Server cluster capacity determination method and device, equipment, medium and product

Abstract

The invention relates to the technical field of cloud computing, and particularly provides a server cluster capacity determination method and device, equipment, a medium and a product, and the method comprises the steps: obtaining the current storage capacity data and network performance data of a to-be-evaluated target server cluster; the storage capacity data and the network performance data are input into an allocated capacity proportion value estimation model, an estimated allocated capacity proportion value of the target server cluster is obtained, the allocated capacity proportion value is the ratio of the allocated capacity to the super-component capacity, the super-component capacity is the product of the total storage capacity of the target server cluster and the super-component rate, and the estimated allocated capacity proportion value of the target server cluster is obtained. The super-division rate is used for indicating a multiplying power that the total storage capacity of the target server cluster is allowed to be excessively allocated; based on the estimated allocated capacity proportion value and the actual allocated capacity proportion value, determining the current allocable total capacity of the target server cluster; according to the invention, the capacity estimation accuracy of the server cluster is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of cloud computing technology, and in particular to a method, apparatus, device, medium, and product for determining the capacity of a server cluster. Background Art

[0002] In the field of cloud computing and distributed storage, cloud service providers typically divide physical server capacity into multiple virtual servers and rent these virtual servers to users. After users obtain the right to use a certain amount of storage space, there may be situations where the storage space utilization rate is less than 100%. In order to improve storage resource utilization and profitability, cloud service providers typically allocate excess storage capacity to users for use.

[0003] In related technologies, by monitoring and managing the storage capacity of the server cluster, it is determined which capacity pools have available capacity and which capacity pools have exhausted their available capacity, thereby dynamically adjusting and allocating capacity to prevent the capacity over-allocated to users from exceeding the actual load capacity of the server cluster.

[0004] However, the capacity management strategies for server clusters provided in related technologies usually focus on the storage capacity of the server cluster itself, resulting in inflated capacity prediction results for the server cluster that cannot accurately reflect the actual load capacity of the system. Summary of the Invention

[0005] The present disclosure is proposed in view of the above problems and provides a method, apparatus, device, medium and product for determining the capacity of a server cluster, which can improve the accuracy of capacity estimation of a server cluster.

[0006] According to a first aspect of the present disclosure, a method for determining the capacity of a server cluster is provided, comprising: Obtain the current storage capacity and network performance data of the target server cluster to be evaluated; Inputting the storage capacity data and network performance data into an allocated capacity ratio estimation model to obtain an estimated allocated capacity ratio of the target server cluster, wherein the allocated capacity ratio is a ratio of the allocated capacity to the over-allocated capacity, the over-allocated capacity being the product of the total storage capacity of the target server cluster and the over-allocation ratio, and the over-allocation ratio being used to indicate the ratio by which the total storage capacity of the target server cluster is allowed to be over-allocated; Based on the estimated allocated capacity ratio value and the actual allocated capacity ratio value, the current allocatable total capacity of the target server cluster is determined.

[0007] According to a second aspect of the present disclosure, a device for determining the capacity of a server cluster is provided, comprising: an acquisition module configured to acquire current storage capacity data and network performance data of a target server cluster to be evaluated; an estimation module configured to input the storage capacity data and the network performance data into an allocated capacity ratio estimation model to obtain an estimated allocated capacity ratio of the target server cluster, wherein the allocated capacity ratio is a ratio of the allocated capacity to the over-allocated capacity, the over-allocated capacity being the product of the total storage capacity of the target server cluster and the over-allocation ratio, the over-allocation ratio being used to indicate a ratio by which the total storage capacity of the target server cluster is allowed to be over-allocated; The determination module is configured to determine the current allocatable total capacity of the target server cluster based on the estimated allocated capacity ratio value and the actual allocated capacity ratio value.

[0008] According to a third aspect of the present disclosure, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the method described in the first aspect.

[0009] According to a fourth aspect of the present disclosure, 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 of the method described in the first aspect are implemented.

[0010] According to a fifth aspect of the present disclosure, a computer program product is provided, comprising a computer program, which implements the steps of the method according to the first aspect when executed by a processor.

[0011] The server cluster capacity determination method, apparatus, equipment, medium and product provided by the embodiments of the present disclosure can determine the current estimated value of the allocated capacity ratio of the target server cluster based on the current storage capacity data and performance indicator data of the server cluster, and determine the current allocatable total capacity of the target server cluster based on the current estimated value of the allocated capacity ratio and the actual allocated capacity ratio value. Since the data of the server cluster in the storage capacity dimension and the performance dimension are referenced in the process of estimating the allocated capacity ratio value, the matching degree between the determined estimated allocated capacity ratio value and the current actual performance of the server cluster can be improved, thereby improving the accuracy and reliability of the final determined current allocatable total capacity.

