Block storage component fault detection method and device, computer equipment, readable storage medium and program product

Abstract

The invention relates to a block storage component fault detection method and device, computer equipment, a computer readable storage medium and a computer program product, and is applied to the technical field of big data, and the method comprises the following steps: obtaining real-time operation data of a block storage component, and obtaining historical operation data of the block storage component; according to the real-time operation data and the historical operation data, the operation condition of the real-time operation data is identified, and the operation condition type of the real-time operation data is obtained; if the running state type represents that the block storage component has a fault, screening a service instruction corresponding to the block storage component and execution data for the service instruction from the real-time running data according to semantic information of the real-time running data; and detecting a fault type of the block storage component according to the service instruction and the execution data to obtain a component fault type. By adopting the method, the fault detection efficiency of the block storage component can be improved.

Description

Technical Field

[0001] The present application relates to the field of big data technology, and in particular to a block storage component fault detection method, apparatus, computer equipment, computer-readable storage medium, and computer program product. Background Art

[0002] With the development of information technology and digital economy, cloud service platforms have also been widely used. The block storage components in the cloud service platform are used to create, delete and mount disk volumes, as well as expand the capacity of existing disks, perform backups and recover data. Therefore, the maintenance of block storage components is crucial.

[0003] At present, block storage component fault detection is usually performed by staff based on the real-time operation data of the block storage components. However, the accuracy and efficiency of fault detection depend on the staff's fault detection experience and professional level, and it is easy for the time required to detect the fault to be long, resulting in low fault detection efficiency of block storage components. Summary of the invention

[0004] Based on this, it is necessary to provide a block storage component fault detection method, apparatus, computer equipment, computer-readable storage medium and computer program product that can improve the fault detection efficiency of block storage components in response to the above technical problems.

[0005] In a first aspect, the present application provides a block storage component failure detection method, comprising:

[0006] Acquire real-time operation data of a block storage component, and acquire historical operation data of the block storage component;

[0007] Identifying the operating status of the real-time operating data according to the real-time operating data and the historical operating data to obtain the operating status type of the real-time operating data;

[0008] If the operation status type indicates that the block storage component has a fault, filtering the service instruction corresponding to the block storage component and the execution data for the service instruction from the real-time operation data according to the semantic information of the real-time operation data;

[0009] According to the service instruction and the execution data, the failure type of the block storage component is detected to obtain the component failure type.

[0010] In a second aspect, the present application also provides a block storage component failure detection device, including:

[0011] An acquisition module, used to acquire real-time operation data of a block storage component, and to acquire historical operation data of the block storage component;

[0012] an identification module, configured to identify the operation status of the real-time operation data according to the real-time operation data and the historical operation data, and obtain the operation status type of the real-time operation data;

[0013] a screening module, configured to screen, if the operation status type indicates that the block storage component is faulty, a service instruction corresponding to the block storage component and execution data for the service instruction from the real-time operation data according to semantic information of the real-time operation data;

[0014] The detection module is used to detect the fault type of the block storage component according to the service instruction and the execution data to obtain the component fault type.

[0015] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0016] Acquire real-time operation data of a block storage component, and acquire historical operation data of the block storage component;

[0017] Identifying the operating status of the real-time operating data according to the real-time operating data and the historical operating data to obtain the operating status type of the real-time operating data;

[0018] If the operation status type indicates that the block storage component has a fault, filtering the service instruction corresponding to the block storage component and the execution data for the service instruction from the real-time operation data according to the semantic information of the real-time operation data;

[0019] According to the service instruction and the execution data, the failure type of the block storage component is detected to obtain the component failure type.

[0020] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0021] Acquire real-time operation data of a block storage component, and acquire historical operation data of the block storage component;

[0022] Identifying the operating status of the real-time operating data according to the real-time operating data and the historical operating data to obtain the operating status type of the real-time operating data;

[0023] If the operation status type indicates that the block storage component has a fault, filtering the service instruction corresponding to the block storage component and the execution data for the service instruction from the real-time operation data according to the semantic information of the real-time operation data;

[0024] According to the service instruction and the execution data, the failure type of the block storage component is detected to obtain the component failure type.

[0025] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0026] Acquire real-time operation data of a block storage component, and acquire historical operation data of the block storage component;

[0027] Identifying the operating status of the real-time operating data according to the real-time operating data and the historical operating data to obtain the operating status type of the real-time operating data;

[0028] If the operation status type indicates that the block storage component has a fault, filtering the service instruction corresponding to the block storage component and the execution data for the service instruction from the real-time operation data according to the semantic information of the real-time operation data;

[0029] According to the service instruction and the execution data, the failure type of the block storage component is detected to obtain the component failure type.

