A BMC reliability test method, device, workstation and storage medium

Abstract

The embodiment of the application provides a BMC reliability test method, device, workstation and storage medium, and relates to the technical field of testing. The method comprises the following steps: in the case that the state of a target server to which a target BMC belongs is normal, a target reading conversion parameter of a target sensor recorded in the target BMC is configured, so that the target BMC converts original readings of the target sensor based on the target reading conversion parameter to obtain first engineering readings; first monitoring data recorded in a target hardware process monitored by the target BMC based on the first engineering readings is acquired; whether the target BMC detects that the target hardware has a fault and whether a corresponding processing strategy is executed after the fault is detected are judged based on the first monitoring data, and a first judgment result is obtained; and a reliability test result of the target BMC is obtained based on the first judgment result. The scheme provided by the embodiment of the application can avoid hardware loss caused by BMC reliability test and improve test efficiency.

Description

Technical Field

[0001] This invention relates to the field of testing technology, and in particular to a BMC reliability testing method, apparatus, workstation, and storage medium. Background Technology

[0002] A server contains hardware such as a Baseboard Management Controller (BMC), CPU, memory, power supply, and cooling system. The BMC monitors all other hardware components in the server. Reliability testing of the BMC checks its ability to promptly and accurately detect hardware failures and, upon detection, to execute appropriate handling strategies.

[0003] Currently, reliability testing of BMCs typically involves injecting faults through manual physical destruction of the hardware. For example, this can be done by heating the hardware with a hot air gun or short-circuiting hardware components. However, this method of manual physical destruction leads to hardware wear and tear, and the testing efficiency is extremely low. Summary of the Invention

[0004] The purpose of this invention is to provide a BMC reliability testing method, apparatus, workstation, and storage medium to avoid hardware losses during BMC reliability testing and improve the efficiency of BMC reliability testing. The specific technical solution is as follows:

[0005] This invention first provides a BMC reliability testing method, the method comprising:

[0006] When the target server to which the target BMC belongs is in normal condition, the target reading conversion parameters of the target sensor recorded in the target BMC are configured so that the target BMC converts the raw readings of the target sensor based on the target reading conversion parameters to obtain a first engineering reading; wherein, the target reading conversion parameters are: parameters that make the first engineering reading characterize a target hardware fault, and the target hardware is: the hardware monitored by the target sensor;

[0007] Acquire the first monitoring data recorded by the target BMC during the process of monitoring the target hardware based on the first engineering reading;

[0008] Based on the first monitoring data, it is determined whether the target BMC detects a fault in the target hardware, and whether the corresponding processing strategy is executed after the fault is detected, to obtain a first judgment result;

[0009] The reliability test results of the target BMC are obtained based on the first judgment result.

[0010] In one possible implementation, the step of determining whether the target BMC has detected a fault in the target hardware based on the first monitoring data, and whether to execute the processing strategy corresponding to the detected fault after the fault is detected, to obtain a first determination result, includes:

[0011] If the first monitoring data records a change in the state of the target hardware from normal to faulty, then the first duration between the first moment and the second moment when the state of the target hardware changes to faulty is obtained; wherein, the second moment is the moment when the target reading conversion parameter is configured.

[0012] If the first monitoring data records a change in the state of the target sensor's collected data from a normal state to an abnormal state, then the second duration between the third moment when the state of the target sensor's collected data changes to an abnormal state and the second moment is obtained.

[0013] If the first duration is less than the first threshold and the second duration is less than the second threshold, then based on the first monitoring data, it is determined whether the target BMC executes the processing strategy corresponding to the detected fault, and a first judgment result is obtained.

[0014] In one possible implementation, configuring the target sensor reading conversion parameters recorded in the target BMC includes:

[0015] Obtain the correspondence between reading conversion parameters and configuration time; wherein, the reading conversion parameters corresponding to each configuration time in the correspondence are determined according to the relationship between the engineering readings characterizing the fault in the test scenario and the change over time;

[0016] Configure the target reading conversion parameters of the target sensor recorded in the target BMC according to the aforementioned correspondence.

[0017] In one possible implementation, obtaining the reliability test result of the target BMC based on the first determination result includes:

[0018] The reading conversion parameters of the target sensor recorded in the target BMC are restored to normal parameters, so that the target BMC converts the original readings of the target sensor based on the normal parameters to obtain a second engineering reading; wherein, the normal parameters are: parameters that make the second engineering reading characterize the target hardware as normal;

[0019] Acquire the second monitoring data recorded by the target BMC during the process of monitoring the target hardware based on the second engineering reading;

[0020] Determine whether the second monitoring data records a change in the target hardware from a fault state to a normal state, and obtain a second determination result;

[0021] The reliability test results of the target BMC are obtained based on the first judgment result and the second judgment result.

[0022] In one possible implementation, obtaining the reliability test result of the target BMC based on the first determination result includes:

[0023] Obtain the status information of the specified hardware other than the target hardware recorded by the target BMC;

[0024] Determine whether the acquired status information indicates that the specified hardware is in a normal state, and obtain a third determination result;

[0025] The reliability test results of the target BMC are obtained based on the first judgment result and the third judgment result.

[0026] In one possible implementation, obtaining the reliability test result of the target BMC based on the first determination result includes:

[0027] After powering down and powering back on the target server, the third monitoring data recorded by the target BMC during the monitoring of the target hardware based on the third engineering reading is obtained; wherein, the third engineering reading is: the reading obtained by converting the original reading of the target sensor based on the target reading conversion parameter after the target BMC is powered back on;

[0028] Based on the third monitoring data, it is determined whether the target BMC has detected a fault in the target hardware, and a fourth determination result is obtained;

[0029] The reliability test results of the target BMC are obtained based on the first judgment result and the fourth judgment result.

[0030] In one possible implementation, after configuring the target sensor's target reading conversion parameters recorded in the target BMC, the method further includes:

[0031] Obtain the performance metrics of the target server;

[0032] Based on the performance metrics, the stability test results of the target server are obtained in the event of a hardware failure characterized by the first engineering reading.

