Method and device for determining fault occurrence, equipment and storage medium

Abstract

The invention relates to a fault occurrence determination method and device, equipment and a storage medium. The method comprises the following steps: acquiring a configuration parameter and a load parameter of a resource pool at a current time point; inputting the configuration parameters and the load parameters into a pre-trained performance prediction model to obtain a predicted IOPS value and predicted delay time at the next time point; determining whether to trigger fault early warning operation according to the predicted IOPS value and the predicted delay time; and when a fault early warning operation is triggered, analyzing the resource pool to obtain fault early warning information. According to the method, the accuracy of fault early warning can be improved, and the normal operation of the resource pool is prevented from being influenced by faults.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method, device, equipment and storage medium for determining the occurrence of a fault. Background Art

[0002] With the development of technology, more and more private cloud service providers use resource pools to operate their own developed projects. Among them, resource pools are an architecture that centrally manages computing resources to improve resource utilization and flexibility.

[0003] In the prior art, after obtaining relevant data of the resource pool, the technician determines whether the resource pool is about to fail based on experience. When it is determined that the resource pool is about to fail, the fault information is analyzed and pre-processed.

[0004] In actual applications, private cloud service providers use a large number of resource pools with various configurations, and the fault judgment conditions corresponding to resource pools with different configurations are different. In this way, technicians will inevitably make mistakes when facing a large number of resource pools with various configurations, resulting in inaccurate fault warnings, causing resource pool failures, and affecting the normal operation of the resource pool. Therefore, a method for determining the occurrence of a fault is urgently needed. Summary of the invention

[0005] The present application provides a method, apparatus, device and storage medium for determining the occurrence of a fault, which can improve the accuracy of fault warning and avoid the occurrence of a fault affecting the normal operation of a resource pool.

[0006] In a first aspect, the present application provides a method for determining a fault occurrence, the method comprising:

[0007] Get the configuration parameters and load parameters of the resource pool at the current time point;

[0008] Inputting the configuration parameters and the load parameters into a pre-trained performance prediction model to obtain a predicted IOPS (Input / Output Operations Per Second) value and a predicted delay time at a next time point;

[0009] Determining whether to trigger a fault warning operation according to the predicted IOPS value and the predicted delay time;

[0010] When a fault warning operation is triggered, the resource pool is analyzed to obtain fault warning information.

[0011] Optionally, the performance prediction model includes a data prediction module, a standard deviation determination module and an output module, and the configuration parameters and the load parameters are input into a pre-trained performance prediction model to obtain a predicted IOPS value and a predicted delay time at a next time point, including:

[0012] Input the configuration parameters and the load parameters into a data prediction module, and output a plurality of reference IOPS values ​​and a plurality of reference delay times;

[0013] Inputting multiple reference IOPS values ​​and multiple reference delay times into a standard deviation determination module to obtain an IOPS standard deviation and a delay standard deviation;

[0014] When both the IOPS standard deviation and the delay standard deviation meet the preset conditions, multiple reference IOPS values ​​and multiple reference delay times are input into the output module to obtain the predicted IOPS value and predicted delay time at the next time point.

[0015] Optionally, determining whether to trigger a fault warning operation according to the predicted IOPS value includes:

[0016] Get the current IOPS value corresponding to the current time point;

[0017] Determine an IOPS change amount according to the current IOPS value and the predicted IOPS value;

[0018] According to the configuration parameters of the resource pool, determining the maximum IOPS change and the minimum IOPS value corresponding to the configuration parameters;

[0019] Whether to trigger a fault warning operation is determined according to the predicted IOPS value, the IOPS change, the maximum IOPS change, and the minimum IOPS value.

[0020] Optionally, determining whether to trigger a fault warning operation according to the predicted delay time includes:

[0021] Get the current delay time corresponding to the current time point;

[0022] Determine a delay variation according to the current delay time and the predicted delay time;

[0023] Determining, according to the configuration parameters of the resource pool, a maximum delay variation and a maximum delay value corresponding to the configuration parameters;

[0024] Whether to trigger a fault warning operation is determined according to the predicted delay time, the delay variation, the maximum delay variation, and the maximum delay value.

[0025] Optionally, the method comprises:

[0026] Obtain a set of IOPS values ​​of the resource pool when it operates normally using different configuration parameters;

[0027] For different configuration parameters, an IOPS average value corresponding to the IOPS value set is determined, and based on the IOPS average value, an IOPS minimum value and an IOPS maximum change amount corresponding to the configuration parameter are determined.

[0028] Optionally, the method further includes:

[0029] Determine, according to the load of the resource pool, an adjustment range to be used, where the adjustment range is used to indicate an adjustment range of the maximum change in IOPS and / or the maximum change in latency;

[0030] According to the adjustment range, the maximum IOPS variation and / or the maximum delay variation are adjusted.

[0031] Optionally, analyzing the resource pool to obtain fault warning information includes:

[0032] According to the configuration parameters, determining an association relationship corresponding to the configuration parameters, the association relationship being an association relationship between an IOPS change, a delay change, and fault warning information;

[0033] According to the IOPS change amount and the delay change amount, fault warning information is determined in the association relationship.

[0034] In a second aspect, the present application provides a device for determining whether a fault occurs, the device comprising:

[0035] An acquisition unit, used to acquire configuration parameters and load parameters of the resource pool at the current time point;

[0036] An input unit, used to input the configuration parameters and the load parameters into a pre-trained performance prediction model to obtain a predicted IOPS value and a predicted delay time at a next time point;

[0037] A first determining unit, configured to determine whether to trigger a fault warning operation according to the predicted IOPS value and the predicted delay time;

[0038] The analysis unit is used to analyze the resource pool to obtain fault warning information when a fault warning operation is triggered.

[0039] Optionally, the performance prediction model includes a data prediction module, a standard deviation determination module and an output module, and the input unit is used to:

[0040] Input the configuration parameters and the load parameters into a data prediction module, and output a plurality of reference IOPS values ​​and a plurality of reference delay times;

[0041] Inputting multiple reference IOPS values ​​and multiple reference delay times into a standard deviation determination module to obtain an IOPS standard deviation and a delay standard deviation;

[0042] When both the IOPS standard deviation and the delay standard deviation meet the preset conditions, multiple reference IOPS values ​​and multiple reference delay times are input into the output module to obtain the predicted IOPS value and predicted delay time at the next time point.

