Signal exception processing method and system, server and storage medium
By introducing signal exception handling methods into the server, the coordinated work of the substrate management controller and the hardware expansion module is used to actively detect and handle signal exceptions, solving the operational problems caused by signal interference in the server and improving the stability of the server.
Patent Information
- Application Number
- CN202510237957.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-02-28
- Publication Date
- 2025-06-10
AI Technical Summary
Signal interference is prone to occur in the server, affecting the normal operation of the server. Especially under high computing pressure, the substrate management controller is prone to encounter errors and slow problems when collecting signals.
Provide a signal exception handling method, through the coordinated work of the substrate management controller and the hardware expansion module, actively detect signal exceptions in the server. The specific steps include taking the signal input by the hardware expansion module as the signal to be detected, obtaining the preset signal parameters, detecting the signal to be detected, and obtaining the register value to be judged logical consistency if it is abnormal, responding if it is consistent, and not responding if it is inconsistent.
By actively detecting and handling signal abnormalities, avoiding error responses, improving the operating stability of the server, and ensuring that the server can operate normally under high computing pressure.
Smart Images

Figure CN120123178A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of servers, and in particular to a signal abnormality processing method, system, server and storage medium. Background Art
[0002] With the continuous development of artificial intelligence technology, the scale and complexity of artificial intelligence models are constantly increasing, and the computing power requirements of the models are also increasing. Since servers can usually provide sufficient computing power, artificial intelligence models are usually deployed on servers and provide model computing services to the outside world. This leads to increasing computing pressure on computing devices, which in turn puts higher requirements on the working stability of such devices.
[0003] In the related art, signal interference is prone to occur in the server due to the influence of hardware design, internal line compression, external signal interference, etc., which in turn affects the normal operation of the server. For example, when the baseboard management controller (BMC) in the server is collecting signals, it is easy to encounter problems such as signal collection errors and slowness, which in turn easily affects the normal operation of the server. Summary of the invention
[0004] The object of the present invention is to provide a signal anomaly processing method, system, server and storage medium, which can actively detect signal anomalies in the server and avoid erroneous responses.
[0005] In order to solve the above technical problems, the present invention provides a signal exception processing method, which is applied to a signal exception processing system. The signal exception processing system includes a baseboard management controller and a hardware expansion module. The hardware expansion module is used to expand the functions of a central processing unit and a general input and output interface. The method includes:
[0006] The baseboard management controller uses the signal input by the hardware expansion module as a signal to be detected, and obtains a preset signal parameter corresponding to the signal to be detected;
[0007] Detecting the signal to be detected according to the preset signal parameters, and if it is determined that the signal to be detected is abnormal, obtaining a register value corresponding to the signal to be detected from the hardware expansion module, and determining whether the logical meaning of the signal to be detected is consistent with the logical meaning of the register value;
[0008] If the logic meaning of the signal to be detected is consistent with the logic meaning of the register value, responding to the signal to be detected;
[0009] If the logic meaning of the signal to be detected is inconsistent with the logic meaning of the register value, no response is made to the signal to be detected.
[0010] Optionally, after detecting the signal to be detected according to the preset signal parameters, the following steps are further included:
[0011] If the baseboard management controller determines that the signal to be detected is normal, it responds to the signal to be detected.
[0012] Optionally, after determining that the logical meaning of the signal to be detected is consistent with the logical meaning of the register value, the following steps are further included:
[0013] The baseboard management controller updates the preset signal parameters by using the signal parameters of the signal to be detected, so as to detect the signals subsequently sent by the hardware expansion module according to the updated preset signal parameters.
[0014] Optionally, the detecting the signal to be detected according to the preset signal parameters includes:
[0015] The baseboard management controller obtains the level conversion time of the signal to be detected and the level conversion interval time between two consecutive level conversions of the signal to be detected;
[0016] If the error between the level conversion time and the normal level conversion time is greater than the first threshold, or the error between the level conversion interval time and the normal level conversion interval time is greater than the second threshold, it is determined that the signal to be detected is abnormal;
[0017] If the error between the level conversion time and the normal level conversion time is not greater than the first threshold, and the error between the level conversion interval time and the normal level conversion interval time is not greater than the second threshold, it is determined that the signal to be detected is normal.
[0018] Optionally, the following steps are further included:
[0019] The baseboard management controller real-time collects the power consumption value of the server where it is located, and determines whether the power consumption value is greater than the third threshold or whether the change value of the power consumption value is greater than the fourth threshold;
[0020] If the power consumption value is greater than the third threshold, or the change value is greater than the fourth threshold, a preset warning message indicating that the signal abnormality handling system is unstable is output.
[0021] Optionally, before the baseboard management controller uses the signal input by the hardware expansion module as the signal to be detected, the following steps are further included:
[0022] The hardware extension module uses the timing signal sent by the data source device as the timing signal to be detected, and obtains the preset timing information corresponding to the timing signal to be detected; wherein, the data source device is the central processing unit or a device connected to the hardware extension module through the general input / output interface;
[0023] Detect the timing signal to be detected by using the preset timing information, and judge whether the signal timing of the timing signal to be detected is correct;
[0024] If it is correct, adjust the register value according to the timing signal to be detected, and send a reporting signal to the baseboard management controller according to the register value;
[0025] If it is incorrect, determine that the timing signal to be detected is abnormal, shield the timing signal to be detected, and send an abnormal signal to the base management controller;
[0026] When receiving the abnormal signal, the baseboard management controller outputs a preset warning message indicating that the hardware extension module encounters signal disorder.
