Server hardware fault diagnosis method, electronic device and storage medium

Abstract

The application discloses a kind of server hardware fault diagnosis method, electronic equipment and storage medium, it is related to server fault diagnosis technical field, including to hardware failure feature information and hardware failure associated feature information are space-time alignment processing, obtain the hardware failure feature information after alignment and the hardware failure associated feature information after alignment;Then, according to the hardware failure feature information after alignment and the hardware failure associated feature information after alignment in hardware failure associated diagnostic rule base are inquired, obtain the query result;Finally, in response to the query result being target hardware failure associated diagnostic rule, according to the hardware failure feature information after alignment, the hardware failure associated feature information after alignment and target hardware failure associated diagnostic rule carry out hardware fault diagnosis, obtain the first server hardware fault diagnosis result, solve the technical problem of low efficiency or low accuracy, reach the technical effect that the accuracy of server hardware fault diagnosis is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of server fault diagnosis, and in particular to a server hardware fault diagnosis method, an electronic device and a storage medium. BACKGROUND

[0002] Servers have been widely used in various fields of social life, and are mainly used for processing critical businesses. System data loss or server abnormal shutdown will cause serious consequences to related fields. Therefore, high availability is required for servers, and high availability requires efficient fault monitoring, fault diagnosis, fault recovery and other technologies to achieve.

[0003] However, the current server hardware fault diagnosis has problems such as low efficiency or low accuracy. SUMMARY

[0004] The present application provides a server hardware fault diagnosis method, an electronic device and a storage medium to at least solve the problem of low efficiency or low accuracy in related technologies.

[0005] In a first aspect, the present application provides a server hardware fault diagnosis method, comprising:

[0006] Obtaining hardware fault feature information monitored by a baseboard management controller and hardware fault association feature information monitored by an operating system;

[0007] Performing space-time alignment processing on the hardware fault feature information and the hardware fault association feature information to obtain aligned hardware fault feature information and aligned hardware fault association feature information;

[0008] According to the aligned hardware fault feature information and the aligned hardware fault association feature information, querying in a hardware fault association diagnosis rule library to obtain a query result;

[0009] In response to the query result being a target hardware fault association diagnosis rule, performing hardware fault diagnosis according to the aligned hardware fault feature information, the aligned hardware fault association feature information and the target hardware fault association diagnosis rule to obtain a first server hardware fault diagnosis result.

[0010] In one of the embodiments, obtaining the hardware fault feature information monitored by the baseboard management controller and the hardware fault association feature information monitored by the operating system comprises: obtaining hardware sensor data, system event logs and hardware error codes of the baseboard management controller; performing feature extraction processing on the hardware sensor data, the system event logs and the hardware error codes to obtain the hardware fault feature information.

[0011] In one of the embodiments, the obtaining the hardware fault feature information monitored by the baseboard management controller and the hardware fault correlation feature information monitored by the operating system further comprises: in response to receiving the fault event reporting request sent by the operating system, sending the receiving fault event data feedback to the operating system according to the fault event reporting request; in response to receiving the fault event data sent by the operating system, sending the fault event data has been received feedback to the operating system according to the fault event data; and performing log structured processing on the fault event data according to a preset data format to obtain the hardware fault correlation feature information.

[0012] In one of the embodiments, before the sending the receiving fault event data feedback to the operating system according to the fault event reporting request in response to receiving the fault event reporting request sent by the operating system, the method further comprises:

[0013] In response to the construction operation of the data transmission channel of the baseboard management controller and the operating system, a virtual universal serial bus data transmission channel between the baseboard management controller and the operating system is established according to the result of the construction operation.

[0014] In one of the embodiments, the first server hardware fault diagnosis result comprises a hardware fault component, a hardware fault time and a hardware fault type; and the method further comprises: inputting the hardware fault component, the hardware fault time and the hardware fault type into a fault grading engine to obtain a hardware fault level; in response to the hardware fault level being less than a level threshold, querying the hardware fault type in a hardware fault repair strategy library to obtain a target hardware fault repair strategy; and performing an automatic repair operation according to the target hardware fault repair strategy.

[0015] In one of the embodiments, the method further comprises: in response to the hardware fault level being greater than or equal to the level threshold, generating a hardware fault repair prompt information according to the hardware fault component, the hardware fault time, the hardware fault type and the hardware fault level; and performing a fault repair prompt according to the hardware fault repair prompt.

[0016] In one of the embodiments, the method further comprises: in response to the query result being empty, inputting the aligned hardware fault feature information and the aligned hardware fault correlation feature information into a pre-trained hardware fault diagnosis time sequence model to output a second server hardware fault diagnosis result and a confidence of the second server hardware fault diagnosis result; and the second server hardware fault diagnosis result comprises a hardware fault component, a hardware fault time and a hardware fault type.

