Automatic Training method and device for switch port and medium

Abstract

The invention discloses an automatic Training method and device for a switch port and a medium, and relates to the technical field of switch communication. The method comprises the following steps: monitoring a port state of a switch in real time, and triggering port Serdes Training state detection when the port state is converted from a Down state to a Up state; if the port is not in the Serdes Training completion state or the Serdes Training non-completion state, detecting whether a communication link of the Serdes is in a Down state or not; when it is determined that the communication link of the Serdes is in the Down state, the port state of the switch is continuously detected for a preset duration so as to determine whether the condition signal state of the port Serdes Training is stable or not, and when it is determined that the condition signal state is stable, the port Serdes Training is carried out; the method comprises the following steps of: polling a Serdes Training state of a port through a timed task, and when the port is determined to be in a Serdes Training completion state, updating parameters of a decision feedback equalizer (DFE) in Serdes according to a Serdes Training result.

Description

Technical Field

[0001] The present application relates to the field of switch communication technology, and in particular to an automatic training method, device and medium for a switch port. Background Art

[0002] With the rapid development of information technology and the continuous expansion of its application fields, especially the rise of artificial intelligence (AI) and high-performance computing (HPC), unprecedented high requirements have been placed on the stability and reliability of network communications. As a key device in network communications, the performance and stability of switches directly determine the operating effect of the entire network system.

[0003] In the traditional switch port docking process, the signal is often interfered by attenuation and noise on the transmission path, which seriously affects the integrity and accuracy of the signal. Especially at the receiving end (Rx side), the performance of the serial deserializer (Serdes) as a key component of signal conversion directly affects whether the signal can be correctly restored on the receiving side. However, due to the unsatisfactory Serdes parameter configuration or hardware design differences, the signal cannot be correctly restored on the receiving side, which in turn causes a series of problems such as the port cannot be activated normally (that is, the port cannot be Up normally), CRC (cyclic redundancy check) packet loss, and packet errors.

[0004] In order to overcome the above signal problems, SerDes usually needs to perform a series of training processes to optimize its parameter settings. However, traditional training mechanisms often have many shortcomings, such as improper selection of training timing, complex and time-consuming training processes, and link oscillations that may be caused during the training process. These problems not only increase the instability of the system, but also seriously affect the user experience.

[0005] In order to solve the above problems, most existing technical solutions use manual configuration or preset parameters to implement the Serdes training process. However, this method is not only cumbersome and inefficient, but also cannot adapt to the changes in different hardware environments and application scenarios, and it is difficult to meet the high requirements of modern network communications for stability and reliability. Therefore, how to implement a more intelligent and efficient switch port automatic training mechanism has become a technical problem that needs to be solved urgently. Summary of the invention

[0006] The embodiments of the present application provide an automatic training method, device and medium for a switch port, so as to solve the following technical problem: how to implement a more intelligent and efficient automatic training mechanism for a switch port.

[0007] In a first aspect, an embodiment of the present application provides an automatic training method for a switch port, characterized in that the method includes: monitoring the port status of the switch in real time, and triggering port Serdes Training status detection when the port status changes from Down state to Up state; if the port is not in the Serdes Training completion state or the Serdes Training incomplete state, detecting whether the communication link of Serdes is in the Down state; when it is determined that the communication link of Serdes is in the Down state, continuously detecting the port status of the switch for a preset time length to determine whether the conditional signal state for port Serdes Training is stable, and performing port Serdes Training when it is determined that the conditional signal state is stable; polling the Serdes Training state of the port through a timed task, and when it is determined that the port is in the Serdes Training completion state, updating the parameters of the decision feedback equalizer DFE in Serdes according to the Serdes Training results.

[0008] In one implementation of the present application, the method further includes: if the port is in a Serdes Training completion state or a Serdes Training incomplete state, starting a timed task to poll the Serdes Training state of the port, and when it is determined that the port is in a Serdes Training completion state, updating the parameters of the decision feedback equalizer DFE in Serdes according to the Serdes Training result.