[0043] Optionally, the first determining unit is used to:

[0044] Get the current IOPS value corresponding to the current time point;

[0045] Determine an IOPS change amount according to the current IOPS value and the predicted IOPS value;

[0046] According to the configuration parameters of the resource pool, determining the maximum IOPS change and the minimum IOPS value corresponding to the configuration parameters;

[0047] Whether to trigger a fault warning operation is determined according to the predicted IOPS value, the IOPS change, the maximum IOPS change, and the minimum IOPS value.

[0048] Optionally, the first determining unit is used to:

[0049] Get the current delay time corresponding to the current time point;

[0050] Determine a delay variation according to the current delay time and the predicted delay time;

[0051] Determining, according to the configuration parameters of the resource pool, a maximum delay variation and a maximum delay value corresponding to the configuration parameters;

[0052] Whether to trigger a fault warning operation is determined according to the predicted delay time, the delay variation, the maximum delay variation, and the maximum delay value.

[0053] Optionally, the device further includes a second determining unit, wherein the second determining unit is configured to:

[0054] Obtain a set of IOPS values ​​of the resource pool when it operates normally using different configuration parameters;

[0055] For different configuration parameters, an IOPS average value corresponding to the IOPS value set is determined, and based on the IOPS average value, an IOPS minimum value and an IOPS maximum change amount corresponding to the configuration parameter are determined.

[0056] Optionally, the device further comprises an adjusting unit, wherein the adjusting unit is configured to:

[0057] Determine, according to the load of the resource pool, an adjustment range to be used, where the adjustment range is used to indicate an adjustment range of the maximum change in IOPS and / or the maximum change in latency;

[0058] According to the adjustment range, the maximum IOPS variation and / or the maximum delay variation are adjusted.

[0059] Optionally, the analysis unit is used to:

[0060] According to the configuration parameters, determining an association relationship corresponding to the configuration parameters, the association relationship being an association relationship between an IOPS change, a delay change, and fault warning information;

[0061] According to the IOPS change amount and the delay change amount, fault warning information is determined in the association relationship.

[0062] In a third aspect, the present application provides a device for determining whether a fault has occurred, comprising: at least one communication interface; at least one bus connected to the at least one communication interface; at least one processor connected to the at least one bus; at least one memory connected to the at least one bus, wherein the processor is configured to:

[0063] Get the configuration parameters and load parameters of the resource pool at the current time point;

[0064] Input the configuration parameters and the load parameters into a pre-trained performance prediction model to obtain a predicted IOPS value and a predicted delay time at a next time point;

[0065] Determining whether to trigger a fault warning operation according to the predicted IOPS value and the predicted delay time;

[0066] When a fault warning operation is triggered, the resource pool is analyzed to obtain fault warning information.

[0067] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for determining the occurrence of a fault is implemented.

[0068] The above technical solution provided by the embodiment of the present application has the following advantages compared with the prior art: In the present application, by obtaining the configuration parameters and load parameters of the resource pool at the current time point and inputting them into the performance prediction model, the predicted IOPS value and predicted delay time of the resource pool at the next time point are predicted. Since the predicted IOPS value and the predicted delay time are parameters related to the performance of the resource pool, these two parameters are used to determine whether the performance of the resource pool at the next time point is normal, that is, these two parameters are used to determine whether to trigger the fault warning operation. When the fault warning operation is triggered, the resource pool is automatically analyzed to obtain fault warning information so that relevant personnel can process the fault warning information. In other words, the present application automatically predicts the performance-related parameters of resource pools with different configurations at the next time point through the performance prediction model, and then determines whether to trigger the fault warning operation based on it, avoiding mistakes in the human judgment process, improving the accuracy of fault warning, and avoiding the occurrence of faults affecting the normal operation of the resource pool. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0070] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0071] One or more embodiments are exemplarily described by pictures in the corresponding drawings, and these exemplified descriptions do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings represent similar elements, and unless otherwise stated, the figures in the drawings do not constitute proportional limitations.

[0072] Figure 1 A flowchart of a method for determining a fault occurrence provided in an embodiment of the present application;

[0073] Figure 2 A flowchart of a data prediction method provided in an embodiment of the present application;

[0074] Figure 3 A flowchart of a fault diagnosis method provided in an embodiment of the present application;

[0075] Figure 4 A flowchart of another fault judgment method provided in an embodiment of the present application;

[0076] Figure 5A flowchart of a calculation method provided in an embodiment of the present application;

[0077] Figure 6 A flowchart of another calculation method provided in an embodiment of the present application;

[0078] Figure 7 A flowchart of a data adjustment method provided in an embodiment of the present application;

[0079] Figure 8 A flowchart of a method for determining fault warning information provided in an embodiment of the present application;

[0080] Fig. 9 A flowchart of another method for determining fault warning information provided in an embodiment of the present application;

[0081] Fig.10 A schematic diagram of a flow chart of a device for determining whether a fault has occurred provided in an embodiment of the present application;

[0082] Fig.11 A schematic diagram of a device for determining whether a fault has occurred is provided in an embodiment of the present application. DETAILED DESCRIPTION

[0083] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0084] The disclosure below provides many different embodiments or examples to implement different structures of the present invention. In order to simplify the disclosure of the present invention, the parts and settings of specific examples are described below. Of course, they are only examples, and the purpose is not to limit the present invention. In addition, the present invention can repeat reference numbers and / or letters in different examples. This repetition is for the purpose of simplification and clarity, and does not itself indicate the relationship between the various embodiments and / or settings discussed.

[0085] In related technologies, after obtaining relevant data of a resource pool, technicians analyze the relevant data based on experience to determine whether the resource pool is about to fail. When it is determined that the resource pool is about to fail, the cause of the failure is analyzed and pre-processed. In actual applications, private cloud service providers will use a large number of resource pools with various configurations, and the analysis methods corresponding to resource pools with different configurations are different. In this way, technicians will inevitably make mistakes when facing a large number of resource pools with various configurations, resulting in inaccurate fault warnings, causing resource pool failures, and affecting the normal operation of the resource pool.