[0012] It is to be understood that both the foregoing general description and the following detailed description are exemplary, and are intended to provide further explanation of the technology as claimed. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The above and other purposes, features, and advantages of the present disclosure will become more apparent through a more detailed description of the embodiments of the present disclosure in conjunction with the accompanying drawings. The accompanying drawings are intended to provide a further understanding of the embodiments of the present disclosure and constitute a part of the specification. Together with the embodiments of the present disclosure, they are used to explain the present disclosure and are not intended to limit the present disclosure. In the drawings, the same reference numerals generally represent the same components or steps.

[0014] Figure 1 It is a schematic diagram of an implementation scenario of the server cluster capacity determination solution of an embodiment of the present disclosure.

[0015] Figure 2 The present invention is a flowchart of a method for determining the capacity of a server cluster according to an embodiment of the present invention.

[0016] Figure 3 The present invention is a block diagram of a device for determining the capacity of a server cluster according to an embodiment of the present invention.

[0017] Figure 4 is a schematic diagram illustrating a computer program product according to an embodiment of the present disclosure.

[0018] Figure 5 is a hardware block diagram illustrating an electronic device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solutions and advantages of the present disclosure more apparent, the following will describe in detail exemplary embodiments of the present disclosure with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all the embodiments of the present disclosure, and it should be understood that the present disclosure is not limited to the exemplary embodiments described herein.

[0020] In order to solve the above problems, the embodiment of the present disclosure provides a solution for determining the capacity of a server cluster, such as Figure 1 As shown, Figure 1 FIG. 1 shows a schematic diagram of an implementation scenario of a server cluster capacity determination solution provided by an exemplary embodiment of the present disclosure. Figure 1 As shown, the implementation scenario 100 includes a server cluster 101 and a terminal device 102, wherein the server cluster 101 is a server cluster in a cloud system or a distributed system, and the number of server clusters can include at least one; the terminal device 102 is a terminal device used for server cluster capacity assessment, and the terminal device can be a computer, notebook, tablet, mobile phone or micro server, etc.

[0021] A communication link may be established between each server cluster 101 and the terminal device 102 to implement the server cluster capacity determination solution provided in the embodiment of the present disclosure.

[0022] Figure 2A flow chart of a method for determining the capacity of a server cluster according to an exemplary embodiment of the present disclosure is shown. The method can be applied to a server, such as Figure 2 As shown, the method of the embodiment of the present disclosure may include: Step S201, obtaining the current storage capacity data and network performance data of the target server cluster to be evaluated; Step S202: Input the storage capacity data and the network performance data into an allocated capacity ratio estimation model to obtain an estimated allocated capacity ratio of the target server cluster. The allocated capacity ratio is the ratio of the allocated capacity to the over-allocated capacity. The over-allocated capacity is the product of the total storage capacity of the target server cluster and the over-allocation ratio. The over-allocation ratio indicates the ratio by which the total storage capacity of the target server cluster is allowed to be over-allocated. Step S203: determining the current allocable total capacity of the target server cluster based on the estimated allocated capacity ratio value and the actual allocated capacity ratio value; To sum up, the server cluster capacity determination method provided by the embodiment of the present disclosure can determine the current estimated value of the allocated capacity ratio of the target server cluster based on the current storage capacity data and performance indicator data of the server cluster, and determine the current allocatable total capacity of the target server cluster based on the current estimated value of the allocated capacity ratio and the actual allocated capacity ratio value. Since the data of the server cluster in the storage capacity dimension and the performance dimension are referred to in the process of estimating the allocated capacity ratio value, the matching degree between the determined estimated allocated capacity ratio value and the current actual performance of the server cluster can be improved, thereby improving the accuracy and reliability of the final determined current allocatable total capacity.

[0023] The following Figure 2 The specific implementation of each step in the embodiment shown is described in detail: In step S201, the terminal device obtains the current storage capacity data and network performance data of the target server cluster to be evaluated.

[0024] In the embodiment of the present disclosure, the storage capacity data includes information such as the total storage capacity, occupied capacity, remaining capacity, and expandable capacity of the hard disks in the target server cluster. The storage capacity data is used to characterize the data storage capabilities of the server cluster. The network performance data includes latency, jitter, packet loss, bandwidth, and the number of reads and writes per second (Input / Output PerSecond, IOPS), etc. The network performance data is used to characterize the network status of the server cluster.

[0025] It should be noted that, in the embodiments of the present disclosure, the terminal device may periodically determine the capacity information of the server cluster, or the terminal device may determine the capacity information of the server cluster after detecting a server cluster capacity determination instruction issued by a user; specifically, it may be determined based on actual needs, which is not limited in the embodiments of the present disclosure. The period for the terminal device to determine the capacity information of the server cluster may be configured based on actual needs, which is not limited in the embodiments of the present disclosure. For example, the terminal device may re-evaluate the total capacity of the server cluster every 24 hours.

[0026] In an optional embodiment, the process of the terminal device obtaining the current storage capacity data and network performance data of the target server cluster to be evaluated includes: at the beginning of the current server cluster capacity evaluation cycle, sending a parameter acquisition instruction to the target server in the target server cluster, and receiving the current storage capacity data and network performance data of the target server cluster returned by the target server in response to the parameter acquisition instruction, wherein the target server cluster can be a server cluster pre-configured by the user and a server cluster among multiple server clusters that needs to undergo regular capacity evaluation; the target server in the target server cluster can be a central server or any server in the server cluster.