[0033] In one possible implementation, configuring the target sensor reading conversion parameters recorded in the target BMC includes:

[0034] During the stress test of the target server, the target reading conversion parameters of the target sensor recorded in the target BMC are configured.

[0035] This invention also provides a BMC reliability testing device, the device comprising:

[0036] The parameter configuration module is used to configure the target reading conversion parameters of the target sensor recorded in the target BMC when the target server to which the target BMC belongs is in normal status, so that the target BMC converts the original reading of the target sensor based on the target reading conversion parameters to obtain a first engineering reading; wherein, the target reading conversion parameters are: parameters that make the first engineering reading characterize the target hardware fault, and the target hardware is: the hardware monitored by the target sensor;

[0037] The first monitoring data acquisition module is used to acquire the first monitoring data recorded by the target BMC during the process of monitoring the target hardware based on the first engineering reading;

[0038] The first judgment result acquisition module is used to determine, based on the first monitoring data, whether the target BMC detects a fault in the target hardware, and whether to execute the processing strategy corresponding to the detected fault after the fault is detected, to obtain the first judgment result.

[0039] The test result acquisition module is used to obtain the reliability test result of the target BMC based on the first judgment result.

[0040] This invention also provides a workstation, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0041] Memory, used to store computer programs;

[0042] The processor, when executing a program stored in memory, implements any of the BMC reliability testing methods described above.

[0043] This invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements any of the BMC reliability testing methods described above.

[0044] This invention also provides a computer program product containing instructions that, when run on a computer, causes the computer to execute any of the BMC reliability testing methods described above.

[0045] Beneficial effects of the embodiments of the present invention:

[0046] This invention provides a BMC reliability testing method. Under normal conditions, the target server to which the target BMC belongs configures target reading conversion parameters for the target sensors recorded in the target BMC. This allows the target BMC to convert the raw readings of the target sensors based on these conversion parameters to obtain a first engineering reading. The target reading conversion parameters are parameters that characterize the target hardware faults, where the target hardware is the hardware monitored by the target sensor. The method then acquires first monitoring data recorded by the target BMC during the monitoring of the target hardware based on the first engineering reading. Based on this first monitoring data, the method determines whether the target BMC detects a fault in the target hardware and whether it executes the corresponding processing strategy after detecting the fault, obtaining a first judgment result. Finally, the method obtains the reliability test result of the target BMC based on the first judgment result. As can be seen, in this embodiment of the invention, by configuring the target reading conversion parameters of the target sensor recorded in the target BMC to achieve virtual fault injection, it is possible to determine whether the target BMC detects a fault and whether the corresponding processing strategy is executed after the fault is detected, thereby obtaining the reliability test results of the target BMC. The entire process can be implemented by programming, without the need for manual physical damage to the hardware to inject faults. Therefore, it can avoid hardware damage during the BMC reliability test and improve the efficiency of the test.

[0047] Of course, implementing any product or method of the present invention does not necessarily require achieving all of the advantages described above at the same time. Attached Figure Description

[0048] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other embodiments can be obtained based on these drawings.

[0049] Figure 1 This is a schematic diagram of the first process of the BMC reliability testing method provided in an embodiment of the present invention;

[0050] Figure 2 This is a schematic diagram of the second process of the BMC reliability testing method provided in the embodiments of the present invention;

[0051] Figure 3 This is a schematic diagram of the third process of the BMC reliability testing method provided in the embodiments of the present invention;

[0052] Figure 4 This is a schematic diagram of the fourth process of the BMC reliability testing method provided in the embodiments of the present invention;

[0053] Figure 5 This is a schematic diagram of the fifth process of the BMC reliability testing method provided in the embodiments of the present invention;

[0054] Figure 6 This is a schematic diagram of the sixth process of the BMC reliability testing method provided in the embodiments of the present invention;

[0055] Figure 7 This is a schematic diagram of the seventh process of the BMC reliability testing method provided in the embodiments of the present invention;

[0056] Figure 8 This is a schematic diagram of the eighth process of the BMC reliability testing method provided in the embodiments of the present invention;

[0057] Figure 9 This is a schematic diagram of the ninth process of the BMC reliability testing method provided in the embodiments of the present invention;

[0058] Figure 10 This is a schematic diagram of the BMC reliability testing device provided in an embodiment of the present invention;

[0059] Figure 11 This is a schematic diagram of the workstation provided in an embodiment of the present invention. Detailed Implementation

[0060] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art based on the present invention are within the scope of protection of the present invention.

[0061] A Server Controller (BMC) can monitor server hardware such as the CPU, memory, power supply, and cooling system to detect hardware failures in a timely manner. It can then implement corresponding handling strategies to address these failures, thereby improving server maintainability and ensuring business continuity. Reliability testing of the BMC aims to verify its ability to promptly and accurately detect monitored hardware failures and to execute appropriate handling strategies after detection. Currently, reliability testing of the BMC typically involves physically damaging the hardware to inject faults; however, this method incurs hardware wear and tear and is highly inefficient.

[0062] To address the aforementioned issues, embodiments of the present invention provide a BMC reliability testing method, apparatus, workstation, and storage medium.

[0063] The following section first introduces the BMC reliability testing method provided in this embodiment of the invention. This method can be applied to electronic devices with data processing capabilities. For example, the electronic device can be the target BMC to be tested, or it can be a workstation communicatively connected to the target BMC. A workstation is a high-end general-purpose microcomputer with more powerful performance than a personal computer, especially in graphics processing performance or task parallelism. When the BMC reliability testing method is applied to a target BMC, the steps of this embodiment can be executed by a program running in the target BMC's OS (Operating System); when the BMC reliability testing method is applied to a workstation, the steps of this embodiment can be executed by a program running in the workstation.