[0030] The block storage component fault detection method, apparatus, computer device, computer-readable storage medium and computer program product obtain real-time operation data of the block storage component and obtain historical operation data of the block storage component; identify the operation status of the real-time operation data according to the real-time operation data and the historical operation data to obtain the operation status type of the real-time operation data; if the operation status type indicates that the block storage component has a fault, filter the service instructions corresponding to the block storage component and the execution data for the service instructions from the real-time operation data according to the semantic information of the real-time operation data; and classify the fault type of the block storage component according to the service instructions and the execution data. The type of fault is detected to obtain the component fault type, thereby realizing the automatic fault detection of block storage components, reducing the manual intervention in the fault detection of block storage components, and getting rid of the dependence of the fault detection of block storage components on the fault detection experience and professional level of the staff. Through the operation status type identification and component fault type detection process, when the amount of real-time operation data is large, a part of the data corresponding to the operation status type representing that the block storage component does not have a fault can be excluded, and there is no need to further detect the component fault type of this part of the data. Therefore, for the overall real-time operation data detection process, the time required for the block storage component fault detection process is shortened. In summary, the fault detection efficiency of the block storage component is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0032] Figure 1 A diagram of an application environment of a block storage component failure detection method in an embodiment;

[0033] Figure 2 A schematic diagram of a flow chart of a method for detecting a block storage component failure in an embodiment;

[0034] Figure 3 A schematic diagram of a process of detecting component fault types using a component fault detection model in one embodiment;

[0035] Figure 4 A flowchart of steps for identifying the operating status of the real-time operating data according to the real-time operating data and the historical operating data to obtain the operating status type of the real-time operating data in one embodiment;

[0036] Figure 5 A flowchart of steps for detecting the failure type of a block storage component according to a service instruction and execution data to obtain the component failure type in an embodiment;

[0037] Figure 6 is a structural block diagram of a block storage component failure detection device in one embodiment;

[0038] Figure 7 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0039] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0040] It should be noted that the information and data involved in this application (including but not limited to data for analysis, stored data, displayed data, etc.) are all information and data authorized by the user or fully authorized by all parties, and the acquisition, transmission, storage, use and processing of relevant data are in compliance with the relevant provisions of national laws and regulations. The content pushed to the user (for example, component failure type, etc.) can be rejected by the user or can be easily rejected by the user. In the embodiments of the present application, some existing solutions in the industry such as certain software, components, models, etc. may be mentioned, and they should be regarded as exemplary. Their purpose is only to illustrate the feasibility of the implementation of the technical solution of this application, but it does not mean that the applicant has or will necessarily use the solution.

[0041] The block storage component failure detection method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. The server 104 obtains the real-time operation data of the block storage component, and obtains the historical operation data of the block storage component; according to the real-time operation data and the historical operation data, the operation status of the real-time operation data is identified to obtain the operation status type of the real-time operation data; if the operation status type indicates that the block storage component has a fault, then according to the semantic information of the real-time operation data, the service instructions corresponding to the block storage component and the execution data for the service instructions are filtered from the real-time operation data; according to the service instructions and the execution data, the fault type of the block storage component is detected to obtain the component fault type. Among them, the terminal 102 can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, projection devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The head mounted device may be a virtual reality (VR) device, an augmented reality (AR) device, smart glasses, etc. The server 104 may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0042] In an exemplary embodiment, Figure 2 As shown, a block storage component failure detection method is provided, and the method is applied to Figure 1 The server 104 in the example is used as an example to illustrate, including the following steps 202 to 208. Among them:

[0043] Step 202: Acquire real-time operation data of the block storage component, and acquire historical operation data of the block storage component.

[0044] Among them, the block storage component in step 202 is a component deployed by the cloud service platform for creating, deleting and mounting disk volumes. The cloud service platform can be a cloud computing management platform, for example, OpenStack (an open source cloud computing management platform project jointly developed and initiated by NASA (National Aeronautics and Space Administration) and Rackspace, and authorized by the Apache License (a free software license issued by the Apache Software Foundation)), and the block storage component can be a Cinder (block storage technology) component. The data generation time of the real-time operation data is later than the data generation time of the historical operation data.