[0027] In an optional embodiment, the process of the terminal device obtaining the current storage capacity data and network performance data of the target server cluster to be evaluated includes: in response to obtaining the server cluster capacity determination instruction, obtaining the target server cluster identifier in the server cluster capacity determination instruction, and sending a parameter acquisition instruction to the target server in the target server cluster associated with the target server cluster identifier, and receiving the target server's response to the parameter acquisition instruction; wherein, the server cluster capacity determination instruction is obtained by the terminal device in response to a user operation.

[0028] In step S202, the terminal device inputs the storage capacity data and the network performance data into an allocated capacity ratio estimation model to obtain an estimated allocated capacity ratio value of the target server cluster.

[0029] In the embodiment of the present disclosure, the allocated capacity ratio value is the ratio of the allocated capacity to the over-allocation capacity, the over-allocation capacity is the product of the total storage capacity of the target server and the over-allocation rate, and the over-allocation rate is used to indicate the ratio at which the total storage capacity of the target server cluster is allowed to be over-allocated, wherein the value of the over-allocation rate can be determined based on actual needs, and the embodiment of the present disclosure does not limit this; it can be understood that the over-allocation rate is greater than or equal to 1.

[0030] For example, assuming that the total storage capacity of the target server cluster is 100T, if the over-resolution ratio is 2, the over-resolution capacity of the target server cluster is 200T; if the over-resolution ratio is 1.5, the over-resolution capacity of the target server cluster is 150T.

[0031] It should be noted that, in the embodiment of the present disclosure, the allocated capacity ratio value estimation model can be a pre-trained neural network model, wherein the specific architecture of the allocated capacity ratio value estimation model can be determined based on actual needs, and the embodiment of the present disclosure does not limit this; for example, the allocated capacity ratio value estimation model includes an input layer, multiple hidden layers, and an output layer.

[0032] In an optional embodiment, the process of training the allocated capacity ratio value estimation model of the terminal device may include: obtaining a sample data set, and dividing the sample data set into a training set and a test set, then, iteratively training the allocated capacity ratio value estimation model to be trained based on the training set to obtain the allocated capacity ratio value estimation model to be evaluated; further, evaluating the allocated capacity ratio value estimation model to be evaluated based on the test set to obtain an evaluation result; finally, when the evaluation result indicates that the allocated capacity ratio value estimation model has converged, determining that the allocated capacity ratio value estimation model has been trained; or, when the evaluation result indicates that the allocated capacity ratio value estimation model has not converged, repeating the above process of iteratively training and evaluating the allocated capacity ratio value estimation model until the evaluation result indicates that the allocated capacity ratio value estimation model has converged.

[0033] It should be noted that, in the embodiment of the present disclosure, the sample data set includes multiple sample data, each sample data includes the original sample feature data of the sample server cluster, and a label value corresponding to the original sample feature data, wherein the original sample feature data includes sample storage capacity data and sample network performance data, and the label value is the sample allocated capacity ratio value; wherein the sample data can be recorded by the sample server cluster during the historical operation process; the ratio of the sample data volume in the training set and the test set can be determined based on actual needs, and the embodiment of the present disclosure does not limit this. For example, the ratio of the sample data volume in the training set and the test set can be 8:2.

[0034] Optionally, in order to further improve the training efficiency of the model, the terminal device can use batch sample data to perform each training process, and the terminal device iteratively trains the allocated capacity ratio value estimation model to be trained based on the training set to obtain the allocated capacity ratio value estimation model to be evaluated. The process may include: dividing the multiple sample data in the training set into multiple sample data subsets, and repeatedly inputting the multiple original sample feature data in each sample data subset into the allocated capacity ratio value estimation model to be trained to obtain the sample estimated allocated capacity ratio value corresponding to each original sample feature data; then, based on the data corresponding to each original sample feature data, the estimated allocated capacity ratio value is obtained. The invention relates to a process of updating the model parameters of the allocated capacity ratio value estimation model based on the estimated allocated capacity ratio value and label value of the sample corresponding to the original sample feature data, as well as the loss function, and updating the model parameters of the allocated capacity ratio value estimation model based on the model parameter updating formula and the gradient of the loss function corresponding to each original sample feature data, until the preset number of iterations is repeated to obtain the allocated capacity ratio value estimation model to be evaluated; wherein the preset number of times can be determined based on actual needs, and the embodiment of the present disclosure does not limit this. For example, the preset number of times can be 3000 times or 2000 times.

[0035] For example, when a sample data subset includes n sample data, the matrix composed of multiple original sample feature data in the sample data subset can be: ;(Formula 1) In formula 1, is the sample network performance data of the i-th original sample feature data, is the sample storage capacity data of the i-th original sample feature data.