[0027] Optionally, the signal abnormal processing system further includes a basic input / output system, and the method further includes:
[0028] When performing the initialization operation, the basic input / output system sends an initialization signal to the baseboard management controller through the serial peripheral interface;
[0029] The baseboard management controller waits to receive the initialization signal input by the basic input / output system, and judges whether the waiting duration of the initialization signal reaches a preset duration;
[0030] If the waiting duration reaches the preset duration, the baseboard management controller obtains the device status from the basic input / output system through the high-speed serial computer expansion bus, and judges whether the device status is normal;
[0031] If the device status is normal, the baseboard management controller determines that the communication link is abnormal;
[0032] If the device status is abnormal, the baseboard management controller determines that the basic input / output system is abnormal.
[0033] Optionally, obtaining the device status from the baseboard management controller through the high-speed serial computer expansion bus includes:
[0034] The basic input / output system writes the device status into the video memory space of the baseboard management controller through the high-speed serial computer expansion bus;
[0035] The baseboard management controller obtains the device status in its own video memory space.
[0036] The present invention also provides a signal anomaly processing system, including: a baseboard management controller and a hardware expansion module;
[0037] The hardware expansion module is used to expand the functions of the central processing unit and the general-purpose input / output interface;
[0038] The baseboard management controller is used to take the signal input by the hardware expansion module as a signal to be detected, and obtain a preset signal parameter corresponding to the signal to be detected; detect the signal to be detected according to the preset signal parameter, if it is determined that the signal to be detected is abnormal, obtain a register value corresponding to the signal to be detected from the hardware expansion module, and determine whether the logical meaning of the signal to be detected is consistent with the logical meaning of the register value; if the logical meaning of the signal to be detected is consistent with the logical meaning of the register value, respond to the signal to be detected; if the logical meaning of the signal to be detected is inconsistent with the logical meaning of the register value, do not respond to the signal to be detected.
[0039] Optionally, the hardware expansion module is a complex programmable logic device or a field programmable gate array.
[0040] The present invention also provides a server, including the signal anomaly processing system as described above.
[0041] The present invention also provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are loaded and executed by a processor, the signal anomaly processing method as described above is implemented.
[0042] The present invention provides a signal anomaly processing method, which is applied to a signal anomaly processing system. The signal anomaly processing system includes a baseboard management controller and a hardware expansion module. The hardware expansion module is used to expand the functions of the central processing unit and the general-purpose input / output interface. The method includes: the baseboard management controller takes the signal input by the hardware expansion module as a signal to be detected, and obtains a preset signal parameter corresponding to the signal to be detected; detects the signal to be detected according to the preset signal parameter, if it is determined that the signal to be detected is abnormal, obtains a register value corresponding to the signal to be detected from the hardware expansion module, and determines whether the logical meaning of the signal to be detected is consistent with the logical meaning of the register value; if the logical meaning of the signal to be detected is consistent with the logical meaning of the register value, responds to the signal to be detected; if the logical meaning of the signal to be detected is inconsistent with the logical meaning of the register value, does not respond to the signal to be detected.
[0043] It can be seen that when the baseboard management controller in the present invention receives a signal sent by the hardware expansion module, it does not immediately respond to the signal. Instead, it can first regard it as a signal to be detected and obtain the preset signal parameters corresponding to the signal to be detected. Subsequently, the baseboard management controller can detect the signal to be detected according to the preset signal parameters to determine whether the signal form of the signal to be detected is abnormal. If it is determined that the signal to be detected is abnormal, in order to determine whether it is a problem of waveform distortion of a normal signal caused by circuit design or external interference, the baseboard management controller can also obtain the register value corresponding to the signal to be detected from the hardware expansion module and determine whether the logical meaning of the signal to be detected is consistent with the logical meaning of the register value; if the logical meaning of the signal to be detected is consistent with the logical meaning of the register value, the signal to be detected is responded to; if the logical meaning of the signal to be detected is inconsistent with the logical meaning of the register value, the signal to be detected is not responded to. In this way, the baseboard management controller can actively detect and effectively process abnormal signals, avoid incorrect responses, and thus improve the operating stability of the server. The present invention also provides a signal anomaly processing system, a server, and a computer-readable storage medium, which have the above beneficial effects. BRIEF DESCRIPTION OF THE DRAWINGS
[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only the embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained according to the provided drawings.
[0045] Figure 1 The structural block diagram of the first signal anomaly processing system provided by the embodiment of the present invention;
[0046] Figure 2 The flowchart of a signal anomaly processing method provided by the embodiment of the present invention;
[0047] Figure 3 The structural block diagram of the second signal anomaly processing system provided by the embodiment of the present invention;
[0048] Figure 4 The structural block diagram of the third signal anomaly processing system provided by the embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS
[0049] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Apparently, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.
[0050] With the continuous development of artificial intelligence technology, the scale and complexity of artificial intelligence models are constantly increasing, and the computing power requirements of such models for devices are also growing. Since servers can usually provide sufficient computing power, servers are generally used to deploy artificial intelligence models and provide model computing services externally. This has led to an increasing computing pressure on computing devices, and thus higher requirements for the working stability of such devices.