[0064] like Figure 1 As shown, the BMC reliability testing method may include the following steps:

[0065] S101, under the condition that the target server to which the target BMC belongs is in normal status, configure the target reading conversion parameters of the target sensor recorded in the target BMC, so that the target BMC converts the raw readings of the target sensor based on the target reading conversion parameters to obtain the first engineering reading; wherein, the target reading conversion parameters are: parameters that make the first engineering reading characterize the target hardware fault, and the target hardware is: the hardware monitored by the target sensor; S102, acquire the first monitoring data recorded by the target BMC during the process of monitoring the target hardware based on the first engineering reading; S103, based on the first monitoring data, determine whether the target BMC detects a fault in the target hardware, and whether it executes the processing strategy corresponding to the detected fault after detecting the fault, and obtain the first judgment result; S104, obtain the reliability test result of the target BMC based on the first judgment result.

[0066] In this embodiment of the invention, the virtual injection of faults is achieved by configuring the target reading conversion parameters of the target sensor recorded in the target BMC. Then, it is determined whether the target BMC detects a fault, and whether the corresponding processing strategy is executed after the fault is detected. The reliability test results of the target BMC can be obtained. The whole process can be implemented by programming, without the need for manual physical damage to the hardware to inject faults. Therefore, it can avoid hardware damage during the BMC reliability test and improve the efficiency of the test.

[0067] Regarding step S101 above, "the target server is in a normal state" specifically means that all hardware components in the target server are in a normal state. The target sensor can be a threshold sensor, that is, a sensor used to monitor quantifiable and continuously changing physical quantities of the hardware, such as temperature, voltage, current, fan speed, etc.

[0068] The BMC OS records the conversion parameters of the readings of each monitored sensor. For example, in the IPMI (Intelligent Platform Management Interface) protocol, the conversion from the sensor's raw reading (x) to the engineered reading (y) follows the formula:

[0069] y=(M×x+B×10^K1)×10^K2; where M (multiplier), B (offset), K1 (offset exponent), and K2 (result exponent) are configurable parameters, which are the reading conversion parameters mentioned above.

[0070] During the normal operation of the target BMC, the parameter combinations of M, B, K1, and K2 can be dynamically modified to achieve precise control over the sensor engineering readings. For example, a parameter configuration command containing the target reading conversion parameters can be sent to the target BMC via a workstation connected to it, causing the target BMC to modify the currently recorded target sensor reading conversion parameters to the target reading conversion parameters. In this way, testers can simulate preset hardware faults through software programming without any physical changes, thereby triggering the target BMC to detect the preset hardware faults. Specifically, by configuring the reading conversion parameters of a voltage sensor, voltage over-limit can be simulated; by configuring the reading conversion parameters of a current sensor, current overload can be simulated; by configuring the reading conversion parameters of a temperature sensor, temperature criticality or exceeding an unrecoverable threshold can be simulated; and by configuring the reading conversion parameters of a fan speed sensor, fan stoppage or abnormal fan speed can be simulated.

[0071] The target reading conversion parameters can also be set according to the type of fault to be injected. For example, the fault type may include: the first engineering reading reaches a high unrecoverable value, a low unrecoverable value, or a critical value.

[0072] The number of target sensors can be multiple, which can simulate complex faults caused by sudden changes in the external environment, i.e., multiple hardware failures at the same time.

[0073] Regarding steps S102 and S103 above, if the first engineering reading indicates a target hardware fault, the target BMC should be able to detect the target hardware fault and record it, for example, in the SEL (System Event Log). The target BMC will also execute the corresponding handling strategy for the detected fault and record the executed handling strategy. For example, when the detected fault is that the target hardware temperature is too high, the corresponding handling strategy may be: increase the speed of the fan associated with the target hardware, or reduce the frequency of the target hardware; when the detected fault is that the target hardware voltage is too low, the corresponding handling strategy may be: switch the target hardware to a redundant power supply; when the detected fault is that the target hardware voltage exceeds the high unrecoverable threshold, the corresponding handling strategy may be to issue an alarm (such as through SNMP Trap (an event-driven notification mechanism) or Redfish Event (an event notification mechanism defined in the Redfish specification) mechanism), etc.

[0074] Therefore, to detect the reliability of the target BMC, the first monitoring data recorded by the target BMC during the monitoring of the target hardware based on the first engineering reading can be obtained. Then, based on the first monitoring data, it can be determined whether the target BMC detected a fault in the target hardware, and whether it executed the corresponding processing strategy after detecting the fault, thus obtaining a first judgment result. In this embodiment of the invention, the specific form of the first monitoring data is not limited. For example, the first monitoring data can be data recorded in the SEL log by the target BMC during the monitoring of the target hardware based on the first engineering reading.

[0075] For example, through embodiments of the present invention, the engineering readings corresponding to the temperature sensors of multiple OCP (OpenCompute Project, an open-source hardware project) network cards in the target server can be modified to high non-critical values ​​or high unrecoverable values ​​at random times to simulate a scenario where the server room unexpectedly overheats during server operation; thereby, it can be determined whether the target BMC has detected high temperature faults in each OCP network card, and whether the fan speed has been increased after the fault has been detected, thus obtaining the first judgment result.

[0076] Regarding step S104 above, in one implementation, the first judgment result can be directly used as the reliability test result of the target BMC. Alternatively, in another implementation, if the first judgment result indicates that the target BMC detected a fault in the target hardware and executed the corresponding processing strategy, the reliability test result of the target BMC can be determined to be successful; otherwise, the reliability test result of the target BMC can be determined to be unsuccessful.

[0077] Furthermore, embodiments of the present invention can also obtain the frequency and number of log records made by the target BMC during the monitoring of the target hardware based on the first engineering reading, and then compare the obtained frequency and number of records with the expected frequency and number of records to detect the integrity of the BMC log records.

[0078] As can be seen, the embodiments of the present invention can accurately and flexibly simulate various hardware failure states, with strong reproducibility. No peripherals are required, and no rework is needed, thus avoiding hardware damage during BMC reliability testing. The implementation cost is almost zero, and the safety of the test is significantly improved. The above process can also be automated, thereby greatly improving testing efficiency.