[0009] In one implementation of the present application, the method also includes: when it is determined that the communication link of Serdes is not in the Down state, detecting whether there is a communication signal in the communication link of Serdes; when it is determined that there is no communication signal in the communication link of Serdes, directly converting the communication link of Serdes to the Down state; when it is determined that there is a communication signal in the communication link of Serdes, continuously sending a remote fault signal to Serdes to force the communication link of Serdes to be converted to the Down state.

[0010] In one implementation of the present application, after the communication link of Serdes is forcibly converted to the Down state, the method also includes: detecting whether the conditional signal states have met the conditions of port Serdes Training; wherein the conditional signals include: signal detection signal Signal Detect, physical coding sublayer alignment lock signal Pcs Align Lock, gearbox lock signal Gear Box Lock; when it is determined that all signals meet the conditions of port Serdes Training, stop sending remote fault signals to Serdes.

[0011] In one implementation of the present application, the port status of the switch is continuously detected for a preset time to determine whether the conditional signal state is stable, specifically including: continuously monitoring the state of the conditional signal within the preset time, and determining whether the conditional signal has no state jump within the preset time; if all conditional signal states have no state jump, it is determined that the conditional signal meets the conditions for port Serdes Training; if any conditional signal has a state jump within the preset time, it is determined that the conditional signal state is unstable and does not meet the conditions for port Serdes Training.

[0012] In one implementation of the present application, port Serdes Training is performed, specifically including: sending a Serdes Training start instruction to a port of a switch through a management interface of the switch; after the port of the switch receives the instruction, starting an internal Serdes Training mechanism to implement port Serdes Training.

[0013] In one implementation of the present application, the parameters of the decision feedback equalizer DFE in Serdes are updated according to the Serdes Training result, specifically including: obtaining the optimal DFE parameter configuration according to the Serdes Training result; sending the optimal DFE parameter configuration to the port of the switch through the management interface of the switch; after the switch port receives the optimal DFE parameter configuration, it automatically updates its internal DFE parameters.

[0014] In one implementation of the present application, after updating the parameters of the decision feedback equalizer DFE in Serdes according to the Serdes Training results, the method also includes: verifying whether the parameters of the decision feedback equalizer DFE in the updated Serdes are valid; if the verification fails, rolling back to the parameters of the decision feedback equalizer DFE in Serdes before the update, and generating an alarm message to notify the administrator to perform manual processing.

[0015] In a second aspect, an embodiment of the present application also provides an automatic Training device for a switch port, characterized in that the device includes: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions that can be executed by at least one processor, and the instructions are executed by at least one processor so that the at least one processor can: monitor the port status of the switch in real time, and trigger the port Serdes Training status detection when the port status changes from the Down state to the Up state; if the port is not in the Serdes Training completion state or the Serdes Training incomplete state, detect whether the communication link of the Serdes is in the Down state; when it is determined that the communication link of the Serdes is in the Down state, continuously detect the port status of the switch for a preset time to determine whether the conditional signal state for port Serdes Training is stable, and when it is determined that the conditional signal state is stable, perform port Serdes Training; poll the Serdes Training state of the port through a scheduled task, and when it is determined that the port is in the Serdes Training completion state, update the parameters of the decision feedback equalizer DFE in Serdes according to the Serdes Training result.

[0016] In a third aspect, an embodiment of the present application further provides a non-volatile computer storage medium for automatic training of a switch port, storing computer executable instructions, characterized in that the computer executable instructions are configured to: monitor the port status of the switch in real time, and trigger port SerdesTraining status detection when the port status changes from Down to Up; if the port is not in the Serdes Training completion state or the Serdes Training incomplete state, detect whether the communication link of Serdes is in the Down state; when it is determined that the communication link of Serdes is in the Down state, continuously detect the port status of the switch for a preset time to determine whether the conditional signal state for port Serdes Training is stable, and when it is determined that the conditional signal state is stable, perform port Serdes Training; poll the Serdes Training state of the port through a timed task, and when it is determined that the port is in the Serdes Training completion state, update the parameters of the decision feedback equalizer DFE in Serdes according to the Serdes Training results.