[0051] In related technologies, affected by hardware design, internal circuit congestion, external signal interference, etc., signal interference is likely to occur in servers, thereby affecting the normal operation of the servers. For example, when the baseboard management controller (BMC) in a server performs signal acquisition, problems such as signal acquisition errors and slowness are likely to occur, which can easily affect the normal operation of the server. In view of this, the present invention can provide a signal anomaly processing method that can actively detect signal anomalies in a server and avoid incorrect responses.
[0052] For ease of understanding, please refer to Figure 1 , Figure 1 which is a structural block diagram of the first signal anomaly processing system provided by the embodiments of the present invention. This method is applied to a signal anomaly processing system, which is set in a server and may include: a baseboard management controller (BMC) and a hardware expansion module. Among them, the hardware expansion module is used to expand the functions of the central processing unit and the general-purpose input / output interface (GPIO). That is, the baseboard management controller is connected to the hardware expansion module, and the hardware expansion module is respectively connected to the central processing unit and the general-purpose input / output interface. In addition, the other end of the general-purpose input / output interface can be connected to other devices, that is, the hardware expansion module can enhance the functions of device signals accessed through the general-purpose input / output port. For example, the hardware expansion module can collect information such as server power-on / off, server reset, processor information, memory information, server temperature, fan working status, indicator light working status, and the presence of each board in the server from various components of the server and feedback it to the baseboard management controller.
[0053] It should be noted that the embodiments of the present invention do not limit the specific hardware type of the hardware expansion module. For example, it can be a Complex Programmable Logic Device (CPLD) or a Field Programmable Gate Array (FPGA). The embodiments of the present invention also do not limit how the baseboard management controller is connected to the hardware expansion module through signal lines. For example, the baseboard management controller can be connected to the hardware expansion module through an I2C bus (Inter-Integrated Circuit, integrated circuit bus) or a GPIO interface. The embodiments of the present invention also do not limit how the hardware expansion module is connected to the central processing unit through signal lines. For example, the hardware expansion module can be connected to the central processing unit through an LPC bus (Low PinCount Bus, reduced pin bus). The embodiments of the present invention also do not limit the number of GPIO interfaces in the hardware expansion module, which can be set according to actual application requirements.
[0054] Please refer to Figure 2 , Figure 2 which is a flowchart of a signal anomaly processing method provided by an embodiment of the present invention. This method is applied to the above signal anomaly processing system and may include:
[0055] S201. The baseboard management controller uses the signal input by the hardware expansion module as a signal to be detected and obtains a preset signal parameter corresponding to the signal to be detected.
[0056] In this step, considering the influence of factors such as circuit design defects, internal wire extrusion, and external signal interference, the signal reported by the hardware expansion module may be abnormal, such as a high signal delay, abnormal level jump, etc., which are likely to affect the baseboard management controller's recognition of the signal, and thus may easily lead to misrecognition by the baseboard management controller and incorrect operations on the server based on the misrecognition result. For example, the baseboard management controller is prone to misrecognize the server shutdown signal and then incorrectly guide the server to shut down. Therefore, when the baseboard management controller receives the signal reported by the hardware expansion module in the embodiments of the present invention, it does not immediately respond. Instead, it first sets the signal as a signal to be detected and obtains the preset signal parameter corresponding to the signal to be detected, so as to use the preset signal parameter to detect the signal and determine whether it is abnormal.
[0057] It should be noted that the baseboard management controller can set corresponding preset signal parameters for each type of signal reported by the hardware expansion module, and the baseboard management controller can distinguish different signals according to the signal receiving interface, and then use the corresponding preset signal parameters to perform anomaly detection on the signals of this interface. For example, when the baseboard management controller is connected to the hardware expansion module through multiple GPIO interfaces, the former can set corresponding preset signal information for each GPIO interface, and use this preset signal information to detect the signals received by each GPIO interface. The embodiments of the present invention do not limit the specific preset signal parameters either, and can be set according to actual application requirements. For example, the transformation of the level signal is usually a transient process, that is, the level conversion time (that is, the time consumed for converting from a low level to a high level, and the time consumed for converting from a high level to a low level) is short; in addition, there is a time interval between each level signal conversion. Therefore, the preset signal parameters can include the normal level conversion time and the normal level conversion interval time.
[0058] S202. Detect the signal to be detected according to the preset signal parameters. If it is determined that the signal to be detected is abnormal, obtain the register value corresponding to the signal to be detected from the hardware expansion module, and determine whether the logical meaning of the signal to be detected is consistent with the logical meaning of the register value.
[0059] In this step, the baseboard management controller can first detect the signal to be detected by using the preset signal parameters. For example, when the preset signal parameters include the above-mentioned normal level conversion time and normal level conversion interval time, the baseboard management controller can obtain the level conversion time of the signal to be detected and the level conversion interval time between two consecutive level conversions of the signal to be detected, and determine whether the level conversion time is less than the first threshold, and whether the level conversion interval time is less than the second threshold. If the error between the level conversion time and the normal level conversion time is greater than the first threshold, or the error between the level conversion interval time and the normal level conversion interval time is greater than the second threshold, it can be determined that the signal to be detected is abnormal; on the contrary, if the error between the level conversion time and the normal level conversion time is not greater than the first threshold, and the error between the level conversion interval time and the normal level conversion interval time is not greater than the second threshold, it can be determined that the signal to be detected is normal. In this way, the baseboard management controller can determine whether the signal to be detected is abnormal according to the form of the signal to be detected.