[0079] In one possible implementation, such as Figure 2 As shown, the above-mentioned determination of whether the target BMC detects a fault in the target hardware based on the first monitoring data, and whether to execute the corresponding processing strategy after detecting the fault, to obtain a first determination result includes: S1031, if the first monitoring data records that the state of the target hardware changes from a normal state to a fault state, then the first duration between the first moment and the second moment when the state of the target hardware changes to the fault state is obtained; wherein, the second moment is the moment when the target reading conversion parameter is configured; S1032, if the first monitoring data records that the state of the target sensor data changes from a normal state to an abnormal state, then the second duration between the third moment when the state of the target sensor data changes to the abnormal state and the second moment is obtained; S1033, if the first duration is less than a first threshold and the second duration is less than a second threshold, then the determination of whether the target BMC executes the corresponding processing strategy for the detected fault is based on the first monitoring data to obtain a first determination result.

[0080] In this embodiment of the invention, after fault injection, by obtaining the first duration between the first moment and the second moment when the state of the target hardware changes to a fault state, and the second duration between the third moment and the second moment when the state of the target sensor data changes to an abnormal state, the delay in the target BMC sensing the change in the hardware state and the delay in the target BMC sensing the change in the state of the target sensor data can be determined. This allows for the determination of whether the target BMC can sense the changes in the state of the hardware and the target sensor data in a timely manner, thereby improving the comprehensiveness of BMC reliability testing.

[0081] Regarding steps S1031-S1033 above, under normal circumstances, when the BMC detects an abnormality in the first engineering reading, such as when the first engineering reading reaches a preset threshold, it records the change in the target sensor's data acquisition state from normal to abnormal, along with the corresponding timestamp, for example, recorded in the SEL log. Similarly, when the first engineering reading indicates a target hardware fault, it also records the change in the target hardware's state from normal to abnormal, along with the corresponding timestamp. Therefore, the aforementioned first and third moments can be obtained from the first monitoring data recorded during the monitoring of the target hardware using the first engineering reading. Recording the current moment when configuring the target sensor's target reading conversion parameters in the target BMC also records the aforementioned second moment. The aforementioned first and second thresholds can be set based on experience and needs; for example, both can be set to 1 second.

[0082] Currently, methods of injecting faults by physically damaging hardware struggle to accurately determine the actual time of a fault occurrence. Consequently, it's difficult to accurately determine the delay in the target BMC's perception of the fault and the delay in the target BMC's perception of changes in the state of the target sensor's data. However, this invention injects faults by configuring reading conversion parameters. This allows the time of configuring the target reading conversion parameters to be used as the time of the fault occurrence and the time of changes in the state of the target sensor's data, thus enabling precise quantification of delays. Furthermore, when the target BMC needs to report an alarm event due to a hardware fault, the event reporting delay of the target BMC can be accurately determined, achieving end-to-end delay detection in the event response chain from fault injection to the BMC generating a SEL log and then reporting the alarm event.

[0083] In one possible implementation, such as Figure 3 As shown, the target reading conversion parameters of the target sensor recorded in the above-mentioned configuration target BMC include: S1011, obtaining the correspondence between the reading conversion parameters and the configuration time; wherein, the reading conversion parameters corresponding to each configuration time in the correspondence are determined according to the relationship between the engineering readings representing the fault in the test scenario and the change over time; S1012, configuring the target reading conversion parameters of the target sensor recorded in the target BMC according to the correspondence.

[0084] In this embodiment of the invention, the reading conversion parameters corresponding to each configuration time in the above correspondence are determined according to the relationship between the engineering readings representing the fault and the time change in the test scenario. Then, the target reading conversion parameters of the target sensor recorded in the target BMC are configured according to the correspondence, which can simulate the changing trend of the engineering readings of the hardware that has failed in the real scenario. Based on this, the reliability test of the target BMC can better reflect the reliability of the target BMC in the real scenario.

[0085] For steps S1011-S1012 above, for example, the above test scenario can be a hardware degradation scenario. It is understood that during the degradation process of hardware, its normal operating temperature will gradually increase until it reaches an abnormal value. Therefore, the above correspondence can be set according to the relationship of temperature increase over time.

[0086] For example, the correspondence may include multiple configuration times. The target BMC converts the raw reading of the target sensor based on the reading conversion parameters corresponding to the later configuration time to obtain a larger engineering reading. Furthermore, the engineering reading obtained by the target BMC based on the reading conversion parameters corresponding to the last configuration time characterizes the abnormal temperature of the target hardware. This can simulate hardware degradation scenarios.

[0087] The above test scenario can also be a transient anomaly scenario, in which multiple hardware components fail simultaneously. To simulate this scenario, the same target configuration time can be set in the correspondence of multiple target sensors. In the correspondence of each target sensor, the reading conversion parameter corresponding to the target configuration time can trigger the abnormal engineering reading of the target sensor. This can simulate the situation where multiple hardware components fail simultaneously.

[0088] The steps described above for configuring the target sensor reading conversion parameters recorded in the target BMC according to the corresponding relationship can be executed repeatedly, and the number of cycles can also be preset. This enables stress testing of the target BMC under long-term, multi-round fault impacts.

[0089] The aforementioned correspondence can be manually set in a preset configuration file. This configuration file can also record the identifier of the target sensor. Therefore, when performing reliability testing on the target BMC, the target sensor can be identified based on the information recorded in this configuration file, and the correspondence between the reading conversion parameters and the configuration time can be obtained. This configuration file can also record the number of cycles mentioned above.

[0090] In one possible implementation, such as Figure 4As shown, the above-mentioned method for obtaining the reliability test result of the target BMC based on the first judgment result includes: S401, restoring the conversion parameters of the target sensor readings recorded in the target BMC to normal parameters, so that the target BMC converts the original readings of the target sensor based on the normal parameters to obtain the second engineering reading; wherein, the normal parameters are: parameters that make the second engineering reading characterize the target hardware as normal; S402, acquiring the second monitoring data recorded by the target BMC during the monitoring of the target hardware based on the second engineering reading; S403, determining whether the second monitoring data records the target hardware changing from a fault state to a normal state, and obtaining the second judgment result; S404, obtaining the reliability test result of the target BMC based on the first judgment result and the second judgment result.

