate with the management system, the second port is used to connect to an external node, and the BMC is used to: obtain the network rate information of the external node from the switch chip, identify the port connection information of the second port according to the network rate information of the external node, and send the port connection information of the switch to the management system. As a result, the switch does not need to be connected to the IB network, and the administrator can view and manage the switch and the external nodes connected to it through the management system. In addition, when an abnormality occurs in the port connected to the switch and the external node, the administrator can directly view the abnormal status of the port through the management system without relying on the IB network to transmit the abnormal information, which solves the problem that the switch port connection information cannot be viewed due to the abnormality of the IB network, improves the efficiency of abnormality handling, and enables the administrator to identify and resolve abnormal conditions more quickly.

[0014] In some specific implementations, the switch further includes an embedded processor, and the embedded processor is connected between the switch chip and the BMC.

[0015] In a fourth aspect, an embodiment of the present application provides a computer program product, which, when executed on a server, enables the server to implement the method of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A schematic diagram of the connection between a switch, an external node and a management system provided in an embodiment of the present application;

[0017] Figure 2 A signaling diagram of an information processing method provided in an embodiment of the present application;

[0018] Figure 3 A schematic diagram of edge detection provided in an embodiment of the present application;

[0019] Figure 4 A schematic diagram of a port of an optical module provided in an embodiment of the present application;

[0020] Figure 5 A schematic diagram of port connection information identification provided in an embodiment of the present application;

[0021] Figure 6 A schematic diagram of a web-side display provided in an embodiment of the present application;

[0022] Figure 7A schematic diagram of the hardware structure of a switch provided in an embodiment of the present application;

[0023] Figure 8 A schematic diagram of a cabinet server provided in an embodiment of the present application. DETAILED DESCRIPTION

[0024] The terms "first" and "second" in the embodiments of the present application are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features.

[0025] First, the technical terms involved in the embodiments of the present application are explained:

[0026] The Baseboard Management Controller (BMC) is a key component in server hardware. It is responsible for monitoring the hardware status of the server, including temperature, voltage, fan speed, etc., and can perform operations such as remote power on, power off, and restart.

[0027] Complex Programmable Logic Device (CPLD) is a programmable logic device that is highly programmable and flexible and is widely used in digital signal processing, communications, computers, control, testing and measurement, etc. The main function of CPLD is to realize digital logic functions. It can change its functions through programming of internal memory and modify the program content at any time to change the circuit function.

[0028] The working principle of the shift register (SR) bus is mainly based on the data storage and shifting mechanism composed of multiple flip-flops. Each flip-flop can store a binary bit. According to the input control signal, the shift register can shift the data to the left or right and provide the shifted data on the output port.

[0029] An embodiment of the present application provides an information processing method, which is applied to a switch. The switch includes a switch chip and a BMC. The BMC of the switch obtains the network rate information of the external node connected to the switch from the switch chip, and then the BMC identifies the port connection information of the switch based on the network rate information, and sends the port connection information to the management system, so that the management system displays the management results including the port connection information to the user. As a result, the switch does not need to be connected to the IB network, and the administrator can view and manage the switch and the external nodes connected to it through the management system. In addition, when an abnormality occurs in the port connected to the switch and the external node, the administrator can directly view the abnormal condition of the port through the management system without relying on the IB network to transmit the abnormal information, which solves the problem that the switch port connection information cannot be viewed due to the abnormality of the IB network, improves the efficiency of exception handling, and enables the administrator to identify and resolve abnormal conditions more quickly.

[0030] In order to make the technical solution of the embodiment of the present application clearer and easier to understand, the architecture of the switch of the embodiment of the present application is first introduced in conjunction with the accompanying drawings.

[0031] See also Figure 1 , this figure is a schematic diagram of the connection between a switch, an external node and a management system provided in an embodiment of the present application.

[0032] The switch 10 includes a plurality of ports, each of which can be connected to one or more network nodes. The switch 10 can provide an exclusive electrical signal path for any two network nodes connected to the switch 10, which means that when two network nodes communicate through the switch, the communication between them will not be interfered by the communication of other network nodes, thereby improving the efficiency and reliability of communication. The network node can be, for example, an external node 20, a management system 30, etc.