[0036] The matrix composed of label values ​​corresponding to the original sample feature data in the sample dataset can be: ;(Formula 2) In formula 2, is the label value corresponding to the original sample feature data.

[0037] For each sample data subset, the terminal device inputs multiple original sample feature data in the sample data subset into the allocated capacity ratio value estimation model to be trained. The process of obtaining the sample estimated allocated capacity ratio value corresponding to each original sample feature data includes: transmitting a matrix composed of multiple original sample feature data in the sample data subset to the input layer to obtain a matrix of sample feature data to be processed; then, inputting the matrix of sample feature data to be processed into the first hidden layer for feature extraction to obtain an initial sample feature data matrix; further, inputting the initial sample feature data matrix into multiple hidden layers in sequence for multiple feature extractions to obtain a matrix of sample feature data to be identified; finally, inputting the matrix of sample feature data to be identified into the output layer for feature recognition to obtain a matrix of sample estimated allocated capacity ratio value corresponding to each original sample feature data in the sample data subset. The characteristic information between the allocated capacity ratio value of the server cluster and the storage capacity and network performance can be learned through multiple hidden layers, thereby improving the reliability of the allocated capacity ratio value estimated by the trained allocated capacity ratio value estimation model based on the storage capacity and network performance of the server cluster.

[0038] It should be noted that, in the embodiment of the present disclosure, the terminal device inputs the sample feature data matrix to be processed into the first hidden layer for feature extraction, and the process of obtaining the initial sample feature data matrix can be implemented based on the first formula, wherein the first formula is: ;(Formula 3) In formula 3, is the initial sample feature data matrix, is the matrix of the sample feature data to be processed, d is the dimension of the original sample feature data; is the weight matrix of the first hidden layer, and m is the number of neurons in the first hidden layer; is the bias term of the first hidden layer. Optionally, the bias term on each neuron can be the same; is the activation function.

[0039] The terminal device sequentially inputs the initial sample feature data matrix into multiple hidden layers for multiple feature extractions to obtain the feature data matrix of the sample to be identified. The process can be implemented based on the second formula, where the second formula is: ;(Formula 4) In formula 4, It is The output matrix of the hidden layer is It is The number of neurons in each hidden layer; It is The weight matrix of the hidden layer, It is The number of neurons in each hidden layer; It is The bias term of the hidden layer.

[0040] The terminal device inputs the sample feature data matrix to be identified into the output layer for feature recognition, and obtains the sample estimated allocated capacity ratio value matrix corresponding to each original sample feature data in the sample data subset. This process can be implemented based on the third formula, where the third formula is: ;(Formula 5) In formula 5, is the output matrix of the output layer, that is, the sample estimated allocated capacity ratio value matrix corresponding to each original sample feature data in the sample data subset, mL is the number of neurons in the output layer; is the weight matrix of the output layer, representing the linear transformation from the last layer to the output; is the bias term of the output layer.

[0041] It should also be noted that the terminal device determines the loss function value corresponding to each original sample feature data based on the estimated allocated capacity ratio value and label value of the sample corresponding to each original sample feature data, as well as the loss function. The loss function is: ;(Formula 6) In formula 6, is the loss function value, is the initial loss function, and is the regularization term, λ is the regularization hyperparameter that controls the penalty strength, θ is the weight parameter in the model, θ contains the weight matrix and bias vector between all layers, m is the number of weight parameters; and, the initial loss function for: ;(Formula 7) In formula 7, , is the prediction error, is the estimated allocated capacity ratio of the sample, is the label value, It is a hyperparameter, which can be determined based on actual needs and is not limited in the embodiments of the present disclosure.

[0042] At the same time, the terminal device determines the gradient of the loss function corresponding to each original sample feature data, and based on the model parameter update formula and the gradient of the loss function corresponding to each original sample feature data, updates the model parameters of the allocated capacity ratio value estimation model. The process includes: initializing the gradient matrix, attenuation factor, learning rate and stability constant to obtain model hyperparameters; then, determining the gradient of the loss function corresponding to each original sample feature data; finally, based on the model hyperparameters, the model parameter update formula and the gradient of the loss function corresponding to each original sample feature data, updates the model parameters of the allocated capacity ratio value estimation model.

[0043] Among them, the gradient of the loss function corresponding to each original sample feature data is: ;(Formula 8) In formula 8, is the gradient of the loss function, is the gradient of the initial loss function, and is the gradient of the regularization term, and the gradient of the initial loss function is expressed as: ;(Formula 9) Optionally, in the process of updating the above model parameters based on Adaptive Moment Estimation (Adam), the gradient matrix includes a first-order gradient matrix and a second-order gradient matrix. The first-order gradient matrix is: ;(Formula 10) In formula 10, is the first-order gradient matrix of this iteration, is the attenuation factor of the first-order gradient, is the first-order gradient matrix in the previous iteration process, is the gradient of the loss function.