[0017] In one of the embodiments, the hardware fault correlation feature information comprises hardware state information, hardware component information, system log information, hardware performance index information and hardware process state information.

[0018] In one of the embodiments, the method further comprises:

[0019] In response to the construction operation on the hardware fault correlation diagnosis rule library, generating the hardware fault correlation diagnosis rule library according to the result of the construction operation;

[0020] In response to the setting operation on the hardware fault correlation diagnosis rule, generating the hardware fault correlation diagnosis rule according to the result of the setting operation, and storing the hardware fault correlation diagnosis rule to the hardware fault correlation diagnosis rule library.

[0021] In a second aspect, a server hardware fault diagnosis apparatus is provided, and the apparatus comprises a feature information acquisition module, a space-time alignment processing module, a diagnosis rule query module, and a fault diagnosis module.

[0022] The feature information acquisition module is configured to acquire hardware fault feature information monitored by a baseboard management controller and hardware fault correlation feature information monitored by an operating system. The space-time alignment processing module is configured to perform space-time alignment processing on the hardware fault feature information and the hardware fault correlation feature information, to obtain the aligned hardware fault feature information and the aligned hardware fault correlation feature information. The diagnosis rule query module is configured to perform a query in a hardware fault correlation diagnosis rule library according to the aligned hardware fault feature information and the aligned hardware fault correlation feature information, to obtain a query result. The fault diagnosis module is configured to, in response to the query result being a target hardware fault correlation diagnosis rule, perform hardware fault diagnosis according to the aligned hardware fault feature information, the aligned hardware fault correlation feature information, and the target hardware fault correlation diagnosis rule, to obtain a first server hardware fault diagnosis result.

[0023] In a third aspect, the present application further provides an electronic device, comprising a memory configured to store a computer program, and a processor configured to execute the computer program to implement the steps of any of the server hardware fault diagnosis methods.

[0024] In a fourth aspect, the present application further provides a computer readable storage medium, which stores a computer program, wherein the computer program is executed by a processor to implement the steps of any of the server hardware fault diagnosis methods.

[0025] With the server hardware fault diagnosis method, the electronic device and the storage medium, the hardware fault feature information monitored by the baseboard management controller and the hardware fault correlation feature information monitored by the operating system are acquired; then, the hardware fault feature information and the hardware fault correlation feature information are subjected to space-time alignment processing to obtain aligned hardware fault feature information and aligned hardware fault correlation feature information; then, the aligned hardware fault feature information and the aligned hardware fault correlation feature information are queried in a hardware fault correlation diagnosis rule library to obtain a query result; finally, in response to the query result being a target hardware fault correlation diagnosis rule, hardware fault diagnosis is performed according to the aligned hardware fault feature information, the aligned hardware fault correlation feature information and the target hardware fault correlation diagnosis rule to obtain a first server hardware fault diagnosis result, thus, the technical problem of low efficiency or low accuracy can be solved, the data fragmentation of different hardware fault feature information is avoided, the OS and the BMC are prevented from processing respective fault feature information to cause a lack of deep perception of the hardware fault feature information at the OS level in the server hardware fault diagnosis process, the dimension of the server hardware fault diagnosis is widened, the efficiency, accuracy and convenience of the server hardware fault diagnosis are improved, and the predictability of the server hardware fault diagnosis is improved. BRIEF DESCRIPTION OF DRAWINGS

[0026] In order to more clearly illustrate the embodiments of the present application, the drawings required to be used in the embodiments will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0027] Figure 1 An application environment diagram of the server hardware fault diagnosis method in an embodiment;

[0028] Figure 2 A first flowchart of the server hardware fault diagnosis method in an embodiment;

[0029] Figure 3 A first flowchart of acquiring the hardware fault feature information monitored by the baseboard management controller and the hardware fault correlation feature information monitored by the operating system in an embodiment;

[0030] Figure 4 A second flowchart of acquiring the hardware fault feature information monitored by the baseboard management controller and the hardware fault correlation feature information monitored by the operating system in an embodiment;

[0031] Figure 5 A second flowchart of the server hardware fault diagnosis method in an embodiment;

[0032] Figure 6 Fig. 3 is a third flowchart illustrating a server hardware fault diagnosis method according to an embodiment;

[0033] Figure 7 Fig. 4 is a structural block diagram of a server hardware fault diagnosis apparatus according to an embodiment. DETAILED DESCRIPTION

[0034] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, any other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0035] It should be noted that, in the description of the present application, the terms “comprise”, “contain” or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not explicitly listed, or includes elements inherent to such process, method, article or device. The terms “first”, “second” and the like in the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence.