[0033] Exemplarily, the switch 10 can provide an electrical signal path for an external node 20 connected to the switch 10 and a management system 30. The external node 20 refers to a hardware device that can be inserted into the switch 10 to increase or expand the function of the switch 10. The external node 20 may include an optical module, an electrical module, an optical-to-electrical module, an electrical-to-optical module, and a server. It is understood that the server includes a processor, a memory, and a storage device. The management system 30 is a centralized management platform for uniformly monitoring and managing the entire cabinet server including the switch 10.

[0034] The switch 10 further includes a switch chip 11, an embedded processor 12 and a BMC 13. The switch chip 11 is connected to the embedded processor 12, and the embedded processor 12 is connected to the BMC 13.

[0035] The switch 10 also includes a plurality of ports. Exemplarily, the switch 10 may include a first port and a second port. The first port is a Gigabit Ethernet (GE) port. The second port is a connector or an Octal Small Form-factor Pluggable (OSFP) port.

[0036] The first port is connected to the BMC 13, and the second port is connected to the switch chip 11. The management system 30 can be connected to the first port to communicate with the BMC 13, so that the network administrator can conveniently remotely monitor and manage the switch 10 through the management system 30. The external node 20 can be connected to the second port to connect to the switch chip 11 and exchange information including network rate information.

[0037] The switch chip 11 is the core processing unit of the switch 10 and is responsible for controlling and managing various functions of the switch 10. For example, when the external node 20 is inserted into the switch 10, the switch chip 11 communicates with the external node 30 through a two-line serial bus (Inter-Integrated Circuit, I2C) to obtain network rate information of the external node 20 connected to the switch 10. The switch chip 11 complies with the IB protocol.

[0038] The embedded processor 12 can be a CPLD or a field programmable gate array (FPGA). The embedded processor 12 can efficiently process and forward various data including network rate information. The embedded processor 12 has components such as a high-speed bus and a cache. These components work together to ensure that various data including network rate information are correctly read, stored and forwarded in a short time. For example, the embedded processor 12 is used to receive the network rate information transmitted by the switch chip 11 through the SR bus, and transmit the network rate information to the BMC 13 through a local bus (such as a local bus bus, etc.) so that the BMC 13 can perform subsequent management operations.

[0039] The local bus is a high-speed data transmission channel with a relatively high transmission rate (eg, 50 MHz), which can ensure that the network rate information transmitted by the embedded processor 12 can reach the BMC 13 in real time and accurately.

[0040] The BMC 13 is a device in the switch 10 that manages the operation status of the switch 10. For example, the BMC 13 is used to obtain network rate information from the switch chip 11 through the embedded processor 12, and obtain port connection information of the switch 10 according to the network rate information. In addition, the BMC 13 is also used to send the port connection information to the management system 30 through the second port for the administrator to view and uniformly monitor and manage.

[0041] Based on the switch 10 provided in the embodiment of the present application, the embodiment of the present application further provides an information processing method. The information processing method in the embodiment of the present application is described in detail below in conjunction with the embodiment.

[0042] See also Figure 2 , which is a flow chart of an information processing method provided by an embodiment of the present application. The method includes:

[0043] S201: The BMC obtains network rate information of an external node accessing a switch.

[0044] The external node may include an optical module, an electrical module, an optical-to-electrical module, an electrical-to-optical module, a server, etc. For ease of understanding, the following description will be made using an external node as a Small Form-factor Pluggable (SFP) optical module as an example.

[0045] Network bandwidth information is an indicator of the data transmission capability of the SFP optical module, which indicates the amount of data transmitted by the SFP optical module per unit time. Network bandwidth information is usually expressed in bits per second (bps), such as Gbps.

[0046] For example, the switch chip can read the register inside the SFP optical module to obtain the network rate information of the SFP optical module. The BMC sends an acquisition instruction to the embedded processor, and the acquisition instruction indicates that the BMC requires to obtain the network rate information. The embedded processor communicates with the switch chip in response to the acquisition instruction, thereby obtaining the network rate information sent by the switch chip.