[0091] In this embodiment of the invention, by restoring the reading conversion parameters to normal parameters, it is determined whether the target BMC records the change of the target hardware from a fault state to a normal state, and a second judgment result is obtained. This can test whether the target BMC can correctly perform detection when the target hardware changes from an abnormal state to a normal state, thereby further improving the comprehensiveness of BMC reliability testing.

[0092] For step S401 above, the normal parameters can be the initial values ​​recorded before configuring the target sensor reading conversion parameters recorded in the target BMC.

[0093] Regarding steps S402-S404 above, in one implementation, the first judgment result and the second judgment result can be summarized and directly used as the reliability test result of the target BMC. Alternatively, in another implementation, if the first judgment result indicates that the target BMC detected a fault in the target hardware and executed the corresponding processing strategy, and the second judgment result indicates that the target hardware changed from a faulty state to a normal state, then the reliability test result of the target BMC is determined to be successful; otherwise, the reliability test result of the target BMC is determined to be unsuccessful.

[0094] The above steps S101-S404 can be executed multiple times in a loop to stress test the stability and policy consistency of the BMC under long-term, multi-round fault impacts.

[0095] In one possible implementation, such as Figure 5 As shown, the above-mentioned method for obtaining the reliability test result of the target BMC based on the first judgment result includes: S501, obtaining the status information of the specified hardware other than the target hardware recorded by the target BMC; S502, determining whether the obtained status information indicates that the specified hardware is in a normal state, and obtaining the third judgment result; S503, obtaining the reliability test result of the target BMC based on the first judgment result and the third judgment result.

[0096] In this embodiment of the invention, by determining whether the specified hardware other than the target hardware is in a normal state, it is possible to detect whether the fault isolation capability of the target BMC is normal, thereby further improving the comprehensiveness of BMC reliability testing.

[0097] For steps S501-S502 above, the specified hardware can be hardware that is not strongly related to the target hardware. For example, abnormal CPU temperature should not affect the memory.

[0098] Similarly, regarding step S503 above, in one implementation, the first judgment result and the third judgment result can be summarized and directly used as the reliability test result of the target BMC. Alternatively, in another implementation, if the first judgment result indicates that the target BMC detected a fault in the target hardware and executed the corresponding processing strategy, and the third judgment result indicates that the acquired status information shows the specified hardware is in a normal state, then the reliability test result of the target BMC is determined to be successful; otherwise, the reliability test result of the target BMC is determined to be unsuccessful.

[0099] In one possible implementation, such as Figure 6 As shown, the above-mentioned reliability test result of the target BMC based on the first judgment result includes: S601, after powering down and powering up the target server, acquiring the third monitoring data recorded by the target BMC during the monitoring of the target hardware based on the third engineering reading; wherein, the third engineering reading is: the reading obtained by converting the original reading of the target sensor based on the target reading conversion parameter after the target BMC is powered up; S602, based on the third monitoring data, determining whether the target BMC has detected a fault in the target hardware, and obtaining the fourth judgment result; S603, obtaining the reliability test result of the target BMC based on the first judgment result and the fourth judgment result.

[0100] In this embodiment of the invention, after powering down and powering up the target server, it is determined whether the target BMC can detect the fault in the target hardware. It can also be determined whether the target BMC can correctly detect the fault again after powering up, thereby further improving the comprehensiveness of BMC reliability testing.

[0101] Regarding steps S601-S602 above, it is understood that the target reading conversion parameters configured by the target BMC will not be changed after power-on. Therefore, the target BMC should still be able to detect the target hardware fault after power-on; otherwise, it indicates that the target BMC has a reliability problem.

[0102] Similarly, regarding step S603 above, in one implementation, the first judgment result and the fourth judgment result can be combined and directly used as the reliability test result of the target BMC. Alternatively, in another implementation, if the first judgment result indicates that the target BMC detected a fault in the target hardware and executed the corresponding processing strategy, and the fourth judgment result indicates that the target BMC detected a fault in the target hardware, then the reliability test result of the target BMC is determined to be successful; otherwise, the reliability test result of the target BMC is determined to be unsuccessful.

[0103] In one possible implementation, such as Figure 7 As shown, after configuring the target sensor reading conversion parameters recorded in the target BMC, the BMC reliability test method further includes: S701, obtaining the performance indicators of the target server; S702, based on the performance indicators, obtaining the stability test results of the target server under the condition of a hardware failure characterized by the first engineering reading.

[0104] In this embodiment of the invention, by configuring the target sensor reading conversion parameters recorded in the target BMC, the performance indicators of the target server can be obtained, thereby testing the service stability of the target server under fault impact.

[0105] For step S701 above, the performance metrics of the target server can be IOPS (Input / Output Operations Per Second) and / or network latency, etc.

[0106] Regarding step S702 above, when a minor hardware malfunction occurs in the target server, such as the CPU temperature reaching a critical value or the fan speed decreasing, it should not significantly impact the normal operation of the target server. Therefore, the stability test result of the target server can be obtained based on performance indicators. For example, it can be determined whether the decline in the target server's performance indicators reaches a preset threshold. If it does, the stability test result is determined to be a failure; if it does not, the stability test result is determined to be a success.

[0107] In one possible implementation, configuring the target reading conversion parameters of the target sensor recorded in the target BMC includes: configuring the target reading conversion parameters of the target sensor recorded in the target BMC during stress testing of the target server.

[0108] In this embodiment of the invention, during the stress test of the target server, fault injection is performed by configuring the target sensor reading conversion parameters recorded in the target BMC, which enables the test of the target server's business stability under extreme conditions.

[0109] The stress test performed on the target server can specifically be a high-pressure I / O (Input / Output) scenario test. For example, a pre-installed stress test program can be run on the target server's operating system. This program controls high-frequency data read and write operations between the target server and storage devices, thus achieving a high-pressure I / O scenario test. Alternatively, another test server can be controlled to perform high-frequency network data transmission and reception with the target server to achieve the same result.

[0110] In one possible implementation, such as Figure 8 As shown, the BMC reliability testing method provided in this embodiment of the invention may include the following steps:

[0111] S801, Initial State Check: Checks the initial state of the threshold sensor to ensure it is in normal condition;

[0112] That is, ensure that the data collected by each sensor in the server is in a normal state.

