Method, device, medium and program product for elastic expansion of storage space

Abstract

The present invention provides an elastic scaling method, device, medium and program product for storage space, which can be applied to the fields of cloud computing and artificial intelligence technology. The elastic scaling method includes: classifying elastic scaling related information according to the decision conditions constructed based on the target decision characteristics in the integrated algorithm model to obtain the elastic scaling judgment result, wherein the integrated algorithm model is constructed based on the target decision characteristics, the decision conditions and the elastic scaling judgment result, the target decision characteristics are determined according to the business requirements related to the storage space to be adjusted and at least one of the elastic scaling related information, and the elastic scaling judgment result represents whether elastic scaling is required or not; when the elastic scaling judgment result is that elastic scaling is required, according to the elastic scaling scale included in the elastic scaling judgment result, the storage capacity request value for requesting the storage space is set; according to the storage capacity request value, the storage space to be adjusted is elastically scaled.

Description

Technical Field

[0001] The present invention relates to the fields of cloud computing and artificial intelligence technology, and more specifically to a method, device, medium and program product for elastically scaling storage space. Background Art

[0002] Elastic Scaling Service (ESS) includes elastic expansion and elastic contraction. When storage resources are insufficient or performance bottlenecks occur, you need to use elastic expansion to expand storage capacity. When storage resources are idle, you can use elastic contraction to shrink storage capacity.

[0003] Due to the lack of advanced intelligent technology to conduct detailed data analysis and decision-making for elastic scaling scenarios and needs, it is impossible to scientifically and accurately judge the timing and scale of capacity expansion, resulting in problems such as waste of resources, reduced performance, and business failure to operate normally. Summary of the invention

[0004] In view of the above problems, the present invention provides a method, device, medium and program product for elastically scaling storage space.

[0005] According to a first aspect of the present invention, there is provided an elastic scaling method for storage space, characterized in that the method comprises: when the elastic scaling mode of the storage space to be adjusted is turned on, obtaining elastic scaling related information related to the storage space to be adjusted; classifying the elastic scaling related information according to the decision conditions constructed based on the target decision characteristics in the integrated algorithm model to obtain an elastic scaling judgment result, wherein the integrated algorithm model is constructed based on the target decision characteristics, the decision conditions and the elastic scaling judgment result, the target decision characteristics are determined based on the business requirements related to the storage space to be adjusted and at least one of the elastic scaling related information, and the elastic scaling judgment result represents whether elastic scaling is required or not; when the elastic scaling judgment result is that elastic scaling is required, setting a storage capacity request value for requesting the storage space according to the elastic scaling scale included in the elastic scaling judgment result; and performing elastic scaling operations on the storage space to be adjusted according to the storage capacity request value.

[0006] According to a second aspect of the present invention, a method for generating an integrated algorithm model is provided, characterized in that the method comprises: determining a target decision feature based on at least one of a business requirement related to a target storage space and sample elastic scaling related information, the decision feature being used to construct a decision condition to classify sample elastic scaling related information to obtain an elastic scaling judgment result, and in the case where the elastic scaling judgment result is that elastic scaling is required, the elastic scaling judgment result also includes an elastic scaling scale corresponding to the required elastic scaling, the elastic scaling scale is used to set a storage capacity request value for requesting storage space, and the storage capacity request value is used to perform elastic scaling operations on the target storage space; and generating an integrated algorithm model based on the target decision feature, the decision condition and the elastic scaling judgment result.

[0007] The third aspect of the present invention provides an electronic device, comprising: one or more processors; a memory for storing one or more computer programs, wherein the one or more processors execute the one or more computer programs to implement the steps of at least one of the methods of the present invention including the elastic scaling method for storage space and the generation method of an integrated algorithm model.

[0008] The fourth aspect of the present invention also provides a computer-readable storage medium on which a computer program or instruction is stored. When the above computer program or instruction is executed by a processor, the steps of at least one of the methods of the present invention for elastically scaling the storage space and generating the integrated algorithm model are implemented.

[0009] The fifth aspect of the present invention also provides a computer program product, including a computer program or instructions, which, when executed by a processor, implement the steps of at least one of the methods of the present invention for elastic scaling of storage space and the method for generating an integrated algorithm model. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The above contents and other objects, features and advantages of the present invention will become more apparent through the following description of the embodiments of the present invention with reference to the accompanying drawings, in which:

[0011] Figure 1 A diagram schematically illustrates an application scenario of at least one of the elastic scaling method for storage space and the generation method of an integrated algorithm model according to an embodiment of the present invention;

[0012] Figure 2 A flowchart of a method for elastically scaling storage space according to an embodiment of the present invention is schematically shown;

[0013] Figure 3 A schematic diagram of a decision tree model according to an embodiment of the present invention is schematically shown;

[0014] Figure 4 A flowchart schematically shows a method for generating an integrated algorithm model according to an embodiment of the present invention;

[0015] Figure 5 The overall flow chart of the elastic scaling method according to an embodiment of the present invention is schematically shown;

[0016] Figure 6 A structural block diagram of an elastic expansion and contraction device for a storage space according to an embodiment of the present invention is schematically shown;

[0017] Figure 7 A schematic diagram of a structure of a device for generating an integrated algorithm model according to an embodiment of the present invention is shown;

[0018] Figure 8 A block diagram of an electronic device suitable for implementing at least one of a method for elastically scaling a storage space and a method for generating an integrated algorithm model according to an embodiment of the present invention is schematically shown. DETAILED DESCRIPTION

[0019] Below, embodiments of the present invention will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present invention. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of embodiments of the present invention. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of concepts of the present invention.

[0020] The terms used herein are only for describing specific embodiments and are not intended to limit the present invention. The terms "comprise", "include", etc. used herein indicate the existence of the features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0021] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0022] When using expressions such as "at least one of A, B, and C, etc.", they should generally be interpreted according to the meaning of the expression commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0023] For stateful application loads with high storage requirements, as the business volume increases, the requirements for storage capacity become higher and higher, and it is difficult to find the right time for elastic scaling and set an accurate and reasonable request value.

[0024] For example, if the system encounters a storage bottleneck, performance or capacity reaches its limit and cannot meet the needs of the application. If capacity is not expanded in time, I / O (input / output) latency will increase and application performance will deteriorate. If storage resources are exhausted, new applications may not be able to start, or existing applications may be evicted due to insufficient resources, resulting in service interruption. If capacity is expanded when it is not necessary, it will lead to resource waste and affect business continuity.

[0025] If the expansion capacity is set too large, it may lead to a waste of storage resources or the expansion failure due to the limitation of actual physical resources, affecting performance; if the expansion capacity is set too small, it will lead to the need to expand the storage multiple times. At this time, the user needs to manually check the storage usage rate and manually adjust the storage space according to the current status of the storage. The operation is cumbersome for the user and the storage bottleneck cannot be discovered and responded in time. At the same time, frequent storage expansion operations will affect the performance of the application or bring data security risks, affecting the provision of business services.

