Centralized storage performance evaluation method and device and electronic equipment

Abstract

The invention provides a centralized storage performance evaluation method and device and electronic equipment, and relates to the technical field of computers.The method comprises the steps that firstly, a performance influence factor set of a centralized storage system to be evaluated in a target deployment environment and a performance influence value corresponding to at least one performance influence factor in the performance influence factor set are analyzed; obtaining performance influence data of the to-be-evaluated centralized storage system in the target deployment environment; and under the condition that the target deployment environment sample corresponding to the performance influence data is matched in the performance sample library, according to the target system operation performance data corresponding to the target deployment environment sample, determining a performance evaluation result of the to-be-evaluated centralized storage system in the target deployment environment. According to the method, the technical problems that a large error exists in performance prediction and an accurate performance reference cannot be provided due to the fact that a large difference possibly exists between a storage product performance baseline and a customer actual deployment environment can be solved, and the accuracy of centralized storage performance evaluation can be improved.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular, to a method, device, and electronic device for evaluating the performance of a centralized storage system. Background Art

[0002] The performance evaluation of a centralized storage system is crucial for aspects such as system performance optimization, ensuring business continuity, ensuring data security, and supporting technical maintenance. An efficient and reliable performance evaluation method can not only further confirm whether the centralized storage system meets the requirements of customer services, but also serve as an important indicator for the delivery of a storage solution project to assist in troubleshooting delivery implementation problems. In related technologies, performance prediction is provided based on the performance baseline of the storage products of the centralized storage system. However, there may be a large difference between the performance baseline of the storage products and the actual deployment environment of the customer, resulting in a large error in performance prediction and unable to provide an accurate performance reference. Summary of the Invention

[0003] The present disclosure provides a method, device, and electronic device for evaluating the performance of a centralized storage system. Its main purpose is to solve the problem of low accuracy in evaluating the performance of a centralized storage system.

[0004] According to a first aspect of the present disclosure, there is provided a method for evaluating the performance of a centralized storage system, including: Determining performance impact data of a centralized storage system to be evaluated in a target deployment environment, where the performance impact data includes a set of performance impact factors and performance impact values corresponding to at least one performance impact factor in the set of performance impact factors; Matching the performance impact data in a performance sample library, where the performance sample library includes multiple deployment environment samples, and sample performance impact data and system operation performance data corresponding to at least one deployment environment sample among the multiple deployment environment samples; In the case where there is a target deployment environment sample in the performance sample library that matches the performance impact data, determining a performance evaluation result of the centralized storage system to be evaluated in the target deployment environment according to the target system operation performance data corresponding to the target deployment environment sample.

[0005] According to a second aspect of the present disclosure, there is provided a device for evaluating the performance of a centralized storage system, including: A data determination unit for determining performance impact data of a centralized storage system to be evaluated in a target deployment environment, where the performance impact data includes a set of performance impact factors and performance impact values corresponding to at least one performance impact factor in the set of performance impact factors; A sample matching unit for matching performance impact data in a performance sample library, where the performance sample library includes multiple deployment environment samples, and sample performance impact data and system operation performance data corresponding to at least one deployment environment sample among the multiple deployment environment samples; A performance evaluation unit for determining a performance evaluation result of the centralized storage system to be evaluated in the target deployment environment according to the target system operation performance data corresponding to the target deployment environment sample when there is a target deployment environment sample matching the performance impact data in the performance sample library.

[0006] According to a third aspect of the present disclosure, there is provided an electronic device, including: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method described in the foregoing first aspect.

[0007] According to a fourth aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause the computer to execute the method described in the foregoing first aspect.

[0008] According to a fifth aspect of the present disclosure, there is provided a computer program product including a computer program, and the computer program implements the method described in the foregoing first aspect when executed by a processor.

[0009] The present disclosure first analyzes the performance impact factor set of the centralized storage system to be evaluated in the target deployment environment and the performance impact values corresponding to at least one performance impact factor in the performance impact factor set to obtain the performance impact data of the centralized storage system to be evaluated in the target deployment environment; then, when a target deployment environment sample corresponding to the performance impact data is matched in the performance sample library, according to the target system operation performance data corresponding to the target deployment environment sample, the performance evaluation result of the centralized storage system to be evaluated in the target deployment environment is determined. Therefore, the technical problem that there may be a large difference between the performance baseline of the storage product and the actual deployment environment of the customer, resulting in a large error in performance prediction and inability to provide an accurate performance reference can be solved, and the accuracy of centralized storage performance evaluation can be improved.

[0010] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it used to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The accompanying drawings are used to better understand the present solution and do not limit the present disclosure. Among them: Figure 1 It is a schematic flowchart of a method for evaluating the performance of a centralized storage provided by an embodiment of the present disclosure; Figure 2 It is a schematic flowchart of another method for evaluating the performance of a centralized storage provided by an embodiment of the present disclosure; Figure 3 It is a schematic structural diagram of a centralized storage performance evaluation architecture provided by an embodiment of the present disclosure; Figure 4 It is a schematic structural diagram of a centralized storage performance evaluation device provided by an embodiment of the present disclosure. Detailed implementation manners

[0012] The following describes exemplary embodiments of the present disclosure with reference to the accompanying drawings. Various details of the embodiments of the present disclosure are included to facilitate understanding and should be considered merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted below.