[0113] S802, Fault Injection: Fault injection is achieved by adjusting the parameters in the configuration file under BMC OS;

[0114] That is, configure the target sensor reading conversion parameters recorded in the target BMC.

[0115] S803, Abnormal Trigger: Observe whether the sensor status abnormality is successfully triggered.

[0116] That is, to determine whether the target BMC has detected a fault in the target hardware.

[0117] S804, Fault Identification: Observe whether the relevant fault handling logic takes effect in a timely manner;

[0118] That is, to determine whether the target BMC executes the corresponding handling strategy after detecting a fault.

[0119] S805, Fault Isolation: Observe whether non-strongly related business modules are affected;

[0120] That is, obtain the status information of the specified hardware other than the target hardware recorded in the target BMC; and determine whether the obtained status information indicates that the specified hardware is in a normal state.

[0121] S806, Fault Maintenance: Power on and off the server and observe whether the fault status is maintained.

[0122] That is, after powering down and powering up the target server, the target BMC obtains the third monitoring data recorded during the monitoring of the target hardware based on the third engineering readings. Based on the third monitoring data, it is determined whether the target BMC has detected a fault in the target hardware.

[0123] S807, Fault Elimination: Fault elimination is achieved by adjusting configuration files and parameters under BMC OS;

[0124] That is, the reading conversion parameters of the target sensor recorded in the target BMC are restored to normal parameters, so that the target BMC can convert the original reading of the target sensor based on the normal parameters to obtain the second engineering reading.

[0125] S808, Status Recovery: Observe whether the hardware status has returned to normal and whether the alarm has been cleared.

[0126] That is, the second monitoring data recorded by the target BMC during the process of monitoring the target hardware based on the second engineering reading is obtained, and it is determined whether the second monitoring data records that the target hardware has changed from a fault state to a normal state.

[0127] In one possible implementation, such as Figure 9 As shown, the BMC reliability testing method provided in this embodiment of the invention may include the following steps:

[0128] S901 is used to test high-pressure I / O scenarios on servers.

[0129] S902 monitors the status of IO services on the server.

[0130] That is, to obtain the performance metrics of the target server.

[0131] S903, correct server time, clear logs.

[0132] S904, the sensor for fault injection is configured via a configuration file.

[0133] That is, configure the target reading conversion parameters of the target sensor recorded in the target BMC.

[0134] S905 performs fault injection at fixed cycles and time points.

[0135] That is, obtain the correspondence between the reading conversion parameters and the configuration time; and configure the target reading conversion parameters of the target sensor recorded in the target BMC according to the correspondence.

[0136] S906, determine if the current time is greater than or equal to the set time; if yes, execute S912; if no, execute S907.

[0137] S907: Determine if the IO service is interrupted; if yes, the test fails; otherwise, execute S908.

[0138] That is, based on performance metrics, obtain the stability test results of the target server under the condition of hardware failure represented by the first engineering reading.

[0139] S908 determines whether the hardware monitoring is insensitive or the sensing time is greater than 1 second; if yes, the test fails; otherwise, S909 is executed.

[0140] That is, determine whether the first monitoring data records a change in the state of the target hardware from normal to fault. If not, it means that the hardware monitoring is not detected. If so, obtain the first duration between the first moment and the second moment when the state of the target hardware changes to fault. The first duration obtained at this time is the detection time.

[0141] S909: Determine whether the sensor information is not perceived or the perception time is greater than 1 second; if yes, determine that the test has failed; if no, execute S910.

[0142] That is, it is determined whether the first monitoring data records a change in the state of the target sensor's collected data from a normal state to an abnormal state. If not, it means that the sensor information is not perceived. If so, the second duration between the third moment when the state of the target sensor's collected data changes to an abnormal state and the second moment is obtained. The second duration obtained at this time is the perception time.

[0143] S910: Determine if the reliability function is not working; if yes, determine that the test failed; otherwise, execute S911.

[0144] That is, determine whether to execute the corresponding handling strategy after the target BMC detects a fault.

[0145] S911, determine whether the health LED (light-emitting diode) of the earpiece is unresponsive; if yes, the test is determined to have failed; if no, return to execute S905.

[0146] Among them, the server chassis health LED is an LED light located on the raised part of the outer layer of the server chassis. It can reflect the health status of the server through different colors and flashing patterns. When there is a hardware failure in the server, the server chassis health LED should also change its color and flashing pattern to indicate that the server is malfunctioning.

[0147] S912, Overall Summary.

[0148] For example, the first detection result can be obtained by detecting whether there is an interruption in business I / O; the second detection result can be obtained by detecting the frequency and number of test log recordings; the third detection result can be obtained by detecting the duration of hardware monitoring anomaly records; the fourth detection result can be obtained by checking sensor historical records; and the fifth detection result can be obtained by detecting whether the reliability function is effective. These detection results can be summarized as the reliability test result of BMC. It can also be determined whether these detection results meet their respective preset conditions, thereby obtaining the reliability test result of BMC. For example, if all detection results meet their respective preset conditions, the reliability test result of BMC can be considered successful; otherwise, the reliability test result of BMC is considered successful.

[0149] S913, Eliminate fault: Observe whether the abnormal state has been eliminated.

[0150] That is, the reading conversion parameters of the target sensor recorded in the target BMC are restored to normal parameters, so that the target BMC can convert the original reading of the target sensor based on the normal parameters to obtain the second engineering reading; the second monitoring data recorded by the target BMC during the monitoring of the target hardware based on the second engineering reading is acquired; and it is determined whether the second monitoring data records that the target hardware has changed from a fault state to a normal state.

[0151] The above steps S905-S911 can be executed repeatedly in a nested loop until the current time reaches the set value, so as to stress test the stability and policy consistency of BMC under long-term, multi-round fault impacts.