[0086] In order to solve the above problems, the present application obtains the configuration parameters and load parameters of the resource pool at the current time point, and inputs them into the performance prediction model to predict the predicted IOPS value and predicted delay time of the resource pool at the next time point. Since the predicted IOPS value and the predicted delay time are parameters related to the performance of the resource pool, these two parameters are used to determine whether the performance of the resource pool at the next time point is normal, that is, these two parameters are used to determine whether to trigger the fault warning operation. When the fault warning operation is triggered, the resource pool is automatically analyzed to obtain fault warning information so that relevant personnel can process the fault warning information. In other words, the present application automatically predicts the performance-related parameters of resource pools with different configurations at the next time point through a performance prediction model, and then determines whether to trigger the fault warning operation based on it, thereby avoiding mistakes in the human judgment process, improving the accuracy of fault warnings, and avoiding the occurrence of faults that affect the normal operation of the resource pool.

[0087] In summary, the embodiment of the present application provides a method for determining the occurrence of a fault, which can improve the accuracy of fault warning and avoid the occurrence of a fault affecting the normal operation of the resource pool. Figure 1 As shown, the specific steps include:

[0088] Step 101, obtaining configuration parameters and load parameters of the resource pool at the current time point.

[0089] The configuration parameters include RAID scheme, data block size, read-write ratio, queue depth, and number of jobs, etc. The RAID scheme is a data storage virtualization technology that combines multiple disks into a logical unit, including the number of disks used and the number of logical units based on the number of disks. For example, the number of disks in the RAID scheme is 5, the number of logical units is 1, the data block size is 4KB, the read-write ratio is 1:1, the queue depth is 32, and the number of jobs is 4. The load parameter is the load size of the resource pool.

[0090] In this step, the detection device periodically obtains the configuration parameters and load parameters of the resource pool at the current time point. When it is necessary to detect the performance of a resource pool, since the configuration parameters of the resource pool have been set, the detection device only needs to find the configuration parameters used in the resource pool. Since the load of the resource pool changes in real time, the detection device can obtain the load of the resource pool in real time and obtain the load parameters of the resource pool.

[0091] Step 102 , input the configuration parameters and load parameters into a pre-trained performance prediction model to obtain a predicted IOPS value and a predicted delay time at the next time point.

[0092] Among them, the performance prediction model is a machine learning model, which can predict the IOPS value and delay time at the next time point based on the configuration parameters and load parameters at the current time point. The IOPS value is an indicator used to measure the performance of the storage device. The delay time indicates the time it takes for the resource pool to respond. The current time point is the time point at which the load condition is obtained in step 101. Since the detection device periodically obtains the load condition in the resource pool, the next time point is the time point for obtaining the load condition next time, which is specifically the sum of the current time point and the period interval.

[0093] In this step, the configuration parameters and load parameters are input into a pre-trained performance prediction model, and the performance prediction model is used to process the input parameters, predict the performance of the resource pool, obtain the IOPS value and delay time, and determine them as the predicted IOPS value and predicted delay time at the next time point.

[0094] The performance prediction model includes an input layer, a CatBoost regression model, a generation model, and an output layer in terms of structure. The input of the performance prediction model is configuration parameters and load parameters, and the output is IOPS value and delay time. Through data collection, data input, model training, evaluation and deployment, accurate prediction of resource pool performance is achieved. In the data collection process, performance data of resource pools under different configuration parameters and loads can be collected, including but not limited to IOPS, delay, RAID scheme, number of disks, data block size, read-write ratio, queue depth and number of jobs. The collected data is cleaned and formatted to ensure the quality and consistency of the data. After that, the collected data is input into the input layer, and relevant features can be obtained from the collected data. The selected features are subjected to necessary transformation and engineering processing, such as normalization and encoding, to improve the generalization ability and prediction accuracy of the model. Then, the CatBoost regression model is used as the core algorithm, the input is preprocessed and feature-engineered data, and the output is IOPS value and delay time. At the same time, the model parameters are adjusted through methods such as cross-validation to find the optimal model configuration. The trained model is evaluated using an independent test data set to ensure the model's prediction accuracy and generalization ability. The reliability of the model's prediction results is verified by comparing them with actual measurements.

[0095] Step 103: Determine whether to trigger a fault warning operation according to the predicted IOPS value and the predicted delay time.

[0096] In this step, the technician can pre-set the minimum IOPS value and the maximum delay value of the resource pool under the configuration parameters and store them in the detection device. When the detection device needs to execute step 103, it can obtain the minimum IOPS value and the maximum delay value of the resource pool under the configuration, and detect whether the predicted IOPS value is less than the minimum IOPS value and whether the delay time is greater than the maximum delay value. When the predicted IOPS value is less than the minimum IOPS value and / or the predicted delay time is greater than the maximum delay value, it is determined to trigger the fault warning operation.

[0097] For example, the minimum IOPS value of the preset resource pool is 40000, and the maximum delay is 1ms. Based on the performance prediction model, the predicted IOPS value is 30000, and the predicted delay time is 2ms. Since the predicted IOPS value is less than the minimum IOPS value, and the predicted delay time is greater than the maximum delay time, it is determined that the fault warning operation is triggered.

[0098] Of course, the detection device can also determine whether to trigger a fault warning operation based on the IOPS change and the delay change. Specifically, the detection device can also store the maximum IOPS change and the maximum delay change of the resource pool under the configuration parameters. At the same time, the detection device obtains the current IOPS value and the current delay time of the resource pool at the current time point, and then determines the IOPS change based on the current IOP value and the predicted IOPS value, and determines the delay change based on the current delay time and the predicted delay time. When the IOPS change is greater than the maximum IOPS change or / and the delay change is greater than the maximum delay change, it is determined that a fault warning operation is triggered. The above two methods can also be combined here to determine whether to trigger a fault warning operation, which will not be repeated here one by one.