[0013] It should be noted that in the project delivery stage of the centralized storage system, it is necessary to evaluate whether the centralized storage system meets the customer requirements, what the theoretical performance values of the current networking and configured storage are, and whether the current test conforms to the theoretical evaluation, etc. However, the performance evaluation of the centralized storage system is a complex systematic problem, and the performance of the centralized storage system is affected by the combination of many factors. Such a large number of influencing factors also determine the complexity of accurately evaluating the storage performance. For example, there are many differences between the shipped configuration of the centralized storage system and the baseline performance configuration of the laboratory, the network topology at the customer site is quite different from that of the laboratory, and the upper-layer service models vary widely and do not completely match the performance baseline model, etc., all of which will affect the accuracy of the performance evaluation.

[0014] Among them, a sample library including multiple deployment environment samples and the performance data corresponding to each deployment environment sample can be constructed, and the deployment environment required by the centralized storage system can be matched in the sample library to achieve the performance evaluation of the centralized storage system. However, due to the large number of factors involved in the deployment environment and the different combination methods, it is difficult to achieve 100% coverage of all deployment environments in the sample library, it is difficult to match a deployment environment sample that is exactly the same as the required application's deployment environment, and in the similar deployment environment samples that are matched, it is also possible that most of the same factors do not affect the performance, resulting in inaccurate final evaluation results.

[0015] The following describes a method, apparatus, and electronic device for evaluating the performance of a centralized storage according to embodiments of the present disclosure with reference to the accompanying drawings.

[0016] Figure 1 FIG. 4 is a flowchart of a method for evaluating the performance of a centralized storage provided by an embodiment of the present disclosure.

[0017] As Figure 1 shown, the method includes the following steps: Step 101, determine the performance impact data of the centralized storage system to be evaluated in the target deployment environment.

[0018] Among them, the centralized storage system to be evaluated refers to the centralized storage system that needs to be evaluated for performance.

[0019] Among them, the deployment environment refers to the actual operating environment in which the software or system runs, and this environment includes components such as hardware, operating system, network configuration, and dependent software. The target deployment environment refers to the environment in which the centralized storage system to be evaluated needs to be deployed.

[0020] Among them, the performance impact data refers to the relevant data that affects the running performance of the centralized storage system to be evaluated in the target deployment environment. The performance impact data includes a set of performance impact factors and performance impact values corresponding to at least one performance impact factor in the set of performance impact factors.

[0021] Among them, the performance impact factor refers to the factor that affects the running performance of the centralized storage system to be evaluated in the target deployment environment. The performance impact value refers to the impact value when the performance impact factor affects the running performance of the centralized storage system to be evaluated.

[0022] Step 102, match the performance impact data in the performance sample library.

[0023] According to some embodiments, the performance sample library includes multiple deployment environment samples, and sample performance impact data and system running performance data corresponding to at least one deployment environment sample among the multiple deployment environment samples.

[0024] Among them, the deployment environment sample refers to a sample of the deployment environment. The sample performance impact data refers to the performance impact data corresponding to the deployment environment sample. The system running performance data refers to the running performance data of the centralized storage system to be evaluated in this deployment environment sample.

[0025] Step 103, in the case that there is a target deployment environment sample in the performance sample library that matches the performance impact data, determine the performance evaluation result of the centralized storage system to be evaluated in the target deployment environment according to the target system running performance data corresponding to the target deployment environment sample.

[0026] Among them, the target deployment environment sample refers to the deployment environment sample in the performance sample library that matches the performance impact data. The target system operation performance data refers to the system operation performance data corresponding to the target deployment environment sample.

[0027] Among them, the performance evaluation result refers to the operation performance data of the to-be-evaluated centralized storage system obtained through evaluation in the target deployment environment.

[0028] In summary, for the method provided by the embodiments of the present disclosure, by first analyzing the set of performance impact factors of the to-be-evaluated centralized storage system in the target deployment environment and the performance impact values corresponding to at least one performance impact factor in the set of performance impact factors, the performance impact data of the to-be-evaluated centralized storage system in the target deployment environment is obtained; then, when the target deployment environment sample corresponding to the performance impact data is matched in the performance sample library, according to the target system operation performance data corresponding to the target deployment environment sample, the performance evaluation result of the to-be-evaluated centralized storage system in the target deployment environment is determined. Therefore, the technical problem that there may be a large difference between the performance baseline of the storage product and the actual deployment environment of the customer, resulting in a large error in performance prediction and inability to provide accurate performance reference can be solved, and the accuracy of centralized storage performance evaluation can be improved; secondly, since the composition factors of each deployment environment are numerous and the combination methods are also different, compared with directly matching the target deployment environment in the performance sample library, since the factors in the performance impact data are only performance impact factors and their quantity is less than the quantity of factors in the target deployment environment, the matching efficiency and the accuracy of matching can be improved.

[0029] It should be noted that there may be multiple steps in the embodiments of the present disclosure. For the convenience of description, these steps are numbered, but these numbers are not intended to limit the execution time slots and execution orders between the steps; these steps can be implemented in any order, and the embodiments of the present disclosure do not make any limitations in this regard.

[0030] Further, in a possible implementation manner of this embodiment, a centralized storage performance evaluation method is provided, and this method includes the following steps: Step 201, determine the architecture-level performance impact factors of the to-be-evaluated centralized storage system in the target deployment environment, and obtain the architecture-level performance impact factor set.

[0031] According to some embodiments, the architecture-level performance impact factor set includes at least one architecture-level performance impact factor. The architecture-level performance impact factor refers to the factor in the architecture level of the target deployment environment that affects the operation performance of the to-be-evaluated centralized storage system.

[0032] In some embodiments, the architecture level includes but is not limited to the application layer, the host layer, the network layer, and the storage layer.