[0060] Based on this, the detecting the signal to be detected according to the preset signal parameters may include:
[0061] Step 11: The baseboard management controller obtains the level conversion time of the signal to be detected and the level conversion interval time between two consecutive level conversions of the signal to be detected.
[0062] Step 12: If the error between the level conversion time and the normal level conversion time is greater than the first threshold, or the error between the level conversion interval time and the normal level conversion interval time is greater than the second threshold, it is determined that the signal to be detected is abnormal.
[0063] Step 13: If the error between the level conversion time and the normal level conversion time is not greater than the first threshold, and the error between the level conversion interval time and the normal level conversion interval time is not greater than the second threshold, it is determined that the signal to be detected is normal.
[0064] It should be noted that the embodiments of the present invention do not limit the specific values of the first threshold and the second threshold, which can be set according to actual application requirements.
[0065] Furthermore, if it is determined that the signal to be detected is abnormal, it indicates that the reliability of the signal to be detected is poor, and the hardware expansion module may have false alarms. At this time, the baseboard management controller needs to recheck with the hardware expansion module. Specifically, since the hardware expansion module sets corresponding registers for each type of signal, and the register value stored in the register is used to indicate how the hardware expansion module reports feedback signals to the baseboard management controller, the baseboard management controller can obtain the register value corresponding to the signal to be detected from the hardware expansion module, and determine whether the logical meaning of the signal to be detected is consistent with the logical meaning of the register value.
[0066] For example, if the signal to be detected is a shutdown signal, and the logical meaning of the signal to be detected is shutdown, the baseboard management controller can obtain the register value related to the shutdown signal from the hardware expansion module, and determine whether the logical meaning of the register value is also shutdown. If the logical meaning of the register value is not shutdown, it indicates that the hardware expansion module has false alarms. On the contrary, if the register value indicates shutdown, it means that the hardware expansion module does not have false alarms, but only the signal fluctuates under the interference of external factors. Furthermore, when it is determined that the logical meaning of the signal to be detected is consistent with the logical meaning of the register value, the baseboard management controller can respond normally, such as controlling the server to shut down; when it is determined that the logical meaning of the signal to be detected is inconsistent with the logical meaning of the register value, the baseboard management controller should not respond.
[0067] S203. If the logical meaning of the signal to be detected is consistent with the logical meaning of the register value, respond to the signal to be detected.
[0068] As described above, when it is determined that the logical meaning of the signal to be detected is consistent with the logical meaning of the register value, it indicates that the hardware expansion module does not have false alarms, but only the signal it emits fluctuates under the interference of external factors. Therefore, the baseboard management controller can respond normally.
[0069] Further, since the interference of external factors on the signal may be persistent, in order to avoid repeatedly determining that the signal sent by the hardware expansion module is an abnormal signal, when it is determined in this time that the logical meaning of the signal to be detected is consistent with the logical meaning of the register value, the baseboard management controller can update the preset signal parameters by using the signal parameters of the signal to be detected, so as to detect the signals subsequently sent by the hardware expansion module according to the updated preset signal parameters.
[0070] Based on this, after determining that the logical meaning of the signal to be detected is consistent with the logical meaning of the register value, it may further include:
[0071] Step 21: The baseboard management controller updates the preset signal parameters by using the signal parameters of the signal to be detected, so as to detect the signals subsequently sent by the hardware expansion module according to the updated preset signal parameters.
[0072] It should be noted that the embodiments of the present invention do not limit the specific update method. For example, the signal parameters of the signal to be detected can be directly added to the preset signal parameters, that is, the preset signal parameters may include multiple groups of parameters; or the corresponding values in the preset signal parameters can be replaced by using the signal parameters of the signal to be detected, which can be set according to actual application requirements.
[0073] S204. If the logical meaning of the signal to be detected is inconsistent with the logical meaning of the register value, the signal to be detected is not responded to.
[0074] As described above, when it is determined that the logical meaning of the signal to be detected is inconsistent with the logical meaning of the register value, it indicates that there is a false alarm in the hardware expansion module, which may be caused by internal disorders of the hardware expansion module or other devices (such as the central processing unit). At this time, the baseboard management controller will no longer respond to this signal to be detected, thus avoiding misoperation of the server due to signal non-recognition.
[0075] Of course, after determining that the logical meaning of the signal to be detected is inconsistent with the logical meaning of the register value, the baseboard management controller can also output an alarm message or record a log to remind relevant personnel to perform hardware inspection.
[0076] Further, if the baseboard management controller determines that it is a normal signal after detecting the signal to be detected by using the preset signal parameters, the baseboard management controller can normally respond to the signal to be detected.
[0077] Based on this, after detecting the signal to be detected according to the preset signal parameters, it may further include:
[0078] S205. If the baseboard management controller determines that the signal to be detected is normal, it responds to the signal to be detected.
[0079] Based on the above embodiments, when the baseboard management controller in the present invention receives a signal sent by the hardware expansion module, it does not immediately respond to the signal. Instead, it first takes the signal as a signal to be detected and obtains the preset signal parameters corresponding to the signal to be detected. Subsequently, the baseboard management controller can detect the signal to be detected according to the preset signal parameters to determine whether the signal form of the signal to be detected is abnormal. If it is determined that the signal to be detected is abnormal, in order to determine whether it is a problem of waveform distortion of a normal signal caused by circuit design or external interference, the baseboard management controller can also obtain the register value corresponding to the signal to be detected from the hardware expansion module and determine whether the logical meaning of the signal to be detected is consistent with the logical meaning of the register value. If the logical meaning of the signal to be detected is consistent with the logical meaning of the register value, it responds to the signal to be detected. If the logical meaning of the signal to be detected is inconsistent with the logical meaning of the register value, it does not respond to the signal to be detected. In this way, the baseboard management controller can actively detect and effectively process abnormal signals, avoid incorrect responses, and thus improve the running stability of the server.