[0099] It should be noted that the fault warning operation will not be triggered when the fault warning operation is not triggered based on the predicted IOPS value and the fault warning operation is not triggered based on the predicted delay time. That is, the fault warning operation will be triggered as long as the fault warning operation is triggered based on one data.

[0100] Step 104: When a fault warning operation is triggered, the resource pool is analyzed to obtain fault warning information.

[0101] In this step, when the fault warning operation is triggered, the detection equipment can automatically analyze the resource pool to detect the relevant data of the resource pool, and then detect the fault warning information, and notify the technical staff of the fault warning information so that the technical staff can take corresponding measures according to the fault warning information.

[0102] The above-mentioned fault warning information includes hardware failure, software problem, improper configuration or sudden load change, etc. The corresponding measures taken include adjusting the configuration, optimizing load distribution or performing hardware inspection, etc.

[0103] In an embodiment of the present application, the detection device can analyze the resource pool based on the IOPS change and delay change time obtained in the above process to obtain fault warning information. The detection device can also analyze the resource pool based on the relevant data of the resource pool at the current time point to obtain fault warning information. The detection device can also extend the preset time length from the current time point forward to obtain a time period including the current time point, and analyze the resource pool based on the relevant data of the resource pool in the time period to obtain fault warning information. Among them, the above-mentioned relevant data includes configuration parameters, load parameters, current IOPS value, current delay time, predicted IOPS value, predicted delay time and other data.

[0104] In addition, in this step, the detection device analyzes the resource pool only after the fault warning operation is triggered. There is no need to analyze the resource pool all the time, which can save computing resources to a certain extent.

[0105] In the embodiment of the present application, the fault warning operation and the measures taken can also be recorded, and this information can be fed back into the model training process to optimize the prediction accuracy of the model. At the same time, the accuracy of the entire scheme is regularly evaluated, and the relevant parameters and other relevant data in the performance prediction model are adjusted according to the evaluation results. In the present application, the configuration parameters and load parameters of the resource pool at the current time point are obtained and input into the performance prediction model to predict the predicted IOPS value and predicted delay time of the resource pool at the next time point. Since the predicted IOPS value and the predicted delay time are parameters related to the performance of the resource pool, these two parameters are used to determine whether the performance of the resource pool at the next time point is normal, that is, these two parameters are used to determine whether to trigger the fault warning operation. When the fault warning operation is triggered, the resource pool is automatically analyzed to obtain fault warning information so that relevant personnel can process the fault warning information. In other words, the present application automatically predicts the performance-related parameters of resource pools with different configurations at the next time point through the performance prediction model, and then determines whether to trigger the fault warning operation based on it, avoiding mistakes in the human judgment process, improving the accuracy of fault warning, and avoiding the occurrence of faults affecting the normal operation of the resource pool.

[0106] In an embodiment of the present application, when the performance prediction model includes a data prediction module, a standard deviation determination module, and an output module, the embodiment of the present application provides a data prediction method, which can obtain a predicted IOPS value and a predicted delay time for the next time. The specific method is as follows: Figure 2 As shown, including:

[0107] Step 201: input configuration parameters and load parameters into a data prediction module, and output a plurality of reference IOPS values ​​and a plurality of reference delay times.

[0108] The data prediction module is a machine learning module, which is used to output multiple IOPS values ​​and delay times. In the actual training process, the data prediction module can be trained separately so that the data prediction module outputs multiple IOPS values ​​and multiple delay times. The performance prediction model can also be trained as a whole to obtain a pre-trained performance prediction model, which includes the pre-trained data prediction module.

[0109] Step 202: input a plurality of reference IOPS values ​​and a plurality of reference delay times into a standard deviation determination module to obtain an IOPS standard deviation and a delay standard deviation.

[0110] Step 203: When both the IOPS standard deviation and the delay standard deviation meet the preset conditions, multiple reference IOPS values ​​and multiple reference delay times are input into the output module to obtain the predicted IOPS value and predicted delay time at the next time point.

[0111] Among them, the preset conditions are that the IOPS standard deviation is less than a preset value, and the delay standard deviation is less than another preset value. These two preset values ​​can be set by technicians based on experience, and can be the same or different, and are not limited here.

[0112] In this step, when the IOPS standard deviation is less than the preset value, it means that the difference between the multiple reference IOPS values ​​is not large, and the IOPS value output by the data prediction module is relatively accurate, and the next step can be performed. When the IOPS standard deviation is greater than the preset value, it means that the difference between the multiple reference IOPS values ​​is large, and the IOPS value output by the data prediction module is not very accurate, and the next step cannot be performed. Therefore, it is necessary to first determine the IOPS standard deviation of multiple reference IOPS values ​​and determine whether it is less than the preset value, so as to determine whether the data output by the data prediction module is accurate, and then determine whether the next step can be performed.

[0113] Similarly, when the delay standard deviation is less than the preset value, it means that the difference between the multiple reference delay times is not large, the delay time output by the data prediction module is relatively accurate, and the next step can be performed. When the delay standard deviation is greater than the preset value, it means that the difference between the multiple reference delay times is large, the delay time output by the data prediction module is not very accurate, and the next step cannot be performed. Therefore, it is necessary to obtain the delay standard deviation of multiple reference delay times and determine whether it is less than the preset value, so as to determine whether the data output by the data prediction module is accurate, and then determine whether the next step can be performed.

[0114] In this step, when both the IOPS standard deviation and the delay standard deviation meet the preset conditions, it means that the data output by the data prediction module is relatively accurate. In order to make the output result more accurate, the average values ​​corresponding to the two parameters can be calculated and used as the prediction result. At this time, the output module can be an average value determination module, and the specific steps for obtaining the predicted data according to the average value determination module are: when both the IOPS standard deviation and the delay standard deviation meet the preset conditions, multiple reference IOPS values ​​and multiple reference delay times are input into the average value determination module to obtain the IOPS average value and the average delay time. The IOPS average value and the average delay time are determined as the predicted IOPS value and the predicted delay time at the next time point.