[0045] Among them, OpenStack is an open source software platform that follows the IaaS model (Infrastructure as a Service) and is specifically designed to build and manage public and private cloud infrastructure. As a comprehensive cloud computing solution, OpenStack provides a complete set of tools and services designed to efficiently manage computing, storage, and network resources. With this platform, enterprises can easily operate and manage cloud resources in a secure, efficient, and user-friendly cloud environment.

[0046] Among the many core components of OpenStack, Cinder plays a vital role and is mainly responsible for providing block storage services. It works in conjunction with other service components such as Nova (computing service component) and Neutron (network service component). Cinder not only supports common basic operations such as creating, deleting, and mounting disk volumes, but also enables users to expand existing disks, perform advanced management tasks such as backup and data recovery.

[0047] Exemplarily, obtaining the real-time operation data of the block storage component includes: obtaining the operation data generated by the block storage component in real time, and obtaining the real-time operation data of the block storage component.

[0048] Exemplarily, obtaining the historical operation data of the block storage component includes: querying the operation log of the block storage component to obtain the historical operation data of the block storage component.

[0049] As an embodiment, the method also includes: performing data preprocessing on historical operation data and real-time operation data, wherein the data preprocessing includes but is not limited to deleting typos, deleting duplicate words, format unification, etc., format unification includes but is not limited to unifying the description format into Chinese and unifying the description format into English, etc., and unifying the description format into English includes but is not limited to unifying the description format into uppercase English and unifying the description format into lowercase English, etc.

[0050] Step 204 , identifying the operation status of the real-time operation data according to the real-time operation data and the historical operation data, and obtaining the operation status type of the real-time operation data.

[0051] The operation status type in step 204 includes at least one of an operation warning status type, an operation error status type, an operation notification status type, and an operation troubleshooting status type.

[0052] Exemplarily, step 204 includes: comparing the real-time operation data with the historical operation data to obtain a comparison result; and identifying the operation status of the real-time operation data according to the comparison result to obtain the operation status type of the real-time operation data.

[0053] Step 206: If the operation status type indicates that the block storage component has a fault, the service instructions corresponding to the block storage component and the execution data for the service instructions are filtered from the real-time operation data according to the semantic information of the real-time operation data.

[0054] As an embodiment, before step 206, the method further includes at least one of the following items: if the operating status type includes an operating alarm status type, determining that the operating status type indicates that the block storage component has a fault; if the operating status type includes an operating error status type, determining that the operating status type indicates that the block storage component has a fault.

[0055] Exemplarily, based on the semantic information of the real-time operation data, service instructions corresponding to the block storage component and execution data for the service instructions are filtered from the real-time operation data, including: based on the semantic information of the real-time operation data, the real-time operation data is split to obtain split data, and the service instructions corresponding to the block storage component and execution data for the service instructions are filtered from the split data.

[0056] Step 208: Detect the failure type of the block storage component according to the service instruction and the execution data to obtain the component failure type.

[0057] The component failure type in step 208 includes at least one of a service execution failure type, a synchronization failure type, and a service component failure type.

[0058] Exemplarily, step 208 includes: determining the service status of the block storage component according to the execution data; and detecting the fault type of the block storage component according to the service status and the service instruction to obtain the component fault type.

[0059] As an embodiment, step 208 includes: obtaining a pre-trained component fault detection model, wherein the component fault detection model includes a bidirectional long short-term memory network layer, a first deletion layer, a convolutional neural network layer and a fault detection layer connected in sequence; extracting a long-distance dependency relationship in a time series dimension from the service instruction and the execution data through the bidirectional long short-term memory network layer in the component fault detection model to obtain a first component operation feature; performing regularization processing on the first component operation feature through the first deletion layer in the component fault detection model to obtain a first processing feature; performing feature extraction on the first processing feature through the convolutional neural network layer in the component fault detection model to obtain a second component operation feature; and detecting the fault type of the block storage component according to the second component operation feature through the fault detection layer in the component fault detection model to obtain a component fault type.

[0060] As another embodiment, the component fault detection model includes a sequentially connected embedding layer, a bidirectional long short-term memory network layer, a first deletion layer, a convolutional neural network layer, a batch normalization layer, a fully connected layer, a second deletion layer, and a classification layer.