[0036] The server hardware fault diagnosis method provided by the present application can be applied to an application environment as shown in Figure 1 . In the application environment, the terminal 102 communicates with the server 104 through a network. The terminal 102 can be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers and portable wearable devices, and the server 104 can be implemented by an independent server or a server cluster composed of multiple servers. The server 104 is configured with a baseboard management controller (BMC), an operating system (OS), a central processing unit (CPU), a basic input / output system (BIOS), a complex programmable logic device (CPLD) and a field programmable gate array (FPGA).

[0037] In a first aspect, as shown in Figure 2 , a server hardware fault diagnosis method is provided. The method is applied to the application environment as shown in Figure 1The following steps are used as an example to illustrate the process of using the baseboard management controller in server 104, including steps 201 to 204.

[0038] Step 201: Obtain hardware fault characteristic information monitored by the baseboard management controller and hardware fault association characteristic information monitored by the operating system.

[0039] Among them, the hardware fault characteristic information is the hardware characteristic information required for hardware fault diagnosis. The hardware fault association characteristic information is the hardware association characteristic information required for hardware fault diagnosis. Specifically, the baseboard management controller in server 104 obtains the hardware fault characteristic information monitored by the baseboard management controller and the hardware fault association characteristic information monitored by the operating system.

[0040] In one embodiment, such as Figure 3 As shown, the process of obtaining hardware fault characteristic information monitored by the baseboard management controller and hardware fault related characteristic information monitored by the operating system includes steps 301 to 302.

[0041] Step 301: Obtain hardware sensor data, system event logs, and hardware error codes from the baseboard management controller.

[0042] Step 302: Perform feature extraction processing on hardware sensor data, system event logs, and hardware error codes to obtain hardware fault feature information.

[0043] Specifically, the baseboard management controller in server 104 acquires hardware sensor data, system event logs, and hardware error codes from the baseboard management controller; then, it performs feature extraction processing on the hardware sensor data, system event logs, and hardware error codes to obtain hardware fault feature information, thereby improving the accuracy, efficiency, and convenience of acquiring hardware fault feature information.

[0044] In a specific example, hardware sensor data may include, but is not limited to, temperature, power consumption, and ECC errors. The baseboard management controller may, but is not limited to, employ wavelet transform feature extraction algorithms to extract features from hardware sensor data, system event (SEL) logs, and hardware error codes to obtain hardware fault feature information. The above is only a specific example, and in actual applications, it can be flexibly configured according to user needs, without any restrictions.

[0045] In this embodiment, hardware sensor data, system event logs, and hardware error codes of the baseboard management controller are acquired. Then, feature extraction processing is performed on the hardware sensor data, system event logs, and hardware error codes to obtain hardware fault feature information, thereby improving the accuracy and efficiency of acquiring hardware fault feature information.

[0046] In one embodiment, such as Figure 4As shown, the obtaining the hardware fault feature information monitored by the baseboard management controller and the hardware fault correlation feature information monitored by the operating system further includes steps 401 to 403.

[0047] Step 401, in response to receiving the fault event reporting request sent by the operating system, sending the receiving fault event data feedback to the operating system according to the fault event reporting request.

[0048] Specifically, the baseboard management controller in the server 104, in response to receiving the fault event reporting request sent by the operating system, sends the receiving fault event data feedback to the operating system according to the fault event reporting request, so as to timely notify the baseboard management controller that it has made preparations for receiving the fault event data according to the receiving fault event data feedback.

[0049] In one of the embodiments, as shown, before responding to receiving the fault event reporting request sent by the operating system and sending the receiving fault event data feedback to the operating system according to the fault event reporting request, step 400 is further included. Figure 4

[0050] Step 400, in response to the construction operation of the data transmission channel between the baseboard management controller and the operating system, establishing a virtual Universal Serial Bus (USB) data transmission channel between the baseboard management controller and the operating system according to the result of the construction operation.

[0051] Specifically, the baseboard management controller in the server 104, in response to the construction operation of the data transmission channel between the baseboard management controller and the operating system, establishes a virtual Universal Serial Bus (USB) data transmission channel between the baseboard management controller and the operating system according to the result of the construction operation, so as to facilitate data transmission between the BMC and the OS, and avoid the fault diagnosis data between the BMC and the OS being mutually fragmented.

[0052] In one specific example, the virtual Universal Serial Bus (USB) data transmission channel can be, but is not limited to, an encrypted data transmission link established by the Redfish API and the OS agent. The above is only a specific example, and in actual application, it is flexibly set according to user demand, which is not limited here.