[0026] In the relevant elastic scaling mechanism, the judgment of the timing of elastic scaling and the selection of the method are often simple and crude. For some applications with obvious peaks and troughs in business growth, capacity expansion according to fixed thresholds may lead to capacity expansion too early or too late. Expansion too early will cause idle resources and waste of costs, while expansion too late may affect the business. At the same time, there is no advanced intelligent technology for detailed data analysis and decision-making, and no full consideration of factors such as the dynamic changes in actual business needs, regular fluctuations in storage usage, and special needs in different application scenarios, so reasonable elastic scaling cannot be performed.

[0027] Embodiments of the present invention provide an elastic scaling method, device, medium and program product for storage space. The elastic scaling method includes: obtaining elastic scaling related information related to the storage space to be adjusted when the elastic scaling mode is turned on for the storage space to be adjusted; classifying the elastic scaling related information according to the decision conditions constructed based on the target decision features in the integrated algorithm model to obtain an elastic scaling judgment result, wherein the integrated algorithm model is constructed based on the target decision features, the decision conditions and the elastic scaling judgment result, the target decision features are determined based on the business requirements related to the storage space to be adjusted and at least one of the elastic scaling related information, and the elastic scaling judgment result indicates whether elastic scaling is required or not; when the elastic scaling judgment result is that elastic scaling is required, setting a storage capacity request value for requesting the storage space according to the elastic scaling scale included in the elastic scaling judgment result; and performing elastic scaling operations on the storage space to be adjusted according to the storage capacity request value.

[0028] Figure 1 An application scenario diagram of at least one of the elastic scaling method for storage space and the generation method of the integrated algorithm model according to an embodiment of the present invention is schematically shown.

[0029] like Figure 1 As shown, the application scenario 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 is used to provide a medium for a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or optical fiber cables, etc.

[0030] The user can use the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 through the network 104 to receive or send messages, etc. Various communication client applications can be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only for example).

[0031] The first terminal device 101, the second terminal device 102, and the third terminal device 103 may be various electronic devices having display screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

[0032] The server 105 may be a server that provides various services, such as a background management server (only as an example) that provides support for websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103. The background management server may analyze and process the received data such as user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal device.

[0033] It should be noted that at least one of the elastic scaling method for storage space and the generation method of integrated algorithm model provided in the embodiment of the present invention can generally be executed by the server 105. Accordingly, at least one of the elastic scaling device for storage space and the generation method of integrated algorithm model provided in the embodiment of the present invention can generally be set in the server 105. At least one of the elastic scaling method for storage space and the generation method of integrated algorithm model provided in the embodiment of the present invention can also be executed by a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105. Accordingly, at least one of the elastic scaling device for storage space and the generation method of integrated algorithm model provided in the embodiment of the present invention can also be set in a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105.

[0034] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0035] The following will be based on Figure 1 The scene described by Figure 2~Figure 5 The elastic scaling method for storage space in the disclosed embodiment is described in detail.

[0036] Figure 2 The flowchart of the elastic scaling method for storage space according to an embodiment of the present invention is schematically shown.

[0037] like Figure 2 As shown, the elastic scaling method for storage space of this embodiment includes operations S210 to S240, and the elastic scaling method for storage space can be executed by at least one of the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105.

[0038] In operation S210, when the elastic scaling mode is enabled for the storage space to be adjusted, elastic scaling related information related to the storage space to be adjusted is obtained.

[0039] According to an embodiment of the present invention, the storage space to be adjusted can represent the storage space of a conventional application system, or the storage space of a containerized application system, which is not limited here. A parameter can be defined in advance for the elastic scaling mode, for example, it can include: allowESS parameter, which represents that elastic scaling is allowed, including expansion and contraction. allowVolumeExpansion parameter, which represents that only expansion is allowed. allowVolumeCompression parameter, which represents that only contraction is allowed. This makes the method applicable to various scenarios such as only expansion, only contraction, dynamic expansion and contraction, etc.

[0040] For example, if you need to enable the capacity expansion mode only, you can enable the capacity expansion mode by setting allowVolumeExpansion=true.

[0041] According to an embodiment of the present invention, the elastic scaling related information may represent all storage requirements, read / write performance and other information associated with and interacting with the storage space to be adjusted, as well as the space situation information of the storage space to be adjusted itself, but is not limited thereto.

[0042] According to an embodiment of the present invention, after the initial information related to elastic scaling is initially collected, the initial information related to elastic scaling can be directly determined as the elastic scaling related information. The initial information related to elastic scaling that is initially collected can also be subjected to data preprocessing to obtain the elastic scaling related information. The initial information related to elastic scaling that is initially collected can also be sampled to obtain the elastic scaling related information. The initial information related to elastic scaling that is initially collected can also be subjected to data preprocessing and sampling operations in sequence to obtain the elastic scaling related information. The specific method for determining the elastic scaling related information is not limited herein.

[0043] For example, for the initial information related to elastic scaling that is initially collected, data cleaning can be performed first, including: cleaning the initial information related to elastic scaling to remove outliers; using methods such as mean filling and median filling to process default values, and obtaining candidate information related to elastic scaling after removing outliers and supplementing default values. Then, according to the principle of sampling with replacement, the candidate information related to elastic scaling can be sampled to generate a data subset as the elastic scaling related information. Specifically, sampling with replacement can be performed from the original elastic scaling related initial information D containing n (n is a positive integer) samples. Each time an elastic scaling related information is extracted, the sample is put back into D with the same probability p = 1 / n before extracting the next elastic scaling related information. Based on this method, it is beneficial to obtain elastic scaling related information with relatively balanced and stable data features that can represent the current main data features, and can effectively improve the accuracy of subsequent output information.

[0044] In operation S220, the elastic scaling related information is classified according to the decision conditions constructed based on the target decision features in the integrated algorithm model to obtain an elastic scaling judgment result, wherein the integrated algorithm model is constructed based on the target decision features, the decision conditions and the elastic scaling judgment result, the target decision features are determined based on at least one of the business requirements related to the storage space to be adjusted and the elastic scaling related information, and the elastic scaling judgment result represents whether elastic scaling is required or not.

[0045] According to an embodiment of the present invention, appropriate features can be selected as target decision features according to data characteristics of elastic scaling related information and business requirements. For example, the target decision feature can be selected from at least one of the following: remaining space ratio, recent business data growth rate, current storage type, etc., but is not limited thereto.