[0044] And the second-order gradient matrix is: ;(Formula 11) In formula 11, is the second-order gradient matrix of this iteration, is the attenuation factor of the second-order gradient, is the second-order gradient matrix in the previous iteration.

[0045] Among them, the model parameter update formula is: ;(Formula 12) In formula 12, are the updated model parameters, are the model parameters before updating, is the correction value of the second-order gradient matrix, is the learning rate, is a stability constant that can be determined based on actual needs. is the correction value of the first-order gradient matrix, where the correction value of the first-order gradient matrix is: ;(Formula 13) In formula 13, is the correction coefficient of the first-order gradient matrix, which can be determined based on actual needs.

[0046] The corrected value of the second-order gradient matrix is: ;(Formula 14) In formula 14, is the correction coefficient of the second-order gradient matrix, which can be determined based on actual needs.

[0047] Optionally, the terminal device evaluates the allocated capacity ratio value estimation model to be evaluated based on the test set, and the process of obtaining the evaluation result may include: inputting each sample feature data in the test set into the allocated capacity ratio value estimation model to be evaluated to obtain a sample estimated allocated capacity ratio value associated with each sample feature data; then, based on the estimated allocated capacity ratio value associated with each sample feature data sample and the evaluation model, determining the evaluation result; wherein the evaluation model may be: ;(Formula 15) In formula 15, is the evaluation parameter value, is the estimated allocated capacity ratio of the sample associated with the i-th sample feature data, is the label value associated with the feature data of the i-th sample, is the average label value associated with the feature data of all samples in the test set.

[0048] It should be noted that in the embodiment of the present disclosure, when the first difference between the evaluation parameter values ​​for multiple consecutive times and 1 is less than the first difference threshold, and the second difference between the evaluation parameter values ​​for multiple consecutive times is less than the second difference threshold, it is determined that the estimation model of the allocated capacity ratio value to be evaluated has converged; wherein, the first difference threshold and the second difference threshold can be determined based on actual needs, and the embodiment of the present disclosure does not limit this.

[0049] In an optional implementation, the terminal device may input the storage capacity data and the network performance data into an allocated capacity ratio value estimation model to obtain an estimated allocated capacity ratio value of the target server cluster.

[0050] It can be understood that the allocated capacity ratio estimation model is obtained by training based on the model training method in the above embodiment.

[0051] In step S203, the terminal device determines the current allocatable total capacity of the target server cluster based on the estimated allocated capacity ratio value and the actual allocated capacity ratio value.

[0052] In the embodiment of the present disclosure, the currently allocatable total capacity is the total capacity currently allowed to be allocated in the target server cluster.

[0053] In an optional embodiment, the process of the terminal device determining the current allocatable total capacity of the target server cluster based on the estimated allocated capacity ratio and the actual allocated capacity ratio may include: if the actual allocated capacity ratio of the target server cluster is less than the estimated allocated capacity ratio, then determining the product of the estimated allocated capacity ratio and the over-allocation rate to obtain a revised allocated capacity ratio; then, determining the ratio of the allocated storage capacity to the revised allocated capacity ratio to obtain the current allocatable total capacity of the target server cluster. When the actual allocated capacity ratio of the target server cluster is less than the estimated allocated capacity ratio, it can be determined that the target server cluster has sufficient available resources, and a more reasonable current allocatable total capacity of the target server cluster can be determined by using the estimated allocated capacity ratio, the over-allocation rate, and the allocated storage capacity.

[0054] It should be noted that in the embodiment of the present disclosure, since the allocated capacity ratio value is the ratio of the allocated capacity to the over-allocation capacity, and the over-allocation capacity is the product of the total storage capacity of the target server cluster and the over-allocation rate, when the actual allocated capacity ratio value of the target server cluster is less than the estimated allocated capacity ratio value, and the over-allocation rate and the allocated storage capacity are known quantities, a more reasonable current allocable total capacity of the target server cluster can be determined based on the estimated allocated capacity ratio value, the over-allocation rate, and the allocated storage capacity, so as to improve the effective utilization of resources.

[0055] Wherein, when the actual allocated capacity ratio value of the target server cluster is less than the estimated allocated capacity ratio value, the process of the terminal device determining the current allocable total capacity of the target server cluster can be implemented based on the fourth formula, which is: ;(Formula 16) In formula 16, total_cap is the current allocatable total capacity of the target server cluster, and provisioned_capacity is the allocated storage capacity. It is the estimated allocated capacity ratio, and subscription_ratio is the over-allocation ratio.

[0056] In an optional embodiment, the process of the terminal device determining the current allocatable total capacity of the target server cluster based on the estimated allocated capacity ratio value and the actual allocated capacity ratio value may include: if the actual allocated capacity ratio value of the target server cluster is greater than or equal to the estimated allocated capacity ratio value, then determining the total storage capacity of the target server cluster as the current allocatable total capacity of the target server cluster. When the actual allocated capacity ratio value of the target server cluster is greater than or equal to the estimated allocated capacity ratio value, it can be determined that the capacity utilization of the target server cluster is large, and the total storage capacity of the target server cluster can be directly determined as the current allocatable total capacity of the target server cluster. This can prevent the phenomenon of the target server cluster's service stability being reduced due to over-allocation of capacity when the capacity utilization of the target server cluster is large, and improve the service stability of the target server cluster when the capacity utilization is large.