[0033] Among them, the Application Layer (AL) refers to the software layer directly facing business logic and user interaction. The impact it has on running performance can be reflected in the behavioral characteristics of AL services, such as the I / O service models and characteristics related to Input / Output (I / O), including but not limited to block size, read-write ratio, cache hit rate, whether it is bursty, duration, etc. It is necessary to provide the storage product performance baseline of the centralized storage system for the performance indicators of different I / O service models, and analyze and summarize the application of the centralized storage system and the I / O service model at the customer site. For example, the basic I / O service model of a certain centralized storage system is the Online Transaction Processing (OLTP) model, with a read-write ratio of 7:3 and a cache hit rate of 70%. Only by establishing the correlation between the basic I / O service model tested in the laboratory and the I / O service model of the customer's actual application can a relatively accurate performance prediction be provided without actual use.

[0034] Among them, the Host Layer (HL) refers to the physical or virtual computing resource layer that hosts the running of application programs. Configurations such as the type of physical machine, the type of operating system, the settings of host kernel parameters, and the multipath configuration in the host layer are all related to running performance. Different applications may perform differently under different configurations, or rather, each application has an optimal configuration. The optimal parameter configuration of the centralized storage system to be evaluated can be provided in the host layer, and there may be differences between it and the target deployment environment.

[0035] Among them, the Network Layer (NL) is responsible for data transmission and communication between components in the deployment environment. The network parameters of the network layer include but are not limited to network type (such as Fibre Channel Storage Area Network (FC SAN), Internet Protocol Storage Area Network (IP SAN), etc.), interface type, number of interfaces, etc. As an intermediate link, anomalies in its links, as well as interface type and network type, will all affect running performance.

[0036] Among them, the Storage Layer (SL) is responsible for the persistent storage and access of data. The storage layer is the core node when applying the centralized storage system to be evaluated, and the storage layer itself is a complex operating system. Therefore, there are many factors affecting its performance, including but not limited to the type of backend disks, storage topology, pool type, number of volume types, advanced features, etc.

[0037] In some embodiments, in order to simplify the set of performance impact factors at the architecture level, the top target number of factors that have a greater impact on the operating performance of the centralized storage system to be evaluated can be selected from the application side, host side, network side, and storage side as the performance impact factors at the architecture level. For example, for a certain centralized storage system to be evaluated, the finally selected performance impact factors at the architecture level can be the storage platform, storage version, storage model, networking architecture, and upper-layer I / O model.

[0038] Step 202: Determine a subset of configuration-level performance impact factors corresponding to at least one architecture-level performance impact factor in the set of architecture-level performance impact factors in the target deployment environment, to obtain a set of configuration-level performance impact factors.

[0039] According to some embodiments, the configuration level of the architecture-level performance impact factors may include multiple configuration factors. For example, the configuration level of the networking architecture includes configuration factors such as network type and connection topology; the configuration level of the storage platform includes Redundant Array of Independent Disks (RAID) type, number of RAID, disk type, number of disks, volume type, number of volumes, etc.

[0040] In some embodiments, the factors among the multiple configuration factors at the configuration level that have an impact on the operating performance of the centralized storage system to be evaluated can form a subset of configuration-level performance impact factors corresponding to this architecture-level performance impact factor. The set of configuration-level performance impact factors may include multiple subsets of configuration-level performance impact factors.

[0041] Step 203: Perform quantitative analysis on the set of configuration-level performance impact factors to obtain the performance impact values corresponding to at least one configuration-level performance impact factor in the set of configuration-level performance impact factors.

[0042] According to some embodiments, the correlation relationship between at least one configuration-level performance impact factor in the set of configuration-level performance impact factors and the system operating performance can be determined; based on the correlation relationship, quantitative analysis is performed on the set of configuration-level performance impact factors to obtain the performance impact values corresponding to at least one configuration-level performance impact factor in the set of configuration-level performance impact factors. Therefore, the efficiency and accuracy of obtaining the performance impact values can be improved.

[0043] In some embodiments, the correlation between the configuration-level performance influencing factors and the system operation performance can be obtained through pre-tests. For example, the parameters of a certain configuration-level performance influencing factor in the deployment environment can be adjusted, while the parameters of other configuration-level performance influencing factors are kept unchanged, and the corresponding system operation performance data is recorded, so as to obtain the correlation between the certain configuration-level performance influencing factor and the system operation performance. It is also possible to quantify and linearize the configuration-level performance influencing factors by establishing a performance impact analysis matrix.

[0044] Among them, the configuration-level performance influencing factors have the linear superposition property of the configuration. After the parameters of a certain configuration-level performance influencing factor reach the bottleneck, increasing the parameters will not increase the corresponding system operation performance data. For example, when the number of mechanical disks is small, increasing the mechanical disks can linearly increase the performance. However, when the number of mechanical disks reaches a certain number, increasing the mechanical disks will not increase the performance.

[0045] For example, the parameters of the RAID type include RAID10, RAID5, and RAID6. The correlation between the RAID type and the system operation performance is that the system operation performance data corresponding to RAID10 is 10% higher than that corresponding to RAID5, showing a linear growth value, and the system operation performance data corresponding to RAID5 is 10% higher than that corresponding to RAID6, showing a linear growth value.

[0046] For example, the correlation between the number of RAID and the system operation performance is that the linear growth value of the system operation performance data is 1 / current number of RAID; until the number of RAID reaches 6, the system operation performance data reaches the upper limit and remains unchanged.

[0047] For example, for the disk type, the disk performance of the Non-Volatile Memory Express (Nvme) type disk is the highest, which is 5% higher than that of the Serial Attached Small Computer System Interface (SAS) type disk, and there is a 3% linear growth value in the system operation performance data between them.