[0046] According to an embodiment of the present invention, the decision condition can be constructed based on one or more decision features. For example, the decision condition may include: the remaining space is less than AA; the remaining space is less than AA, and the recent business growth rate is greater than BB; the remaining space is greater than AA, and the recent business growth rate is greater than BB; the remaining space is less than AA, and the recent business growth rate is less than BB, etc., and may not be limited thereto. Among them, AA and BB are both positive numbers.

[0047] According to an embodiment of the present invention, the integrated algorithm model can receive elastic scaling related information as input. Then, according to the target decision feature, target decision feature related information associated with the target decision feature in the elastic scaling related information can be extracted. After that, the target decision feature related information can be classified in combination with the decision conditions, and the result of whether elastic scaling is required or not is output.

[0048] In operation S230, when the elastic scaling determination result indicates that elastic scaling is required, a storage capacity request value for requesting storage space is set according to the elastic scaling scale included in the elastic scaling determination result.

[0049] According to an embodiment of the present invention, when the elastic scaling judgment result is that elastic scaling is not required, no operation may be performed. When the elastic scaling judgment result is that elastic scaling is required, the elastic scaling judgment result may also include an elastic scaling scale corresponding to the required elastic scaling, characterizing the specific capacity size of the expansion or reduction. Specifically, when the elastic scaling judgment result is that expansion is required, the storage capacity request value may be set to XX, where XX represents the expansion scale and XX is a positive number. When the elastic scaling judgment result is that reduction is required, the storage capacity request value may be set to YY, where YY represents the reduction scale and YY is a negative number.

[0050] For example, a containerized application system may include a container orchestration engine. The container orchestration engine can be used to automate the deployment, expansion, and management of containerized applications. In a container orchestration engine, the management of storage resources is very different from the management of computing resources such as CPU (Central Processing Unit) and memory. In order to shield the details of the underlying storage implementation and make it easier for users to use and administrators to manage, the container orchestration engine can introduce two resource objects, PV (Persistent Volume) and PVC (Persistent Volume Claim), as well as dynamic storage provisioning implemented through SC (StorageClass) to implement the storage management subsystem. PV can represent the pre-configured storage space in the cluster, which is independent of the life cycle of Pod (a collection of containers) to ensure that data remains persistent after the container is restarted or deleted. PVC can represent the user's application for storage space and can define the required storage size and access mode. The container orchestration engine can meet storage needs by matching PVC and PV. SC is an abstract definition of storage resources. It shields the details of backend storage from the PVC application set by the user. On the one hand, it can reduce the user's attention to the details of storage resources. On the other hand, it can reduce the administrator's manual management of PV. The system automatically completes the creation and binding of PV, realizing the dynamic elastic scaling function of the storage space to be adjusted.

[0051] In operation S240, an elastic scaling operation is performed on the storage space to be adjusted according to the storage capacity request value.

[0052] According to an embodiment of the present invention, after the storage capacity request value is set, the storage space to be adjusted can be automatically expanded or reduced according to the storage capacity request value.

[0053] For example, the container orchestration engine can provide an online expansion mechanism. When you need to expand the capacity of a PVC, you can first set allowVolumeExpansion=true in the SC definition corresponding to the PVC. When expanding the capacity of a PVC, you only need to modify the storage capacity request value represented by the PVC, and automatically set the storage capacity request value according to the elastic scaling scale. The system will trigger the expansion of the backend PV based on the newly set storage space of the PVC.

[0054] It should be noted that the method described above for the container orchestration engine scenario is only an exemplary embodiment and is not limited thereto. In actual implementation, the above method can also be applied to conventional scenarios. It is only necessary to configure the corresponding elastic scaling mode and storage capacity request value for the conventional scenario to support the implementation of the above method. No limitation is made here.

[0055] Through the above-mentioned embodiments of the present invention, an integrated algorithm model is used to deeply analyze various elastic scaling related information related to the storage space to be adjusted, and a corresponding expansion strategy can be generated at the appropriate expansion time. The storage capacity request value is automatically modified according to the expansion optimization strategy, and scientific storage expansion can be achieved. The scientificity and accuracy of expansion decisions are improved, storage bottlenecks can be discovered and responded to in a timely manner, resource waste and performance loss can be reduced, and business risks can be reduced.

[0056] According to an embodiment of the present invention, the operation S210 may include: periodically acquiring storage capacity information, performance indicator information, and business demand information related to the storage space to be adjusted according to a preset time interval, and determining elastic scaling related information according to at least one of the storage capacity information, performance indicator information, and business demand information.

[0057] According to an embodiment of the present invention, when the elastic scaling mode is enabled, elastic scaling related data can be continuously collected.

[0058] For example, the total capacity, used capacity, and remaining capacity of each storage pool, such as an NFS (Network File System) storage pool and a local disk storage pool, can be continuously detected to obtain storage capacity information. In a specific embodiment, data can be collected every 5 minutes, and for each storage space to be adjusted and the storage capacity request value, the currently allocated capacity, usage ratio, and other information can be recorded to obtain storage capacity information.

[0059] For example, you can detect the read and write speed, read and write latency and other performance indicators of storage devices in real time or periodically to obtain performance indicator information. For network storage, you can detect network bandwidth utilization as performance indicator information. Considering that node resource shortage may affect elastic scaling operations, you can also collect the CPU and memory usage of application instances in the corresponding nodes during storage operations as performance indicator information.

[0060] For example, the growth trend of storage capacity for different applications can be analyzed based on application logs or business indicators to obtain business demand information. In a specific embodiment, the database application may have a specific storage growth pattern based on the growth of the number of business transactions.

[0061] Through the above-mentioned embodiments of the present invention, multiple factors such as storage capacity, performance, business requirements, storage system characteristics, etc. can be comprehensively considered to accurately determine the timing and strategy of capacity expansion, making capacity expansion decisions more comprehensive and scientific, and able to adapt to various complex business scenarios and storage environments, thereby improving the scientificity and accuracy of capacity expansion decisions.

[0062] According to an embodiment of the present invention, the integrated algorithm model may include at least one decision tree model, the decision tree model may include a root node, a leaf node, and a conditional branch for associating the root node and the leaf node, the root node is used to configure the target decision feature, the leaf node is used to configure the elastic scaling judgment result, and the conditional branch is used to configure the decision condition. The above operation S220 may include: taking the elastic scaling related information as the input of the root node, calling the conditional branch to classify the elastic scaling related information, and determining the target leaf node corresponding to the elastic scaling related information. The elastic scaling judgment result is determined based on at least one target leaf node obtained by processing the elastic scaling related information based on at least one decision tree model.

[0063] Figure 3 The figure schematically shows a decision tree model according to an embodiment of the present invention.