[0061] Further, as an embodiment, the fault type of the block storage component is detected according to the service instructions and the execution data through the component fault detection model to obtain the component fault type, including: reducing the dimension of the service instructions and the execution data through the embedding layer in the component fault detection model to obtain the reduced dimension data; extracting the long-distance dependency of the time series from the reduced dimension data through the bidirectional long short-term memory network layer in the component fault detection model to obtain the first component operation feature; regularizing the first component operation feature through the first deletion layer in the component fault detection model to obtain the first processing feature; extracting the first processing feature through the convolutional neural network layer in the component fault detection model to obtain the second component operation feature; batch normalizing the second component operation feature through the batch normalization layer in the component fault detection model to obtain the second processing feature; fully connecting the second processing feature through the fully connected layer in the component fault detection model to obtain the connection feature; regularizing the connection feature through the second deletion layer in the component fault detection model to obtain the third processing feature; classifying the third processing feature through the classification layer in the component fault detection model to obtain the component fault type.

[0062] As an embodiment, training samples can be screened and generated from historical operation data by dividing the historical operation data into a training set and a validation set, wherein the data quantity ratio of the training set and the validation set can be set by the user as needed, for example, the data quantity ratio of the training set is set to 75%, and the data quantity ratio of the validation set is set to 25%; or, the data quantity ratio of the training set is set to 70%, and the data quantity ratio of the validation set is set to 30%, etc.; during the training process of the component fault detection model, the confusion matrix and F1 score can be used to evaluate the training effect of the component fault detection model.

[0063] Optionally, refer to Figure 3 The component fault detection model includes a sequentially connected embedding layer (the Embedding layer shown in the figure), a bidirectional long short-term memory network layer (the Bi-LSTM layer shown in the figure), a first deletion layer (the Dropout layer at the front end shown in the figure), a convolutional neural network layer (the CNN layer (3 layers) + pooling layer shown in the figure), a batch normalization layer (the BN layer shown in the figure), a fully connected layer (the Dense layer shown in the figure), a second deletion layer (the Dropout layer at the back end shown in the figure) and a classification layer (the Softmax layer shown in the figure). Service instructions and execution data can be input (the Input shown in the figure) to each structure in the component fault detection model, and the component fault detection model outputs (the Output shown in the figure) the component fault type.

[0064] In the above block storage component fault detection method, by acquiring the real-time operation data of the block storage component and the historical operation data of the block storage component; identifying the operation status of the real-time operation data according to the real-time operation data and the historical operation data, and obtaining the operation status type of the real-time operation data; if the operation status type indicates that the block storage component has a fault, then filtering the service instructions corresponding to the block storage component and the execution data for the service instructions from the real-time operation data according to the semantic information of the real-time operation data; detecting the fault type of the block storage component according to the service instructions and the execution data, and obtaining the component fault type. This model realizes the automatic fault detection of block storage components, reduces the manual intervention in the fault detection of block storage components, and gets rid of the dependence of the fault detection of block storage components on the fault detection experience and professional level of the staff. Through the operation status type identification and component fault type detection process, when the amount of real-time operation data is large, a part of the data corresponding to the operation status type representing that the block storage component does not have a fault can be excluded, and there is no need to further detect the component fault type of this part of the data. Therefore, for the overall real-time operation data detection process, the time required for the block storage component fault detection process is shortened. In summary, the fault detection efficiency of the block storage component is improved.

[0065] In an exemplary embodiment, as shown in FIG. 4 , the historical operation data includes multiple historical operation sub-data; a method for accurately identifying the operation status type is provided, and the operation status of the real-time operation data is identified according to the real-time operation data and the historical operation data, and obtaining the operation status type of the real-time operation data includes steps 302 to 306. Among them:

[0066] Step 302: Obtain operation status type identifiers corresponding to a plurality of historical operation sub-data.

[0067] As an embodiment, step 302 includes: for each historical operation sub-data in multiple historical operation sub-data, filtering historical execution data for historical service instructions from the historical operation sub-data; extracting execution keywords for the historical service instructions from the historical execution data; and generating an operation status type identifier corresponding to the historical operation sub-data based on the execution keywords.

[0068] Further, as an embodiment, extracting execution keywords for historical service instructions from historical execution data includes: extracting execution keywords for characterizing execution status of historical service instructions from historical execution data according to semantic information of the historical execution data.