[0080] Based on the above embodiments, since the signals sent by other devices to the hardware expansion module may also be incorrect, if the hardware expansion module directly feeds back the incorrect signal to the baseboard management controller, it is also likely to cause errors. Therefore, in the embodiments of the present invention, the hardware expansion module can also detect the signals sent by other devices and only feed back to the baseboard management controller when it determines that the signals are normal. The processing flow of the hardware expansion module will be introduced below. Before the baseboard management controller takes the signal input by the hardware expansion module as a signal to be detected, the method may further include:
[0081] S301. The hardware expansion module takes the timing signal sent by the data source device as the timing signal to be detected and obtains the preset timing information corresponding to the timing signal to be detected; wherein, the data source device is the central processing unit or a device connected to the hardware expansion module through the general-purpose input / output interface.
[0082] In this step, when the hardware expansion module receives the timing signal sent by the data source device (such as the central processing unit or a device connected to the hardware expansion module through the general-purpose input / output interface), it also does not immediately respond to the timing signal. Instead, it can first take the signal as the timing signal to be detected and obtain the preset timing information corresponding to the timing signal to be detected, so as to detect the timing signal to be detected by using the preset timing information.
[0083] It should be noted that the embodiments of the present invention do not limit specific preset timing information, and relevant technologies of timing signals can be referred to, such as signal transmission timing, software operation timing, etc.
[0084] S302. Detect the to-be-detected timing signal by using the preset timing information, and determine whether the signal timing of the to-be-detected timing signal is correct. If it is correct, go to step S303; if it is incorrect, go to step S304.
[0085] In this step, the hardware extension module will detect the to-be-detected timing signal by using the preset timing information, and determine whether the signal timing of the to-be-detected timing signal is correct. If it is correct, the hardware extension module can respond normally; otherwise, the hardware extension module cannot respond to this timing signal.
[0086] S303. Adjust the register value according to the to-be-detected timing signal, and send a reporting signal to the baseboard management controller according to the register value.
[0087] In this step, when it is determined that the signal timing of the to-be-detected timing signal is normal, the hardware extension module can respond normally, that is, adjust the relevant register value, and send a reporting signal to the baseboard management controller according to the updated register value, so as to transfer the change of the hardware information to the baseboard management controller.
[0088] S304. Determine that the to-be-detected timing signal is abnormal, shield the to-be-detected timing signal, and send an abnormal signal to the basic management controller.
[0089] In this step, when it is determined that the signal timing of the to-be-detected timing signal is abnormal, the hardware extension module cannot respond to this signal, and needs to actively shield this timing signal, and send an abnormal signal to the basic management controller to prompt that there is disorder in the underlying signal transmission of the basic management controller.
[0090] S305. When the baseboard management controller receives the abnormal signal, output a preset alarm message indicating that the hardware extension module encounters signal disorder.
[0091] In this step, when the baseboard management controller receives the abnormal signal, it outputs a preset alarm message indicating that the hardware extension module encounters signal disorder to remind relevant personnel to perform hardware troubleshooting in time. In this way, the hardware extension module can actively detect the underlying signal disorder situation and can actively report the underlying signal disorder situation, so as to effectively ensure the normal operation of the server.
[0092] Based on the above embodiments, considering that the stable operation of the Basic Input / Output System (BIOS) is also crucial for the stable operation of the server. Especially during the initialization phase of the server, the normal startup of the basic input output system and the timely transmission of initialization signals to the Baseboard Management Controller are of great significance for ensuring the normal operation of the server. However, affected by the basic input output system itself and the signal link, it may not be able to correctly and timely transmit the initialization signal to the Baseboard Management Controller, thus affecting the monitoring of the system by the Baseboard Management Controller. Therefore, in the embodiments of the present invention, when the Baseboard Management Controller determines that the basic input output system cannot correctly transmit the initialization signal, it can also actively obtain the device status of the system to determine the cause of the failure. For ease of understanding, please refer to Figure 3 , Figure 3 FIG. Figure 3 is a structural block diagram of a second signal anomaly handling system provided by an embodiment of the present invention. The system may further include a basic input output system, where the basic input output system is directly connected to the Baseboard Management Controller through a Serial Peripheral Interface (SPI), and indirectly connected through a Central Processing Unit and a PCIe bus. The basic input output system may also be connected to the Central Processing Unit through the SPI bus. The method may further include:
[0093] S401. When performing an initialization operation, the basic input output system sends an initialization signal to the Baseboard Management Controller through a serial peripheral interface.
[0094] In this step, when the basic input output system normally performs an initialization operation, it can send an initialization signal to the Baseboard Management Controller through a serial peripheral interface. This initialization signal represents the status of the basic input output system performing the initialization operation. It should be noted that the embodiments of the present invention do not limit the specific initialization signal, and relevant technologies of the basic input output system can be referred to.
[0095] S402. The Baseboard Management Controller waits to receive the initialization signal input by the basic input output system and determines whether the waiting duration of the initialization signal reaches a preset duration.