[0152] As can be seen, the solution provided by this invention elevates BMC reliability testing from "physical destruction" to "digital twin," achieving non-destructive, precise, and programmable fault injection, completely eliminating test safety risks and hardware wear and tear, and improving testing efficiency by several orders of magnitude compared to manual methods. Through flexible manipulation of sensor models, it can cover complex and edge testing scenarios, including transient anomalies, trend degradation, single faults, concurrent faults of multiple components, and long-term stress testing, greatly improving test coverage. Furthermore, it achieves a fully automated, batch-reproducible testing process, supporting precise quantification of BMC fault response performance indicators (such as millisecond-level response latency), enabling earlier and more comprehensive exposure of design flaws in the BMC fault management chain, thereby significantly improving the overall reliability and robustness of server products during the R&D phase. This invention provides an automated testing system architecture integrating fault injection, multi-dimensional response monitoring, and performance analysis, which can significantly improve the testing technology level and product quality of servers and BMCs.

[0153] Based on the same inventive concept, embodiments of the present invention also provide a BMC reliability testing device, such as... Figure 10 As shown, the device includes:

[0154] The parameter configuration module 1001 is used to configure the target reading conversion parameters of the target sensor recorded in the target BMC when the target server to which the target BMC belongs is in normal status, so that the target BMC converts the original reading of the target sensor based on the target reading conversion parameters to obtain a first engineering reading; wherein, the target reading conversion parameters are: parameters that make the first engineering reading characterize the target hardware fault, and the target hardware is: the hardware monitored by the target sensor;

[0155] The first monitoring data acquisition module 1002 is used to acquire the first monitoring data recorded by the target BMC during the process of monitoring the target hardware based on the first engineering reading;

[0156] The first judgment result acquisition module 1003 is used to determine, based on the first monitoring data, whether the target BMC detects a fault in the target hardware, and whether to execute the processing strategy corresponding to the detected fault after the fault is detected, and to obtain the first judgment result.

[0157] The test result acquisition module 1004 is used to obtain the reliability test result of the target BMC based on the first judgment result.

[0158] In one possible implementation, the first determination result obtaining module 1003 is specifically used for:

[0159] If the first monitoring data records a change in the state of the target hardware from normal to faulty, then the first duration between the first moment and the second moment when the state of the target hardware changes to faulty is obtained; wherein, the second moment is the moment when the target reading conversion parameter is configured.

[0160] If the first monitoring data records a change in the state of the target sensor's collected data from a normal state to an abnormal state, then the second duration between the third moment when the state of the target sensor's collected data changes to an abnormal state and the second moment is obtained.

[0161] If the first duration is less than the first threshold and the second duration is less than the second threshold, then based on the first monitoring data, it is determined whether the target BMC executes the processing strategy corresponding to the detected fault, and a first judgment result is obtained.

[0162] In one possible implementation, the parameter configuration module 1001 includes:

[0163] The correspondence acquisition submodule is used to acquire the correspondence between reading conversion parameters and configuration time; wherein, the reading conversion parameters corresponding to each configuration time in the correspondence are determined according to the relationship between the engineering readings representing the fault in the test scenario and the change over time;

[0164] The parameter configuration submodule is used to configure the target reading conversion parameters of the target sensor recorded in the target BMC according to the correspondence.

[0165] In one possible implementation, the test result acquisition module 1004 includes:

[0166] The parameter recovery submodule is used to restore the reading conversion parameters of the target sensor recorded in the target BMC to normal parameters, so that the target BMC can convert the original readings of the target sensor based on the normal parameters to obtain a second engineering reading; wherein, the normal parameters are: parameters that make the second engineering reading characterize the target hardware as normal;

[0167] The second monitoring data acquisition submodule is used to acquire second monitoring data recorded by the target BMC during the process of monitoring the target hardware based on the second engineering readings;

[0168] The second judgment submodule is used to determine whether the second monitoring data records that the target hardware has changed from a fault state to a normal state, and to obtain a second judgment result.

[0169] The first result acquisition submodule is used to obtain the reliability test results of the target BMC based on the first judgment result and the second judgment result.

[0170] In one possible implementation, the test result acquisition module 1004 includes:

[0171] The status information acquisition submodule is used to acquire the status information of specified hardware other than the target hardware recorded by the target BMC;

[0172] The third judgment submodule is used to determine whether the acquired status information indicates that the specified hardware is in a normal state, and to obtain the third judgment result;

[0173] The second result acquisition submodule is used to obtain the reliability test results of the target BMC based on the first judgment result and the third judgment result.

[0174] In one possible implementation, the test result acquisition module 1004 includes:

[0175] The third monitoring data acquisition submodule is used to acquire the third monitoring data recorded by the target BMC during the monitoring of the target hardware based on the third engineering reading after the target server is powered off and powered on again; wherein, the third engineering reading is: the reading obtained by converting the original reading of the target sensor based on the target reading conversion parameter after the target BMC is powered on again;

[0176] The fourth judgment submodule is used to determine, based on the third monitoring data, whether the target BMC has detected a fault in the target hardware, and to obtain a fourth judgment result;

[0177] The third result acquisition submodule is used to obtain the reliability test results of the target BMC based on the first judgment result and the fourth judgment result.

[0178] In one possible implementation, the device further includes:

[0179] The performance index acquisition submodule is used to acquire the performance index of the target server after the parameter configuration module 1001 configures the target reading conversion parameters of the target sensor recorded in the target BMC.

[0180] The stability test result acquisition module is used to obtain the stability test results of the target server under the condition of the hardware failure characterized by the first engineering reading, based on the performance indicators.

[0181] In one possible implementation, the parameter configuration module 1001 is specifically used for:

[0182] During the stress test of the target server, the target reading conversion parameters of the target sensor recorded in the target BMC are configured.

[0183] This invention also provides a workstation, such as... Figure 11 As shown, it includes a processor 1101, a communication interface 1102, a memory 1103, and a communication bus 1104, wherein the processor 1101, the communication interface 1102, and the memory 1103 communicate with each other through the communication bus 1104.

[0184] Memory 1103 is used to store computer programs;

[0185] When the processor 1101 executes the program stored in the memory 1103, it implements the steps of any of the above-described BMC reliability testing methods.