[0069] As one embodiment, based on the execution keyword, an operation status type identifier corresponding to the historical operation sub-data is generated, including: if the execution keyword is used to represent the execution alarm status for the historical service instruction, the operation alarm status type is determined as the operation status type identifier corresponding to the historical operation sub-data; if the execution keyword is used to represent the execution error status for the historical service instruction, the operation error status type is determined as the operation status type identifier corresponding to the historical operation sub-data; if the execution keyword is used to represent the execution notification status for the historical service instruction, the operation notification status type is determined as the operation status type identifier corresponding to the historical operation sub-data; if the execution keyword is used to represent the execution troubleshooting status for the historical service instruction, the operation troubleshooting status type is determined as the operation status type identifier corresponding to the historical operation sub-data.

[0070] Step 304 : Select a target identifier from the operation status type identifiers corresponding to the plurality of historical operation sub-data according to the matching degree between the real-time operation data and the plurality of historical operation sub-data.

[0071] As an embodiment, step 304 includes: obtaining the matching degree between the real-time operation data and the plurality of historical operation sub-data, and selecting the target identification whose matching degree meets the preset matching degree condition from the operation status type identifications of the plurality of historical operation sub-data.

[0072] Furthermore, obtaining the degree of match between the real-time operation data and the plurality of historical operation sub-data includes: obtaining the degree of similarity between the real-time operation data and the plurality of historical operation sub-data; determining the degree of match between the real-time operation data and the plurality of historical operation sub-data according to the degree of similarity between the real-time operation data and the plurality of historical operation sub-data, wherein the higher the similarity, the higher the degree of match.

[0073] Among them, the preset matching condition can be greater than the preset matching threshold, and the preset matching threshold is the matching critical value set as needed to determine when the real-time operation data matches the historical operation sub-data; the preset matching condition can also be the maximum value among all matching degrees.

[0074] Step 306: determine the target identifier as the operating status type of the real-time operating data.

[0075] In this embodiment, the operation status type identifiers corresponding to multiple historical operation sub-data are obtained; according to the matching degree between the real-time operation data and the multiple historical operation sub-data, a target identifier is selected from the operation status type identifiers corresponding to the multiple historical operation sub-data; the target identifier is determined as the operation status type of the real-time operation data, and the matching degree between the real-time operation data and the multiple historical operation sub-data is used as the basis for selecting the operation status type identifier, thereby ensuring the accuracy of determining the operation status type of the real-time operation data.

[0076] In an exemplary embodiment, Figure 5 As shown, in order to provide a method for accurately detecting the component failure type, the component failure type includes at least one of the service execution failure type, the synchronization failure type and the service component failure type; according to the service instruction and the execution data, the failure type of the block storage component is detected, and the component failure type is obtained, including steps 402 to 406. Among them:

[0077] Step 402: If it is detected that the execution data indicates that the service instruction execution fails, a service execution failure type is generated according to the service instruction.

[0078] The service instruction in step 402 includes at least one of a mirror synchronization instruction, a clock synchronization instruction, a cloud hard disk creation instruction, a cloud hard disk deletion instruction, a cloud hard disk expansion instruction, and a cloud hard disk backup instruction.

[0079] As an embodiment, step 402 includes: if it is detected that the execution data represents that the service instruction execution fails, then when the service instruction includes a mirror synchronization instruction, the mirror synchronization instruction execution failure type is determined as the service execution failure type; when the service instruction includes a clock synchronization instruction, the clock synchronization instruction execution failure type is determined as the service execution failure type; when the service instruction includes a cloud hard disk creation instruction, the cloud hard disk creation instruction execution failure type is determined as the service execution failure type; when the service instruction includes a cloud hard disk deletion instruction, the cloud hard disk deletion instruction execution failure type is determined as the service execution failure type; when the service instruction includes a cloud hard disk expansion instruction, the cloud hard disk expansion instruction execution failure type is determined as the service execution failure type; when the service instruction includes a cloud hard disk backup instruction, the cloud hard disk backup instruction execution failure type is determined as the service execution failure type.

[0080] Step 404: if it is detected that the execution data represents that the service state changes alternately between the first state and the second state, or if it is detected that the execution data is not synchronized, a synchronization fault type is generated according to the service instruction.

[0081] Exemplarily, step 404 includes: if it is detected that the execution data represents that the service state alternates between a first state and a second state, or if it is detected that the execution data is not synchronized, then when the service instruction includes a mirror synchronization instruction, the mirror synchronization fault type is determined as a synchronization fault type; when the service instruction includes a clock synchronization instruction, the clock synchronization fault type is determined as a synchronization fault type; when the service instruction includes a cloud hard disk creation instruction, the cloud hard disk creation synchronization fault type is determined as a synchronization fault type; when the service instruction includes a cloud hard disk deletion instruction, the cloud hard disk deletion synchronization fault type is determined as a synchronization fault type; when the service instruction includes a cloud hard disk expansion instruction, the cloud hard disk expansion synchronization fault type is determined as a synchronization fault type; when the service instruction includes a cloud hard disk backup instruction, the cloud hard disk backup synchronization fault type is determined as a synchronization fault type.