[0048] For example, the volume type can include a regular volume, a thin volume, and a compressed volume. The volume performance of the thin volume can be 90% of the volume performance of the regular volume, and the volume performance of the compressed volume can be 70% of the volume performance of the regular volume, etc. There is a 20% linear growth value in the system operation performance data between them.

[0049] For example, for the number of volumes, the linear growth value of the corresponding system running performance data is 1 / current number of volumes; until the number of volumes reaches 16, the system running performance data reaches the upper limit and remains unchanged.

[0050] Among them, when determining the performance impact value corresponding to the performance impact factor at the configuration level, it can be determined according to the linear growth value indicated in the association relationship.

[0051] It should be noted that the performance impact data can be embodied in the form of a performance evaluation model. The performance evaluation model includes a basic architecture layer and a storage configuration layer. The basic architecture layer includes a set of architecture-level performance impact factors, and the storage configuration layer includes a set of configuration-level performance impact factors and performance impact values.

[0052] Among them, the sample performance impact data corresponding to a certain deployment environment sample in the performance sample library can also be embodied in the form of a performance evaluation model. For example, the sample performance impact data and system running performance data corresponding to a certain deployment environment sample in the performance sample library can be exemplified as follows: The basic architecture layer includes an FC architecture, a Haiguang CPU platform, a storage model of HF8000, and a storage system version 6.X; The storage configuration layer includes 128 NVMEs, 4 RAID5s, 10 thin volumes, and an upper-layer IO model with an 8K 7:3 read-write ratio; The system running performance data includes a performance of X million IOPS, a latency of 0.5 ms, and a bandwidth of 4 GB.

[0053] In some embodiments, by performing step S201 to step S203, the performance impact factors in the target deployment environment can be hierarchically stratified, and the set of architecture-level performance impact factors and the set of configuration-level performance impact factors can be determined in sequence. Among them, as the architecture or foundation of storage performance evaluation, determining the set of architecture-level performance impact factors first and then further determining the set of configuration-level performance impact factors can improve the accuracy of determining performance impact data. Secondly, on the basis of hierarchical stratification, the configuration-level performance impact factors are quantified and linearized to obtain the performance impact values corresponding to at least one configuration-level performance impact factor, which can improve the acquisition efficiency and accuracy of performance impact values.

[0054] Step 204, match the set of architecture-level performance impact factors in the performance sample library, and when there is a set of sample performance impact data in the performance sample library that matches the set of architecture-level performance impact factors, match the set of sample performance impact data with the set of configuration-level performance impact factors and the performance impact values of at least one configuration-level performance impact factor in the set of configuration-level performance impact factors.

[0055] According to some embodiments, since the architecture layer serves as the architecture or foundation for storage performance evaluation, there must be sample performance impact data in the performance sample library that includes the set of performance impact factors at the architecture layer for further evaluation. Therefore, when matching the set of performance impact factors at the architecture layer in the performance sample library, a complete match search needs to be performed in the performance sample library, that is, it is necessary to query the sample performance impact data in the performance sample library that includes the set of performance impact factors at the architecture layer. If there is a set of sample performance impact data that matches the set of performance impact factors at the architecture layer, the basic architecture layer query is completed; if the query result is none, it means that there is no matching basic architecture layer data in the performance sample library and further evaluation is not possible.

[0056] In some embodiments, since there are many and ever-changing performance impact factors at the storage layer, the performance sample library may not be able to achieve 100% coverage, and the impact of the performance impact factors at the storage layer can be quantified as a performance impact value. Therefore, imprecise matching can be used for the matching at the configuration layer. For example, when performing imprecise matching, the total performance impact value corresponding to the set of performance impact factors at the configuration layer can be determined; in the set of sample performance impact data, query for sample performance impact data whose difference between the sample performance impact total value and the performance impact total value is less than the difference threshold and that includes a preset number of performance impact factors at the configuration layer in the set of performance impact factors at the configuration layer. Therefore, the matching efficiency and matching effect for the set of sample performance impact data can be improved.

[0057] Among them, the total performance impact value refers to the sum of the performance impact values of multiple performance impact factors at the configuration layer in the set of performance impact factors at the configuration layer.

[0058] Among them, the difference threshold and the preset number do not specifically refer to a certain fixed value. The difference threshold and the preset number can be determined according to the actual application scenario.

[0059] In some embodiments, when querying in the set of sample performance impact data for sample performance impact data whose difference between the sample performance impact total value and the performance impact total value is less than the difference threshold and that includes a preset number of performance impact factors at the configuration layer in the set of performance impact factors at the configuration layer, first query for sample performance impact data in the set of sample performance impact data whose difference between the sample performance impact total value and the performance impact total value is less than the difference threshold; if relevant sample performance impact data is queried, then query for sample performance impact data from these sample performance impact data that includes a preset number of performance impact factors at the configuration layer in the set of performance impact factors at the configuration layer.

[0060] Among them, the query order for the total performance impact value and the set of performance impact factors at the configuration layer is not limited to the above order, and it is also possible to first query the set of performance impact factors at the configuration layer and then query the total performance impact value.

[0061] It should be noted that in the case where the query result is none, the feedback mechanism can be entered. That is, in the case where there is no sample performance impact data set in the performance sample library that matches the set of performance impact factors at the architecture level, the first matching failure feedback information can be sent; among them, the first matching failure feedback information is used to indicate that the performance of the to-be-evaluated centralized storage system is tested based on the set of performance impact factors at the architecture level. In the case where there is no sample performance impact data subset in the deployment environment sample set that matches the set of performance impact factors at the configuration level and the performance impact value, the second matching failure feedback information is sent; among them, the second matching failure feedback information is used to indicate that the performance of the to-be-evaluated centralized storage system is tested based on the set of performance impact factors at the configuration level and the performance impact value. Therefore, relevant personnel can be reminded to perform on-site actual performance testing on the to-be-evaluated centralized storage system in a timely manner based on the set of performance impact factors at the configuration level or the set of performance impact factors at the architecture level.