[0115] Of course, this step can also select one data from multiple reference data and determine it as the predicted data. In this case, the output module is a selection module, and the specific steps of obtaining the predicted data according to the selection module are: when the IOPS standard deviation and the delay standard deviation both meet the preset conditions, multiple reference IOPS values ​​and multiple reference delay times are input into the selection module to obtain a reference IOPS value and a reference delay time, and determine them as the predicted IOPS value and predicted delay time at the next time point.

[0116] The selection rule of the selection module may be to determine the maximum value among multiple reference IOPS values ​​as the predicted IOPS value, and to determine the maximum value among multiple reference delay times as the predicted delay time. Alternatively, the minimum value among multiple reference IOPS values ​​may be determined as the predicted IOPS value, and the minimum value among multiple reference delay times may be determined as the predicted delay time. Of course, this step may also use other selection rules, which are not limited here.

[0117] In the embodiment of the present application, the configuration parameters and the load parameters are first input into the data prediction module, and multiple reference IOPS values ​​and multiple reference delay times are output, and then the accuracy of these data is verified by the standard deviation of these data. When these data are accurate, the predicted data at the next time point is determined to ensure the accuracy of the predicted data.

[0118] In the embodiment of the present application, it is also possible to determine whether the performance of the resource pool is normal based on the predicted IOPS value, thereby determining whether to trigger a fault warning operation. Therefore, the embodiment of the present application also provides a fault judgment method, which method is as follows: Figure 3 As shown, the specific steps include:

[0119] Step 301, obtaining the current IOPS value corresponding to the current time point.

[0120] In this step, the detection device can detect the performance of the resource pool to obtain the current IOPS value corresponding to the current time point.

[0121] Step 302: Determine the IOPS change amount according to the current IOPS value and the predicted IOPS value.

[0122] In this step, the predicted IOPS value is subtracted from the current IOPS value to obtain the difference between the predicted IOPS value and the current IOPS value. If the difference is a positive number, the difference is determined as the IOPS change. If the difference is a negative number, the absolute value of the difference is determined as the IOPS change.

[0123] Step 303: According to the configuration parameters of the resource pool, determine the maximum IOPS change and the minimum IOPS value corresponding to the configuration parameters.

[0124] In this step, when the resource pool is operating normally, the performance of resource pools with different configuration parameters will be different, which will lead to differences in the corresponding maximum IOPS change and minimum IOPS value. Therefore, it is necessary to determine the maximum IOPS change and minimum IOPS value corresponding to the configuration parameters according to the configuration parameters of the resource pool. The specific steps are: detecting the association relationship between the configuration parameters, the maximum IOPS change and the minimum IOPS value pre-stored in the device, and obtaining the association relationship when it is necessary to execute this step, and determining the maximum IOPS change and minimum IOPS value corresponding to the configuration parameters according to the configuration parameters of the resource pool and the association relationship.

[0125] Step 304: Determine whether to trigger a fault warning operation based on the predicted IOPS value, the IOPS change, the maximum IOPS change, and the minimum IOPS value.

[0126] In this step, the detection device may first detect whether the predicted IOPS value is less than the minimum IOPS value. When the predicted IOPS value is less than the minimum IOPS value, it is determined to trigger a fault warning operation. When the predicted IOPS value is greater than or equal to the minimum IOPS value, it is detected whether the IOPS change is greater than the maximum IOPS change. When the IOPS change is greater than the maximum IOPS change, it is determined to trigger a fault warning operation. Alternatively, the detection device directly detects whether the predicted IOPS value is less than the minimum IOPS value, and whether the IOPS change is greater than the maximum IOPS change. When the predicted IOPS value is less than the minimum IOPS value, and the IOPS change is greater than the maximum IOPS change, it is determined to trigger a fault warning operation; otherwise, it is determined not to trigger a fault warning operation.

[0127] In this step, the IOPS change trend can also be determined based on the current IOPS value and the predicted IOPS value, and then whether to trigger a fault warning operation can be determined based on the IOPS change trend, the predicted IOPS value, the IOPS change amount, the IOPS maximum change amount, and the IOPS minimum value. The specific steps are: the detection device can detect whether the IOPS change trend is decreasing, whether the IOPS change amount is greater than the IOPS maximum change amount, and whether the predicted IOPS value is less than the IOPS minimum value. When the IOPS change trend is decreasing, the IOPS change amount is greater than the IOPS maximum change amount, and the predicted IOPS value is less than the IOPS minimum value, it is determined to trigger a fault warning operation.

[0128] Assume that the maximum IOPS change is 3600 and the minimum IOPS is 36000. When the IOPS value drops from 3700 to 35000, it is determined that a fault warning operation is triggered.

[0129] In the embodiment of the present application, it is also possible to determine whether the performance of the resource pool is normal based on the predicted delay time, thereby determining whether to trigger a fault warning operation. Therefore, the embodiment of the present application also provides another fault judgment method, which is as follows: Figure 4 As shown, the specific steps include:

[0130] Step 401, obtaining the current delay time corresponding to the current time point.

[0131] In this step, the detection device may detect the performance of the resource pool to obtain the current delay time corresponding to the current time point.

[0132] Step 402: Determine the delay variation according to the current delay time and the predicted delay time.

[0133] In this step, the predicted delay time is subtracted from the current delay time to obtain a difference between the two. If the difference is a positive number, the difference is determined as the delay variation. If the difference is a negative number, the absolute value of the difference is determined as the delay variation.

[0134] Step 403: Determine the maximum delay variation and the maximum delay value corresponding to the configuration parameters according to the configuration parameters of the resource pool.

[0135] In this step, when the resource pool operates normally, the performance of resource pools with different configuration parameters will be different, which will lead to differences in the corresponding maximum delay changes and maximum delay values. Therefore, it is necessary to determine the maximum delay change and the maximum delay value corresponding to the configuration parameters according to the configuration parameters of the resource pool, and the specific steps are: pre-store the association relationship between the configuration parameters, the maximum delay change and the maximum delay value in the detection device, and when it is necessary to perform this step, obtain the association relationship, and determine the maximum delay change and the maximum delay value corresponding to the configuration parameters according to the configuration parameters of the resource pool and the association relationship.