[0017] The embodiments of the present application provide an automatic training method, device, and medium for a switch port, which have the following beneficial effects:

[0018] 1. Improved the stability and reliability of network communication: This application monitors the port status of the switch in real time and triggers Serdes Training at the appropriate time to ensure that the switch port automatically adjusts to the optimal link quality after the optical module is inserted and activated, greatly reducing communication errors caused by signal attenuation and noise interference, thereby significantly improving the stability and reliability of network communication.

[0019] 2. Reduce the impact of link oscillation: The traditional Serdes Training process may cause link oscillation and affect the performance of the entire system. This application effectively minimizes the occurrence of link oscillation and ensures the smoothness of network communication through reasonable Training timing selection and mechanism design.

[0020] 3. Enhanced compatibility and adaptability of equipment: This application does not rely on a specific optical module brand or model, but automatically adjusts and optimizes Serdes parameters through unified software implementation, which improves the compatibility of the equipment, enables it to adapt to more types of optical modules, and simplifies the complexity of equipment configuration and maintenance.

[0021] 4. Improved system performance and user experience: This application can ensure that the switch port is always in the best working state by automatically adjusting and optimizing Serdes parameters, thereby improving the efficiency and accuracy of data transmission. This is especially important for application scenarios that require high-speed and stable network communication (such as AI, HPC, etc.), and can significantly improve user experience and system performance.

[0022] 5. Reduced operation and maintenance costs: Traditional SerDes parameter configuration often needs to be done manually, which is not only time-consuming and labor-intensive, but also prone to errors. The automatic training method of this application greatly simplifies this process, reduces operation and maintenance costs, and improves work efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0024] Figure 1 A flow chart of an automatic training method for a switch port provided in an embodiment of the present application;

[0025] Figure 2 A schematic diagram of the internal structure of an automatic training device for a switch port provided in an embodiment of the present application. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0027] The embodiments of the present application provide an automatic training method, device and medium for a switch port, so as to solve the following technical problem: how to implement a more intelligent and efficient automatic training mechanism for a switch port.

[0028] The technical solution proposed in the embodiments of the present application is described in detail below with reference to the accompanying drawings.

[0029] Figure 1 A flow chart of an automatic training method for a switch port provided in an embodiment of the present application. Figure 1 As shown, an automatic training method for a switch port provided in an embodiment of the present application specifically includes the following steps:

[0030] Step 101: monitor the port status of the switch in real time, and trigger port Serdes Training status detection when the port status changes from Down to Up.

[0031] In one embodiment of the present application, in order to implement an automatic training method for a switch port, it is first necessary to monitor the port status of the switch in real time, and trigger port Serdes Training status detection when the port status changes from Down to Up.

[0032] In one embodiment, the status of each port is first tracked in real time through the status monitoring mechanism inside the switch. This monitoring mechanism can be event-driven or timed polling to ensure that changes in port status can be discovered in a timely manner. The monitoring content mainly includes the physical connection status of the port, that is, whether the port is in a connected (Up) state or a disconnected (Down) state. This is usually achieved by detecting the presence or absence of physical layer signals, for example, by detecting the strength of optical signals or the voltage level of electrical signals.

[0033] When the state of a port is monitored to change from Down to Up, it indicates that a new optical module has been inserted and activated, or the previous connection failure has been restored. This is the key time to trigger the Serdes Training state detection. In order to accurately capture this state transition, this application adopts state change detection logic, which can compare the results of the previous and subsequent state detections to determine whether the port state has changed.