[0062] In some embodiments, in response to receiving the first performance test data uploaded in response to the first matching failure feedback information, the first performance test data can be placed in the performance sample library; among them, the first performance test data includes a deployment environment sample constructed based on the set of performance impact factors at the architecture level, the sample performance impact data corresponding to the deployment environment sample, and the system operation performance data. In response to receiving the second performance test data uploaded in response to the second matching failure feedback information, the second performance test data is placed in the performance sample library; among them, the second performance test data includes a deployment environment sample constructed based on the set of performance impact factors at the configuration level, the sample performance impact data corresponding to the deployment environment sample, and the system operation performance data. Therefore, the performance use cases of the performance sample library can be supplemented for subsequent performance evaluation.

[0063] Step 205, in the case where there is a sample performance impact data subset in the sample performance impact data set that matches the set of performance impact factors at the configuration level and the performance impact value, select the sample performance impact data with the lowest difference value between the set of performance impact factors at the configuration level and the performance impact value from the sample performance impact data subset as the target sample performance impact data.

[0064] According to some embodiments, the difference value can be, for example, the sum of the first similarity corresponding to the set of performance impact factors at the configuration level and the second similarity corresponding to the total performance impact value.

[0065] Step 206, use the deployment environment sample corresponding to the target sample performance impact data as the target deployment environment sample that matches the performance impact data.

[0066] It should be noted that by executing step 204 to step 206, therefore, the matching of performance impact data can be carried out step by step hierarchically, which can improve the matching efficiency and matching effect of performance impact data.

[0067] Step 207, in the case that there is a target deployment environment sample matching the performance impact data in the performance sample library, determine the performance evaluation result of the centralized storage system to be evaluated in the target deployment environment according to the target system running performance data corresponding to the target deployment environment sample.

[0068] According to some embodiments, when there is a target deployment environment sample matching the performance impact data in the performance sample library, in the case that the performance impact data is the same as the target sample performance impact data, use the target system running performance data corresponding to the target deployment environment sample as the performance evaluation result of the centralized storage system to be evaluated in the target deployment environment; in the case that the performance impact data is different from the target sample performance impact data, the target system running performance data can be adjusted according to the set of performance impact factors at the configuration level and the performance impact value, and the adjusted target system running performance data is used as the performance evaluation result of the centralized storage system to be evaluated in the target deployment environment. Therefore, the data accuracy of the performance evaluation result can be improved.

[0069] In some embodiments, the difference between the set of performance impact factors at the configuration level and the performance impact value can be calculated, and linear calculations are performed on each configuration item corresponding to the target sample performance impact data in turn according to the performance impact value of the performance impact factors at the configuration level, and finally the adjusted target system running performance data is obtained.

[0070] In some embodiments, for the performance impact factors at the configuration level with the performance impact value being the upper limit value, the parameters corresponding to its upper limit value are used for comparison. For example, if 100 hard disks can reach the performance full load, and the hard disk configuration is 120, then the configuration comparison is carried out according to the saturated value of 100 hard disks.

[0071] Step 208, obtain the actual running performance data of the centralized storage system to be evaluated in the target deployment environment.

[0072] According to some embodiments, the actual running performance data can be obtained by conducting performance tests on the centralized storage system to be evaluated by building a target deployment environment in the laboratory, or can be obtained through the actual operation feedback of the customer after delivering the centralized storage system to be evaluated to the customer using the target deployment environment.

[0073] Step 209, in the case that the performance data difference between the actual running performance data and the performance evaluation result is greater than the performance difference threshold, send out an evaluation calibration message.

[0074] According to some embodiments, the evaluation calibration information is used to indicate the adjustment strategy when calibrating and adjusting the target system operation performance data. Among them, the performance data difference being greater than the performance difference threshold indicates that there is a problem with the adjustment strategy itself and it needs to be updated, which can be specifically achieved by the intervention of relevant staff.

[0075] In some embodiments, the performance difference threshold does not specifically refer to a fixed threshold. This performance difference threshold can be determined according to the actual application scenario, for example.

[0076] Step 210: Upload the target deployment environment, performance impact data, and actual operation performance data to the performance sample library.

[0077] It should be noted that by executing steps 208 to 210, therefore, the feedback of the performance evaluation can be improved, and the accuracy of the performance evaluation can be gradually increased.

[0078] Taking a scenario as an example, Figure 2 is a schematic flowchart of another centralized storage performance evaluation method provided by the embodiments of the present disclosure. As Figure 2 shown, first, the performance impact data of the centralized storage system to be evaluated in the target deployment environment can be obtained through performance evaluation input or actual environment information input. Then, a performance sample (deployment environment sample) query can be performed in the performance sample library based on the performance impact data. If the query result is a complete match, the corresponding evaluation result is output and the process ends. If the query result is an incomplete match, a performance evaluation algorithm is used to adjust the target system operation performance data to evaluate the performance; afterwards, the actual operation performance data of the centralized storage system to be evaluated in the target deployment environment is obtained to evaluate whether the performance data evaluation accuracy is met, that is, to determine whether the performance data difference is greater than the performance difference threshold; if it is met, the corresponding evaluation result is output and the process ends; if it is not met, manual intervention is performed for evaluation, the performance evaluation algorithm is calibrated, and the performance sample library is supplemented and improved.