[0136] Step 404 , determining whether to trigger a fault warning operation based on the predicted delay time, the delay variation, the maximum delay variation, and the maximum delay value.

[0137] In this step, the detection device may first detect whether the predicted delay time is greater than the maximum delay value, and when the predicted delay time is greater than the maximum delay value, determine to trigger the fault warning operation. When the predicted delay time is less than or equal to the maximum delay value, detect whether the delay change is greater than the maximum delay change, and when the delay change is greater than the maximum delay change, determine to trigger the fault warning operation. Or the detection device directly detects whether the predicted delay time is greater than the maximum delay value, and whether the delay change is greater than the maximum delay change. When the predicted delay time is greater than the maximum delay value, and the delay change is greater than the maximum delay change, determine to trigger the fault warning operation, otherwise, determine not to trigger the fault warning operation.

[0138] In this step, the delay change trend can also be determined based on the current delay time and the predicted delay time, and then whether to trigger the fault warning operation can be determined based on the delay change trend, the predicted delay time, the delay change amount, the maximum delay change amount and the minimum delay value. The specific steps are: the detection device can detect whether the delay change trend is decreasing, whether the delay change amount is greater than the maximum delay change amount, and whether the predicted delay time is greater than the maximum delay value. When the delay change trend is decreasing, the delay change amount is greater than the maximum delay change amount, and the predicted delay time is greater than the maximum delay value, it is determined to trigger the fault warning operation.

[0139] Assume that the maximum delay variation is 0.24ms and the maximum delay value is 1.2ms. When the delay time increases from 0.3 to 1.3ms, it is determined that the fault warning operation is triggered.

[0140] In the embodiment of the present application, technicians can set the maximum IOPS change and the minimum IOPS value based on experience, or they can be obtained based on a certain calculation method. Therefore, the embodiment of the present application provides a calculation method. Figure 5 As shown, specifically including:

[0141] Step 501: Obtain a set of IOPS values ​​of a resource pool when it operates normally using different configuration parameters.

[0142] In this step, the technician can collect the IOPS values ​​of the resource pool when it is operating normally with different configuration parameters, and form an IOPS value set, and then store the IOPS value set and the corresponding configuration parameters in the detection device. In this way, when necessary, the detection device can obtain the IOPS value set of the resource pool when it is operating normally with different configuration parameters.

[0143] Step 502: For different configuration parameters, determine the IOPS average value corresponding to the IOPS value set.

[0144] In this step, for different configuration parameters, the number of IOPS values ​​in the IOPS value set is counted, all IOPS values ​​in the IOPS value set are added together to obtain the sum of the IOPS values, and the sum of the IOPS values ​​is divided by the number to obtain the IOPS average value.

[0145] Step 503: Determine the IOPS minimum value and the IOPS maximum change amount corresponding to the configuration parameters according to the IOPS average value.

[0146] In this step, the IOPS average value corresponding to the configuration parameter can be determined as the IOPS minimum value corresponding to the configuration parameter, and the product of the IOPS minimum value and the first preset percentage can be determined as the IOPS maximum variation corresponding to the configuration parameter.

[0147] The first preset percentage is set by technicians based on experience and can generally be set to 10%.

[0148] In the embodiment of the present application, the technician can set the maximum delay change amount and the minimum delay value based on experience, or obtain the maximum delay change amount and the minimum delay value based on a certain calculation method. After obtaining these data, they can be stored in the detection device for subsequent use. Therefore, the embodiment of the present application provides another calculation method, which is as follows: Figure 6 As shown, specifically including:

[0149] Step 601: Obtain a delay time set when a resource pool operates normally using different configuration parameters.

[0150] In this step, the technician can collect the delay time when the resource pool is operating normally with different configuration parameters, and form a delay time set, and then store the delay time set and the corresponding configuration parameters in the detection device. In this way, when necessary, the detection device can obtain the delay time set when the resource pool is operating normally with different configuration parameters.

[0151] Step 602: for different configuration parameters, determine the average delay time corresponding to the delay time set.

[0152] In this step, for different configuration parameters, the number of delay times in the delay time set is counted, all delay times in the delay time set are added together to obtain the sum of the delay times, and the sum of the delay times is divided by the number to obtain the average delay time.

[0153] Step 603: Determine the maximum delay value and the maximum delay variation corresponding to the configuration parameters according to the average delay time.

[0154] In this step, the average delay time corresponding to the configuration parameter can be determined as the maximum delay value corresponding to the configuration parameter, and the product of the average delay time and the second preset percentage can be determined as the maximum delay variation corresponding to the configuration parameter.

[0155] The second preset percentage is set by technicians based on experience and can generally be set to 20%.

[0156] In the embodiment of the present application, when the storage space of the resource pool is insufficient, the resource pool is more likely to fail. In order to detect whether the resource pool fails in time, the maximum change in IOPS and the maximum change in latency can be adjusted to make the detection method more sensitive to avoid failure of the resource pool. Therefore, the embodiment of the present application provides a data adjustment method, which is as follows: Figure 7 As shown, specifically including:

[0157] Step 701: Determine the adjustment range to be used according to the load of the resource pool.

[0158] The adjustment range is used to indicate the range of adjusting the maximum change in IOPS and / or the maximum change in latency.

[0159] In this step, it is determined whether the storage space of the resource pool is sufficient based on the load of the resource pool, and then the sensitivity of the fault warning is adjusted based on whether the storage space of the resource pool is sufficient. For example, when only 80% of the storage space of the resource pool is left, it is determined that the storage space of the resource pool is very insufficient, and the adjustment amplitude can be set to a negative value to reduce the relevant change amount, making the fault warning more sensitive. When more than half of the storage space of the resource pool is not used, it is determined that the storage space of the resource pool is sufficient, and the adjustment amplitude can be set to a positive value to increase the relevant change amount, making the fault warning relatively insensitive. When more than half of the storage space of the resource pool is unused, but less than 80%, it is determined that the storage space of the resource pool is relatively sufficient, and the adjustment amplitude can be set to 0.

[0160] Step 702: adjust the maximum IOPS variation and / or the maximum latency variation according to the adjustment range.