[0096] In this step, affected by the basic input output system and the SPI bus, the Baseboard Management Controller may not be able to receive the initialization signal input by the basic input output system in a timely manner. To avoid waiting for too long, during the waiting process, the Baseboard Management Controller can also actively determine whether the waiting duration for receiving this initialization signal reaches a preset duration. If it is greater, it is necessary to detect the basic input output system and the link; if it is not greater, it can continue to wait.
[0097] S403. If the waiting duration reaches the preset duration, the baseboard management controller obtains the device status from the basic input / output system via the Peripheral Component Interconnect Express (PCIe) bus, and determines whether the device status is normal.
[0098] It can be understood that if the waiting duration reaches the preset duration, it means that the basic input / output system cannot communicate with the baseboard management controller via the Serial Peripheral Interface (SPI) bus normally. Therefore, the baseboard management controller can indirectly obtain the device status from the basic input / output system via the Peripheral Component Interconnect Express (PCIe) bus provided by the central processing unit, and determine whether the device status is normal. The device status represents the working status of the basic input / output system itself.
[0099] It should be noted that the embodiments of the present invention do not limit the specific device status, and relevant technologies of the basic input / output system can be referred to.
[0100] It should also be noted that the embodiments of the present invention do not limit the specific process of the baseboard management controller obtaining the device status from the basic input / output system via the Peripheral Component Interconnect Express (PCIe) bus. For example, the baseboard management controller can be connected to the server motherboard as a PCIe device, and a video memory space can be set inside the baseboard management controller to meet its own needs. The basic input / output system needs to boot the initialization of the PCIe device, that is, the basic input / output system can communicate with the PCIe device. Therefore, the basic input / output system can actively write the device status into the video memory space of the baseboard management controller via the Peripheral Component Interconnect Express (PCIe) bus, and the baseboard management controller can obtain the device status in its own video memory space.
[0101] Based on this, obtaining the device status from the baseboard management controller via the Peripheral Component Interconnect Express (PCIe) bus may include:
[0102] Step 31: The basic input / output system writes the device status into the video memory space of the baseboard management controller via the Peripheral Component Interconnect Express (PCIe) bus;
[0103] Step 32: The baseboard management controller obtains the device status in its own video memory space.
[0104] S404. If the device status is normal, the baseboard management controller determines that the communication link is abnormal.
[0105] If it is determined that the device status is normal, it means that the signal transmission delay is caused by the communication link. At this time, the baseboard management controller can continue to wait or output an alarm signal to prompt relevant personnel to check in time.
[0106] S405. If the device status is abnormal, the baseboard management controller determines that the basic input / output system is abnormal.
[0107] If it is determined that the device status is abnormal, it indicates that the signal transmission delay is caused by the basic input / output system. At this time, the baseboard management controller can output an alarm signal to prompt relevant personnel to promptly troubleshoot the faults of the basic input / output system.
[0108] Based on the above embodiments, since the high-load operation of the server easily causes signal disorders, thereby affecting its own operation, the baseboard management controller in the embodiments of the present invention can also collect the power consumption value of the server where it is located and actively prompt for abnormal situations of the power consumption value. Based on this, the method can further include:
[0109] S501. The baseboard management controller continuously collects the power consumption value of the server where it is located and determines whether the power consumption value is greater than a third threshold or whether the change value of the power consumption value is greater than a fourth threshold.
[0110] In this step, the baseboard management controller will continuously collect the power consumption value of the server where it is located and determine whether the power consumption value is greater than a third threshold, or whether the change value of the power consumption value is greater than a fourth threshold, so as to determine whether the server power consumption is too high or whether the power consumption value of the server has a jump.
[0111] It should be noted that the embodiments of the present invention do not limit the specific values of the third threshold and the fourth threshold, which can be set according to actual application requirements.
[0112] S502. If the power consumption value is greater than the third threshold or the change value is greater than the fourth threshold, output a preset alarm message indicating that the signal anomaly processing system is unstable.
[0113] When it is determined that the power consumption value is greater than the third threshold or the change value is greater than the fourth threshold, the baseboard management controller can output a preset alarm message indicating that the signal anomaly processing system is unstable, thereby reminding relevant personnel to pay attention to the unstable situation of the server.
[0114] Next, the signal anomaly processing system, computer program product, and computer-readable storage medium provided by the embodiments of the present invention are introduced. The signal anomaly processing system, computer program product, and computer-readable storage medium described below can be mutually corresponded and referred to the signal anomaly processing method described above.
[0115] Please refer to Figure 1 , Figure 1 which is a structural block diagram of a signal anomaly processing system provided by an embodiment of the present invention. This signal anomaly processing system includes: a baseboard management controller and a hardware expansion module;
[0116] The hardware expansion module is used to expand the functions of the central processing unit and the general input / output interface;
[0117] The baseboard management controller is used to take the signal input by the hardware expansion module as a signal to be detected, and obtain a preset signal parameter corresponding to the signal to be detected; detect the signal to be detected according to the preset signal parameter. If it is determined that the signal to be detected is abnormal, obtain the register value corresponding to the signal to be detected from the hardware expansion module, and determine whether the logical meaning of the signal to be detected is consistent with the logical meaning of the register value; if the logical meaning of the signal to be detected is consistent with the logical meaning of the register value, respond to the signal to be detected; if the logical meaning of the signal to be detected is inconsistent with the logical meaning of the register value, do not respond to the signal to be detected.
[0118] Optionally, the hardware expansion module is a complex programmable logic device or a field programmable gate array.
