SSD data exception rapid detection method, server, medium and program product

Abstract

The invention provides an SSD data exception rapid detection method, a server, a medium and a program product, and relates to the technical field of solid state disk detection. The method comprises the following steps: acquiring performance data of different types of SSDs as samples, and training through a machine learning algorithm to obtain an SSD type adaptation model for determining the type of the current SSD. Next, after obtaining new performance data of a new SSD, the new performance data is input into the model to determine the SSD type. And then, according to the SSD type, adjusting an exception threshold parameter of the SSD data exception determination model, and inputting the new performance data into the model, thereby determining the data exception condition of the SSD. By implementing the method, different types of SSD data anomalies can be found in time, so that the security and stability of the data are guaranteed.

Description

Technical Field

[0001] The present application relates to the field of solid state drive detection technology, and in particular to a method, server, medium and program product for rapid detection of SSD data anomalies. Background Art

[0002] With the development of information technology, the usage of various types of servers has continued to increase. Solid-state drives (SSDs) are widely used in servers due to their small size and fast reading speed. To ensure the normal operation of the server, it is necessary to regularly detect the SSD in the server to find out any data anomalies.

[0003] The existing technology uses a fixed abnormal data judgment threshold to detect all SSDs. The specific method is to first collect normal data and abnormal data of different SSDs, and set the threshold parameters for determining abnormalities based on these data; then when detecting a new SSD, directly use the preset threshold parameters to compare with the data of the new SSD to determine whether it is abnormal.

[0004] However, due to the differences in performance parameters between SSDs of different manufacturers and models, the use of fixed or uniform threshold parameters for detection will result in poor data anomaly detection for certain models of SSDs, making it difficult to accurately determine anomalies. Therefore, it is difficult for existing methods to achieve efficient abnormal data detection on different SSDs based on accurate adaptation for various unknown SSDs. Summary of the invention

[0005] The present application provides a method, server, medium and program product for rapid detection of SSD data anomalies, which are used to accurately and rapidly detect data anomalies of different types of SSDs when the existing technology is difficult to adapt to the performance differences of different SSDs.

[0006] In a first aspect, the present application provides a method for rapid detection of SSD data anomalies, which is applied to a server, and the method includes: obtaining performance data of different types of SSDs as sample data; training an SSD type adaptation model through a machine learning algorithm based on the sample data, and the SSD type adaptation model is used to determine the type of the current SSD; after obtaining new performance data of a new SSD, inputting the new performance data into the SSD type adaptation model to determine the SSD type; adjusting the anomaly threshold parameters corresponding to the SSD data anomaly determination model according to the SSD type, and the SSD data anomaly determination model is a model constructed based on multiple normal data and abnormal data of the SSD obtained in advance; inputting the new performance data into the SSD data anomaly determination model to determine the data anomaly of the SSD.

[0007] By adopting the above technical solution, the SSD type adaptation model trained by the machine learning algorithm can be used to quickly and accurately determine the type of the current SSD. Then, the abnormal threshold parameters of the SSD data abnormality determination model are adjusted according to the SSD type, and the new performance data is input into the model, thereby realizing the rapid detection of SSD data abnormalities. This method improves the detection efficiency and accuracy, can timely detect SSD data abnormalities, and ensure the security and stability of data.

[0008] In combination with some embodiments of the first aspect, in some embodiments, after the step of inputting the new performance data into the SSD data anomaly determination model to determine the data anomaly situation of the SSD, it also includes: if the data anomaly situation is that the new performance data is abnormal, SSD data anomaly alarm information is sent to the management end; after determining the new performance data with the abnormality as abnormal data, the abnormal data is fed back to the SSD data anomaly determination model for updating.

[0009] By adopting the above technical solution, relevant personnel can be notified in time to handle the problem, reducing the losses caused by data anomalies. At the same time, feeding back the abnormal data to the SSD data anomaly determination model for updating helps improve the accuracy and adaptability of the model, enabling it to better detect future SSD data anomalies.