[0047] To explain this process more specifically, we take the embedded processor as CPLD as an example to explain in detail: the switch chip will continuously send a waveform signal including network rate information to the CPLD. In order to ensure the accuracy of information reception, the CPLD adopts advanced capture edge detection technology. Whenever the CPLD detects the rising edge of the waveform (that is, the moment when the signal changes from low level to high level), the CPLD will immediately start collecting network rate information; and when the waveform has a falling edge (that is, the moment when the signal changes from high level to low level), the CPLD will end the collection of network rate information. It can be seen that the capture edge detection technology can accurately lock the start and end of the network rate information, which helps to reduce the error and loss of network rate information in information transmission, and ensure the integrity and accuracy of the network rate information.

[0048] After the CPLD receives the network rate information, it will first perform necessary sorting and processing on the received network rate information, such as converting the information format to ensure that the BMC can correctly interpret the above network rate information; it will also perform error detection and correction on the network rate information to eliminate any errors that may be introduced during the information transmission process; it will also perform other possible pre-processing steps on the network rate information, such as data compression or encryption. The purpose of these processes is to ensure that the network rate information reported to the BMC is accurate, complete and easy to understand.

[0049] After completing the preprocessing of the network rate information, the CPLD caches the network rate information in a register inside the CPLD, and transmits the network rate information cached in the register to the BMC through a local bus port (such as a local bus, etc.) of the BMC.

[0050] It should be noted that during the transmission of network rate information, due to the difference between the SR bus frequency (usually 5MHz) and the local bus frequency (usually 50MHz), the shift reporting function is ensured to have no buffer overflow problem. This is because the local bus frequency is more than 2.5 times the SR bus frequency, and the high frequency of the local bus provides a larger transmission bandwidth and speed, so that the network rate information can be quickly transmitted in a short time, avoiding congestion or loss of network rate information due to insufficient transmission rate. It should be noted that the above 2.5 times is the target multiple, and the embodiment of the present application does not limit the specific target multiple, and the ratio of the bus frequencies can be adjusted according to specific needs and system configuration to achieve the best data transmission effect.

[0051] See also Figure 3 , which is a schematic diagram of edge detection provided by an embodiment of the present application. Figure 3It can be seen that CPLD can not only collect network rate information by detecting the rising edge of the waveform, but also collect node presence information and node power supply information by detecting the rising edge of the waveform.

[0052] Among them, the node presence information reflects whether the SFP optical module has been correctly installed and connected to the port of the switch. Specifically, some physical sensors, such as photoelectric sensors or contact sensors, are usually set in the port groove of the second port of the switch to detect the physical insertion status of the SFP optical module. When the SFP optical module is inserted into the port slot of the second port of the switch, these photoelectric sensors or contact sensors will send a signal to the switch chip. The switch chip can determine whether the SFP optical module is in place based on the received signal, that is, obtain the node presence information. Subsequently, the CPLD can send the node presence information to the BMC via the local bus.

[0053] The node power information is related to whether the SFP optical module has a stable power supply. Specifically, the switch chip can read the power status register inside the SFP optical module through I2C to obtain the power supply status of the SFP optical module, such as whether it is powered on, whether the power supply voltage is stable, etc. Then, the CPLD can send the node power information to the BMC through the local bus.

[0054] It should be noted that the SR bus between the CPLD and the switch chip is a bus that allows bidirectional transmission of information. Therefore, in addition to the network rate information, node presence information, and node power information sent by the switch chip to the CPLD via the SR bus, the CPLD also sends presence interrupt information, version verification information, etc. to the switch chip. Contrary to the information sent by the switch chip to the CPLD, at the falling edge of each waveform, the CPLD starts sending the above information to the switch chip, and at the rising edge of each waveform, the CPLD stops sending the above information to the switch chip.

[0055] S202: The BMC identifies the port connection information of the switch according to the network rate information of the external node.

[0056] See also Figure 4 , which is a schematic diagram of a port of an optical module provided in an embodiment of the present application. For ease of understanding, the following description will be made using an SFP optical module including an A port (i.e., a first sub-port) and a B port (a second sub-port), and the two sub-ports as an embodiment. It can be understood that the A port and the B port are two different sub-ports on the SFP optical module, and each of them has an independent function. The two sub-ports realize bidirectional transmission of optical signals through optical fiber connection, thereby ensuring the normal operation of the SFP optical module.