[0053] In this embodiment, in response to the construction operation of the data transmission channel between the baseboard management controller and the operating system, a virtual Universal Serial Bus (USB) data transmission channel is established between the baseboard management controller and the operating system according to the result of the construction operation, so as to facilitate data transmission between the BMC and the OS, and avoid the fault diagnosis data between the BMC and the OS being mutually fragmented.​

[0054] At step 402, in response to receiving the fault event data sent by the operating system, the fault event data is sent to the operating system according to the fault event data that the feedback has been received.

[0055] At step 403, the fault event data is log-structured according to a preset data format, and hardware fault correlation characteristic information is obtained.

[0056] Specifically, the baseboard management controller in the server 104, in response to receiving the fault event data sent by the operating system, sends the fault event data to the operating system according to the fault event data that the feedback has been received; and then, the fault event data is log-structured according to a preset data format, and hardware fault correlation characteristic information is obtained, which improves the accuracy and efficiency of obtaining the hardware fault correlation characteristic information.

[0057] In this embodiment, in response to receiving the fault event reporting request sent by the operating system, the fault event data is sent to the operating system according to the fault event reporting request that the feedback has been received; then, in response to receiving the fault event data sent by the operating system, the fault event data is sent to the operating system according to the fault event data that the feedback has been received; and then, the fault event data is log-structured according to a preset data format, and hardware fault correlation characteristic information is obtained, which improves the accuracy and efficiency of obtaining the hardware fault correlation characteristic information.

[0058] In one of the embodiments, the hardware fault correlation characteristic information includes hardware state information, hardware component information, system log information, hardware performance index information, and hardware process state information; the above-mentioned rich hardware fault correlation characteristic information improves the accuracy of server hardware fault diagnosis.

[0059] In one specific example, the hardware state information can include but is not limited to DMA transmission error and hardware interrupt frequency obtained in real time based on eBPF technology; the hardware component information can include but is not limited to PCIE information and raid information; the system log information can include but is not limited to / var / log / messages log file in the Linux system; the hardware performance index information can include but is not limited to CPU utilization and memory utilization; and the hardware process state information can include but is not limited to running state, blocking state, and suspension state; the above are only specific examples, and in actual application, they are flexibly set according to user needs, which are not limited herein.

[0060] At step 202, the hardware fault characteristic information and the hardware fault correlation characteristic information are processed for space-time alignment, and the aligned hardware fault characteristic information and the aligned hardware fault correlation characteristic information are obtained.

[0061] Specifically, the baseboard management controller in the server 104 performs spatio-temporal alignment processing on the hardware fault feature information and the hardware fault correlation feature information, to obtain the aligned hardware fault feature information and the aligned hardware fault correlation feature information, so that the hardware fault feature information and the hardware fault correlation feature information are synchronized in milliseconds, thereby solving the problem of time inconsistency between the hardware fault feature information and the hardware fault correlation feature information, facilitating subsequent hardware fault diagnosis and analysis, and improving the accuracy and efficiency of hardware fault analysis.

[0062] In one specific example, the baseboard management controller in the server 104 adopts a spatio-temporal alignment algorithm with an attention mechanism to perform spatio-temporal alignment processing on the hardware fault feature information and the hardware fault correlation feature information, to obtain the aligned hardware fault feature information and the aligned hardware fault correlation feature information. The spatio-temporal alignment processing process is based on the NTP protocol. The above is only a specific example, and in actual application, it is flexibly set according to user demand, which is not limited here.

[0063] In step 203, the aligned hardware fault feature information and the aligned hardware fault correlation feature information are queried in the hardware fault correlation diagnosis rule library to obtain a query result.

[0064] The query result includes a target hardware fault correlation diagnosis rule or null. It can be understood that the target hardware fault correlation diagnosis rule is a hardware fault correlation diagnosis rule that takes the aligned hardware fault feature information and the aligned hardware fault correlation feature information as rule conditions. When the query result is the target hardware fault correlation diagnosis rule, it indicates that the target hardware fault correlation diagnosis rule exists in the hardware fault correlation diagnosis rule library. When the query result is null, it indicates that the target hardware fault correlation diagnosis rule does not exist in the hardware fault correlation diagnosis rule library.

[0065] Specifically, the baseboard management controller in the server 104 queries the aligned hardware fault feature information and the aligned hardware fault correlation feature information in the hardware fault correlation diagnosis rule library to obtain a query result.

[0066] In one of the embodiments, the method further includes:

[0067] In response to the construction operation on the hardware fault correlation diagnosis rule library, a hardware fault correlation diagnosis rule library is generated according to the result of the construction operation;

[0068] In response to the setting operation on the hardware fault correlation diagnosis rule, a hardware fault correlation diagnosis rule is generated according to the result of the setting operation, and the hardware fault correlation diagnosis rule is stored in the hardware fault correlation diagnosis rule library.