[0082] Step 406: If it is detected that the execution data indicates that the execution time of the service instruction meets a preset time condition, a service component fault type is generated according to the service instruction.

[0083] Among them, the preset time condition in step 406 can be that the corresponding execution duration is greater than the preset duration threshold, and the preset duration threshold is a critical value of the service instruction execution duration when determining that a service component failure exists, which is set as needed; the preset time condition can also be later than the preset time, and the preset time is a critical value of the service instruction execution time point when determining that a service component failure exists, which is set as needed.

[0084] Exemplarily, step 406 includes: if it is detected that the execution data represents that the execution time of the service instruction satisfies a preset time condition, then when the service instruction includes a mirror synchronization instruction, the mirror synchronization instruction execution failure type is determined as a service component failure type; when the service instruction includes a clock synchronization instruction, the clock synchronization instruction execution failure type is determined as a service component failure type; when the service instruction includes a cloud hard disk creation instruction, the cloud hard disk creation instruction execution failure type is determined as a service component failure type; when the service instruction includes a cloud hard disk deletion instruction, the cloud hard disk deletion instruction execution failure type is determined as a service component failure type; when the service instruction includes a cloud hard disk expansion instruction, the cloud hard disk expansion instruction execution failure type is determined as a service component failure type; when the service instruction includes a cloud hard disk backup instruction, the cloud hard disk backup instruction execution failure type is determined as a service component failure type.

[0085] In the present embodiment, if it is detected that the execution data represents that the execution of a service instruction fails, a service execution failure type is generated according to the service instruction; if it is detected that the execution data represents that the service state alternates between a first state and a second state, or if it is detected that the execution data is not synchronized, a synchronization failure type is generated according to the service instruction; if it is detected that the execution data represents that the execution time of the service instruction satisfies a preset time condition, a service component failure type is generated according to the service instruction, thereby achieving identification of component failure types in various situations and improving the accuracy of identifying component failure types.

[0086] As a detailed embodiment, real-time operation data of a block storage component is obtained, and historical operation data of the block storage component is obtained; for each historical operation sub-data in a plurality of historical operation sub-data, historical execution data for historical service instructions are filtered from the historical operation sub-data; execution keywords for historical service instructions are extracted from the historical execution data; based on the execution keywords, an operation status type identifier corresponding to the historical operation sub-data is generated; based on the matching degree between the real-time operation data and the plurality of historical operation sub-data, a target identifier is selected from the operation status type identifiers corresponding to the plurality of historical operation sub-data; and the target identifier is determined as the operation status type of the real-time operation data.

[0087] Further, if the operation status type includes an operation alarm status type, it is determined that the operation status type indicates that the block storage component has a fault; if the operation status type includes an operation error status type, it is determined that the operation status type indicates that the block storage component has a fault; if the operation status type indicates that the block storage component has a fault, then according to the semantic information of the real-time operation data, the service instructions corresponding to the block storage component and the execution data for the service instructions are filtered from the real-time operation data; a pre-trained component fault detection model is obtained, wherein the component fault detection model includes a bidirectional long short-term memory network layer, a first deletion layer, a convolutional neural network layer and a fault detection layer connected in sequence. layer; through the bidirectional long short-term memory network layer in the component fault detection model, the long-distance dependency relationship in the time series dimension is extracted from the service instruction and the execution data to obtain the first component operation feature; through the first deletion layer in the component fault detection model, the first component operation feature is regularized to obtain the first processing feature; through the convolutional neural network layer in the component fault detection model, the first processing feature is feature extracted to obtain the second component operation feature; through the fault detection layer in the component fault detection model, according to the second component operation feature, the fault type of the block storage component is detected to obtain the component fault type.