[0057] See also Figure 5, which is a schematic diagram of port connection information identification provided by an embodiment of the present application. First, the BMC checks whether the sum of the network rate of port A and the network rate of port B is 400Gbps. If it is detected that the sum of the network rate of port A and the network rate of port B is not 400Gbps, the BMC will continue to wait for the next update of the network rate information and repeat the network rate judgment cycle. This is because the network rate may change with changes in the network load or the configuration of the SFP optical module, so the BMC needs to continuously monitor the network rate information and update its identification results.

[0058] If the sum of the network rates of port A and port B is detected to be 400Gbps, the BMC will further refine the analysis. In the scenario where the SFP optical module includes port A and port B, the 400Gbps network rate of the SFP optical module is usually achieved by combining two 200Gbps ports, so the BMC will check the network rates of port A and port B separately.

[0059] First, the BMC continues to determine whether the network rate of the A port of the SFP optical module is 200Gbps. If the network rate of the A port is 200Gbps, it is determined whether the A port is in a connected state (link). This is usually achieved by detecting the physical connection status or a specific signal status. It should be noted that even if the network rate of the A port is 200Gbps, it is necessary to confirm whether the physical connection status between the SFP optical module and the switch is good. This is because even if the network rate is 200Gbps, the physical connection problem may cause interruption of information transmission, packet loss or increased delay, etc., thereby affecting the stability and reliability of information transmission. Therefore, checking the physical connection status can help prevent potential faults, such as loose fiber connection, small fiber bending radius, dirt or damage to the fiber, etc., thereby improving the stability and reliability of information transmission.

[0060] If port A is in a connected state, it continues to determine whether port B is in a connected state. This is also achieved by detecting the physical connection status or a specific signal status. If port B is also in a connected state, the port connection information obtained by BMC is: the network rate of the switch is 400Gbps, both port A and port B are working normally, and the network rate of each subport is 200Gbps. If port B is not in a connected state, the port connection information obtained by BMC is: the network rate of the switch is 200Gbps, port A is working normally, and the network rate of port A is 200Gbps. This means that although port B is not connected, port A can still work normally and achieve a network rate of 200Gbps.

[0061] If port A is not in a connected state, but the sum of the network rates of port A and port B is still 400Gbps, the BMC will turn to check whether the network rate of port B of the SFP optical module is 200Gbps. If the network rate of port B is 200Gbps, the BMC will continue to determine whether port B is in a connected state. This is also achieved by detecting the physical connection status or specific signal status.

[0062] If the network rate of port B is 200Gbps and port B is in connected state, the port connection information obtained by BMC is: the network rate of the switch is 200Gbps, port B is working normally, and the network rate of port B is 200Gbps. This means that although port A is not connected, port B can still work normally and achieve a network rate of 200Gbps. If both port A and port B are not in connected state, or the network rate of port A and / or port B does not meet expectations (not 200Gbps), the port connection information obtained by BMC is: unconnected state or unrecognized state, indicating that the SFP optical module and / or switch may have a fault or configuration problem, which requires further investigation and repair.

[0063] In summary, the BMC can obtain the following three possible port connection information of the switch: First, when the sum of the network rate of port A and the network rate of port B is a first value, if port A is in a connected state and port B is in an unconnected state or an unrecognized state, it is determined that the switch is connected to port A at the first network rate. Wherein, the first network rate is less than the first value. Exemplarily, the first network rate can be half of the first value, for example, the first network rate is 200Gbps and the first value is 400Gbps. Second, when the sum of the network rate of port A and the network rate of port B is a first value, if port A and port B are not in a connected state, it is determined that the port connection information of the switch is an unconnected state or an unrecognized state. Third, when the sum of the network rate of port A and the network rate of port B is a first value, if port A and port B are both in a connected state, it is determined that the switch is connected to port A and port B at the network rate of the first network rate.

[0064] S203: The BMC sends the port connection information of the switch to the management system, so that the management system displays the management result including the port connection information to the user.

[0065] After the BMC obtains the port connection information of the switch, it can package the port connection information into a format suitable for transmission and send it to the management system through the first port and a specific management protocol.