[0010] In combination with some embodiments of the first aspect, in some embodiments, if the data anomaly is that the new performance data is anomaly, the step of sending SSD data anomaly alarm information to the management end specifically includes: determining the log information when the new performance data is sent abnormally; determining the association rule between the two based on the data anomaly and the log information; when the log information meets the association rule corresponding to the data anomaly, sending SSD data anomaly alarm information to the management end in advance.

[0011] By adopting the above technical solution, potential problems can be discovered more promptly, the accuracy and timeliness of fault warnings can be improved, and the stable operation of the server can be further guaranteed.

[0012] In combination with some embodiments of the first aspect, in some embodiments, after the step of adjusting the abnormality threshold parameters corresponding to the SSD data anomaly determination model according to the SSD type, it also includes: acquiring working environment data of the new SSD through a sensor, and the working environment data at least includes the temperature and humidity of the new SSD in a working state; inputting the working environment data into the environmental impact model to obtain SSD performance impact data, and the environmental impact model is a model established based on the impact of different temperature and humidity environments on SSD performance data obtained in advance; and correcting the abnormality threshold parameters in the SSD data anomaly determination model according to the SSD performance impact data.

[0013] By adopting the above technical solution, it is possible to more accurately determine whether SSD data is abnormal, reduce misjudgments caused by environmental factors, and improve the reliability of detection.

[0014] In combination with some embodiments of the first aspect, in some embodiments, after the step of correcting the abnormal threshold parameter in the SSD data anomaly determination model according to the SSD performance impact data, it also includes: obtaining the service life data of the new SSD; and adjusting the abnormal threshold parameter in the SSD data anomaly determination model again according to the service life data.

[0015] By adopting the above technical solution, the influence of the service life of the SSD on its performance can be taken into account, so that the abnormal threshold parameters are more reasonable, the accuracy and pertinence of the detection are improved, and the normal operation of the SSD is better guaranteed.

[0016] In combination with some embodiments of the first aspect, in some embodiments, after the step of inputting the new performance data into the SSD data anomaly determination model to determine the data anomaly situation of the SSD, it also includes: when the data anomaly situation is that the new performance data matches the anomaly threshold parameter for multiple consecutive times, it is determined that the new SSD has a fault; obtaining the current operating status data of the server; inputting the operating status data into a fault impact model, and the fault impact model determines the type and degree of impact of the fault on server performance and data integrity based on the operating status data; when it is determined that the fault impact type meets the set conditions, marking the physical location of the new SSD; and determining the isolation method of the new SSD based on the physical location.

[0017] By adopting the above technical solution, the faulty SSD can be isolated in time, reducing its impact on the server, and ensuring the stable operation of the server and data security.

[0018] In combination with some embodiments of the first aspect, in some embodiments, after the step of inputting the new performance data into the SSD data anomaly determination model to determine the data anomaly of the SSD, it also includes: sending an inspection prompt message to the management end based on the data anomaly; after receiving the inspection result fed back by the management end, determining the cause of the anomaly of the new performance data based on the inspection result; determining an optimization plan based on the cause of the anomaly, and the optimization plan is used to eliminate the factors that cause the new performance data anomaly so that the new SSD can return to a normal working state.

[0019] By adopting the above technical solution, measures can be taken in time to eliminate the factors that cause data anomalies, so that the new SSD can be restored to a normal working state, and the reliability and stability of the SSD can be improved.

[0020] In a second aspect, the present application provides a server, comprising: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to cause the server to execute the method described in the first aspect and any possible implementation of the first aspect.

[0021] In a third aspect, the present application provides a computer-readable storage medium comprising instructions, which, when executed on a server, causes the server to execute the method described in the first aspect and any possible implementation of the first aspect.

[0022] In a fourth aspect, the present application provides a computer program product, which, when executed on a server, enables the server to execute the method described in the first aspect and any possible implementation manner of the first aspect.

[0023] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. The present invention adopts the technical means of obtaining the performance data of different types of SSDs as sample data, obtaining the SSD type adaptation model through training with a machine learning algorithm, and adjusting the abnormal threshold parameters corresponding to the SSD data abnormality determination model according to the SSD type. Therefore, the problem of low efficiency and easy errors in manual identification of SSD types in the prior art is effectively solved, and the technical effect of fast and accurate identification of SSD types and precise detection of SSD data abnormalities is achieved.