[0064] like Figure 3 As shown, the root node 310 is configured with target decision features: remaining space s, s is a non-negative number; business growth rate v, v is a real number. The root node 310 can be divided into at least conditional branches that are respectively configured with the following decision conditions: the first conditional branch [s≥a, and v<b], the second conditional branch [s<a, and v<b], the third conditional branch [s<a, and v≥b], etc., and may not be limited to this. Among them, a and b are both positive numbers. The first conditional branch is associated with the first leaf node 311, which can be configured: no elastic scaling is required. The second conditional branch is associated with the second leaf node 312, which can be configured: no elastic scaling is required. The third conditional branch can be associated with the third leaf node 313, which can be configured: expansion is required, and the expansion scale is XX.

[0065] According to an embodiment of the present invention, after the elastic scaling related information is used as the input of the root node 310, the target decision feature related information related to the remaining space and the business growth rate can be extracted according to the target decision feature configured in the root node 310. Then, the target decision feature related information can be classified in combination with the first conditional branch, the second conditional branch, and the third conditional branch. For example, it can be classified into the third conditional branch, and the elastic scaling judgment result output by the decision tree model can be the required expansion defined by the third leaf node 313, and the expansion scale is XX.

[0066] According to an embodiment of the present invention, Figure 3 The decision tree model shown can be multiple, and multiple elastic scaling judgment results can be output based on the multiple decision tree models. On this basis, the above elastic scaling method for storage space can also include: when multiple elastic scaling judgment results meet the preset conditions, obtaining candidate elastic scaling scales of the target elastic scaling judgment result, obtaining multiple candidate elastic scaling scales, and the target elastic scaling judgment result is that elastic scaling is required. According to the multiple candidate elastic scaling scales, determine the target elastic scaling scale. The above operation S230 may include: according to the target elastic scaling scale, setting a storage capacity request value for requesting storage space.

[0067] According to an embodiment of the present invention, the preset condition may include: the ratio of the target elastic scaling judgment results that indicate the need for elastic scaling among the multiple elastic scaling judgment results is within a preset range, and may not be limited thereto. For example, it may also include: the number of the target elastic scaling judgment results that indicate the need for elastic scaling among the multiple elastic scaling judgment results is greater than the number of other elastic scaling judgment results that indicate the need for elastic scaling.

[0068] For example, the decision on whether to perform elastic scaling can be made by voting. If the output of most decision tree models is that capacity expansion is required, the final decision is that capacity expansion is required.

[0069] According to an embodiment of the present invention, in the process of determining a target elastic scaling scale based on multiple elastic scaling candidates, the elastic scaling candidate with the largest scale value among the multiple elastic scaling candidates may be determined as the target elastic scaling scale.

[0070] According to an embodiment of the present invention, determining the target elastic scaling scale according to multiple elastic scaling candidates may further include: calculating an average elastic scaling scale of the multiple elastic scaling candidates, and determining the average elastic scaling scale as the target elastic scaling scale.

[0071] For example, the average method can be used to predict the expansion scale. If the expansion scales predicted by multiple decision tree models are 10GB, 12GB, and 8GB respectively, the final predicted expansion scale can be (10+12+8) / 3 GB= 10GB.

[0072] Through the above-mentioned embodiments of the present invention, advanced intelligent technologies such as decision tree models can be used to perform detailed data analysis and decision-making, fully considering factors such as the dynamic changes in actual business needs, regular fluctuations in storage usage, and special needs in different application scenarios, to achieve comprehensive and scientific decision-making.

[0073] According to an embodiment of the present invention, the operation S240 may include: in response to detecting that the storage capacity request value has changed, calling the storage interface plug-in, using the storage interface plug-in to read the storage capacity request value, and performing elastic scaling operations on the storage space to be adjusted.

[0074] According to an embodiment of the present invention, the storage interface plug-in may include various types of automated elastic scaling programs, or various types of automated elastic scaling programs may be called based on the storage interface plug-in to implement automated elastic scaling operations on the storage space to be adjusted according to the storage capacity request value.

[0075] According to an embodiment of the present invention, in response to detecting a change in the storage capacity request value, an elastic scaling notification may be generated first, and then sent to the management end so that the management object can choose to accept or not accept the elastic scaling notification at the management end.

[0076] For example, the value change status of the storage capacity request value can be detected regularly, and when the storage capacity request value is detected to have changed, an elastic scaling notification containing detailed elastic scaling information such as the current time, elastic scaling requirements, and elastic scaling identifiers can be generated and sent to the management end. Among them, the elastic scaling requirements can describe the target elastic scaling scale and the remaining storage space and required storage space of the storage space to be adjusted, and are not limited to this. The elastic scaling identifier can represent the identifier of the node related to the storage space to be adjusted, or can represent the space identifier of the storage space to be adjusted, and are not limited to this, as long as the storage space to be adjusted can be located according to the elastic scaling identifier.

[0077] After receiving the elastic scaling notification on the management side, the administrator can determine the content of the elastic scaling notification and decide whether to accept it or not, and the acceptance method, such as automatic processing or manual processing.

[0078] According to an embodiment of the present invention, in response to detecting a change in the storage capacity request value, calling the storage interface plug-in includes: when it is determined that the elastic scaling notification has been accepted, in response to receiving an elastic scaling configuration instruction corresponding to the elastic scaling notification, calling the storage interface plug-in.

[0079] According to an embodiment of the present invention, the elastic scaling configuration instruction may represent an instruction manually initiated by an administrator at a management end, or may represent an instruction automatically started when it is determined that the elastic scaling notification has been accepted, which is not limited here.

[0080] For example, when the administrator has received the elastic scaling notification through the management terminal, the administrator can perform manual configuration using a command line statement that can generate an elastic scaling configuration instruction.

[0081] Through the above-mentioned embodiments of the present invention, by generating an elastic scaling notification and sending it to the management end, an intervention interface can be provided for the management personnel, so as to facilitate the controllable management of the elastic scaling process and improve the user experience.

[0082] According to an embodiment of the present invention, in the case where the storage space to be adjusted represents the storage space of the containerized application system, the containerized application system may include a control node and a working node controlled by the control node. The storage interface plug-in may include a container storage interface plug-in. The elastic scaling notification may include a node identifier related to the storage space to be adjusted. The above-mentioned use of the storage interface plug-in to read the storage capacity request value and perform elastic scaling operations on the storage space to be adjusted may include: calling the control node elastic scaling program of the container storage interface plug-in, performing elastic scaling operations on the target storage space related to the node identifier according to the storage capacity request value, and updating the current space information of the target storage space. In response to detecting that the current space information of the target storage space has changed, calling the working node elastic scaling program of the container storage interface plug-in, performing elastic scaling operations on the file system of the target working node according to the target storage space, and the target working node represents the working node related to the node identifier.