[0088] In this way, by acquiring the real-time operation data of the block storage component and acquiring the historical operation data of the block storage component; identifying the operation status of the real-time operation data according to the real-time operation data and the historical operation data, and obtaining the operation status type of the real-time operation data; if the operation status type indicates that the block storage component has a fault, then according to the semantic information of the real-time operation data, the service instruction corresponding to the block storage component and the execution data for the service instruction are screened from the real-time operation data; according to the service instruction and the execution data, the fault type of the block storage component is detected to obtain the component fault type, thereby realizing the automatic fault detection of the block storage component, reducing the manual intervention in the fault detection of the block storage component, and getting rid of the dependence of the fault detection of the block storage component on the fault detection experience and professional level of the staff. Through the operation status type identification and component fault type detection process, when the amount of real-time operation data is large, a part of the data corresponding to the operation status type indicating that the block storage component does not have a fault can be excluded, and there is no need to further detect the component fault type for this part of the data. Therefore, for the overall real-time operation data detection process, the time required for the block storage component fault detection process is shortened. In summary, the fault detection efficiency of the block storage component is improved.

[0089] Furthermore, by obtaining the operating status type identifiers corresponding to the multiple historical operating sub-data respectively; selecting the target identifier from the operating status type identifiers corresponding to the multiple historical operating sub-data respectively according to the matching degree between the real-time operating data and the multiple historical operating sub-data respectively; determining the target identifier as the operating status type of the real-time operating data, and using the matching degree between the real-time operating data and the multiple historical operating sub-data respectively as the basis for selecting the operating status type identifier, the accuracy of determining the operating status type of the real-time operating data is ensured, and the identification of component failure types in various situations is realized, thereby improving the accuracy of identifying component failure types.

[0090] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0091] Based on the same inventive concept, the embodiment of the present application also provides a block storage component failure detection device for implementing the block storage component failure detection method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiments of one or more block storage component failure detection devices provided below can refer to the limitations of the block storage component failure detection method above, and will not be repeated here.

[0092] In an exemplary embodiment, Figure 6 As shown, a block storage component failure detection device 600 is provided, including: an acquisition module 602, an identification module 604, a screening module 606 and a detection module 608, wherein:

[0093] The acquisition module 602 is used to acquire the real-time operation data of the block storage component and the historical operation data of the block storage component;

[0094] An identification module 604 is used to identify the operation status of the real-time operation data according to the real-time operation data and the historical operation data, and obtain the operation status type of the real-time operation data;

[0095] A screening module 606 is configured to screen the service instructions corresponding to the block storage component and the execution data for the service instructions from the real-time operation data according to the semantic information of the real-time operation data if the operation status type indicates that the block storage component has a fault;

[0096] The detection module 608 is used to detect the fault type of the block storage component according to the service instruction and the execution data to obtain the component fault type.

[0097] In one of the embodiments, the historical operation data includes multiple historical operation sub-data; the identification module 604 is also used to obtain the operation status type identifiers corresponding to the multiple historical operation sub-data; according to the matching degree between the real-time operation data and the multiple historical operation sub-data, a target identifier is selected from the operation status type identifiers corresponding to the multiple historical operation sub-data; and the target identifier is determined as the operation status type of the real-time operation data.

[0098] In one of the embodiments, the identification module 604 is also used to filter historical execution data for historical service instructions from the historical operation sub-data for each of the multiple historical operation sub-data; extract execution keywords for the historical service instructions from the historical execution data; and generate an operation status type identifier corresponding to the historical operation sub-data based on the execution keywords.

[0099] In one of the embodiments, the detection module 608 is also used to obtain a pre-trained component fault detection model, wherein the component fault detection model includes a sequentially connected embedding layer, a bidirectional long short-term memory network layer, a first deletion layer, a convolutional neural network layer, a batch normalization layer, a fully connected layer, a second deletion layer and a classification layer; through the component fault detection model, the fault type of the block storage component is detected according to the service instructions and the execution data to obtain the component fault type.

[0100] In one of the embodiments, the component failure type includes at least one of a service execution failure type, a synchronization failure type, and a service component failure type; the detection module 608 is also used to generate a service execution failure type according to the service instruction if it is detected that the execution data indicates that the service instruction fails to execute; if it is detected that the execution data indicates that the service state alternates between a first state and a second state, or if it is detected that the execution data is not synchronized, then a synchronization failure type is generated according to the service instruction; if it is detected that the execution data indicates that the execution time of the service instruction satisfies a preset time condition, then a service component failure type is generated according to the service instruction.

[0101] In one of the embodiments, the operating status type includes at least one of an operating alarm status type, an operating error status type, an operating notification status type, and an operating troubleshooting status type; the device also includes: a determination module, which is used to determine that the operating status type indicates that a block storage component has a fault if the operating status type includes an operating alarm status type; and to determine that the operating status type indicates that a block storage component has a fault if the operating status type includes an operating error status type.