[0034] Once it is detected that the port status changes from Down to Up, the Serdes Training status detection process will be triggered immediately. The purpose of this process is to confirm whether the Serdes of the current port has completed the necessary training and optimization to ensure the link quality. The triggering method can be to send a start signal or instruction to the hardware or software module responsible for managing Serdes, which will activate the Training mechanism or status detection logic inside Serdes. In the Serdes Training status detection process, the current status of Serdes will be checked, including whether Training is in progress, whether Training has been completed, and whether the result of Training is successful. This status information is usually obtained by reading the status register inside Serdes or receiving the status report sent by Serdes. Based on this status information, it can be decided whether the Serdes Training process needs to be started or restarted.

[0035] Step 102: If the port is not in the Serdes Training completed state or the Serdes Training incomplete state, detect whether the Serdes communication link is in the Down state.

[0036] In one embodiment of the present application, after the port Serdes Training state detection is triggered, if the port is not in the Serdes Training completion state or the Serdes Training incomplete state, it is detected whether the Serdes communication link is in the Down state.

[0037] In one embodiment of the present application, when it is determined that the communication link of Serdes is not in the Down state, it is detected whether there is a communication signal in the communication link of Serdes; when it is determined that there is no communication signal in the communication link of Serdes, the communication link of Serdes is directly converted to the Down state; when it is determined that there is a communication signal in the communication link of Serdes, a remote fault signal is continuously sent to Serdes to force the communication link of Serdes to be converted to the Down state.

[0038] In one embodiment, if the port is not in the Serdes Training completed state or the Serdes Training uncompleted state, further detect whether the Serdes communication link is in the Down state to confirm whether the communication link has been established. If it is detected that the Serdes communication link is not in the Down state, that is, the link has been established, further detect whether there is a communication signal in the link to confirm whether the link is active, that is, whether there is data transmitted on the link. The method of detecting the communication signal may include monitoring the data transmission volume on the link, detecting a specific signal mode or frame structure, etc. If no communication signal is detected within a certain period of time, it will be determined that the link is established but not active. At this time, in order to save resources and avoid unnecessary interference, the Serdes communication link can be directly converted to the Down state. This conversion can be achieved by closing the relevant physical layer interface, stopping sending or receiving data, etc. On the other hand, if it is determined that there is a communication signal in the communication link of Serdes, that is, the link is both established and active, but for some reason (such as poor link quality, too high bit error rate, etc.), it needs to be optimized or reset. Specifically, a remote fault signal (Remote Fault Signal) is continuously sent to Serdes to notify the peer device that there is a problem with the current link and request the peer device to cooperate in resetting or optimizing the link. This remote fault signal is usually a specific signal mode that complies with the relevant communication protocol or standard, and can be correctly identified and responded to by the peer device. By sending a remote fault signal, the communication link of Serdes can be forced to convert to the Down state, thereby creating conditions for subsequent Serdes Training or optimization operations. After the link is converted to the Down state, the SerdesTraining process can be triggered again to re-establish and optimize the link parameters to ensure the stability and performance of the communication.

[0039] In one embodiment of the present application, after the communication link of Serdes is forcibly converted to the Down state, the method also includes: detecting whether the conditional signal states have met the conditions of port Serdes Training; wherein the conditional signals include: signal detection signal Signal Detect, physical coding sublayer alignment lock signal Pcs Align Lock, gearbox lock signal Gear Box Lock; when it is determined that all signals meet the conditions of port Serdes Training, stop sending remote fault signals to Serdes.

[0040] In one embodiment, when the communication link of Serdes is forcibly converted to the Down state, in order to ensure that the port can smoothly perform Serdes Training, the state of a series of conditional signals is further detected. These conditional signals are prerequisites that must be met for the port to perform Serdes Training. Only when they are all in the expected state can the Training process be effectively started and executed.