[0069] The above is only a specific example, and in actual application, it can be flexibly set according to user needs, and is not limited herein.

[0070] In one specific example, the specific content of the hardware fault correlation diagnosis rule of the disk failure includes:

[0071] “if BMC.SMART_Error == "MediaError" and OS.dmesg.contains("I / O timeout"):

[0072] return FaultType.DISK_HARD_FAILURE”, the above is only a specific example, and in actual application, it can be flexibly set according to user needs, and is not limited herein.

[0073] In step 204, in response to the query result being the target hardware fault correlation diagnosis rule, hardware fault diagnosis is performed according to the aligned hardware fault feature information, the aligned hardware fault correlation feature information, and the target hardware fault correlation diagnosis rule, to obtain a first server hardware fault diagnosis result.

[0074] Specifically, the baseboard management controller in the server 104, in response to the query result being the target hardware fault correlation diagnosis rule, performs hardware fault diagnosis according to the aligned hardware fault feature information, the aligned hardware fault correlation feature information, and the target hardware fault correlation diagnosis rule, to obtain a first server hardware fault diagnosis result, avoiding data fragmentation of different hardware fault feature information, and also avoiding the lack of deep perception of hardware fault feature information at the OS level in the server hardware fault diagnosis process due to the OS and the BMC respectively processing their own fault feature information, thereby widening the dimension of server hardware fault diagnosis, improving the efficiency, accuracy and convenience of fault diagnosis, and also improving the predictability of server hardware fault diagnosis.

[0075] The server hardware fault diagnosis method obtains hardware fault feature information monitored by a baseboard management controller and hardware fault correlation feature information monitored by an operating system, then performs space-time alignment processing on the hardware fault feature information and the hardware fault correlation feature information to obtain aligned hardware fault feature information and aligned hardware fault correlation feature information, then queries the aligned hardware fault feature information and the aligned hardware fault correlation feature information in a hardware fault correlation diagnosis rule library to obtain a query result, and finally, in response to the query result being a target hardware fault correlation diagnosis rule, performs hardware fault diagnosis according to the aligned hardware fault feature information, the aligned hardware fault correlation feature information, and the target hardware fault correlation diagnosis rule to obtain a first server hardware fault diagnosis result. This avoids data fragmentation of different hardware fault feature information, avoids a lack of deep perception of hardware fault feature information at an OS level in a server hardware fault diagnosis process due to the OS and the BMC processing their respective fault feature information, widens the dimension of server hardware fault diagnosis, improves the efficiency, accuracy, and convenience of fault diagnosis, improves the predictability of server hardware fault diagnosis, and saves human cost and server resources.

[0076] In one of the embodiments, the first server hardware fault diagnosis result includes a hardware fault component, a hardware fault time, and a hardware fault type; and as shown in Figure 5 The method further includes steps 501 to 503.

[0077] Step 501: inputting the hardware fault component, the hardware fault time, and the hardware fault type into a fault grading engine to obtain a hardware fault level.

[0078] Step 502: in response to the hardware fault level being less than a level threshold, querying a hardware fault repair strategy library according to the hardware fault type to obtain a target hardware fault repair strategy.

[0079] Step 503: performing an automatic repair operation according to the target hardware fault repair strategy.

[0080] Specifically, the baseboard management controller in the server 104 inputs the hardware fault component, the hardware fault time, and the hardware fault type into the fault grading engine to obtain a hardware fault level, then in response to the hardware fault level being less than a level threshold, queries the hardware fault repair strategy library according to the hardware fault type to obtain a target hardware fault repair strategy, and finally performs an automatic repair operation according to the target hardware fault repair strategy, which improves the convenience of server hardware fault diagnosis and the automatic repair capability of the server.

[0081] In the embodiment, the hardware fault component, the hardware fault time and the hardware fault type are input to the fault grading engine to obtain a hardware fault level; then, in response to the hardware fault level being less than a level threshold, a target hardware fault repair strategy is obtained by querying the hardware fault repair strategy library according to the hardware fault type; and then, automatic repair operation is performed according to the target hardware fault repair strategy, thereby improving the convenience of server hardware fault diagnosis and the automatic repair capability of the server.

[0082] In one of the embodiments, as shown in Figure 5 The method further includes steps 504 and 505.

[0083] Step 504: in response to the hardware fault level being greater than or equal to the level threshold, hardware fault repair prompt information is generated according to the hardware fault component, the hardware fault time, the hardware fault type and the hardware fault level.

[0084] Step 505: fault repair prompting is performed according to the hardware fault repair prompt.

[0085] Specifically, the baseboard management controller in the server 104 generates hardware fault repair prompt information according to the hardware fault component, the hardware fault time, the hardware fault type and the hardware fault level in response to the hardware fault level being greater than or equal to the level threshold; and then, fault repair prompting is performed according to the hardware fault repair prompt, thereby improving the convenience of server hardware fault diagnosis and the operation safety of the server.