[0057] Wherein, when the actual allocated capacity ratio value of the target server cluster is greater than or equal to the estimated allocated capacity ratio value, the process of the terminal device determining the current allocatable total capacity of the target server cluster can be implemented based on the fifth formula, which is: total_cap = total_capacity; (Equation 17) In Formula 17, total_capacity is the total storage capacity of the target server cluster.

[0058] In an optional embodiment, the terminal device may further determine the difference between the total storage capacity of the target server cluster and the current remaining storage capacity to obtain the current allocated capacity of the target server cluster; then, determine the difference between the current allocatable total capacity of the target server cluster and the current allocated capacity to obtain the current remaining allocatable capacity of the target server cluster. After determining the current allocatable total capacity of the target server cluster, the current remaining allocatable capacity of the target server cluster may be determined, thereby increasing the richness of the acquired capacity information for the target server cluster and providing a more accurate reference indicator for resource allocation of the server cluster.

[0059] The process of the terminal device determining the current remaining allocatable capacity of the target server cluster can be implemented based on the sixth formula, which is: free_cap = total_cap - (total_capacity- free_capacity); (Formula 18) In the formula 18, free_cap is the current remaining allocable capacity, and free_capacity is the current remaining storage capacity.

[0060] In an optional implementation, if the terminal device determines that the current remaining allocable capacity of the target server cluster is a negative value, the terminal device determines a difference between the target parameter value and the estimated allocated capacity proportion value, to obtain an estimated unallocated capacity proportion value; then, the terminal device determines a product of the total storage capacity of the target server cluster and the estimated unallocated capacity proportion value, to obtain the updated current remaining allocable capacity of the target server cluster; and the target parameter value is 1. In the case that the current remaining allocable capacity of the target server cluster is a negative value, the current remaining allocable capacity of the target server cluster is corrected, so as to improve the reliability of the determined current remaining allocable capacity of the target server cluster.

[0061] The terminal device determines the updated current remaining allocable capacity based on the seventh formula, and the seventh formula is as follows: ; (formula 19) In an optional implementation, before the terminal device determines the current allocable total capacity of the target server cluster based on the estimated allocated capacity proportion value and the actual allocated capacity proportion value, the terminal device can also: if it is determined that the current latency rate is greater than or equal to the latency rate threshold, and the estimated allocated capacity proportion value is less than the allocated capacity proportion threshold, the allocated capacity proportion threshold is determined as the updated estimated allocated capacity proportion value. In the case that the current latency rate is greater than or equal to the latency rate threshold, it can be determined that the current network performance is poor, and if the estimated allocated capacity proportion value is less than the allocated capacity proportion threshold, the estimated allocated capacity proportion value needs to be increased for the current allocable total capacity estimation of the target server cluster, so as to further consider the current network status of the target server cluster for the current allocable total capacity estimation, and then determine the current allocable total capacity that is more matched with the current hardware and network status, and improve the reliability of the determined current allocable total capacity.

[0062] It can be understood that, after the updated estimated allocated capacity proportion value is obtained, the process in which the terminal device determines the current allocable total capacity of the target server cluster based on the estimated allocated capacity proportion value and the actual allocated capacity proportion value can include: determining the current allocable total capacity of the target server cluster based on the updated estimated allocated capacity proportion value and the actual allocated capacity proportion value.

[0063] It should be noted that the terminal device determines the current allocable total capacity of the target server cluster based on the updated estimated allocated capacity ratio value and the actual allocated capacity ratio value. For details, refer to the process of determining the current allocable total capacity of the target server cluster based on the estimated allocated capacity ratio value and the actual allocated capacity ratio value by the terminal device in the above embodiments, which will not be repeated here.

[0064] The exemplary embodiments of the present disclosure provide a server cluster capacity determination apparatus, which can be a terminal device or a chip applied to a terminal device. Figure 3 A functional module schematic block diagram of a server cluster capacity determination apparatus according to an exemplary embodiment of the present disclosure is shown. As shown in Figure 3 The server cluster capacity determination apparatus 300 includes: An acquisition module 301 configured to acquire current storage capacity data and network performance data of a target server cluster to be evaluated; An estimation module 302 configured to input the storage capacity data and the network performance data into an allocated capacity ratio value estimation model to obtain an estimated allocated capacity ratio value of the target server cluster, wherein the allocated capacity ratio value is a ratio of an allocated capacity to an oversubscription capacity, the oversubscription capacity is a product of a total storage capacity of the target server cluster and an oversubscription rate, and the oversubscription rate is used to indicate a multiple of the total storage capacity of the target server cluster that is allowed to be oversubscribed; A determination module 303 configured to determine a current allocable total capacity of the target server cluster based on the estimated allocated capacity ratio value and an actual allocated capacity ratio value.