[0024] 2. The present invention adopts a technical method of obtaining the working environment data of the new SSD through a sensor and inputting it into the environmental impact model to obtain the SSD performance impact data, thereby correcting the abnormal threshold parameters in the SSD data abnormality determination model according to the data. Therefore, the technical problem of misjudgment of SSD data abnormality detection caused by failure to consider environmental factors in the prior art is effectively solved, thereby achieving the technical effect of more accurately judging whether the SSD data is abnormal.

[0025] 3. When the new performance data matches the abnormal threshold parameters for multiple consecutive times, it is determined that the new SSD is faulty, and the current operating status data of the server is obtained and input into the fault impact model to determine the type and degree of impact of the fault on server performance and data integrity, and then the physical location of the new SSD is marked and the isolation method is determined. Therefore, the technical problem that the prior art cannot isolate the faulty SSD in time to reduce its impact on the server is effectively solved, thereby achieving the technical effect of timely isolating the faulty SSD and ensuring the stable operation of the server and data security. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 This is a flow chart of a method for rapid detection of SSD data anomalies in an embodiment of the present application; Figure 2 This is another flowchart of the method for rapid detection of SSD data anomalies in an embodiment of the present application; Figure 3 It is a schematic diagram of a physical device structure of a server in an embodiment of the present application. DETAILED DESCRIPTION

[0027] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to be used as limitations to the present application. As used in the specification and appended claims of the present application, the singular expressions "one", "a kind of", "said", "above", "the" and "this" are intended to also include plural expressions, unless there is a clear indication to the contrary in the context. It should also be understood that the term "and / or" used in the present application refers to and includes any or all possible combinations of one or more listed items.

[0028] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.

[0029] For ease of understanding, an application scenario of the relevant method is introduced below.

[0030] In a large data center, massive amounts of data are stored, using solid-state drives (SSDs) from different manufacturers and models. In order to ensure the security and stability of data, the administrator of the data center uses a unified threshold detection method in the existing technology to monitor data anomalies of SSDs. One day, the data center introduced a batch of high-performance SSDs from different manufacturers. During operation, the performance parameters of these new SSDs are very different from those of the previously used SSDs. When testing according to fixed threshold parameters, some new SSDs that are actually in normal working condition are misjudged as data anomalies, and frequent alarms are issued, making the administrator exhausted. At the same time, some new SSDs that actually have data anomalies are not detected in time, which brings huge risks to data security.

[0031] It can be seen that the existing methods are obviously unable to meet the requirements of accurate adaptation to various unknown SSDs and efficient abnormal data detection.

[0032] The SSD data anomaly rapid detection method in the embodiment of the present application is used to obtain the performance data of different types of SSDs as sample data, and train the SSD type adaptation model based on the sample data through a machine learning algorithm, so as to quickly and accurately determine the type of the current SSD. In addition, the anomaly threshold parameter corresponding to the SSD data anomaly determination model can be adjusted according to the SSD type, and new performance data can be input into the model, so as to accurately detect the data anomaly of the SSD.

[0033] For ease of understanding, the following describes the process of the method provided by this implementation in combination with the above content. Figure 1 , which is a flow chart of a method for rapid detection of SSD data anomalies in an embodiment of the present application.

[0034] S101, obtaining performance data of different types of SSDs as sample data; The server first needs to collect performance data of different types of SSDs as sample data. Specifically, the server can connect to SSDs produced by various manufacturers, and then read and collect performance parameters of these SSDs, such as read and write speed, I / O response time, life cycle, etc. In order to obtain sufficient and comprehensive sample data, the server needs to connect to as many different models of SSDs from different manufacturers as possible, at least covering the mainstream products of mainstream manufacturers.

[0035] S102: obtaining an SSD type adaptation model through training with a machine learning algorithm according to the sample data, where the SSD type adaptation model is used to determine the type of the current SSD; The server inputs the collected rich SSD performance sample data into the machine learning algorithm for training to obtain the SSD type adaptation model. This model can accurately identify the characteristics of different types of SSDs and is used to quickly determine the category and model of the new SSD. The machine learning algorithm can use a neural network, and the server can build a deep neural network that includes an input layer, multiple hidden layers, and an output layer. The number of input layer nodes corresponds to the number of features of the sample data, and the number of output layer nodes corresponds to the number of SSD types. The hidden layer can be set up in multiple layers, and the number of nodes in each layer gradually decreases, which increases the network's ability to extract and abstract features of the sample data.