[0066] In some possible implementations, if the BMC obtains the node presence information and / or node power information of the SFP optical module in step S201, the BMC also sends the node presence information and / or node power information to the management system, so that the management system displays the management results including the node presence information and / or node power information to the user. It should be noted that the above-mentioned node presence information refers to whether the SFP optical module is inserted into the port slot of the second port of the switch, and the port connection information refers to which sub-port of the SFP optical module and at what network rate information the SFP optical module and the switch use to transmit information. Therefore, even if the node presence information indicates that port A has been inserted into the port slot of the second port of the switch, it is possible that information cannot be transmitted to the switch through port A due to reasons such as loose optical fiber connection.

[0067] After receiving the switch port connection information, the SFP optical module node position information, and the node power information, the management system will further integrate and analyze it, and provide a web interface to display the switch port connection information, the SFP optical module node position information, and the node power information to the administrator. This information is displayed in a graphical or tabular form, allowing the administrator to quickly understand the network connection and hardware status of the switch, cabinet server, or data center. Figure 6 , which is a schematic diagram of a web-side display provided by an embodiment of the present application. When the administrator views the web interface, he can clearly see the detailed status of each port of the switch. Among them, Figure 6 The module presence information in the module may also be referred to as node presence information, and the module power supply information may also be referred to as node power supply information.

[0068] For example, the web terminal will display module presence information including whether the SFP optical module is in place, and the module presence information can clearly indicate which SFP optical modules have been correctly installed in the port slots of the second port, and which port slots are free. Thus, the administrator can quickly find out whether there is an abnormal situation such as the SFP optical module is missing or improperly installed, and take corresponding measures accordingly.

[0069] For another example, the web terminal will also display the module power information that indicates whether the SFP optical module power supply is normal. The display of module power information allows the administrator to understand the power supply status of each SFP optical module. By checking parameters such as voltage and current, the administrator can determine whether the SFP optical module has obtained a stable power supply, and then evaluate whether the SFP optical module is working properly. Once a power supply anomaly is found, the administrator can take immediate action to avoid potential performance degradation or failure.

[0070] For example, the web terminal will also display the line rate and port rate of each port of the switch. Administrators can compare the rate differences between different ports to determine whether there is a rate bottleneck or configuration problem.

[0071] For example, the web terminal can display "Port 1 - In place - Normal - 400Gbps - A - 200Gbps, B - 200Gbps", which indicates that the external node of port 1 of the switch is in place and working normally, and the total line rate is 400Gbps. This rate is achieved by the two sub-ports A and B of the external node, and the rate of each sub-port is 200Gbps.

[0072] Moreover, in the web terminal, different colors can be highlighted based on the different port connection information of the switch. In this way, the administrator can quickly identify the working status of each port of the switch and take corresponding management measures. For example, for the ports of the switch that are displayed as "in place" and "normal", they can be highlighted in green. For the ports of the switch that are displayed as "not in place" or "abnormal", they can be highlighted in red or other eye-catching colors.

[0073] In addition, different colors or icons can be used to distinguish the ports of switches with different network speeds. For example, blue can be used to represent the ports of switches with a network speed of 200Gbps, while purple can be used to represent the ports of switches with a network speed of 400Gbps. In this way, administrators can not only understand the port connection status of the switch, but also quickly grasp the network speed information of each switch port.

[0074] It should be noted that after the BMC sends the switch port connection information and the module position information and module power information of the SFP optical module to the management system, not only the management system web interface can display the management results, but the management system can also display the management results through a non-web management interface. This application does not limit this.

[0075] In summary, an embodiment of the present application discloses an information processing method, which includes: the BMC of the switch obtains the network rate information of the external node connected to the switch from the switch chip, identifies the port connection information of the switch according to the network rate information, and sends the port connection information to the management system. As a result, the switch does not need to be connected to the IB network, and the administrator can view and manage the switch and the external nodes connected to it through the management system. In addition, when an abnormality occurs in the port connected to the switch and the external node, the administrator can directly view the abnormal condition of the port through the management system without relying on the IB network to transmit abnormal information, which solves the problem of being unable to view the switch port connection information due to the abnormality of the IB network, improves the efficiency of exception handling, and enables the administrator to identify and resolve abnormal conditions more quickly.