[0079] In some embodiments, Figure 3 is a schematic structural diagram of a centralized storage performance evaluation architecture provided by the embodiments of the present disclosure. As Figure 3 shown, this centralized storage performance evaluation architecture has an automatic evaluation and error correction mechanism and framework. This centralized storage performance evaluation architecture includes an automatic performance evaluation mechanism state machine, and this automatic performance evaluation mechanism state machine is responsible for executing the centralized storage performance evaluation method, that is, establishing a performance evaluation model, performing performance sample library matching, executing the core algorithm (performance evaluation algorithm), and executing the feedback mechanism.

[0080] Among them, the performance sample library can include the measured performance data of the basic laboratory scenarios and the performance feedback results delivered at the actual customer sites. The goal of establishing the performance sample library is to achieve 100% coverage. After the performance sample library is 100% established, it is possible to directly complete the matching to output the corresponding data without the participation of subsequent performance evaluation algorithms. By implementing the feedback mechanism, it is possible to continuously analyze, summarize, and judge various deployment environments of the centralized storage system to be evaluated, give performance evaluation results, supplement them into the performance sample library, and improve and correct the core algorithm. With the increase of samples in the performance sample library and the error correction of the core algorithm, the accuracy of performance evaluation can be continuously improved until it reaches the ideal state, so that this centralized storage performance evaluation architecture can gradually handle the performance evaluation in the pre-sales stage of the customer site and the further accurate evaluation after the deployment environment in the after-sales handover stage, thereby enhancing the customer experience and solving the scenario where the performance cannot support after the business goes live in the later stage.

[0081] Among them, when obtaining the measured performance data of the basic laboratory scenarios, the measured performance data of different deployment environment samples can be imported in an automated manner. For example, when the system operation performance data of a group of characteristic version models under a network configuration is completed, it is possible to start traversing the system operation performance data of different performance models. After traversing different performance models, start traversing the system operation performance data of different versions. After traversing different versions, start traversing the system operation performance data of different hardware models. After traversing different hardware models, start traversing the system operation performance data of different types of network topologies.

[0082] Among them, the existence of the feedback mechanism enables this centralized storage performance evaluation architecture to have learning ability, and it can operate in the following three scenarios: There is a new deployment environment, that is, the scenario where the query result for the performance sample library is none. In this scenario, only the corresponding performance test data needs to be uploaded to the performance sample library; The scenario where the performance data difference between the actual operation performance data and the performance evaluation result is greater than the performance difference threshold. In this scenario, relevant personnel need to intervene to update the core algorithm; The scenario where the adjustment fails when using the performance evaluation algorithm to adjust the target system operation performance data. This scenario is mainly caused by the mismatch of the difference threshold and the preset number of values with the performance evaluation algorithm during incomplete matching, and the performance impact data that the performance evaluation algorithm cannot evaluate is matched. It is possible to adjust the difference threshold and the preset number through the intervention of relevant personnel, or update and improve the performance evaluation algorithm.

[0083] Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by means of software plus a necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases, the former is a better implementation method.

[0084] According to an embodiment of the present disclosure, the present disclosure also provides a centralized storage performance evaluation device.

[0085] Exemplarily, Figure 4 FIG. is a schematic structural diagram of a centralized storage performance evaluation device provided by an embodiment of the present disclosure. The centralized storage performance evaluation device 400 includes: A data determination unit 401, configured to determine performance impact data of a centralized storage system to be evaluated in a target deployment environment, where the performance impact data includes a set of performance impact factors and performance impact values corresponding to at least one performance impact factor in the set of performance impact factors; A sample matching unit 402, configured to match the performance impact data in a performance sample library, where the performance sample library includes multiple deployment environment samples, and sample performance impact data and system operation performance data corresponding to at least one deployment environment sample in the multiple deployment environment samples; A performance evaluation unit 403, configured to determine a performance evaluation result of the centralized storage system to be evaluated in the target deployment environment according to the target system operation performance data corresponding to the target deployment environment sample when there is a target deployment environment sample matching the performance impact data in the performance sample library.

[0086] Further, when the data determination unit 401 is configured to determine the performance impact data of the centralized storage system to be evaluated in the target deployment environment, it is specifically configured to: Determine the architecture-level performance impact factors of the centralized storage system to be evaluated in the target deployment environment, and obtain an architecture-level performance impact factor set; Determine a subset of configuration-level performance impact factors corresponding to at least one architecture-level performance impact factor in the architecture-level performance impact factor set in the target deployment environment, and obtain a configuration-level performance impact factor set; Perform quantitative analysis on the configuration-level performance impact factor set, and obtain performance impact values corresponding to at least one configuration-level performance impact factor in the configuration-level performance impact factor set.

[0087] Further, when the data determination unit 401 is configured to perform quantitative analysis on the configuration-level performance impact factor set and obtain performance impact values corresponding to at least one configuration-level performance impact factor in the configuration-level performance impact factor set, it is specifically configured to: Determine the correlation between at least one configuration-level performance influencing factor in the set of configuration-level performance influencing factors and the system running performance; Perform quantitative analysis on the set of configuration-level performance influencing factors based on the correlation, and obtain the performance influence values corresponding to at least one configuration-level performance influencing factor in the set of configuration-level performance influencing factors.