[0083] According to an embodiment of the present invention, a control node may represent a Controller-side in a container orchestration engine. A working node may represent a Node-side in a container orchestration engine. The container storage interface plug-in may use, for example, a CSI (Container Storage Interface) plug-in, or a custom plug-in with corresponding functions, which is not limited here. A node identifier may represent a Pod identifier in a container orchestration engine. The control node elastic scaling program may use the ControllerExpandVolume method of the CSI plug-in, but may not be limited thereto. The target storage space may represent a PV storage space. The working node elastic scaling program may use the NodeExpandVolume method of the CSI plug-in, but may not be limited thereto.

[0084] For example, if the administrator applies the expansion configuration, the controller-side expansion operation can be performed first. When it is detected that the storage capacity request value represented by the PVC has been modified, the corresponding CSI plug-in ControllerExpandVolume method can be called. For different storage backends, the CSI plug-in can perform specific underlying storage expansion operations. After successfully expanding the underlying storage, the CSI plug-in can update the current space information of the PV. Then, after the controller-side expansion is completed, the node-side expansion can be performed. When the container orchestration engine detects that the capacity of the PV has increased, the file system on the node may not have been expanded. The container orchestration engine can call the NodeExpandVolume method of the CSI plug-in to expand the file system on the node. For example, if it is an ext4 (Fourth extended file system, fourth generation extended file system) file system, the corresponding resize2fs (resize to filesystem, adjust the space size of the file system) operation can be performed in the Linux (an open source operating system) environment to ensure that the file system can use the newly added storage space.

[0085] Through the above-mentioned embodiments of the present invention, an automated and intelligent elastic scaling method for container orchestration scenarios is implemented, manual operations are simplified, and elastic scaling efficiency is improved.

[0086] According to an embodiment of the present invention, before executing the above elastic scaling method, an integrated algorithm model may be first constructed.

[0087] Figure 4The flowchart of the method for generating an integrated algorithm model according to an embodiment of the present invention is schematically shown.

[0088] like Figure 4 As shown, the generation method of the integrated algorithm model of this embodiment includes operations S410 to S420, and the generation method of the integrated algorithm model can be executed by at least one of the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105.

[0089] In operation S410, a target decision feature is determined based on at least one of the business requirements related to the target storage space and the sample elastic scaling related information. The decision feature is used to construct a decision condition to classify the sample elastic scaling related information to obtain an elastic scaling judgment result. When the elastic scaling judgment result is that elastic scaling is required, the elastic scaling judgment result also includes an elastic scaling scale corresponding to the required elastic scaling. The elastic scaling scale is used to set a storage capacity request value for requesting storage space. The storage capacity request value is used to perform elastic scaling operations on the target storage space.

[0090] According to an embodiment of the present invention, the target storage space may have the same or similar technical features as the aforementioned storage space to be adjusted. The sample elastic scaling related information may have the same or similar technical features as the aforementioned elastic scaling related information. The description of the target storage space, sample elastic scaling related information, target decision features, decision conditions, elastic scaling judgment results, elastic scaling scale, storage capacity request value, and elastic scaling operation can refer to the aforementioned embodiment and will not be repeated here.

[0091] In operation S420, an integrated algorithm model is generated according to the target decision feature, the decision condition, and the elastic scaling judgment result.

[0092] According to an embodiment of the present invention, the integrated algorithm model may be an algorithm model capable of implementing corresponding functions, or may include at least one of the above-mentioned decision tree models, to support the implementation of the above-mentioned elastic scaling method for storage space.

[0093] For example, when automatic capacity expansion is enabled, the currently collected sample elastic scaling related information can be input into the constructed decision tree model or integrated algorithm model to output the capacity expansion decision.

[0094] Through the above-mentioned embodiments of the present invention, an integrated algorithm model is constructed with the help of a large amount of sample elastic scaling related information collected, which realizes the optimization and improvement of the elastic scaling method, and can intelligently realize elastic scaling decisions based on sample elastic scaling related information, which is conducive to realizing scientific and accurate elastic scaling processing.

[0095] According to an embodiment of the present invention, the operation S410 may include: determining at least one candidate decision feature according to at least one of a business requirement related to a target storage space and sample elastic scaling related information. Calculating an information gain value according to the sample elastic scaling related information and the at least one candidate decision feature to obtain at least one information gain value. Determining a target decision feature according to the at least one information gain value.

[0096] For example, you can first determine the target storage space based on the business requirements related to the target storage space and the sample elastic scaling related information or the initially collected elastic scaling related information. candidate decision features, is a positive integer. Select from the candidate decision feature data features as the final candidate decision features. Then, for the selected (or ) candidate decision features, the information gain or Gini index of the corresponding sample elastic scaling related information can be calculated to obtain at least one information gain value. After that, the best feature can be selected as the target decision feature, and an integrated algorithm model or decision tree model can be constructed based on it.

[0097] According to an embodiment of the present invention, after determining the target decision feature, corresponding to the above operation S420, a decision condition can be recursively constructed based on the target decision feature until a stop condition is met. The stop condition can include at least one of the following: the sample data input to the model has been assigned to the same category, and a preset tree depth has been reached.

[0098] According to an embodiment of the present invention, the target decision feature corresponding to each sample elastic scaling related information can be determined by sampling the sample elastic scaling related information multiple times, so that by repeating the above steps k times, k decision tree models can be obtained to form a random forest model, where k is a positive integer. In practical applications, for multiple elastic scaling judgment results output by classification of the random forest model, the final elastic scaling judgment result can be determined based on the sampling method in the above embodiment.

[0099] According to an embodiment of the present invention, the actual result representing success or failure obtained by applying the above integrated algorithm model each time can be fed back to the integrated algorithm model. The model can continuously adjust its own parameters and decision logic based on these feedbacks to further improve the accuracy of subsequent elastic scaling decisions.

[0100] Figure 5 The overall flow chart of the elastic scaling method according to an embodiment of the present invention is schematically shown.

[0101] like Figure 5As shown, the method includes operations S501 to S513.

[0102] In operation S501, it is determined whether the capacity expansion mode has been turned on. If so, operation S502 is executed; if not, operation S513 is executed.

[0103] In operation S502, elastic scaling related data is obtained.

[0104] In operation S503, data is pre-processed.

[0105] In operation S504, the integrated algorithm model is called to perform classification processing.

[0106] In operation S505 , the elastic scaling decision is output.

[0107] In operation S506, it is determined whether elastic scaling is required. If yes, operation S507 is executed; if no, operation S513 is executed.

[0108] In operation S507, the integrated algorithm model is optimized based on the feedback and learning mechanism.

[0109] In operation S508 , the storage capacity request value represented by the PVC is modified according to the elastic scaling decision.

[0110] In operation S509, a capacity expansion notification is generated.

[0111] In operation S510, elastic scaling configuration instructions are manually / automatically generated.

[0112] In operation S511, the Controller-side is expanded.

[0113] .In operation S512, Node-side capacity is expanded.

[0114] In operation S513, no capacity expansion operation is performed.