[0036] The server feeds the collected rich SSD performance sample data into the neural network for iterative training, adjusts the network edge weights to fit the complex mapping relationship between SSD performance data and SSD types, and obtains a model that can accurately identify the SSD type of new input SSD performance data. The model contains both SSD performance data features and SSD type outputs, and the new SSD type adaptation model can quickly determine its category.

[0037] S103, after obtaining new performance data of the new SSD, input the new performance data into the SSD type adaptation model to determine the SSD type; After the server is connected to a new SSD, it will obtain the latest performance data of the SSD. The server can obtain various performance data such as the read and write speed, IOPS, and average response time of the SSD through acquisition commands. The server inputs these newly acquired performance data into the trained SSD type adaptation model for inference calculation. The model analyzes the characteristics of these data and outputs that the new SSD is likely to be a 512GB type for a certain brand of mobile phone.

[0038] Here, through the accurate judgment of the model, the server can quickly know the detailed category information of the new SSD, laying the foundation for subsequent customized anomaly detection.

[0039] S104, adjusting an abnormality threshold parameter corresponding to an SSD data abnormality determination model according to the SSD type, where the SSD data abnormality determination model is a model constructed based on a plurality of normal data and abnormal data of the SSD acquired in advance; The server adjusts the parameters of the model used to detect data anomalies based on the type of new SSD.

[0040] The SSD data anomaly detection model is pre-trained by the server based on a large amount of normal and abnormal data collected from SSDs. SSDs of different types and specifications have different performance data. Therefore, the detection model needs to dynamically adjust the threshold parameters for judging data anomalies according to the SSD category and specification to achieve accurate anomaly detection.

[0041] For example, for a 512GB PCIe SSD of a certain brand of mobile phone, based on its read and write speed range, the server can determine that its read speed is lower than 3000MB / s as abnormal; its write speed is lower than 1500MB / s as abnormal; its average read latency is higher than 100μs as abnormal, etc. Only after adjusting the thresholds of multiple performance parameters can the model make accurate judgments for the specific model of SSD.

[0042] S105 . Input the new performance data into the SSD data anomaly determination model to determine the data anomaly of the SSD.

[0043] After obtaining the parameterized anomaly detection model adjusted for the new SSD, the server can use the model to perform anomaly detection on the SSD.

[0044] The server will regularly obtain the latest performance data of the new SSD and input it into the adjusted model for calculation to determine whether the data of each performance indicator is abnormal, for example: read speed 3200MB / s → normal; write speed 1400MB / s → normal; average read latency 120μs → abnormal... By inputting it into the parameterized detection model, the server can quickly and automatically determine whether there are any abnormalities in the data of the new SSD. Once an anomaly is detected, feedback measures can be taken quickly to ensure data security. In addition, the detection results can also be used to add abnormal data samples of the new SSD and feed them back to the model to enhance its detection capabilities. And as the model processes more new SSDs, its generalization performance will continue to improve, and it will be able to adapt to more unknown SSDs, thereby achieving efficient and accurate SSD data anomaly detection.

[0045] In the embodiments of the present application, the performance data of different types of SSDs are obtained as samples, and the SSD type adaptation model is obtained through training with a machine learning algorithm, and the parameters of the SSD data anomaly determination model are dynamically adjusted according to the SSD type. This effectively solves the problem that fixed threshold parameters in the prior art are difficult to adapt to the performance differences of different SSDs, and achieves accurate identification of SSD types and customization of data anomaly detection models by model, thereby achieving the technical effect of fast and accurate data anomaly detection for different SSD models.

[0046] In some embodiments, when the server detects that the performance data of the new SSD is abnormal, it needs to send an alarm message to the management end in time so that the administrator can handle it as soon as possible. At the same time, it is also necessary to feed back the abnormal data to the SSD data anomaly detection model to improve the accuracy of the model. The sending of alarm information can be optimized in combination with log information to achieve more intelligent and accurate early warning.