[0065] Optionally, the determination module 303 is configured to: If the actual allocated capacity ratio value of the target server cluster is less than the estimated allocated capacity ratio value, determine a product of the estimated allocated capacity ratio value and the oversubscription rate to obtain a corrected allocated capacity ratio value; Determine a ratio of an allocated storage capacity to the corrected allocated capacity ratio value to obtain the current allocable total capacity of the target server cluster.

[0066] Optionally, the determination module 303 is configured to: If the actual allocated capacity ratio value of the target server cluster is greater than or equal to the estimated allocated capacity ratio value, determine the total storage capacity of the target server cluster as the current allocable total capacity of the target server cluster.

[0067] Optionally, the determination module 303 is further configured to: Determine the difference between the total storage capacity of the target server cluster and the current remaining storage capacity to obtain the current allocated capacity of the target server cluster; The difference between the current allocatable total capacity of the target server cluster and the current allocated capacity is determined to obtain the current remaining allocatable capacity of the target server cluster.

[0068] Optionally, the determining module 303 is further configured to: If the current remaining allocatable capacity of the target server cluster is a negative value, determining the difference between the target parameter value and the estimated allocated capacity ratio value to obtain an estimated unallocated capacity ratio value; The total storage capacity of the target server cluster and the product of the estimated unallocated capacity ratio are determined to obtain the updated current remaining allocatable capacity of the target server cluster.

[0069] Optionally, the apparatus further includes an updating module 304 configured to: If the current delay rate is greater than or equal to the delay rate threshold, and the estimated allocated capacity ratio value is less than the allocated capacity ratio threshold, determining the allocated capacity ratio threshold as the updated estimated allocated capacity ratio value; The determining module 303 is further configured to: Based on the updated estimated allocated capacity ratio value and the actual allocated capacity ratio value, the current allocatable total capacity of the target server cluster is determined.

[0070] The exemplary embodiments of the present disclosure further provide an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor. The memory stores a computer program executable by the at least one processor, the computer program being configured to cause the electronic device to perform a method according to an exemplary embodiment of the present disclosure when executed by the at least one processor.

[0071] Exemplary embodiments of the present disclosure further provide a non-transitory computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor of a computer, is used to cause the computer to perform a method according to an embodiment of the present disclosure.

[0072] like Figure 4 As shown, the exemplary embodiment of the present disclosure further provides a computer program product 400, including a computer program 401, wherein when the computer program is executed by a processor of a computer, it is used to enable the computer to perform the method according to the embodiment of the present disclosure.

[0073] refer to Figure 5, a block diagram of an electronic device 500 that can be used as a terminal device of the present disclosure will now be described, which is an example of a hardware device that can be applied to various aspects of the present disclosure. The electronic device is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0074] like Figure 5 As shown, electronic device 500 includes a computing unit 501, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 502 or a computer program loaded from a storage unit 508 into a random access memory (RAM) 503. RAM 503 may also store various programs and data required for the operation of electronic device 500. Computing unit 501, ROM 502, and RAM 503 are interconnected via a bus 504. An input / output (I / O) interface 505 is also connected to bus 504.

[0075] Multiple components within electronic device 500 are connected to I / O interface 505, including an input unit 506, an output unit 507, a storage unit 508, and a communication unit 509. Input unit 506 can be any type of device capable of inputting information into electronic device 500. Input unit 506 can receive input numeric or character information and generate key input signals related to user settings and / or function control of the electronic device. Output unit 507 can be any type of device capable of presenting information and may include, but is not limited to, a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer. Storage unit 508 may include, but is not limited to, a magnetic disk or an optical disk. Communication unit 509 allows electronic device 500 to exchange information / data with other devices via computer networks such as the Internet and / or various telecommunication networks and may include, but is not limited to, a modem, a network card, an infrared communication device, a wireless communication transceiver and / or chipset, such as a Bluetooth™ device, a WiFi device, a WiMax device, a cellular communication device, and / or the like.

[0076] The computing unit 501 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 501 performs the various methods and processes described above. For example, in some embodiments, the methods of the exemplary embodiments of the present disclosure may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 508. In some embodiments, part or all of the computer program may be loaded and / or installed onto the electronic device 500 via the ROM 502 and / or the communication unit 509. In some embodiments, the computing unit 501 may be configured to perform the methods of the exemplary embodiments of the present disclosure by any other suitable means (e.g., via firmware).

[0077] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0078] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of machine-readable storage media may include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), optical fibers, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0079] As used in this disclosure, the terms "machine-readable medium" and "computer- readable medium" refer to any computer program product, apparatus and / or device (e.g., magnetic discs, optical disks, memory, Programmable Logic Devices (PLDs)) used to provide machine instructions and / or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal used to provide machine instructions and / or data to a programmable processor.