[0115] Through the above embodiments of the present invention, an intelligent elastic scaling method is provided. The method is not based on empirical guesses or simple fixed rules, but through an intelligent storage elastic scaling evaluation mechanism, sample data and real-time data are analyzed to draw elastic scaling conclusions, which can optimize the traditional elastic scaling mechanism of the container orchestration engine. It alleviates the judgment of elastic scaling timing and the simple and rough elastic scaling method in the relevant elastic scaling mechanism, and can only find storage bottlenecks through user investigation and manually perform elastic scaling operations, and cannot timely address the bottlenecks and those elastic scaling and complex operations.

[0116] Based on the above elastic expansion method for storage space, the present invention also provides an elastic expansion device for storage space. Figure 6The device is described in detail.

[0117] Figure 6 The structure block diagram of the elastic expansion device for storage space according to an embodiment of the present invention is schematically shown.

[0118] like Figure 6 As shown, the elastic scaling device 600 for storage space of this embodiment includes an elastic scaling related information acquisition module 610 , a model classification module 620 , a storage capacity request value setting module 630 and an elastic scaling module 640 .

[0119] The elastic scaling related information acquisition module 610 is used to acquire elastic scaling related information related to the storage space to be adjusted when the elastic scaling mode is enabled for the storage space to be adjusted. In one embodiment, the elastic scaling related information acquisition module 610 can be used to perform the operation S210 described above, which will not be described in detail here.

[0120] The model classification module 620 is used to classify elastic scaling related information according to the decision conditions constructed based on the target decision features in the integrated algorithm model to obtain an elastic scaling judgment result, wherein the integrated algorithm model is constructed based on the target decision features, the decision conditions and the elastic scaling judgment result, the target decision features are determined based on at least one of the business requirements related to the storage space to be adjusted and the elastic scaling related information, and the elastic scaling judgment result represents whether elastic scaling is required or not. In one embodiment, the model classification module 620 can be used to perform the operation S220 described above, which will not be repeated here.

[0121] The storage capacity request value setting module 630 is used to set the storage capacity request value for requesting storage space according to the elastic scaling scale included in the elastic scaling judgment result when the elastic scaling judgment result indicates that elastic scaling is required. In one embodiment, the storage capacity request value setting module 630 can be used to perform the operation S230 described above, which will not be described in detail here.

[0122] The elastic scaling module 640 is used to perform elastic scaling operations on the storage space to be adjusted according to the storage capacity request value. In one embodiment, the elastic scaling module 640 can be used to perform the operation S240 described above, which will not be described in detail here.

[0123] According to an embodiment of the present invention, the integrated algorithm model includes at least one decision tree model, the decision tree model includes a root node, a leaf node, and a conditional branch for associating the root node and the leaf node, the root node is used to configure the target decision feature, the leaf node is used to configure the elastic scaling judgment result, and the conditional branch is used to configure the decision condition. The model classification module includes a classification unit and an elastic scaling judgment result determination unit.

[0124] The classification unit is used to take the elastic scaling related information as the input of the root node, call the conditional branch to classify the elastic scaling related information, and determine the target leaf node corresponding to the elastic scaling related information.

[0125] The elastic scaling judgment result determining unit is used to determine the elastic scaling judgment result according to at least one target leaf node obtained by processing elastic scaling related information based on at least one decision tree model.

[0126] According to an embodiment of the present invention, there are multiple elastic scaling judgment results. The elastic scaling device for storage space also includes a candidate elastic scaling scale obtaining module and a target elastic scaling scale determining module.

[0127] The candidate elastic scaling scale obtaining module is used to obtain the candidate elastic scaling scale of the target elastic scaling judgment result when multiple elastic scaling judgment results meet preset conditions, and obtain multiple candidate elastic scaling scales, and the target elastic scaling judgment result is that elastic scaling is required.

[0128] The target elastic scaling scale determination module is used to determine the target elastic scaling scale according to multiple candidate elastic scaling scales.

[0129] According to an embodiment of the present invention, the storage capacity request value setting module includes a storage capacity request value setting unit.

[0130] The storage capacity request value setting unit is used to set the storage capacity request value for requesting storage space according to the target elastic scaling scale.

[0131] According to an embodiment of the present invention, the preset condition includes: a proportion of target elastic scaling judgment results indicating that elastic scaling is required among the plurality of elastic scaling judgment results is within a preset range.

[0132] According to an embodiment of the present invention, the target elastic scaling scale determination module includes an average elastic scaling scale calculation unit and a target elastic scaling scale determination unit.

[0133] The average elastic scaling scale calculation unit is used to calculate the average elastic scaling scale of multiple candidate elastic scaling scales.

[0134] The target elastic scaling scale determining unit is used to determine the average elastic scaling scale as the target elastic scaling scale.

[0135] According to an embodiment of the present invention, the elastic scaling module includes a plug-in calling unit and an elastic scaling unit.

[0136] The plug-in calling unit is used to call the storage interface plug-in in response to detecting that the storage capacity request value has changed.

[0137] The elastic scaling unit is used to use the storage interface plug-in to read the storage capacity request value and perform elastic scaling operations on the storage space to be adjusted.

[0138] According to an embodiment of the present invention, the elastic expansion device for storage space further includes a notification generating module and a notification sending module.

[0139] The notification generation module is used to generate elastic scaling notifications.

[0140] The notification sending module is used to send the elastic scaling notification to the management end, so that the management object can choose to accept the elastic scaling notification or not accept the elastic scaling notification on the management end.

[0141] According to an embodiment of the present invention, the plug-in calling unit includes a plug-in calling sub-unit.

[0142] The plug-in calling subunit is used to call the storage interface plug-in in response to receiving the elastic scaling configuration instruction corresponding to the elastic scaling notification when it is determined that the elastic scaling notification has been accepted.

[0143] According to an embodiment of the present invention, the storage space to be adjusted represents the storage space of the containerized application system, the containerized application system includes a control node and a working node controlled by the control node, the storage interface plug-in includes a container storage interface plug-in, and the elastic scaling notification includes a node identifier related to the storage space to be adjusted. The elastic scaling unit includes a storage space elastic scaling subunit and a file system elastic scaling subunit.

[0144] The storage space elastic scaling subunit is used to call the control node elastic scaling program of the container storage interface plug-in, perform elastic scaling operations on the target storage space related to the node identifier according to the storage capacity request value, and update the current space information of the target storage space.

[0145] The file system elastic scaling subunit is used to call the working node elastic scaling program of the container storage interface plug-in in response to detecting that the current space information of the target storage space has changed, and perform elastic scaling operations on the file system of the target working node according to the target storage space. The target working node represents a working node related to the node identifier.

[0146] According to an embodiment of the present invention, the elastic scaling related information acquisition module includes an information acquisition unit and an elastic scaling related information determination unit.