[0047] Specifically, when the server detects an abnormality in performance data, it will immediately extract the relevant log information of the SSD before the abnormality occurs, such as the interface statistics log, which records the interface response time, transmission speed and other information. The server will then use the association rule algorithm to determine the correlation between the detected performance abnormality and the interface log information. For example, if an abnormal reading speed is detected, the read speed data item in the interface log is analyzed to see if there is also an abnormal value; if an interface response timeout is detected, the response time in the performance data is analyzed to see if it is abnormal.

[0048] When the log information meets the association rules corresponding to the current performance anomaly, it is confirmed that the two are highly correlated, that is, the log information can verify and predict the occurrence of performance anomalies. At this time, the server will send a performance anomaly warning to the management side in advance. For example, the interface log of a PCIe SSD showed that it encountered multiple sudden drops in read speed in the previous period, but the performance data was still normal. The detection model matches the interface log with the association rule of "reduced read speed" and meets the corresponding relationship. The server will determine that the read speed anomaly may be brewing, and promptly warn the management side of the "SSD read speed degradation warning", so that the administrator has time to optimize the configuration and avoid failures.

[0049] In this way, through correlation analysis with log information, more intelligent and accurate performance anomaly warnings can be achieved, ensuring that managers have enough time to prevent faults, avoid data anomalies from expanding into faults, and improve system reliability.

[0050] At the same time, when the new performance data is determined to be abnormal data, the server will also feed it back to the SSD anomaly detection model to enhance the model's ability to judge abnormal data. This allows the model to learn new types and patterns of anomalies and continuously optimize the accuracy of the model.

[0051] In some embodiments, the server periodically monitors the performance data of all SSDs, such as read and write speeds, IOPS, response time, etc.

[0052] Compare the latest performance data of the new SSD with the normal threshold parameters. The abnormal threshold parameters can be preset or dynamically generated by analyzing historical data. If the latest performance data of the new SSD matches the abnormal threshold parameters for multiple times (for example, 5 times) in a row, it is determined that the new SSD is faulty. Obtain the current operating status data of the server, including the utilization rate, workload, number of IO requests, etc. of subsystems such as CPU, memory, and network. Input the operating status data into a pre-trained fault impact model. The model can use algorithms such as neural networks or decision trees to predict the type and degree of impact of the fault on server performance and data integrity based on the operating status data.

[0053] The impact type can be divided into: reduced performance, data loss, service unavailability, etc. The impact degree can be expressed in terms of probability or score. According to the output of the fault impact model, if it is determined that the fault will cause data loss or service unavailability, it meets the set severe impact condition. Mark the physical installation location of the new SSD. For example, the rack number, server number, slot number, etc. The location information can be obtained from the device asset database. If the new SSD is installed in a chassis of a rack server, we can directly turn off the power switch of the chassis, cut off the power supply of the new SSD, and isolate it from the system. In this way, there is no need to open the chassis. Simply turn off the power to simply and quickly isolate the faulty SSD to avoid affecting other running servers. If a server uses RAID, multiple hard disks will be combined into a disk array. If the new SSD is a member of the array, we can delete or remove it from the array through the RAID management interface and remove it from the current disk array. In this way, the faulty new SSD can be isolated. At the same time, since it is removed through software logic, there will be no physical power outage, so the impact on server operation is small.

[0054] Through the above embodiments, the automated and intelligent management capabilities can be fully utilized to accurately locate the cause of SSD failure, evaluate the impact of the failure, and ultimately take isolation and backup measures to ensure reliable operation of the system.

[0055] In some embodiments, when the performance data of the new SSD is continuously abnormal, the server can push a prompt message of the new SSD failure to the management end through the alarm system. The information contains key information of the new SSD, such as time, serial number, and abnormal data indicators. After the management end receives the prompt, the server needs to provide the necessary interface and permissions to allow the management end to log in remotely and check the detailed status of the new SSD through the tool. After the relevant personnel of the management end complete the new SSD status check, they will feedback the results to the server. The server needs to parse the inspection results and determine the cause of the performance abnormality, such as firmware problems, interface incompatibility, improper parameter settings, etc. According to the abnormal cause, the server can determine the corresponding optimization measures, such as upgrading the SSD firmware, adjusting interface parameters, compatibility settings, etc. The goal is to eliminate the factors that cause the abnormality and restore the new SSD to normal. The server needs to actively control the entire optimization process and provide status data on demand to form a closed loop with the management end to locate the problem and verify the optimization effect as soon as possible, so that the new SSD can return to normal working state.