[0161] In this step, if the maximum IOPS change needs to be adjusted, the maximum IOPS change and the adjustment range can be added to obtain the adjusted maximum IOPS change. If the maximum delay change needs to be adjusted, the maximum delay change and the adjustment range can be added to obtain the adjusted maximum delay change.

[0162] The present application embodiment provides a method for determining fault warning information, which further defines step 104. Specifically, Figure 8 As shown, including:

[0163] Step 801: Determine, according to the configuration parameters, the association relationship corresponding to the configuration parameters.

[0164] The correlation relationship is the correlation relationship between the IOPS change, the latency change, and the fault warning information.

[0165] In this step, the detection device pre-stores association relationships corresponding to different configuration parameters. Therefore, when it is necessary to obtain an association relationship corresponding to a certain configuration parameter, the detection device can find the association relationship corresponding to the configuration parameter among the association relationships corresponding to different configuration parameters based on the configuration parameter.

[0166] Step 802: Determine fault warning information in the associated relationship according to the IOPS change and the delay change.

[0167] In this step, the detection device can search in the association relationship according to the IOPS change amount and the delay change amount to obtain fault warning information.

[0168] In practice, if only the data at the current time point or the next time point is analyzed, the fault warning information obtained may be inaccurate. Therefore, in order to obtain more accurate fault warning information, the present application can analyze the relevant data of the time period to which the current time point belongs, analyze the data change process of the entire time period, and then obtain the fault warning information. Therefore, the present application embodiment also provides a method for determining fault warning information, which is a further limitation of step 104, specifically as follows Fig. 9 As shown, including:

[0169] Step 901, taking the current time point as the end time point, searching forward for a start time point that is separated from the end time point by a preset time length.

[0170] Among them, the preset duration is the duration set by the technician based on experience.

[0171] In this step, when the fault warning operation is triggered, the detection device can obtain the current time point, and use the current time point as the end time point, and look forward to find the start time point with a preset time interval from the end time point.

[0172] Step 902: Determine a detection time period according to the start time point and the end time point.

[0173] In this step, the detection device uses the start time point as the start point of the detection time period and uses the end time point as the end point of the detection time period to obtain the detection time period.

[0174] Step 903: Obtain relevant data to be tested of the resource pool within the detection time period.

[0175] The data to be tested may include IOPS value, delay time, configuration parameters, load parameters, and other data of the resource pool.

[0176] Step 904: Test the relevant data to be tested to obtain fault warning information.

[0177] In this step, the technician can analyze the change trend of the data to be tested and obtain fault warning information. The detection equipment can also store the change curves of the relevant data when various faults occur in the resource pool, compare these change curves with the change curves corresponding to the relevant data to be tested, find out the fault corresponding to the closest change curve, and obtain fault warning information.

[0178] In the embodiment of the present application, a device for determining whether a fault occurs is also provided, which corresponds to the method embodiment, specifically as follows: Fig.10 As shown, including:

[0179] The acquisition unit 1001 is used to acquire the configuration parameters and load parameters of the resource pool at the current time point;

[0180] An input unit 1002 is used to input the configuration parameters and the load parameters into a pre-trained performance prediction model to obtain a predicted IOPS value and a predicted delay time at a next time point;

[0181] A first determining unit 1003 is used to determine whether to trigger a fault warning operation according to the predicted IOPS value and the predicted delay time;

[0182] The analyzing unit 1004 is used to analyze the resource pool to obtain fault warning information when a fault warning operation is triggered.

[0183] Optionally, the performance prediction model includes a data prediction module, a standard deviation determination module and an output module, and the input unit 1002 is used to:

[0184] Input the configuration parameters and the load parameters into a data prediction module, and output a plurality of reference IOPS values ​​and a plurality of reference delay times;

[0185] Inputting multiple reference IOPS values ​​and multiple reference delay times into a standard deviation determination module to obtain an IOPS standard deviation and a delay standard deviation;

[0186] When both the IOPS standard deviation and the delay standard deviation meet the preset conditions, multiple reference IOPS values ​​and multiple reference delay times are input into the output module to obtain the predicted IOPS value and predicted delay time at the next time point.

[0187] Optionally, the first determining unit 1003 is configured to:

[0188] Get the current IOPS value corresponding to the current time point;

[0189] Determine an IOPS change amount according to the current IOPS value and the predicted IOPS value;

[0190] According to the configuration parameters of the resource pool, determining the maximum IOPS change and the minimum IOPS value corresponding to the configuration parameters;

[0191] Whether to trigger a fault warning operation is determined according to the predicted IOPS value, the IOPS change, the maximum IOPS change, and the minimum IOPS value.

[0192] Optionally, the first determining unit 1003 is configured to:

[0193] Get the current delay time corresponding to the current time point;

[0194] Determine a delay variation according to the current delay time and the predicted delay time;

[0195] Determining, according to the configuration parameters of the resource pool, a maximum delay variation and a maximum delay value corresponding to the configuration parameters;

[0196] Whether to trigger a fault warning operation is determined according to the predicted delay time, the delay variation, the maximum delay variation, and the maximum delay value.

[0197] Optionally, the device further includes a second determining unit 1005, and the second determining unit 1005 is configured to:

[0198] Obtaining a set of IOPS values ​​of the resource pool when it operates normally using the configuration parameters;

[0199] Determine an IOPS average value corresponding to the IOPS value set;

[0200] According to the IOPS average value, the IOPS minimum value and the IOPS maximum change amount corresponding to the configuration parameter are determined.

[0201] Optionally, the device further includes an adjustment unit 1006, and the adjustment unit 1006 is used to:

[0202] Determine, according to the load of the resource pool, an adjustment range to be used, where the adjustment range is used to indicate an adjustment range of the maximum change in IOPS and / or the maximum change in latency;

[0203] According to the adjustment range, the maximum IOPS variation and / or the maximum delay variation are adjusted.

[0204] Optionally, the analysis unit 1004 is used for:

[0205] According to the configuration parameters, determining an association relationship corresponding to the configuration parameters, the association relationship being an association relationship between an IOPS change, a delay change, and fault warning information;

[0206] According to the IOPS change amount and the delay change amount, fault warning information is determined in the association relationship.