[0147] The information acquisition unit is used to periodically acquire storage capacity information, performance indicator information, and business demand information related to the storage space to be adjusted according to a preset time interval.

[0148] The elastic scaling related information determining unit is used to determine the elastic scaling related information according to at least one of the storage capacity information, the performance indicator information and the business demand information.

[0149] Based on the above-mentioned method for generating an integrated algorithm model, the present invention also provides a device for generating an integrated algorithm model. Figure 7 The device is described in detail.

[0150] Figure 7 The structural block diagram of the device for generating the integrated algorithm model according to an embodiment of the present invention is schematically shown.

[0151] like Figure 7 As shown, the generation device 700 of the integrated algorithm model of this embodiment includes a target decision feature determination module 710 and a model generation module 720.

[0152] The target decision feature determination module 710 is used to determine the target decision feature according to at least one of the business requirements related to the target storage space and the sample elastic scaling related information. The decision feature is used to construct a decision condition to classify the sample elastic scaling related information to obtain an elastic scaling judgment result. In the case where the elastic scaling judgment result is that elastic scaling is required, the elastic scaling judgment result also includes an elastic scaling scale corresponding to the required elastic scaling. The elastic scaling scale is used to set the storage capacity request value for requesting the storage space. The storage capacity request value is used to perform an elastic scaling operation on the target storage space. In one embodiment, the target decision feature determination module 710 can be used to perform the operation S410 described above, which will not be repeated here.

[0153] The model generation module 720 is used to generate an integrated algorithm model according to the target decision feature, decision condition and elastic scaling judgment result. In one embodiment, the model generation module 720 can be used to perform the operation S420 described above, which will not be repeated here.

[0154] According to an embodiment of the present invention, the target decision feature determination module includes a candidate decision feature determination unit, an information gain value calculation unit and a target decision feature determination unit.

[0155] The candidate decision feature determination unit is used to determine at least one candidate decision feature according to at least one of the business requirements related to the target storage space and the sample elastic scaling related information.

[0156] The information gain value calculation unit is used to calculate the information gain value according to the sample elastic scaling related information and at least one candidate decision feature to obtain at least one information gain value.

[0157] The target decision feature determination unit is used to determine the target decision feature according to at least one information gain value.

[0158] According to an embodiment of the present invention, any multiple modules of the elastic scaling related information acquisition module 610, the model classification module 620, the storage capacity request value setting module 630 and the elastic scaling module 640, or the target decision feature determination module 710 and the model generation module 720 can be combined in one module for implementation, or any one of them can be split into multiple modules. Alternatively, at least part of the functions of one or more of these modules can be combined with at least part of the functions of other modules and implemented in one module. According to an embodiment of the present invention, at least one of the elastic scaling related information acquisition module 610, the model classification module 620, the storage capacity request value setting module 630 and the elastic scaling module 640, or the target decision feature determination module 710 and the model generation module 720 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application specific integrated circuit (ASIC), or can be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or implemented in any one of the three implementation methods of software, hardware and firmware or in an appropriate combination of any of them. Alternatively, the elastic scaling related information acquisition module 610, the model classification module 620, the storage capacity request value setting module 630 and the elastic scaling module 640, or at least one of the target decision feature determination module 710 and the model generation module 720 can be at least partially implemented as a computer program module, and when the computer program module is executed, the corresponding function can be executed.

[0159] Figure 8 A block diagram of an electronic device suitable for implementing at least one of a method for elastically scaling a storage space and a method for generating an integrated algorithm model according to an embodiment of the present invention is schematically shown.

[0160] like Figure 8 As shown, the electronic device 800 according to an embodiment of the present invention includes a processor 801, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 802 or a program loaded from a storage part 808 to a random access memory (RAM) 803. The processor 801 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 801 may also include an onboard memory for caching purposes. The processor 801 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present invention.

[0161] In RAM 803, various programs and data required for the operation of electronic device 800 are stored. Processor 801, ROM 802 and RAM 803 are connected to each other via bus 804. Processor 801 performs various operations of the method flow according to the embodiment of the present invention by executing the programs in ROM 802 and / or RAM 803. It should be noted that the program can also be stored in one or more memories other than ROM 802 and RAM 803. Processor 801 can also perform various operations of the method flow according to the embodiment of the present invention by executing the programs stored in the one or more memories.

[0162] According to an embodiment of the present invention, the electronic device 800 may further include an input / output (I / O) interface 805, which is also connected to the bus 804. The electronic device 800 may further include one or more of the following components connected to the input / output (I / O) interface 805: an input portion 806 including a keyboard, a mouse, etc.; an output portion 807 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 808 including a hard disk, etc.; and a communication portion 809 including a network interface card such as a LAN card, a modem, etc. The communication portion 809 performs communication processing via a network such as the Internet. A drive 810 is also connected to the input / output (I / O) interface 805 as needed. A removable medium 811, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 810 as needed, so that the computer program read therefrom is installed into the storage portion 808 as needed.

[0163] The present invention also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiment; or may exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, at least one of the elastic scaling method for storage space and the generation method of integrated algorithm model according to the embodiment of the present invention is implemented.

[0164] According to an embodiment of the present invention, the computer-readable storage medium may be a non-volatile computer-readable storage medium, for example, it may include but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), 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, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, an apparatus or a device. For example, according to an embodiment of the present invention, the computer-readable storage medium may include the ROM 802 and / or RAM 803 described above and / or one or more memories other than ROM 802 and RAM 803.

[0165] The embodiment of the present invention also includes a computer program product, which includes a computer program, and the computer program includes a program code for executing the method shown in the flowchart. When the computer program product is run in a computer system, the program code is used to enable the computer system to implement at least one of the elastic scaling method for storage space and the generation method of the integrated algorithm model provided in the embodiment of the present invention.

[0166] The computer program executes the above functions defined in the system / device of the embodiment of the present invention when the processor 801 executes the computer program. According to the embodiment of the present invention, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0167] In one embodiment, the computer program may rely on tangible storage media such as optical storage devices, magnetic storage devices, etc. In another embodiment, the computer program may also be transmitted and distributed in the form of signals on a network medium, and downloaded and installed through the communication part 809, and / or installed from a removable medium 811. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0168] In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 809, and / or installed from the removable medium 811. When the computer program is executed by the processor 801, the above functions defined in the system of the embodiment of the present invention are performed. According to the embodiment of the present invention, the system, device, means, module, unit, etc. described above can be implemented by a computer program module.

[0169] It will be appreciated by those skilled in the art that the features described in the various embodiments of the present invention may be combined and / or combined in various ways, even if such combinations or combinations are not explicitly described in the present invention. In particular, without departing from the spirit and teachings of the present invention, the features described in the various embodiments of the present invention may be combined and / or combined in various ways. All of these combinations and / or combinations fall within the scope of the present invention.