[0119] Optionally, the baseboard management controller is further used for:
[0120] If it is determined that the signal to be detected is normal, respond to the signal to be detected.
[0121] Optionally, the baseboard management controller is further used for:
[0122] Update the preset signal parameter by using the signal parameter of the signal to be detected, so as to detect the signal subsequently sent by the hardware expansion module according to the updated preset signal parameter.
[0123] Optionally, the baseboard management controller is further used for:
[0124] Obtain the level conversion time of the signal to be detected and the level conversion interval time between two consecutive level conversions of the signal to be detected;
[0125] If the error between the level conversion time and the normal level conversion time is greater than the first threshold, or the error between the level conversion interval time and the normal level conversion interval time is greater than the second threshold, it is determined that the signal to be detected is abnormal;
[0126] If the error between the level conversion time and the normal level conversion time is not greater than the first threshold, and the error between the level conversion interval time and the normal level conversion interval time is not greater than the second threshold, it is determined that the signal to be detected is normal.
[0127] Optionally, the baseboard management controller is further used for:
[0128] Collect the power consumption value of the server where it is located in real time, and determine whether the power consumption value is greater than a third threshold or whether the change value of the power consumption value is greater than a fourth threshold;
[0129] If the power consumption value is greater than the third threshold, or the change value is greater than the fourth threshold, then output a preset warning message indicating that the signal anomaly handling system is unstable.
[0130] Optionally, the hardware expansion module is configured to use the timing signal sent by the data source device as the timing signal to be detected, and obtain the preset timing information corresponding to the timing signal to be detected; wherein, the data source device is the central processing unit or a device connected to the hardware expansion module through the general purpose input / output interface; use the preset timing information to detect the timing signal to be detected, and determine whether the signal timing of the timing signal to be detected is correct; if correct, adjust the register value according to the timing signal to be detected, and send a reporting signal to the baseboard management controller according to the register value; if incorrect, determine that the timing signal to be detected is abnormal, shield the timing signal to be detected, and send an abnormal signal to the basic management controller;
[0131] The baseboard management controller is further configured to, when receiving the abnormal signal, output a preset warning message indicating that the hardware expansion module encounters signal disorder.
[0132] Optionally, please refer to Figure 3 The signal anomaly handling system further includes a basic input / output system, which is configured to: when performing an initialization operation, send an initialization signal to the baseboard management controller through a serial peripheral interface;
[0133] The baseboard management controller is further configured to wait for receiving the initialization signal input by the basic input / output system, and determine whether the waiting duration of the initialization signal reaches a preset duration; if the waiting duration reaches the preset duration, the baseboard management controller obtains the device status from the basic input / output system through a high-speed serial computer expansion bus, and determines whether the device status is normal; if the device status is normal, the baseboard management controller determines that the communication link is abnormal; if the device status is abnormal, the baseboard management controller determines that the basic input / output system is abnormal.
[0134] Optionally, the basic input / output system is further configured to write the device status into the video memory space of the baseboard management controller through the high-speed serial computer expansion bus;
[0135] The baseboard management controller is further configured to obtain the device status in its own video memory space.
[0136] Further, for ease of understanding the communication methods between devices and modules, please refer to Figure 4 , Figure 4 FIG. Figure 4 is a structural block diagram of a third signal anomaly processing system provided by an embodiment of the present invention. This figure shows the communication methods between devices and modules in the signal anomaly processing system, and also shows the communication methods between devices and modules in the signal anomaly processing system and the central processing unit.
[0137] An embodiment of the present invention further provides a server, including the signal anomaly processing system described above.
[0138] Since the embodiments of the server part correspond to the embodiments of the signal anomaly processing method part, please refer to the description of the embodiments of the signal anomaly processing method part for the embodiments of the server part, which will not be elaborated here.
[0139] An embodiment of the present invention further provides a computer program product, including a computer program / instructions. When the computer program / instructions are executed by a processor, the signal anomaly processing method described in the above embodiments is implemented.
[0140] Since the embodiments of the computer program product part correspond to the embodiments of the signal anomaly processing method part, please refer to the description of the embodiments of the signal anomaly processing method part for the embodiments of the computer program product part, which will not be elaborated here.
[0141] An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the signal anomaly processing method described in the above embodiments is implemented.
[0142] Since the embodiments of the computer-readable storage medium part correspond to the embodiments of the signal anomaly processing method part, please refer to the description of the embodiments of the signal anomaly processing method part for the embodiments of the storage medium part, which will not be elaborated here.
[0143] The embodiments in the specification are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the description in the method part.
[0144] Those skilled in the art may further realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described according to functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods for each specific application to implement the described functions, but such implementation should not be considered as exceeding the scope of the present invention.
[0145] The steps of the methods or algorithms described in combination with the embodiments disclosed herein can be directly implemented by hardware, software modules executed by a processor, or a combination of the two. The software modules can be placed in a random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.
[0146] The signal anomaly processing method, signal anomaly processing system, server, and storage medium provided by the present invention have been introduced in detail above. Specific examples are used herein to illustrate the principles and implementation manners of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and modifications can be made to the present invention, and these improvements and modifications also fall within the protection scope of the present invention.