[0041] Specifically, the present invention detects the following three key conditional signal states:

[0042] Signal Detect: This is a flag that indicates whether the physical layer has detected a valid input signal. Confirm whether the Signal Detect signal is activated, that is, whether a valid optical or electrical signal from the other end device is detected. Only when the Signal Detect signal is valid, it indicates that a physical connection has been established at both ends of the link, which is the basis for Serdes Training.

[0043] Physical Coding Sublayer Alignment Lock Signal (Pcs Align Lock): This signal indicates whether the physical coding sublayer (PCS) has completed the alignment and locking process. The PCS layer is responsible for encoding and decoding data to ensure the integrity and reliability of data during transmission. The present invention checks whether the Pcs Align Lock signal has been locked, that is, whether the PCS layer is ready for data transmission. This is one of the key conditions for the correct execution of Serdes Training.

[0044] Gear Box Lock signal: For Serdes interfaces that support multiple rates and modes, the Gear Box Lock signal is used to indicate whether the gear box has been locked at a specific rate or mode. The gear box is responsible for adjusting the data transmission rate and format according to the actual situation of the link. Verify whether the Gear Box Lock signal is valid to ensure that the gear box has been stably locked at the expected rate or mode before Serdes Training.

[0045] In the process of detecting these conditional signals, the present application can adopt polling, interruption or event-driven methods to ensure timely acquisition of changes in signal status. Once it is detected that all signals meet the conditions of port Serdes Training, that is, the Signal Detect signal is valid, the Pcs Align Lock signal is locked, and the Gear Box Lock signal is valid, the present invention will stop sending remote fault signals to Serdes. This indicates that the link is ready for Serdes Training and can start adjusting and optimizing the transmission performance of the port.

[0046] Step 103: When it is determined that the Serdes communication link is in the Down state, the port state of the switch is continuously detected for a preset time to determine whether the conditional signal state for port Serdes Training is stable, and when it is determined that the conditional signal state is stable, port Serdes Training is performed.

[0047] In one embodiment of the present application, when it is determined that the Serdes communication link is in the Down state, the port state of the switch needs to be continuously detected for a preset time to determine whether the conditional signal state for port Serdes Training is stable.

[0048] Specifically, within the preset time length, the state of the conditional signal is continuously monitored, and it is determined whether the conditional signal has no state jump within the preset time length; if the state of all conditional signals has no state jump, it is determined that the conditional signal meets the conditions for port Serdes Training; if any conditional signal has a state jump within the preset time length, it is determined that the state of the conditional signal is unstable and does not meet the conditions for port Serdes Training.

[0049] In one embodiment, when it is determined that the communication link of Serdes is in the Down state, in order to ensure the smooth progress of the subsequent port Serdes Training, the present application introduces a continuous detection mechanism to continuously monitor the port state of the switch for a preset time to verify whether the conditional signal state on which Serdes Training depends is stable, thereby avoiding Training failure or performance degradation caused by unstable signal state. In the specific implementation process, the present application will set a preset time, such as a few seconds or a few minutes, which can be adjusted according to the actual application scenario and requirements. Within the preset time, the system will continuously monitor the status of a series of key conditional signals, including but not limited to signal detection signals (Signal Detect), physical coding sublayer alignment lock signals (Pcs Align Lock) and gearbox lock signals (Gear Box Lock). During the continuous monitoring process, the state changes of each conditional signal are recorded. If all monitored conditional signals do not have a state jump during the entire preset time, that is, their states are always consistent and stable, it is determined that these conditional signals meet the conditions for port Serdes Training, which means that the link state is stable and subsequent Training operations can be performed. If any conditional signal changes state within the preset time, such as from an activated state to an inactivated state, or from a locked state to an unlocked state, it is determined that the conditional signal state is unstable. In this case, due to the instability of the signal state, performing Serdes Training may lead to unpredictable results or performance problems, so the present invention determines that the conditions for performing port Serdes Training are not currently met.

[0050] Further, when it is determined that the conditional signal state is stable, port Serdes Training is performed.