[0170] The embodiments of the present invention are described above. However, these embodiments are only for the purpose of illustration, and are not intended to limit the scope of the present invention. Although each embodiment is described above, it does not mean that the measures in each embodiment cannot be used in combination advantageously. Without departing from the scope of the present invention, those skilled in the art may make various substitutions and modifications, which should all fall within the scope of the present invention.

Claims

1. A method for elastically scaling storage space, characterized in that: The method comprises: When the storage space to be adjusted has enabled the elastic scaling mode, obtaining elastic scaling related information related to the storage space to be adjusted includes: periodically acquiring storage capacity information, performance indicator information, and business demand information related to the storage space to be adjusted according to a preset time interval; and Determine the elastic scaling related information according to at least one of the storage capacity information, the performance indicator information and the business demand information; According to the decision conditions constructed based on the target decision features in the integrated algorithm model, the elastic scaling related information is classified to obtain an elastic scaling judgment result, wherein the integrated algorithm model is constructed based on the target decision features, the decision conditions, and the elastic scaling judgment result, the target decision features are determined based on at least one of the business requirements related to the storage space to be adjusted and the elastic scaling related information, and the elastic scaling judgment result indicates whether elastic scaling is required or not; If the elastic scaling determination result indicates that elastic scaling is required, setting a storage capacity request value for requesting storage space according to the elastic scaling scale included in the elastic scaling determination result; and According to the storage capacity request value, an elastic scaling operation is performed on the storage space to be adjusted.

2. The method according to claim 1, characterized in that The integrated algorithm model includes at least one decision tree model, the decision tree model includes a root node, a leaf node, and a conditional branch for associating the root node and the leaf node, the root node is used to configure the target decision feature, the leaf node is used to configure the elastic scaling judgment result, and the conditional branch is used to configure the decision condition; The classifying the elastic scaling related information according to the decision conditions constructed based on the target decision features in the integrated algorithm model to obtain the elastic scaling judgment result includes: Taking the elastic scaling related information as the input of the root node, calling the conditional branch to classify the elastic scaling related information, and determining a target leaf node corresponding to the elastic scaling related information; as well as The elastic scaling judgment result is determined according to at least one target leaf node obtained by processing the elastic scaling related information based on at least one decision tree model.

3. The method according to claim 1 or 2, characterized in that: The elastic scaling judgment result has multiple results; the method further includes: When the plurality of elastic scaling judgment results satisfy a preset condition, obtaining a candidate elastic scaling scale of a target elastic scaling judgment result to obtain a plurality of candidate elastic scaling scales, wherein the target elastic scaling judgment result is the required elastic scaling; and Determining a target elastic scaling scale according to the plurality of candidate elastic scaling scales; The setting of the storage capacity request value for requesting storage space according to the elastic scaling scale included in the elastic scaling determination result includes: A storage capacity request value for requesting storage space is set according to the target elastic scaling scale.

4. The method according to claim 3, characterized in that The preset condition includes: a ratio of target elastic scaling judgment results indicating that elastic scaling is required among the plurality of elastic scaling judgment results is within a preset range.

5. The method according to claim 3, characterized in that: The determining the target elastic scaling scale according to the plurality of candidate elastic scaling scales includes: Calculating an average elastic scaling scale of the plurality of candidate elastic scaling scales; and The average elastic scaling scale is determined as the target elastic scaling scale.

6. The method according to claim 1, characterized in that The performing elastic scaling operation on the storage space to be adjusted according to the storage capacity request value includes: In response to detecting a change in the storage capacity request value, calling a storage interface plug-in; and The storage interface plug-in is used to read the storage capacity request value and perform elastic scaling operations on the storage space to be adjusted.

7. The method according to claim 6, characterized in that The method further comprises: Generate elastic scaling notification; and The elastic scaling notification is sent to a management end, so that the management object can choose to accept the elastic scaling notification or not accept the elastic scaling notification on the management end.

8. The method according to claim 7, characterized in that In response to detecting that the storage capacity request value has changed, calling the storage interface plug-in includes: In a case where it is determined that the elastic scaling notification has been accepted, in response to receiving an elastic scaling configuration instruction corresponding to the elastic scaling notification, the storage interface plug-in is called.

9. The method according to claim 6 or 7, characterized in that: The storage space to be adjusted represents the storage space of a containerized application system, the containerized application system includes a control node and a working node controlled by the control node, the storage interface plug-in includes a container storage interface plug-in, and the elastic scaling notification includes a node identifier related to the storage space to be adjusted; The using the storage interface plug-in to read the storage capacity request value and perform elastic scaling operations on the storage space to be adjusted includes: Calling the control node elastic scaling program of the container storage interface plug-in, performing elastic scaling operations on the target storage space associated with the node identifier according to the storage capacity request value, and updating the current space information of the target storage space; as well as In response to detecting that the current space information of the target storage space has changed, the working node elastic scaling program of the container storage interface plug-in is called to perform elastic scaling operations on the file system of the target working node according to the target storage space, and the target working node represents the working node related to the node identifier.

10. A method for generating an integrated algorithm model, characterized in that: The method comprises: Determine a target decision feature according to at least one of the business demand related to the target storage space and the sample elastic scaling related information, wherein the decision feature is used to construct a decision condition to classify the sample elastic scaling related information to obtain an elastic scaling judgment result, wherein when the elastic scaling judgment result is that elastic scaling is required, the elastic scaling judgment result also includes an elastic scaling scale corresponding to the required elastic scaling, wherein the elastic scaling scale is used to set a storage capacity request value for requesting storage space, and the storage capacity request value is used to perform an elastic scaling operation on the target storage space, wherein the sample elastic scaling related information includes: at least one of storage capacity information, performance indicator information, and business demand information related to the target storage space periodically obtained according to a preset time interval; and An integrated algorithm model is generated according to the target decision feature, the decision condition and the elastic scaling judgment result.

11. The method according to claim 10, characterized in that The determining of the target decision feature according to at least one of the business requirements related to the target storage space and the sample elastic scaling related information includes: Determine at least one candidate decision feature according to at least one of the business requirements related to the target storage space and the sample elastic scaling related information; Calculating an information gain value according to the sample elastic scaling related information and at least one of the candidate decision features to obtain at least one information gain value; and The target decision feature is determined according to at least one of the information gain values.

12. An electronic device comprising: one or more processors; a memory for storing one or more computer programs, It is characterized in that the one or more processors execute the one or more computer programs to implement the steps of the method according to any one of claims 1 to 11.

13. A computer-readable storage medium having a computer program or instruction stored thereon, characterized in that: When the computer program or instruction is executed by a processor, the steps of the method according to any one of claims 1 to 11 are implemented.

14. A computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the method according to any one of claims 1 to 11.

Images