[0088] Further, when the sample matching unit 402 is used to match performance influence data in the performance sample library, it is specifically used for: Match the set of architecture-level performance influencing factors in the performance sample library, and when there is a set of sample performance influence data in the performance sample library that matches the set of architecture-level performance influencing factors, match the set of sample performance influence data with the set of configuration-level performance influencing factors and the performance influence values of at least one configuration-level performance influencing factor in the set of configuration-level performance influencing factors; When there is a subset of sample performance influence data in the set of sample performance influence data that matches the set of configuration-level performance influencing factors and the performance influence values, select the sample performance influence data with the lowest difference value between the set of configuration-level performance influencing factors and the performance influence values from the subset of sample performance influence data as the target sample performance influence data; Use the deployment environment sample corresponding to the target sample performance influence data as the target deployment environment sample that matches the performance influence data.

[0089] Further, when the sample matching unit 402 is used to match the set of architecture-level performance influencing factors in the performance sample library, it is specifically used for: Query the sample performance influence data including the set of architecture-level performance influencing factors in the performance sample library.

[0090] Further, when the sample matching unit 402 is used to match the set of sample performance influence data with the set of configuration-level performance influencing factors and the performance influence values of at least one configuration-level performance influencing factor in the set of configuration-level performance influencing factors, it is specifically used for: Determine the total performance influence value corresponding to the set of configuration-level performance influencing factors; Query in the set of sample performance influence data the sample performance influence data whose difference value between the sample performance influence total value and the performance influence total value is less than the difference threshold and that includes a preset number of configuration-level performance influencing factors in the set of configuration-level performance influencing factors.

[0091] Further, when the performance evaluation unit 403 is used to determine the performance evaluation result of the centralized storage system to be evaluated in the target deployment environment according to the target system running performance data corresponding to the target deployment environment sample, it is specifically used for: When the performance impact data is the same as the target sample performance impact data, the target system running performance data corresponding to the target deployment environment sample is used as the performance evaluation result of the centralized storage system to be evaluated in the target deployment environment; When the performance impact data is different from the target sample performance impact data, the target system running performance data is adjusted according to the set of performance impact factors at the configuration level and the performance impact value, and the adjusted target system running performance data is used as the performance evaluation result of the centralized storage system to be evaluated in the target deployment environment.

[0092] Furthermore, the centralized storage performance evaluation device 400 further includes an evaluation feedback unit 404. After determining the performance evaluation result of the centralized storage system to be evaluated in the target deployment environment, the evaluation feedback unit 404 is used for: Obtain the actual running performance data of the centralized storage system to be evaluated in the target deployment environment; When the performance data difference between the actual running performance data and the performance evaluation result is greater than the performance difference threshold, an evaluation calibration message is sent, where the evaluation calibration message is used to indicate the adjustment strategy for adjusting the target system running performance data; Upload the target deployment environment, performance impact data, and actual running performance data to the performance sample library.

[0093] Furthermore, after matching the set of performance impact factors at the architecture level in the performance sample library, the evaluation feedback unit 404 is used for: When there is no set of sample performance impact data in the performance sample library that matches the set of performance impact factors at the architecture level, a first matching failure feedback message is sent, where the first matching failure feedback message is used to indicate a performance test on the centralized storage system to be evaluated based on the set of performance impact factors at the architecture level; When there is no subset of sample performance impact data in the deployment environment sample set that matches the set of performance impact factors at the configuration level and the performance impact value, a second matching failure feedback message is sent, where the second matching failure feedback message is used to indicate a performance test on the centralized storage system to be evaluated based on the set of performance impact factors at the configuration level and the performance impact value.

[0094] Furthermore, the evaluation feedback unit 404 is also used for: In response to receiving the first performance test data uploaded in response to the first matching failure feedback message, put the first performance test data into the performance sample library; In response to receiving the second performance test data uploaded in response to the second matching failure feedback message, put the second performance test data into the performance sample library.

[0095] It should be noted that for the description of the features in the embodiments corresponding to the centralized storage performance evaluation device, reference can be made to the relevant descriptions in the embodiments corresponding to the centralized storage performance evaluation method, which will not be elaborated here one by one.

[0096] Embodiments of the present disclosure also provide an electronic device, including a memory and a processor. A computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any of the above embodiments of the centralized storage performance evaluation method.

[0097] Embodiments of the present disclosure also provide a computer-readable storage medium, in which a computer program is stored. The computer program is configured to execute the steps in any of the above embodiments of the centralized storage performance evaluation method when running.

[0098] In an exemplary embodiment, the above computer-readable storage medium may include, but is not limited to: USB flash drives, read-only memories (ROMs), random access memories (RAMs), external hard drives, magnetic disks, or optical discs and other media that can store computer programs.

[0099] Embodiments of the present disclosure also provide a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, it implements the steps in any of the above embodiments of the centralized storage performance evaluation method.

[0100] Embodiments of the present disclosure also provide another computer program product, including a non-volatile computer-readable storage medium. The non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it implements the steps in any of the above embodiments of the centralized storage performance evaluation method.

[0101] Those skilled in the art can further realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the components and steps of each example have been generally described according to functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present disclosure.

[0102] The above has introduced in detail a method for evaluating the performance of a centralized storage. Specific examples are used in this article to elaborate on the principles and implementation manners of the present disclosure. The description of the above embodiments is only used to help understand the method and its core idea of the present disclosure. It should be noted that for those of ordinary skill in the art in this technical field, without departing from the principles of the present disclosure, several improvements and modifications can be made to the present disclosure, and these improvements and modifications also fall within the protection scope of the claims of the present disclosure.

Claims

1. A method for evaluating the performance of a centralized storage, characterized in that, Including: Determine the performance impact data of the centralized storage system to be evaluated in the target deployment environment, where the performance impact data includes a set of performance impact factors and the performance impact values corresponding to at least one performance impact factor in the set of performance impact factors; Match the performance impact data in the performance sample library, where the performance sample library includes multiple deployment environment samples, and the sample performance impact data and system operation performance data corresponding to at least one deployment environment sample in the multiple deployment environment samples; When there is a target deployment environment sample in the performance sample library that matches the performance impact data, determine the performance evaluation result of the centralized storage system to be evaluated in the target deployment environment according to the target system operation performance data corresponding to the target deployment environment sample.