[0051] Specifically, an instruction to start Serdes Training is sent to the port of the switch through the management interface of the switch; after the port of the switch receives the instruction, an internal Serdes Training mechanism is started to implement port SerdesTraining.

[0052] In one embodiment, in order to perform port Serdes Training, an instruction to start Serdes Training is first sent to the port of the switch through the management interface of the switch. The management interface may be a command line interface (CLI), a simple network management protocol (SNMP) interface, or other proprietary management interface, depending on the model and configuration of the switch. The instruction to start Serdes Training may be a specific command or message, which tells the switch port that the internal Serdes Training mechanism needs to be started now. This instruction may contain some parameters, such as the mode and duration of Training, which can be set according to actual conditions. After the port of the switch receives the instruction to start SerdesTraining, it will start the internal Serdes Training mechanism. This mechanism usually includes a series of complex algorithms and processes for automatically adjusting and optimizing the transmission parameters of the port to ensure the stability and efficiency of data during high-speed transmission. The Serdes Training mechanism may involve adjustments and optimizations in multiple aspects, including but not limited to clock synchronization, signal equalization, noise suppression, etc. Through these adjustments, the port can better adapt to the current transmission environment and conditions, thereby improving the quality and speed of data transmission. During the Serdes Training process, the switch port may perform multiple handshakes and negotiations with the peer device to ensure that both parties can achieve the best transmission status. This process may take a certain amount of time, depending on the complexity of the link and the performance of the port.

[0053] Step 104: poll the Serdes Training status of the port through a timed task, and when it is determined that the port is in the Serdes Training completion state, update the parameters of the decision feedback equalizer DFE in the Serdes according to the Serdes Training result.

[0054] In one embodiment of the present application, during the port Serdes Training process, the Serdes Training status of the port is polled through a timer task, and when it is determined that the port is in the Serdes Training completion state, the parameters of the decision feedback equalizer DFE in Serdes are updated according to the Serdes Training result.

[0055] Specifically, according to the result of Serdes Training, the optimal DFE parameter configuration is obtained; the optimal DFE parameter configuration is sent to the port of the switch through the management interface of the switch; after the port of the switch receives the optimal DFE parameter configuration, the internal DFE parameters thereof are automatically updated.

[0056] In one embodiment, when a port performs Serdes Training, the present application introduces a mechanism to dynamically monitor the status of Training and optimize the performance of the port according to the results of Training. The core of this mechanism is to poll the Serdes Training status of the port through a timed task and update the decision feedback equalizer (DFE) parameters in Serdes according to the results of Training. First, a timed task is started, which periodically polls the port of the switch to check the current status of Serdes Training. The frequency of polling can be set according to actual needs to ensure that the update of the Training status can be obtained in time. During the polling process, once it is detected that the port is in the SerdesTraining completion state, the results of Serdes Training will be further obtained. These results usually include a series of key indicators about link performance and the optimal DFE parameter configuration recommended based on these indicators. After obtaining the optimal DFE parameter configuration, these parameters are sent to the corresponding port through the management interface of the switch. This step ensures that the port can receive the most appropriate parameter configuration according to its actual transmission environment and conditions, thereby optimizing its performance. After receiving the optimal DFE parameter configuration, the switch port will automatically trigger its internal parameter update mechanism. This mechanism will be responsible for applying the received parameter configuration to the port's DFE, thereby completing the parameter update process. The updated DFE parameters can better adapt to the current transmission environment and improve the signal reception quality and transmission efficiency of the port.

[0057] In one embodiment of the present application, after updating the parameters of the decision feedback equalizer DFE in Serdes according to the Serdes Training results, the method also includes: verifying whether the parameters of the decision feedback equalizer DFE in the updated Serdes are valid; if the verification fails, rolling back to the parameters of the decision feedback equalizer DFE in Serdes before the update, and generating an alarm message to notify the administrator to perform manual processing.