[0186] The communication bus mentioned in the workstation above can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in the diagram, but this does not mean that there is only one bus or one type of bus.

[0187] The communication interface is used for communication between the workstation and other devices.

[0188] The memory may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0189] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0190] In another embodiment of the present invention, a computer-readable storage medium is also provided, which stores a computer program that, when executed by a processor, implements the steps of any of the BMC reliability testing methods described above.

[0191] In another embodiment of the present invention, a computer program product containing instructions is also provided, which, when run on a computer, causes the computer to execute any of the BMC reliability testing methods described above.

[0192] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0193] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0194] The various embodiments in this specification are described in a related manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments of apparatus, workstations, readable storage media, and computer program products are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0195] The above description is merely a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention are included within the scope of protection of the present invention.

Claims

1. A BMC reliability testing method, characterized in that, The method includes: When the target server to which the target BMC belongs is in normal condition, the target reading conversion parameters of the target sensor recorded in the target BMC are configured so that the target BMC converts the raw readings of the target sensor based on the target reading conversion parameters to obtain a first engineering reading; wherein, the target reading conversion parameters are: parameters that make the first engineering reading characterize a target hardware fault, and the target hardware is: the hardware monitored by the target sensor; Acquire the first monitoring data recorded by the target BMC during the process of monitoring the target hardware based on the first engineering reading; Based on the first monitoring data, it is determined whether the target BMC detects a fault in the target hardware, and whether the corresponding processing strategy is executed after the fault is detected, to obtain a first judgment result; The reliability test results of the target BMC are obtained based on the first judgment result.

2. The method according to claim 1, characterized in that, The first determination, based on the first monitoring data, includes determining whether the target BMC detects a fault in the target hardware, and whether, after detecting the fault, it executes the corresponding processing strategy for the detected fault, to obtain a first determination result, including: If the first monitoring data records a change in the state of the target hardware from normal to faulty, then the first duration between the first moment and the second moment when the state of the target hardware changes to faulty is obtained; wherein, the second moment is the moment when the target reading conversion parameter is configured. If the first monitoring data records a change in the state of the target sensor's collected data from a normal state to an abnormal state, then the second duration between the third moment when the state of the target sensor's collected data changes to an abnormal state and the second moment is obtained. If the first duration is less than the first threshold and the second duration is less than the second threshold, then based on the first monitoring data, it is determined whether the target BMC executes the processing strategy corresponding to the detected fault, and a first judgment result is obtained.

3. The method according to claim 1, characterized in that, The configuration of the target sensor reading conversion parameters recorded in the target BMC includes: Obtain the correspondence between reading conversion parameters and configuration time; wherein, the reading conversion parameters corresponding to each configuration time in the correspondence are determined according to the relationship between the engineering readings characterizing the fault in the test scenario and the change over time; Configure the target reading conversion parameters of the target sensor recorded in the target BMC according to the aforementioned correspondence.

4. The method according to claim 1, characterized in that, The process of obtaining the reliability test result of the target BMC based on the first judgment result includes: The reading conversion parameters of the target sensor recorded in the target BMC are restored to normal parameters, so that the target BMC converts the original readings of the target sensor based on the normal parameters to obtain a second engineering reading; wherein, the normal parameters are: parameters that make the second engineering reading characterize the target hardware as normal; Acquire the second monitoring data recorded by the target BMC during the process of monitoring the target hardware based on the second engineering reading; Determine whether the second monitoring data records a change in the target hardware from a fault state to a normal state, and obtain a second determination result; The reliability test results of the target BMC are obtained based on the first judgment result and the second judgment result.

5. The method according to claim 1, characterized in that, The process of obtaining the reliability test result of the target BMC based on the first judgment result includes: Obtain the status information of the specified hardware other than the target hardware recorded by the target BMC; Determine whether the acquired status information indicates that the specified hardware is in a normal state, and obtain a third determination result; The reliability test results of the target BMC are obtained based on the first judgment result and the third judgment result.

6. The method according to claim 1, characterized in that, The process of obtaining the reliability test result of the target BMC based on the first judgment result includes: After powering down and powering back on the target server, the third monitoring data recorded by the target BMC during the monitoring of the target hardware based on the third engineering reading is obtained; wherein, the third engineering reading is: the reading obtained by converting the original reading of the target sensor based on the target reading conversion parameter after the target BMC is powered back on; Based on the third monitoring data, it is determined whether the target BMC has detected a fault in the target hardware, and a fourth determination result is obtained; The reliability test results of the target BMC are obtained based on the first judgment result and the fourth judgment result.

7. The method according to any one of claims 1-6, characterized in that, After configuring the target sensor reading conversion parameters recorded in the target BMC, the method further includes: Obtain the performance metrics of the target server; Based on the performance metrics, the stability test results of the target server are obtained in the event of a hardware failure characterized by the first engineering reading.

8. The method according to claim 7, characterized in that, The configuration of the target sensor reading conversion parameters recorded in the target BMC includes: During the stress test of the target server, the target reading conversion parameters of the target sensor recorded in the target BMC are configured.

9. A BMC reliability testing device, characterized in that, The device includes: The parameter configuration module is used to configure the target reading conversion parameters of the target sensor recorded in the target BMC when the target server to which the target BMC belongs is in normal status, so that the target BMC converts the original reading of the target sensor based on the target reading conversion parameters to obtain a first engineering reading; wherein, the target reading conversion parameters are: parameters that make the first engineering reading characterize the target hardware fault, and the target hardware is: the hardware monitored by the target sensor; The first monitoring data acquisition module is used to acquire the first monitoring data recorded by the target BMC during the process of monitoring the target hardware based on the first engineering reading; The first judgment result acquisition module is used to determine, based on the first monitoring data, whether the target BMC detects a fault in the target hardware, and whether to execute the processing strategy corresponding to the detected fault after the fault is detected, to obtain the first judgment result. The test result acquisition module is used to obtain the reliability test result of the target BMC based on the first judgment result.

10. A workstation, characterized in that, It includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, when executing a program stored in memory, implements the steps of the method described in any one of claims 1-8.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the method described in any one of claims 1-8.

Images