[0076] See also Figure 7 , which is a schematic diagram of the hardware structure of a switch provided in an embodiment of the present application. Figure 7 It can be seen that the switch in actual application, in addition to the above-mentioned switch chip that complies with the IB protocol, complex programmable logic device (CPLD) and baseboard management controller (BMC), can also include any of the following hardware: power supply unit (PowerSupply Unit, PSU), flash memory (Flash), liquid cooling monitoring, board-to-board connectors (Board-to-board Connectors, BTB), soft start, fan (FAN) and 16* octal small form-factor pluggable (Octal Small Form-factor Pluggable, OSFP) board (OSFP Board), network detection and response module (Network Detection and Response, NDR).

[0077] Depend on Figure 7 It can be seen that the BMC is also connected to the fan module (6*4056+FAN Board) and the 16*OSFP Board. For example, the fan module includes 6 fans, each of which is used to dissipate heat to prevent the switch from being damaged due to overheating. When the internal temperature of the switch rises, the fan will automatically speed up to improve the heat dissipation efficiency. The 16*OSFP Board is a 16-fiber channel port board using the OSFP standard. The OSFP Board includes multiple OSFP ports. The OSFP port is a standardized port for high-speed data transmission, which enables the switch to effectively connect and communicate with other high-speed network devices.

[0078] In addition, the PSU provides stable power to the switch to ensure the normal operation of the switch and all its components. Flash is used to store the configuration information, operating system, firmware, etc. of the switch. Flash memory is non-volatile and can retain data even when the power is turned off. Liquid cooling monitoring is used to cool the hardware components in the switch through liquid circulation to ensure that they can work stably in a high temperature environment. Liquid cooling systems are generally more efficient than traditional fan heat dissipation. BTB is used to provide channels for connection and data transmission for various components in the switch. It is like a central hub that enables various components to communicate and work together. The soft start module is used to control the startup process of the switch to ensure that the current is stable when the power is turned on to avoid shock or damage to the hardware. NDR is used to insert optical modules and provide comprehensive network security protection after the optical modules are inserted.

[0079] The above hardware components work together to enable the switch to achieve efficient and stable data exchange and communication functions. Different switches may have different hardware structures and configurations to adapt to different application scenarios and requirements. This application does not limit the specific hardware structure of the switch.

[0080] The switch also includes a GE port (i.e., the first port), the GE port is connected to the BMC, and the BMC is connected to the management node via the GE. It is understandable that the management system involved in the above embodiments runs on the management node. The GE port is a network port standard widely used in local area networks (LANs) and wide area networks (WANs). It provides high-speed and stable data transmission capabilities and is suitable for various network management scenarios. Compared with the traditional solution in which the BMC is directly connected to the OSFP (Octal Small Form-factor Pluggable), the BMC connects to the management node via the GE port to simplify the network structure, reduce network complexity, and improve network stability. In addition, the high-speed data transmission capability of the GE port enables the BMC to communicate with the management node more quickly, thereby improving the efficiency of remote management.

[0081] The switch also includes a connector group, which includes multiple connectors, and the connectors are used to connect to the server. At the same time, the switch chip is also connected to the OSFP port, which is a high-speed, high-density optical interface standard mainly used to connect optical modules. It can be understood that since the OSFP port and the connector are both used to establish a connection with an external device, they can be collectively referred to as the second port.

[0082] See also Figure 8 , which is a schematic diagram of a cabinet server provided in an embodiment of the present application. The cabinet server includes a power supply area, a server area, a switch area and a management area. Among them, the switch area includes any number of switches provided in an embodiment of the present application.

[0083] Among them, the power supply in the power supply area is usually used for centralized power supply to provide stable and reliable power supply for other equipment in the cabinet.

[0084] The server area is the part of the cabinet used to place servers. Figure 8 There are multiple server units placed horizontally in a server, which is usually used for blade servers. Blade servers achieve efficient and intensive computing power by sharing resources such as power, cooling and network connections, and are suitable for scenarios that require large amounts of computing and storage capabilities.

[0085] The switch area is located below the server area and occupies a height of four units. The switch in the switch area is a key device in the computer network, used to connect multiple servers or other network devices to achieve data packet forwarding and communication.