[0058] The above is an embodiment of the method proposed in this application. Based on the same inventive concept, the embodiment of this application also provides an automatic training device for a switch port, and its structure is as follows: Figure 2 shown.

[0059] Figure 2 The following is a schematic diagram of the internal structure of an automatic training device for a switch port provided in an embodiment of the present application. Figure 2 As shown, the device includes:

[0060] at least one processor 201;

[0061] and, a memory 202 communicatively connected to the at least one processor;

[0062] The memory 202 stores instructions that can be executed by at least one processor, and the instructions are executed by at least one processor 201 to enable at least one processor 201 to:

[0063] Monitor the port status of the switch in real time, and trigger the port Serdes Training status detection when the port status changes from Down to Up;

[0064] If the port is not in the Serdes Training completed state or the Serdes Training is not completed state, check whether the Serdes communication link is in the Down state;

[0065] When it is determined that the Serdes communication link is in the Down state, the port state of the switch is continuously detected for a preset time to determine whether the conditional signal state for port Serdes Training is stable, and when it is determined that the conditional signal state is stable, the port Serdes Training is performed;

[0066] The Serdes Training state of the port is polled through a scheduled task, and when it is determined that the port is in the SerdesTraining completion state, the parameters of the decision feedback equalizer DFE in the Serdes are updated according to the Serdes Training result.

[0067] Some embodiments of the present application provide corresponding Figure 1 A non-volatile computer storage medium for automatic training of a switch port stores computer executable instructions, wherein the computer executable instructions are set to:

[0068] Monitor the port status of the switch in real time, and trigger the port Serdes Training status detection when the port status changes from Down to Up;

[0069] If the port is not in the Serdes Training completed state or the Serdes Training is not completed state, check whether the Serdes communication link is in the Down state;

[0070] When it is determined that the Serdes communication link is in the Down state, the port state of the switch is continuously detected for a preset time to determine whether the conditional signal state for port Serdes Training is stable, and when it is determined that the conditional signal state is stable, the port Serdes Training is performed;

[0071] The Serdes Training state of the port is polled through a scheduled task, and when it is determined that the port is in the SerdesTraining completion state, the parameters of the decision feedback equalizer DFE in the Serdes are updated according to the Serdes Training result.

[0072] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the IoT device and medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0073] The system and medium provided in the embodiments of the present application correspond one-to-one to the method. Therefore, the system and medium also have similar beneficial technical effects to the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the system and medium will not be repeated here.

[0074] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0075] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0076] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0077] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0078] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0079] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0080] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0081] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity 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, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0082] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. An automatic training method for switch ports. It is characterized in that The method comprises: Monitor the port status of the switch in real time, and trigger port Serdes Training status detection when the port status changes from Down to Up; If the port is not in the Serdes Training completed state or the Serdes Training is not completed state, check whether the Serdes communication link is in the Down state; When it is determined that the Serdes communication link is in the Down state, the port state of the switch is continuously detected for a preset time to determine whether the conditional signal state for port Serdes Training is stable, and when it is determined that the conditional signal state is stable, port Serdes Training is performed; The Serdes Training state of the port is polled through a timed task, and when it is determined that the port is in the Serdes Training completion state, the parameters of the decision feedback equalizer DFE in the Serdes are updated according to the Serdes Training result.

2. The automatic training method for a switch port according to claim 1, It is characterized in that The method further comprises: If the port is in the Serdes Training completion state or the Serdes Training incomplete state, start the scheduled task to poll the Serdes Training state of the port, and when it is determined that the port is in the Serdes Training completion state, update the parameters of the decision feedback equalizer DFE in the Serdes according to the Serdes Training result.

3. The automatic training method for a switch port according to claim 1, It is characterized in that The method further comprises: When it is determined that the communication link of the Serdes is not in the Down state, detecting whether there is a communication signal in the communication link of the Serdes; When it is determined that there is no communication signal in the communication link of the Serdes, directly converting the communication link of the Serdes to a Down state; When it is determined that there is a communication signal in the communication link of the Serdes, a remote fault signal is continuously sent to the Serdes, so that the communication link of the Serdes is forcibly converted to a Down state.