[0080] To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0081] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0082] In the above embodiments, all or part of the embodiments may be implemented using software, hardware, firmware, or any combination thereof. When implemented using software, all or part of the embodiments may be implemented in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer programs or instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present disclosure are fully or partially executed. The computer may be a general-purpose computer, a special-purpose computer, a computer network, a terminal, a user device, or other programmable device. The computer program or instructions may be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another. For example, the computer program or instructions may be transferred from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless means. The computer-readable storage medium may be any available medium accessible by a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium, such as a floppy disk, hard disk, or magnetic tape; an optical medium, such as a digital video disc (DVD); or a semiconductor medium, such as a solid-state drive (SSD).

[0083] Although the present disclosure has been described with reference to specific features and embodiments thereof, it will be apparent that various modifications and combinations may be made thereto without departing from the spirit and scope of the present disclosure. Accordingly, this specification and the drawings are merely illustrative of the present disclosure as defined by the appended claims and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present disclosure. Obviously, those skilled in the art may make various modifications and variations to the present disclosure without departing from the spirit and scope of the present disclosure. Thus, the present disclosure is intended to include such modifications and variations if they fall within the scope of the claims of the present disclosure and their equivalents.

Claims

1. A method for determining the capacity of a server cluster, characterized in that: include: Obtain the current storage capacity and network performance data of the target server cluster to be evaluated; Inputting the storage capacity data and network performance data into an allocated capacity ratio estimation model to obtain an estimated allocated capacity ratio of the target server cluster, wherein the allocated capacity ratio is a ratio of the allocated capacity to the over-allocated capacity, the over-allocated capacity being the product of the total storage capacity of the target server cluster and the over-allocation ratio, and the over-allocation ratio being used to indicate the ratio by which the total storage capacity of the target server cluster is allowed to be over-allocated; Based on the estimated allocated capacity ratio value and the actual allocated capacity ratio value, the current allocatable total capacity of the target server cluster is determined.

2. The method for determining the capacity of a server cluster according to claim 1, wherein: The determining, based on the estimated allocated capacity ratio and the actual allocated capacity ratio, of the current allocatable total capacity of the target server cluster includes: If the actual allocated capacity ratio value of the target server cluster is less than the estimated allocated capacity ratio value, determining the product of the estimated allocated capacity ratio value and the over-allocation rate to obtain a revised allocated capacity ratio value; The ratio of the allocated storage capacity to the modified allocated capacity ratio is determined to obtain the current allocatable total capacity of the target server cluster.

3. The method for determining the capacity of a server cluster according to claim 1, wherein: The determining, based on the estimated allocated capacity ratio and the actual allocated capacity ratio, of the current allocatable total capacity of the target server cluster includes: If the actual allocated capacity ratio value of the target server cluster is greater than or equal to the estimated allocated capacity ratio value, the total storage capacity of the target server cluster is determined as the current allocable total capacity of the target server cluster.

4. The method for determining the capacity of a server cluster according to claim 2 or 3, wherein: The method further comprises: Determine the difference between the total storage capacity of the target server cluster and the current remaining storage capacity to obtain the current allocated capacity of the target server cluster; The difference between the current allocatable total capacity of the target server cluster and the current allocated capacity is determined to obtain the current remaining allocatable capacity of the target server cluster.

5. The method for determining the capacity of a server cluster according to claim 4, wherein: The method further comprises: If the current remaining allocatable capacity of the target server cluster is a negative value, determining the difference between the target parameter value and the estimated allocated capacity ratio value to obtain an estimated unallocated capacity ratio value; The total storage capacity of the target server cluster and the product of the estimated unallocated capacity ratio are determined to obtain the updated current remaining allocatable capacity of the target server cluster.

6. The method for determining the capacity of a server cluster according to claim 1, wherein: The method further comprises: If the current delay rate is greater than or equal to the delay rate threshold, and the estimated allocated capacity ratio value is less than the allocated capacity ratio threshold, then determining the allocated capacity ratio threshold as the updated estimated allocated capacity ratio value; The determining, based on the estimated allocated capacity ratio and the actual allocated capacity ratio, of the current allocatable total capacity of the target server cluster includes: Based on the updated estimated allocated capacity ratio value and the actual allocated capacity ratio value, the current allocatable total capacity of the target server cluster is determined.

7. A device for determining the capacity of a server cluster, characterized in that: include: an acquisition module configured to acquire current storage capacity data and network performance data of a target server cluster to be evaluated; an estimation module configured to input the storage capacity data and the network performance data into an allocated capacity ratio estimation model to obtain an estimated allocated capacity ratio of the target server cluster, wherein the allocated capacity ratio is a ratio of the allocated capacity to the over-allocated capacity, the over-allocated capacity being the product of the total storage capacity of the target server cluster and the over-allocation ratio, the over-allocation ratio being used to indicate a ratio by which the total storage capacity of the target server cluster is allowed to be over-allocated; The determination module is configured to determine the current allocatable total capacity of the target server cluster based on the estimated allocated capacity ratio value and the actual allocated capacity ratio value.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the method according to any one of claims 1 to 6.

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