[0086] In the embodiment, hardware fault repair prompt information is generated according to the hardware fault component, the hardware fault time, the hardware fault type and the hardware fault level in response to the hardware fault level being greater than or equal to the level threshold; and then, fault repair prompting is performed according to the hardware fault repair prompt, thereby improving the convenience of server hardware fault diagnosis and the operation safety of the server.

[0087] In one of the embodiments, as shown in Figure 6 The method further includes step 601.

[0088] Step 601: in response to the query result being empty, the aligned hardware fault feature information and the aligned hardware fault associated feature information are input to a pre-trained hardware fault diagnosis time sequence model to output a second server hardware fault diagnosis result and a confidence of the second server hardware fault diagnosis result.

[0089] The second server hardware fault diagnosis result includes a hardware fault component, a hardware fault time and a hardware fault type. Specifically, the baseboard management controller in the server 104, in response to the query result being empty, indicates that there is no target hardware fault correlation diagnosis rule in the hardware fault correlation diagnosis rule library at this time, so the aligned hardware fault feature information and the aligned hardware fault correlation feature information are input into the pre-trained hardware fault diagnosis time sequence model, and the second server hardware fault diagnosis result and the confidence of the second server hardware fault diagnosis result are output, improving the comprehensiveness, accuracy and convenience of the server hardware fault diagnosis.

[0090] In the embodiment, in response to the query result being empty, it is indicated that there is no target hardware fault correlation diagnosis rule in the hardware fault correlation diagnosis rule library at this time, so the aligned hardware fault feature information and the aligned hardware fault correlation feature information are input into the pre-trained hardware fault diagnosis time sequence model, and the second server hardware fault diagnosis result and the confidence of the second server hardware fault diagnosis result are output, improving the comprehensiveness, accuracy and convenience of the server hardware fault diagnosis.

[0091] In one specific example, the obtained hardware sensor data of the baseboard management controller includes memory voltage fluctuation and error correction count of error checking and correcting (ECC); the obtained data of the operating system includes CE / UE technology reported by an error detection and correction (EDAC) unit and memory controller load rate captured based on eBPF technology; at the same time, the obtained hardware fault feature information monitored by the baseboard management controller includes time domain feature information and frequency domain feature information; the time domain feature information includes ECC error growth rate and voltage fluctuation amplitude; the frequency domain feature information includes FFT analysis voltage ripple main frequency; and the obtained hardware fault correlation feature information monitored by the operating system includes error time and temperature / load correlation.

[0092] The spatio-temporal alignment processing is performed on the hardware fault feature information and the hardware fault correlation feature information, so that the aligned hardware fault feature information and the aligned hardware fault correlation feature information are obtained. Then, the aligned hardware fault feature information and the aligned hardware fault correlation feature information are queried in the hardware fault correlation diagnosis rule library to obtain a query result. Then, in response to the query result being empty, the aligned hardware fault feature information and the aligned hardware fault correlation feature information are input into the pre-trained hardware fault diagnosis time sequence model to output a second server hardware fault diagnosis result and a confidence of the second server hardware fault diagnosis result. The hardware fault type in the second server hardware fault diagnosis result is server memory degradation, and the fault component in the second server hardware fault diagnosis result is DIMM3. The confidence of the second server hardware fault diagnosis result is 92%. In addition, the hardware fault repair prompt information is "migrate key data and replace within 72 hours". The above is only a specific example, and in actual application, it is flexibly set according to user needs, which is not limited here.

[0093] Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be realized by means of software and necessary general hardware platform, of course, it can also be realized by hardware, but in many cases, the former is a better embodiment. It should be understood that, although Figures 2-6 The steps in the flowchart of the method are displayed in sequence according to the arrows, but these steps are not necessarily executed in sequence according to the arrows. Unless otherwise stated herein, the execution of these steps has no strict sequence limitation, and these steps can be executed in other orders. Moreover, Figures 2-6 At least part of the steps in the method can include multiple sub-steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily sequential, but can be alternately executed with other steps or sub-steps or stages of other steps.

[0094] In a second aspect, as shown in Figure 7 embodiment, a server hardware fault diagnosis apparatus is provided, which comprises a feature information acquisition module 710, a spatio-temporal alignment processing module 720, a diagnosis rule query module 730, and a fault diagnosis module 740.

[0095] The characteristic information acquisition module 710 is configured to acquire hardware fault characteristic information monitored by a baseboard management controller and hardware fault correlation characteristic information monitored by an operating system.

[0096] In one of the embodiments, the characteristic information acquisition module 710 comprises a first characteristic information acquisition unit.