[0056] In some scenarios, if the temperature or humidity environment in the server room of the data center fluctuates greatly, it will affect the performance of the SSD. Directly applying the preset anomaly detection model may cause false alarms. In addition, after using the SSD for a period of time, its performance will show a downward trend. If the preset anomaly detection model is directly applied, it may misjudge the degraded performance.

[0057] After combining the above scenarios, the following is a more detailed description of the process of the method provided by this implementation. Figure 2 , is another flow chart of the method for rapid detection of SSD data anomalies in an embodiment of the present application.

[0058] S201, acquiring working environment data of the new SSD through a sensor, where the working environment data at least includes temperature and humidity of the new SSD in a working state; The staff can set up temperature and humidity sensors in the cabinet in advance to detect the working environment temperature and humidity of the new SSD in real time. Considering that the temperature distribution and humidity distribution may be different, the sensor needs to be set close to the new SSD to monitor it directly. For example, if the new SSD is set in the middle layer of the cabinet, set temperature and humidity sensors above and below it to obtain temperature and humidity data in this area.

[0059] The server needs to regularly read the temperature and humidity data collected by the sensor, for example, read the temperature and humidity values ​​of the location of the new SSD every 5 minutes, and record them in the environmental data database. In this way, the real-time working environment temperature and humidity data of the new SSD can be continuously obtained.

[0060] S202, inputting the working environment data into an environmental impact model to obtain SSD performance impact data, wherein the environmental impact model is a model established based on the impact of different temperature and humidity environments on SSD performance data obtained in advance; The server collects a large amount of SSD performance data under different environmental conditions (temperature, humidity) as samples, and inputs them into the machine learning algorithm for training to obtain the environmental impact model.

[0061] The model can input temperature and humidity parameters and output SSD performance data under such environmental conditions, such as changes in read and write speeds, changes in failure rates, etc. Model training can use algorithms such as linear regression to learn the mapping relationship between temperature, humidity, and SSD performance data.

[0062] For example, the server collected the following sample data: Temperature 20°C, humidity 50% --> SSD average read speed 3500MB / s, temperature 30°C, humidity 60% --> SSD average read speed 3200MB / s, temperature 40°C, humidity 70% --> SSD average read speed 3000MB / s... Through a large number of such sample training, we can get the environmental impact model. Then, we input the current temperature and humidity data of the new SSD into the model in real time, and quickly predict the impact data such as the SSD read speed will decrease by xx MB / s and the failure rate will increase by xx% under the environmental conditions. For example, if the current new SSD environmental temperature is 32°C and the humidity is 65%, after inputting the model, the output is expected to decrease the read speed by 100MB / s, decrease the Writes by 80MB / s, and increase the failure rate by 2%. These are the SSD performance impact data.

[0063] S203, modifying the abnormal threshold parameter in the SSD data abnormality determination model according to the SSD performance impact data; After obtaining the SSD performance impact data output by the environmental impact model, the server will apply it to the parameters of the original SSD anomaly detection model for correction. For example, the read speed threshold in the original model is 3000MB / s, which is considered abnormal, and the environmental impact model predicts that the read speed will decrease by 100MB / s in this environment. The server needs to correct the original threshold to 2900MB / s to avoid false alarms caused by environmental changes.

[0064] Similarly, it is also necessary to correct the thresholds of parameters such as write rate and failure rate based on the output data of the environmental impact model, so that the threshold settings used in the final judgment of anomalies are more reasonable, thereby improving the detection effect.

[0065] In this way, the server can dynamically adjust the parameters of its anomaly detection model based on the monitoring of the new SSD environment to solve the false alarm problem caused by environmental changes.