4. The automatic training method for a switch port according to claim 3, It is characterized in that After the communication link of the Serdes is forcibly converted to a Down state, the method further includes: Detect whether the conditional signal states have satisfied the conditions of port Serdes Training; wherein the conditional signals include: signal detection signal Signal Detect, physical coding sublayer alignment lock signal Pcs Align Lock, gearbox lock signal Gear Box Lock; When it is determined that all signals meet the port Serdes Training condition, the sending of the remote fault signal to the Serdes is stopped.

5. The automatic training method for a switch port according to claim 4, It is characterized in that Continuously detecting the port status of the switch for a preset time to determine whether the conditional signal status is stable, specifically including: Within the preset time length, continuously monitoring the state of the conditional signal, and determining whether the conditional signal has no state jump within the preset time length; If no state jump occurs in the states of all conditional signals, it is determined that the conditional signals meet the conditions for performing port SerdesTraining; If any conditional signal has a state jump within a preset time period, it is determined that the state of the conditional signal is unstable and does not meet the conditions for performing port Serdes Training.

6. The automatic training method for a switch port according to claim 1, It is characterized in that Conduct port Serdes training, including: Send a command to start Serdes Training to the switch port through the switch management interface; After the port of the switch receives the instruction, an internal Serdes Training mechanism is started to implement port Serdes Training.

7. The automatic training method for a switch port according to claim 1, It is characterized in that Update the parameters of the decision feedback equalizer DFE in Serdes according to the Serdes Training results, including: According to the results of Serdes Training, the optimal DFE parameter configuration is obtained; Send the optimal DFE parameter configuration to the switch port through the switch management interface; After receiving the optimal DFE parameter configuration, the switch port automatically updates its internal DFE parameters.

8. The automatic training method for a switch port according to claim 1, It is characterized in that After updating the parameters of the decision feedback equalizer DFE in the Serdes according to the Serdes Training result, the method further includes: Verify whether the parameters of the decision feedback equalizer DFE in the updated Serdes are valid; If the verification fails, the parameters of the decision feedback equalizer DFE in the Serdes before the update are rolled back, and an alarm message is generated to notify the administrator to perform manual processing.

9. An automatic training device for switch ports. It is characterized in that The device comprises: at least one processor; and, a memory communicatively coupled to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to: Monitor the port status of the switch in real time, and trigger port Serdes Training status detection when the port status changes from Down to Up; If the port is not in the Serdes Training completed state or the Serdes Training is not completed state, check whether the Serdes communication link is in the Down state; When it is determined that the Serdes communication link is in the Down state, the port state of the switch is continuously detected for a preset time to determine whether the conditional signal state for port Serdes Training is stable, and when it is determined that the conditional signal state is stable, port Serdes Training is performed; The Serdes Training state of the port is polled through a timed task, and when it is determined that the port is in the Serdes Training completion state, the parameters of the decision feedback equalizer DFE in the Serdes are updated according to the Serdes Training result.

10. A non-volatile computer storage medium for automatic training of a switch port, storing computer executable instructions, It is characterized in that The computer executable instructions are configured to: Monitor the port status of the switch in real time, and trigger port Serdes Training status detection when the port status changes from Down to Up; If the port is not in the Serdes Training completed state or the Serdes Training is not completed state, check whether the Serdes communication link is in the Down state; When it is determined that the Serdes communication link is in the Down state, the port state of the switch is continuously detected for a preset time to determine whether the conditional signal state for port Serdes Training is stable, and when it is determined that the conditional signal state is stable, port Serdes Training is performed; The Serdes Training state of the port is polled through a timed task, and when it is determined that the port is in the Serdes Training completion state, the parameters of the decision feedback equalizer DFE in the Serdes are updated according to the Serdes Training result.

Images