2. The method according to claim 1, wherein The determining the performance impact data of the centralized storage system to be evaluated in the target deployment environment includes: Determine the architecture-level performance impact factors of the centralized storage system to be evaluated in the target deployment environment to obtain an architecture-level performance impact factor set; Determine a subset of configuration-level performance impact factors corresponding to at least one architecture-level performance impact factor in the architecture-level performance impact factor set in the target deployment environment to obtain a configuration-level performance impact factor set; Conduct quantitative analysis on the configuration-level performance impact factor set to obtain the performance impact values corresponding to at least one configuration-level performance impact factor in the configuration-level performance impact factor set.

3. The method according to claim 2, characterized in that The conducting quantitative analysis on the configuration-level performance impact factor set to obtain the performance impact values corresponding to at least one configuration-level performance impact factor in the configuration-level performance impact factor set includes: Determine the association relationship between at least one configuration-level performance impact factor in the configuration-level performance impact factor set and the system operation performance; Based on the association relationship, conduct quantitative analysis on the configuration-level performance impact factor set to obtain the performance impact values corresponding to at least one configuration-level performance impact factor in the configuration-level performance impact factor set.

4. The method according to claim 2, wherein The matching the performance impact data in the performance sample library includes: Query the sample performance impact data including the architecture-level performance impact factor set in the performance sample library, and when there is a set of sample performance impact data in the performance sample library that matches the architecture-level performance impact factor set, match the set of sample performance impact data with the configuration-level performance impact factor set and the performance impact values corresponding to at least one configuration-level performance impact factor in the configuration-level performance impact factor set; When there is a subset of sample performance impact data in the set of sample performance impact data that matches the configuration-level performance impact factor set and the performance impact values, select the sample performance impact data with the lowest difference value between the configuration-level performance impact factor set and the performance impact values as the target sample performance impact data; Use the deployment environment sample corresponding to the target sample performance impact data as the target deployment environment sample that matches the performance impact data.

5. The method according to claim 4, wherein The matching of the sample performance impact data set with the configuration-level performance impact factor set and the performance impact value of at least one configuration-level performance impact factor in the configuration-level performance impact factor set includes: Determine the total performance impact value corresponding to the configuration-level performance impact factor set; Query in the sample performance impact data set for sample performance impact data where the difference between the sample performance impact total value and the performance impact total value is less than a difference threshold and that includes a preset number of configuration-level performance impact factors in the configuration-level performance impact factor set.

6. The method according to claim 5, wherein The determining of the performance evaluation result of the centralized storage system to be evaluated in the target deployment environment according to the target system operation performance data corresponding to the target deployment environment sample includes: When the performance impact data is the same as the target sample performance impact data, use the target system operation performance data corresponding to the target deployment environment sample as the performance evaluation result of the centralized storage system to be evaluated in the target deployment environment; When the performance impact data is different from the target sample performance impact data, adjust the target system operation performance data according to the configuration-level performance impact factor set and the performance impact value, and use the adjusted target system operation performance data as the performance evaluation result of the centralized storage system to be evaluated in the target deployment environment.

7. The method according to claim 6, characterized in that After determining the performance evaluation result of the centralized storage system to be evaluated in the target deployment environment, the method further includes: Obtain the actual operation performance data of the centralized storage system to be evaluated in the target deployment environment; When the performance data difference between the actual operation performance data and the performance evaluation result is greater than a performance difference threshold, send an evaluation calibration message, where the evaluation calibration message is used to indicate the adjustment strategy when calibrating the adjustment of the target system operation performance data; Upload the target deployment environment, the performance impact data, and the actual operation performance data to the performance sample library.

8. The method according to claim 4, wherein After matching the architecture-level performance impact factor set in the performance sample library, the method further includes: When there is no sample performance impact data set in the performance sample library that matches the architecture-level performance impact factor set, send a first matching failure feedback message, where the first matching failure feedback message is used to indicate performing a performance test on the centralized storage system to be evaluated based on the architecture-level performance impact factor set; In response to receiving the first performance test data uploaded for the first matching failure feedback message, put the first performance test data into the performance sample library. In the case that there is no subset of sample performance impact data in the set of deployment environment samples that matches the set of configuration-level performance impact factors and the performance impact value, a second matching failure feedback message is sent, where the second matching failure feedback message is used to indicate performance testing of the centralized storage system to be evaluated based on the set of configuration-level performance impact factors and the performance impact value. In response to receiving second performance test data uploaded for the second matching failure feedback message, the second performance test data is placed in the performance sample library.

9. A centralized storage performance evaluation device, characterized in that, Comprising: A data determination unit for determining performance impact data of a centralized storage system to be evaluated in a target deployment environment, where the performance impact data includes a set of performance impact factors and performance impact values corresponding to at least one performance impact factor in the set of performance impact factors. A sample matching unit for matching the performance impact data in a performance sample library, where the performance sample library includes a plurality of deployment environment samples, and sample performance impact data and system operation performance data corresponding to at least one of the plurality of deployment environment samples. A performance evaluation unit for, in the case that there is a target deployment environment sample in the performance sample library that matches the performance impact data, determining a performance evaluation result of the centralized storage system to be evaluated in the target deployment environment according to the target system operation performance data corresponding to the target deployment environment sample.

10. An electronic device, characterized in that Comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method according to any one of claims 1 to 8.

Images