[0066] S204, obtaining service life data of the new SSD; The server needs to track and record the service life of the new SSD in real time in order to consider the impact of SSD usage time on its performance.

[0067] Specifically, when a new SSD is connected, the server can record its factory date, model, expected lifespan and other information. During use, the SSD's working hours, read and write times, wear and tear and other data are counted in real time. Based on this, the proportion of each SSD's used lifespan to the total lifespan, that is, the lifespan percentage, is calculated, for example, 60% of the lifespan has been used. Lifespan data can be collected continuously at a certain period, such as obtaining the latest usage once a day or a week. And it is recorded in the SSD lifespan database for reference in subsequent model adjustments.

[0068] S205. Adjust the abnormal threshold parameter in the SSD data abnormality determination model again according to the service life data.

[0069] Because the longer the SSD is used, the lower its performance will be. Therefore, the server needs to adjust the anomaly detection model again based on the new service life data. Specifically, the mapping relationship between service life and performance degradation can be established in advance. For example, when 50% of the life is used, the read and write speeds are reduced by 10%. When it is obtained that the SSD has used 40% of its life, it can be calculated that its read and write speed parameters need to be lowered accordingly. The aging impact model can also be trained directly by collecting aging SSD performance data in real time. Input the service life and output the impact value on performance, which is used to adjust the detection threshold.

[0070] In this way, as the SSD is used for a longer time, the judgment threshold in the anomaly detection model will be dynamically adjusted to avoid misjudging anomalies due to degraded SSD performance, thereby improving detection accuracy and ensuring server data security.

[0071] In the embodiment of the present application, due to the technical means of obtaining the working environment temperature and humidity data of the new SSD, inputting the environmental impact model to obtain the performance impact value, and then correcting the parameters of the anomaly detection model, the problem of false positives of SSD data anomalies caused by environmental changes in the prior art is effectively solved, thereby achieving the technical effect of improving the accuracy and adaptability of SSD data anomaly detection.

[0072] The following describes the server in the embodiment of the present invention from the perspective of hardware processing. Figure 3 , is a schematic diagram of a physical device structure of a server in an embodiment of the present application.

[0073] It should be noted that Figure 3 The structure of the server shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0074] like Figure 3 As shown, the server includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 302 or the program loaded from the storage part 308 to the random access memory (RAM) 303, such as executing the method described in the above embodiment. In RAM 303, various programs and data required for system operation are also stored. CPU 301, ROM 302 and RAM 303 are connected to each other through bus 304. Input / output (I / O) interface 305 is also connected to bus 304.

[0075] The following components are connected to the I / O interface 305: an input section 306 including an audio input device, a button switch, etc.; an output section 307 including a liquid crystal display (LCD) and an audio output device, an indicator light, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. A removable medium 311, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 310 as needed so that a computer program read therefrom is installed into the storage section 308 as needed.

[0076] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 309, and / or installed from a removable medium 311. When the computer program is executed by the central processing unit (CPU) 301, various functions defined in the present invention are performed.

[0077] It should be noted that specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, apparatus, or device.

[0078] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. Each box in the flowchart or block diagram may represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box may also occur in an order different from that marked in the accompanying drawings.

[0079] Specifically, the server of this embodiment includes a processor and a memory. The memory stores a computer program. When the computer program is executed by the processor, the SSD data anomaly rapid detection method provided in the above embodiment is implemented.

[0080] As another aspect, the present invention further provides a computer-readable storage medium, which may be included in the server described in the above embodiment; or may exist independently without being assembled into the server. The above storage medium carries one or more computer programs, and when the above one or more computer programs are executed by a processor of the server, the server implements the SSD data anomaly rapid detection method provided in the above embodiment.

[0081] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0082] As used in the above embodiments, the term "when..." may be interpreted to mean "if..." or "after..." or "in response to determining..." or "in response to detecting...", depending on the context. Similarly, the phrases "upon determining..." or "if (the stated condition or event) is detected" may be interpreted to mean "if determining..." or "in response to determining..." or "upon detecting (the stated condition or event)" or "in response to detecting (the stated condition or event)", depending on the context.