Claims
1. A signal abnormality processing method, characterized in that: Applied to a signal abnormality processing system, the signal abnormality processing system includes a baseboard management controller and a hardware expansion module, the hardware expansion module is used to expand the functions of a central processing unit and a general input and output interface, and the method includes: The baseboard management controller uses the signal input by the hardware expansion module as a signal to be detected, and obtains a preset signal parameter corresponding to the signal to be detected; Detecting the signal to be detected according to the preset signal parameters, and if it is determined that the signal to be detected is abnormal, obtaining a register value corresponding to the signal to be detected from the hardware expansion module, and determining whether the logical meaning of the signal to be detected is consistent with the logical meaning of the register value; If the logic meaning of the signal to be detected is consistent with the logic meaning of the register value, responding to the signal to be detected; If the logic meaning of the signal to be detected is inconsistent with the logic meaning of the register value, no response is made to the signal to be detected.
2. The signal abnormality processing method according to claim 1, characterized in that: After detecting the signal to be detected according to the preset signal parameter, the method further includes: If the baseboard management controller determines that the signal to be detected is normal, the baseboard management controller responds to the signal to be detected.
3. The signal abnormality processing method according to claim 1, characterized in that: After determining that the logic meaning of the signal to be detected is consistent with the logic meaning of the register value, the method further includes: The baseboard management controller updates the preset signal parameters using the signal parameters of the signal to be detected, so as to detect the signal subsequently sent by the hardware expansion module according to the updated preset signal parameters.
4. The signal abnormality processing method according to claim 1, characterized in that: The detecting the signal to be detected according to the preset signal parameter includes: The baseboard management controller acquires the level conversion time of the signal to be detected and the level conversion interval time between two consecutive level conversions of the signal to be detected; If the error between the level conversion time and the normal level conversion time is greater than a first threshold, or the error between the level conversion interval time and the normal level conversion interval time is greater than a second threshold, then determining that the signal to be detected is abnormal; If the error between the level conversion time and the normal level conversion time is not greater than a first threshold, and the error between the level conversion interval time and the normal level conversion interval time is not greater than a second threshold, it is determined that the signal to be detected is normal.
5. The signal abnormality processing method according to claim 1, characterized in that: Also includes: The baseboard management controller collects the power consumption value of the server where the baseboard management controller is located in real time, and determines whether the power consumption value is greater than a third threshold or whether a change value of the power consumption value is greater than a fourth threshold; If the power consumption value is greater than the third threshold, or the change value is greater than the fourth threshold, a preset alarm message indicating that the signal abnormality processing system is unstable is output.
6. The signal abnormality processing method according to any one of claims 1 to 5, characterized in that: Before the baseboard management controller uses the signal input by the hardware expansion module as a signal to be detected, the method further includes: The hardware expansion module uses the timing signal sent by the data source device as the timing signal to be detected, and obtains the preset timing information corresponding to the timing signal to be detected; wherein the data source device is the central processing unit or a device connected to the hardware expansion module through the general input and output interface; Using the preset timing information to detect the timing signal to be detected, and determining whether the signal timing of the timing signal to be detected is correct; If correct, adjusting the register value according to the timing signal to be detected, and sending a reporting signal to the baseboard management controller according to the register value; If it is incorrect, determining that the timing signal to be detected is abnormal, shielding the timing signal to be detected, and sending an abnormal signal to the basic management controller; When receiving the abnormal signal, the baseboard management controller outputs preset alarm information indicating that the hardware expansion module encounters signal disorder.
7. The signal abnormality processing method according to any one of claims 1 to 5, characterized in that: The signal abnormality processing system further includes a basic input and output system, and the method further includes: When the basic input and output system performs the initialization operation, the basic input and output system sends an initialization signal to the baseboard management controller through the serial peripheral device interface; The baseboard management controller waits to receive the basic input and output system input initialization signal, and determines whether the waiting time of the initialization signal reaches a preset time; If the waiting time reaches the preset time, the baseboard management controller obtains the device status from the basic input and output system through the high-speed serial computer expansion bus, and determines whether the device status is normal; If the device status is normal, the baseboard management controller determines that the communication link is abnormal; If the device status is abnormal, the baseboard management controller determines that the basic input and output system is abnormal.
8. A signal abnormality processing system, characterized in that: include: Baseboard management controller and hardware expansion modules; The hardware expansion module is used to expand the functions of the central processing unit and the general input and output interface; The baseboard management controller is used to take the signal input by the hardware expansion module as a signal to be detected, and obtain preset signal parameters corresponding to the signal to be detected; detect the signal to be detected according to the preset signal parameters, and if it is determined that the signal to be detected is abnormal, obtain the register value corresponding to the signal to be detected from the hardware expansion module, and judge whether the logical meaning of the signal to be detected is consistent with the logical meaning of the register value; if the logical meaning of the signal to be detected is consistent with the logical meaning of the register value, respond to the signal to be detected; if the logical meaning of the signal to be detected is inconsistent with the logical meaning of the register value, do not respond to the signal to be detected.
9. The signal abnormality processing system according to claim 8, characterized in that: The hardware expansion module is a complex programmable logic device or a field programmable gate array.
10. A server, characterized in that: It comprises the signal abnormality processing system as described in claim 8 or 9.
11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are loaded and executed by the processor, the signal exception processing method according to any one of claims 1 to 7 is implemented.
Citation Information
Cited By
Controller function abnormity dynamic repair method, system, equipment, medium and product
CN120353636A
Method, system, equipment, medium and product for dynamic repair of controller function abnormality
CN120353636B
End point detection and response method and electronic equipment
CN121051737A
Endpoint detection and response method, electronic device
CN121051737B