[0097] The first characteristic information acquisition unit is configured to acquire hardware sensor data, system event logs and hardware error codes of the baseboard management controller, and to perform feature extraction processing on the hardware sensor data, the system event logs and the hardware error codes to obtain the hardware fault characteristic information.

[0098] In one of the embodiments, the characteristic information acquisition module 710 comprises a second characteristic information acquisition unit.

[0099] The second characteristic information acquisition unit is configured to, in response to receiving a fault event reporting request sent by the operating system, send a fault event data receiving feedback to the operating system according to the fault event reporting request, to, in response to receiving fault event data sent by the operating system, send a fault event data received feedback to the operating system according to the fault event data, and to perform log structuring processing on the fault event data according to a preset data format to obtain the hardware fault correlation characteristic information.

[0100] In one of the embodiments, the second characteristic information acquisition unit is further configured to, in response to a construction operation of a data transmission channel of the baseboard management controller and the operating system, establish a virtual universal serial bus data transmission channel between the baseboard management controller and the operating system according to a result of the construction operation.

[0101] In one of the embodiments, the first server hardware fault diagnosis result comprises a hardware fault component, a hardware fault time and a hardware fault type, and the apparatus further comprises an automatic repair module.

[0102] The automatic repair module is configured to input the hardware fault component, the hardware fault time and the hardware fault type into the fault grading engine to obtain a hardware fault level; the automatic repair module is configured to, in response to the hardware fault level being less than a level threshold, query the hardware fault repair strategy library according to the hardware fault type to obtain a target hardware fault repair strategy; and the automatic repair module is configured to perform an automatic repair operation according to the target hardware fault repair strategy.

[0103] In one of the embodiments, the apparatus further includes a repair prompt module.

[0104] The repair prompt module is configured to, in response to the hardware fault level being greater than or equal to the level threshold, generate hardware fault repair prompt information according to the hardware fault component, the hardware fault time, the hardware fault type and the hardware fault level; and the repair prompt module is configured to perform a fault repair prompt according to the hardware fault repair prompt.

[0105] In one of the embodiments, the fault diagnosis module 740 is further configured to, in response to the query result being empty, input the aligned hardware fault feature information and the aligned hardware fault associated feature information into a pre-trained hardware fault diagnosis time sequence model to output a second server hardware fault diagnosis result and a confidence degree of the second server hardware fault diagnosis result; wherein the second server hardware fault diagnosis result includes a hardware fault component, a hardware fault time and a hardware fault type.

[0106] In one of the embodiments, the hardware fault associated feature information includes hardware state information, hardware component information, system log information, hardware performance index information and hardware process state information.

[0107] The specific limitations of the server hardware fault diagnosis apparatus can be referred to the limitations of the server hardware fault diagnosis method in the foregoing, which will not be described herein. Each module in the server hardware fault diagnosis apparatus can be realized by software, hardware and combinations thereof in whole or in part. Each module can be embedded in or independent of a processor in a computer device in hardware form, or can be stored in a memory in a computer device in software form, so as to be called and executed by a processor to perform the operations corresponding to each module.

[0108] From the above description of the embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be realized by means of software and necessary general hardware platform, of course, it can also be realized by hardware, but in many cases, the former is a better embodiment.

[0109] In a third aspect, the present application further provides an electronic device, including: a memory configured to store a computer program; and a processor configured to execute the computer program to implement the steps of any of the above server hardware fault diagnosis methods.

[0110] In a fourth aspect, the present application also provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the steps of any of the server hardware fault diagnosis methods.

[0111] In an example embodiment, the computer readable storage medium can include, but is not limited to, a U disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and various media that can store computer programs.

[0112] In a fifth aspect, the embodiments of the present application also provide a computer program product, which includes a computer program, and the computer program is executed by a processor to implement the steps in any of the server hardware fault diagnosis method embodiments.

[0113] In a sixth aspect, the embodiments of the present application also provide another computer program product, which includes a non-volatile computer readable storage medium, and the non-volatile computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the steps in any of the server hardware fault diagnosis method embodiments.

[0114] Those skilled in the art will further appreciate that the functions of the examples described herein, including any related steps of the methods described herein, can be implemented using electronic hardware, computer software, or any combination of the two. To clearly illustrate this interchangeability of hardware and software, various examples have been described herein generally in terms of their functionality, without necessarily describing the corresponding detailed hardware or software mechanisms that correspond to such functionality. Those skilled in the art will appreciate that the mechanisms that constitute the examples described herein are implemented in both hardware and software, and that the detailed software implementation and the detailed hardware implementation will vary from one implementation to another depending, at least in part, upon the particular application and the overall design constraints imposed on the overall system. Those skilled in the art will recognize the same or equivalent features, steps, or functions described herein as such terms as "means for" performing the described operations, yet will also recognize the mechnisms that constitute the examples described herein are not limited to the corresponding described features, steps or functions named with the term "means for".