[0102] Each module in the above-mentioned block storage component fault detection device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each of the above modules.

[0103] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 7 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, near field communication (NFC) or other technologies. When the computer program is executed by the processor, a block storage component fault detection method is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0104] Those skilled in the art will understand that Figure 7The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0105] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0106] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0107] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0108] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0109] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0110] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A block storage component failure detection method, characterized in that: The method comprises: Acquire real-time operation data of a block storage component, and acquire historical operation data of the block storage component; Identifying the operating status of the real-time operating data according to the real-time operating data and the historical operating data to obtain the operating status type of the real-time operating data; If the operation status type indicates that the block storage component has a fault, filtering the service instruction corresponding to the block storage component and the execution data for the service instruction from the real-time operation data according to the semantic information of the real-time operation data; According to the service instruction and the execution data, the failure type of the block storage component is detected to obtain the component failure type.

2. The method according to claim 1, characterized in that The historical operation data includes a plurality of historical operation sub-data; the operation status of the real-time operation data is identified according to the real-time operation data and the historical operation data to obtain the operation status type of the real-time operation data, including: Obtaining the operation status type identifiers corresponding to the plurality of historical operation sub-data respectively; According to the matching degree between the real-time operation data and the plurality of historical operation sub-data, respectively, a target identifier is selected from the operation status type identifiers respectively corresponding to the plurality of historical operation sub-data; The target identifier is determined as the operating status type of the real-time operating data.

3. The method according to claim 2, characterized in that The obtaining the operation status type identifiers respectively corresponding to the plurality of historical operation sub-data includes: For each of the plurality of historical operation sub-data, filtering historical execution data for historical service instructions from the historical operation sub-data; Extracting execution keywords for the historical service instructions from the historical execution data; An operation status type identifier corresponding to the historical operation sub-data is generated according to the execution keyword.

4. The method according to claim 1, characterized in that: The detecting, according to the service instruction and the execution data, the failure type of the block storage component to obtain the component failure type includes: Obtaining a pre-trained component fault detection model, wherein the component fault detection model includes a bidirectional long short-term memory network layer, a first deletion layer, a convolutional neural network layer, and a fault detection layer connected in sequence; Extracting a long-distance dependency relationship in a time series dimension from the service instruction and the execution data through a bidirectional long short-term memory network layer in the component fault detection model to obtain a first component operation feature; Regularizing the first component operation feature through a first deletion layer in the component fault detection model to obtain a first processing feature; Extracting the first processing feature through a convolutional neural network layer in the component fault detection model to obtain a second component operation feature; The fault detection layer in the component fault detection model detects the fault type of the block storage component according to the operating characteristics of the second component to obtain the component fault type.

5. The method according to claim 1, characterized in that The component failure type includes at least one of a service execution failure type, a synchronization failure type, and a service component failure type; the detecting the failure type of the block storage component according to the service instruction and the execution data to obtain the component failure type includes: If it is detected that the execution data indicates that the service instruction execution fails, generating the service execution failure type according to the service instruction; If it is detected that the execution data represents that the service state changes alternately between the first state and the second state, or if it is detected that the execution data is not synchronized, generating the synchronization fault type according to the service instruction; If it is detected that the execution data represents that the execution time of the service instruction meets a preset time condition, the service component fault type is generated according to the service instruction.

6. The method according to any one of claims 1 to 5, characterized in that The operation status type includes at least one of an operation warning status type, an operation error status type, an operation notification status type, and an operation troubleshooting status type; the method further includes at least one of the following items: If the operation status type includes the operation warning status type, determining that the operation status type indicates that the block storage component has a fault; If the operating status type includes the operating error status type, it is determined that the operating status type indicates that a fault exists in the block storage component.

7. A block storage component failure detection device, characterized in that: The device comprises: An acquisition module, used to acquire real-time operation data of a block storage component, and to acquire historical operation data of the block storage component; an identification module, configured to identify the operation status of the real-time operation data according to the real-time operation data and the historical operation data, and obtain the operation status type of the real-time operation data; a screening module, configured to screen, if the operation status type indicates that the block storage component is faulty, a service instruction corresponding to the block storage component and execution data for the service instruction from the real-time operation data according to semantic information of the real-time operation data; The detection module is used to detect the fault type of the block storage component according to the service instruction and the execution data to obtain the component fault type.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images