[0207] like Fig.11 As shown, the embodiment of the present application provides a device for determining whether a fault occurs, including 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.

[0208] Memory 1103, used for storing computer programs;

[0209] In one embodiment of the present application, the processor 1101 is configured to implement the method for determining the occurrence of a fault provided by any one of the aforementioned method embodiments when executing the program stored in the memory 1103, including:

[0210] Get the configuration parameters and load parameters of the resource pool at the current time point;

[0211] Input the configuration parameters and the load parameters into a pre-trained performance prediction model to obtain a predicted IOPS value and a predicted delay time at a next time point;

[0212] Determining whether to trigger a fault warning operation according to the predicted IOPS value and the predicted delay time;

[0213] When a fault warning operation is triggered, the resource pool is analyzed to obtain fault warning information.

[0214] An embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the method for determining the occurrence of a fault as provided in any of the aforementioned method embodiments are implemented.

[0215] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0216] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a general hardware platform, and of course, by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0217] It should be understood that the terms used herein are only for the purpose of describing specific example embodiments and are not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms "one", "an" and "said" as used herein may also be meant to include plural forms. The terms "include", "comprise", "contain", and "have" are inclusive, and therefore specify the existence of stated features, steps, operations, elements and / or parts, but do not exclude the existence or addition of one or more other features, steps, operations, elements, parts, and / or combinations thereof. The method steps, processes, and operations described herein are not interpreted as necessarily requiring them to be performed in the specific order described or illustrated, unless the execution order is clearly indicated. It should also be understood that additional or alternative steps may be used.

[0218] The foregoing is merely a specific embodiment of the present invention, which enables those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A method for determining a fault occurrence, characterized in that: The method comprises: Get the configuration parameters and load parameters of the resource pool at the current time point; Input the configuration parameters and the load parameters into a pre-trained performance prediction model to obtain a predicted IOPS value and a predicted delay time at a next time point; Determining whether to trigger a fault warning operation according to the predicted IOPS value and the predicted delay time; When a fault warning operation is triggered, the resource pool is analyzed to obtain fault warning information.

2. The method according to claim 1, characterized in that: The performance prediction model includes a data prediction module, a standard deviation determination module and an output module. The configuration parameters and the load parameters are input into the pre-trained performance prediction model to obtain a predicted IOPS value and a predicted delay time at the next time point, including: Input the configuration parameters and the load parameters into a data prediction module, and output a plurality of reference IOPS values ​​and a plurality of reference delay times; Inputting multiple reference IOPS values ​​and multiple reference delay times into a standard deviation determination module to obtain an IOPS standard deviation and a delay standard deviation; When both the IOPS standard deviation and the delay standard deviation meet the preset conditions, multiple reference IOPS values ​​and multiple reference delay times are input into the output module to obtain the predicted IOPS value and predicted delay time at the next time point.

3. The method according to claim 1, characterized in that: Determining whether to trigger a fault warning operation according to the predicted IOPS value includes: Get the current IOPS value corresponding to the current time point; Determine an IOPS change amount according to the current IOPS value and the predicted IOPS value; According to the configuration parameters of the resource pool, determining the maximum IOPS change and the minimum IOPS value corresponding to the configuration parameters; Whether to trigger a fault warning operation is determined according to the predicted IOPS value, the IOPS change, the maximum IOPS change, and the minimum IOPS value.

4. The method according to claim 3, characterized in that: Determining whether to trigger a fault warning operation according to the predicted delay time includes: Get the current delay time corresponding to the current time point; Determine a delay variation according to the current delay time and the predicted delay time; Determining, according to the configuration parameters of the resource pool, a maximum delay variation and a maximum delay value corresponding to the configuration parameters; Whether to trigger a fault warning operation is determined according to the predicted delay time, the delay variation, the maximum delay variation, and the maximum delay value.

5. The method according to claim 3, characterized in that: The method comprises: Obtain a set of IOPS values ​​of the resource pool when it operates normally using different configuration parameters; For different configuration parameters, an IOPS average value corresponding to the IOPS value set is determined, and based on the IOPS average value, an IOPS minimum value and an IOPS maximum change amount corresponding to the configuration parameter are determined.

6. The method according to claim 4, characterized in that: The method further comprises: Determine, according to the load of the resource pool, an adjustment range to be used, where the adjustment range is used to indicate an adjustment range of the maximum change in IOPS and / or the maximum change in latency; According to the adjustment range, the maximum IOPS variation and / or the maximum delay variation are adjusted.

7. The method according to claim 4, characterized in that: The analyzing the resource pool to obtain fault warning information includes: According to the configuration parameters, determining an association relationship corresponding to the configuration parameters, the association relationship being an association relationship between an IOPS change, a delay change, and fault warning information; According to the IOPS change amount and the delay change amount, fault warning information is determined in the association relationship.

8. A device for determining whether a fault has occurred, characterized in that: The device comprises: An acquisition unit, used to acquire configuration parameters and load parameters of the resource pool at the current time point; An input unit, used to input the configuration parameters and the load parameters into a pre-trained performance prediction model to obtain a predicted IOPS value and a predicted delay time at a next time point; A first determining unit, configured to determine whether to trigger a fault warning operation according to the predicted IOPS value and the predicted delay time; The analysis unit is used to analyze the resource pool to obtain fault warning information when a fault warning operation is triggered.

9. A device for determining whether a fault has occurred, characterized in that: include: at least one communication interface; at least one bus connected to the at least one communication interface; at least one processor connected to the at least one bus; at least one memory connected to the at least one bus, wherein the processor is configured to: Get the configuration parameters and load parameters of the resource pool at the current time point; Input the configuration parameters and the load parameters into a pre-trained performance prediction model to obtain a predicted IOPS value and a predicted delay time at a next time point; Determining whether to trigger a fault warning operation according to the predicted IOPS value and the predicted delay time; When a fault warning operation is triggered, the resource pool is analyzed to obtain fault warning information.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for determining the occurrence of a fault according to any one of claims 1 to 7 is implemented.

Images