[0086] The management area is used to accommodate management nodes. Management nodes are connected to switches, servers, etc. The management system on the management node communicates with switches and servers to manage switches and servers. Management usually means that the status, performance, configuration and other information of these devices or resources can be monitored and managed in real time by the central system. Through management, administrators can more conveniently perform remote configuration, update, troubleshoot and other operations on these devices to improve operation and maintenance efficiency.

[0087] For example, switches in a switch area are used to obtain network rate information of external nodes connected to the switches; based on the network rate information of the external nodes, port connection information of the switches is identified; and the port connection information of the switches is sent to a management system so that the management system displays management results including the port connection information to users.

[0088] In summary, the embodiment of the present application discloses a cabinet server. Since the cabinet server includes a switch provided by the embodiment of the present application, the cabinet server has the beneficial effects of the above-mentioned switch and information processing method.

[0089] An embodiment of the present application also provides a computer program product. When the computer program product runs on a server, the server implements the information processing method in any of the above embodiments.

[0090] It should be understood that in the embodiments of the present application, "at least one (item)" refers to one or more, and "plurality" refers to two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can represent: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the associated objects before and after are in an "or" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0091] It should also be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0092] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0093] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An information processing method, characterized in that: Applied to a switch, the switch includes a baseboard management controller BMC and a switch chip, and the method includes: The BMC obtains network rate information of an external node connected to the switch from the switch chip; The BMC identifies the port connection information of the switch according to the network rate information of the external node; The BMC sends the port connection information of the switch to the management system.

2. The method according to claim 1, characterized in that The switch further includes an embedded processor, and the BMC obtains network rate information of an external node connected to the switch from the switch chip, including: The BMC receives network rate information of an external node connected to the switch sent by the embedded processor, and the network rate information is obtained by the embedded processor from the switch chip.

3. The method according to claim 1 or 2, characterized in that: The port at which the external node is connected to the switch includes a first sub-port and a second sub-port, and the BMC identifies the port connection information of the switch according to the network rate information of the external node, including: When the sum of the network rate of the first subport and the network rate of the second subport is a first value, if the first subport is in a connected state and the second subport is in an unconnected state or an unrecognized state, the BMC determines that the switch is connected to the first subport at a first network rate, and the first network rate is less than the first value.

4. The method according to claim 1 or 2, characterized in that: The port at which the external node is connected to the switch includes a first sub-port and a second sub-port, and the BMC identifies the port connection information of the switch according to the network rate information of the external node, including: When the sum of the network rate of the first subport and the network rate of the second subport is a first value, if the first subport and the second subport are both in an unconnected state or an unrecognized state, the BMC determines that the port connection information of the switch is unconnected or unrecognized.

5. The method according to claim 1 or 2, characterized in that: The port at which the external node is connected to the switch includes a first sub-port and a second sub-port, and the BMC identifies the port connection information of the switch according to the network rate information of the external node, including: When the sum of the network rate of the first subport and the network rate of the second subport is a first value, if the first subport and the second subport are both in a connected state, the BMC determines that the switch is connected to the first subport and the second subport at a first network rate, and the first network rate is less than the first value.

6. The method according to claim 1, characterized in that The method further comprises: The BMC obtains node presence information and / or node power information of the external node from the switch chip; The BMC sends the node presence information and / or the node power information of the external node to the management system.

7. The method according to claim 1 or 2, characterized in that: The external node includes an optical module, an electrical port module, an optical-to-electrical module, an electrical-to-optical module or a server.

8. A baseboard management controller BMC, characterized in that: The BMC includes: a memory and a controller; The memory is used to store programs; The controller is used to execute the program to implement each step of the method according to any one of claims 1 to 7.

9. A switch, characterized in that: The switch includes: a baseboard management controller BMC, a switch chip, a first port and a second port, the switch chip is connected between the second port and the BMC, the BMC is connected to the first port, the first port is a Gigabit Ethernet port, the first port is used to communicate with the management system, the second port is used to connect to an external node, and the BMC is used to: The network rate information of the external node is obtained from the switch chip, the port connection information of the second port is identified according to the network rate information of the external node, and the port connection information of the switch is sent to the management system.

10. The switch according to claim 9, characterized in that: The switch further includes an embedded processor connected between the switch chip and the BMC.