[0083] Those skilled in the art can understand that to implement all or part of the processes in the above-mentioned embodiments, the processes can be completed by computer programs to instruct related hardware, and the programs can be stored in computer-readable storage media. When the programs are executed, they can include the processes of the above-mentioned method embodiments. The aforementioned storage media include: ROM or random access memory RAM, magnetic disk or optical disk and other media that can store program codes.

Claims

1. A method for rapid detection of SSD data anomalies, applied to a server, characterized in that: The method comprises: Obtain performance data of different types of SSDs as sample data; Obtaining an SSD type adaptation model through training with a machine learning algorithm according to the sample data, wherein the SSD type adaptation model is used to determine the type of the current SSD; After obtaining new performance data of the new SSD, inputting the new performance data into the SSD type adaptation model to determine the SSD type; adjusting an abnormality threshold parameter corresponding to an SSD data abnormality determination model according to the SSD type, wherein the SSD data abnormality determination model is a model constructed based on a plurality of normal data and abnormal data of the SSD acquired in advance; The new performance data is input into the SSD data anomaly determination model to determine the data anomaly of the SSD.

2. The method according to claim 1, characterized in that After the step of inputting the new performance data into the SSD data anomaly determination model to determine the data anomaly of the SSD, the method further includes: If the data abnormality is that the new performance data is abnormal, an SSD data abnormality alarm message is sent to the management end; After the new performance data with anomalies is determined as abnormal data, the abnormal data is fed back to the SSD data anomaly determination model for updating.

3. The method according to claim 2, characterized in that If the data abnormality is that the new performance data is abnormal, the step of sending SSD data abnormality alarm information to the management end specifically includes: Determine log information when the new performance data is sent abnormally; Determine an association rule between the data anomaly and the log information; When the log information satisfies the association rule corresponding to the data anomaly situation, SSD data anomaly alarm information is sent to the management end in advance.

4. The method according to claim 1, characterized in that: After the step of adjusting the abnormality threshold parameter corresponding to the SSD data abnormality determination model according to the SSD type, the method further includes: Acquire working environment data of the new SSD through a sensor, wherein the working environment data at least includes temperature and humidity of the new SSD in a working state; Inputting the working environment data into an environmental impact model to obtain SSD performance impact data, wherein the environmental impact model is a model established based on the impact of different temperature and humidity environments on SSD performance data obtained in advance; The abnormality threshold parameter in the SSD data abnormality determination model is modified according to the SSD performance impact data.

5. The method according to claim 4, characterized in that After the step of correcting the abnormal threshold parameter in the SSD data abnormality determination model according to the SSD performance influencing data, the method further includes: Obtaining service life data of the new SSD; The abnormality threshold parameter in the SSD data abnormality determination model is adjusted again according to the service life data.

6. The method according to claim 1, characterized in that After the step of inputting the new performance data into the SSD data anomaly determination model to determine the data anomaly of the SSD, the method further includes: When the data abnormality is that the new performance data matches the abnormal threshold parameter for multiple consecutive times, it is determined that the new SSD has a fault; Obtaining current operating status data of the server; Inputting the operation status data into a fault impact model, wherein the fault impact model determines the type and degree of impact of the fault on server performance and data integrity based on the operation status data; When it is determined that the fault impact type meets the set condition, marking the physical location of the new SSD; An isolation mode of the new SSD is determined according to the physical location.

7. The method according to claim 1, characterized in that After the step of inputting the new performance data into the SSD data anomaly determination model to determine the data anomaly of the SSD, the method further includes: Sending inspection prompt information to the management terminal according to the data abnormality; After receiving the inspection result fed back by the management end, determining the abnormal cause of the new performance data according to the inspection result; An optimization scheme is determined according to the abnormal cause, and the optimization scheme is used to eliminate the factors causing the abnormality of the new performance data so as to restore the new SSD to a normal working state.

8. A server, characterized in that: The server includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the server to execute the method described in any one of claims 1-7.

9. A computer-readable storage medium comprising instructions, characterized in that: When the instructions are executed on a server, the server is caused to execute the method according to any one of claims 1 to 7.

10. A computer program product, characterized in that When the computer program product is run on a server, the server is caused to execute the method according to any one of claims 1 to 7.

Images