[0115] The above provides a server hardware fault diagnosis method, an electronic device and a storage medium. The principles and implementation manners of the present application are described by using specific examples. The above description of the examples is only used to help understand the method and its core idea of the present application. It should be pointed out that, for those skilled in the art, without departing from the principles of the present application, some improvements and modifications can be made to the present application, and these improvements and modifications also fall within the protection scope of the present application.

Claims

1. A server hardware fault diagnosis method, the method comprising: obtaining hardware fault feature information monitored by a baseboard management controller and hardware fault correlation feature information monitored by an operating system; wherein the hardware fault feature information is hardware feature information required for hardware fault diagnosis; and the hardware fault correlation feature information is hardware correlation feature information required for hardware fault diagnosis; performing space-time alignment processing on the hardware fault feature information and the hardware fault correlation feature information to obtain aligned hardware fault feature information and aligned hardware fault correlation feature information; querying the aligned hardware fault feature information and the aligned hardware fault correlation feature information in a hardware fault correlation diagnosis rule library to obtain a query result; in response to the query result being a target hardware fault correlation diagnosis rule, performing hardware fault diagnosis according to the aligned hardware fault feature information, the aligned hardware fault correlation feature information, and the target hardware fault correlation diagnosis rule to obtain a first server hardware fault diagnosis result; wherein the obtaining of the hardware fault feature information monitored by the baseboard management controller and the hardware fault correlation feature information monitored by the operating system further comprises: in response to receiving a fault event reporting request sent by the operating system, sending a fault event data receiving feedback to the operating system according to the fault event reporting request; in response to receiving fault event data sent by the operating system, sending a fault event data received feedback to the operating system according to the fault event data; performing log structuring processing on the fault event data according to a preset data format to obtain the hardware fault correlation feature information.

2. The method of claim 1, wherein, The obtaining of the hardware fault feature information monitored by the baseboard management controller and the hardware fault correlation feature information monitored by the operating system comprises: obtaining hardware sensor data, system event logs, and hardware error codes of the baseboard management controller; performing feature extraction processing on the hardware sensor data, the system event logs, and the hardware error codes to obtain the hardware fault feature information.

3. The method of claim 1, wherein, The method further comprises, before the sending of the fault event data receiving feedback to the operating system according to the fault event reporting request, in response to a construction operation of a data transmission channel of the baseboard management controller and the operating system: in response to the construction operation, establishing a virtual universal serial bus data transmission channel between the baseboard management controller and the operating system according to a result of the construction operation.

4. The method of claim 1, wherein, The first server hardware fault diagnosis result comprises a hardware fault component, a hardware fault time, and a hardware fault type; wherein the method further comprises: inputting the hardware fault component, the hardware fault time, and the hardware fault type into a fault grading engine to obtain a hardware fault level; in response to the hardware fault level being less than a level threshold, querying a hardware fault repair strategy library according to the hardware fault type to obtain a target hardware fault repair strategy; According to the target hardware fault repair strategy, an automatic repair operation is performed.

5. The method of claim 4, wherein, The method further comprises: In response to the hardware fault level being greater than or equal to the level threshold, generating hardware fault repair prompt information according to the hardware fault component, the hardware fault time, the hardware fault type, and the hardware fault level; According to the hardware fault repair prompt, a fault repair prompt is performed.

6. The method of claim 1, wherein, The method further comprises: In response to the query result being empty, inputting the aligned hardware fault feature information and the aligned hardware fault associated feature information into a pre-trained hardware fault diagnosis time sequence model, and outputting a second server hardware fault diagnosis result and a confidence degree of the second server hardware fault diagnosis result; wherein the second server hardware fault diagnosis result comprises a hardware fault component, a hardware fault time, and a hardware fault type.

7. The method of claim 1, wherein, The hardware fault associated feature information comprises hardware state information, hardware component information, system log information, hardware performance index information, and hardware process state information.

8. The method of claim 1, wherein, The method further comprises: In response to a construction operation on the hardware fault associated diagnosis rule library, generating the hardware fault associated diagnosis rule library according to a result of the construction operation; In response to a setting operation on a hardware fault associated diagnosis rule, generating the hardware fault associated diagnosis rule according to a result of the setting operation, and storing the hardware fault associated diagnosis rule into the hardware fault associated diagnosis rule library.

9. An electronic device, comprising: Comprise: a memory for storing a computer program; a processor for executing the computer program to implement the steps of the server hardware fault diagnosis method according to any one of claims 1 to 8.

Images