Parameter configuration method and device in multi-computing-cluster environment and computer equipment

Abstract

The invention relates to a parameter configuration method and device in a multi-computing-cluster environment, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: determining a value space of each database parameter in a to-be-configured database; according to the plurality of query tasks, determining a performance index function for the to-be-configured database; traversing each value point in the value space, and executing a plurality of query tasks according to database parameters represented by the traversed value points to obtain execution index scores of performance index functions under the database parameters represented by the traversed value points; and determining a target value point in the targeted value space, and performing parameter configuration on the to-be-configured database according to database parameters represented by the target value point. By adopting the method, the overall performance of the database can be improved, and meanwhile it is guaranteed that the computing clusters under different hardware configurations can play the optimal performance.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a parameter configuration method, apparatus, computer equipment, computer-readable storage medium, and computer program product in a multi-computing cluster environment. Background Art

[0002] The storage-computing separation cloud analytical database is a database that provides cloud data analysis services by separating storage and computing. The database can store data separately and perform independent analysis and processing through multiple computing clusters, thereby improving the efficiency of parallel data query and parallel analysis.

[0003] However, since the storage-computing separation database is compatible with multiple operating systems and hardware facilities, that is, the operating systems and hardware facilities of each computing cluster can be inconsistent, and computing clusters with different hardware settings share a set of default database parameter configurations, when computing clusters are deployed using different hosts, the full performance of the host cannot be utilized, resulting in performance loss. Therefore, the current storage-computing separation cloud analytical database has problems of unbalanced resource utilization and low query efficiency in the use scenario of multiple computing clusters. Summary of the invention

[0004] Based on this, it is necessary to provide a parameter configuration method, device, computer equipment, computer-readable storage medium and computer program product in a multi-computing cluster environment that can effectively solve the problems of unbalanced resource utilization and low query efficiency in a storage-computing separation cloud analytical database in a multi-computing cluster environment, improve the overall performance of the database, and ensure that computing clusters under different hardware configurations can perform at their best.

[0005] In a first aspect, the present application provides a parameter configuration method in a multi-computing cluster environment, comprising:

[0006] Determine the value space of each database parameter in the database to be configured;

[0007] Acquire multiple query tasks in a preset database task processing cluster, and determine a performance indicator function for the database to be configured according to the multiple query tasks;

[0008] For each of the value spaces, each value point in the value space is traversed, and the multiple query tasks are executed according to the database parameters represented by the traversed value points to obtain the execution index scores of the performance index functions under the database parameters represented by the traversed value points;

[0009] When the traversal is completed, the target value point is determined in the target value space according to the execution index score of the performance index function under the database parameters represented by each value point in the target value space, and the parameters of the database to be configured are configured according to the database parameters represented by the target value point.

[0010] In one embodiment, determining the value space of each database parameter in the database to be configured includes:

[0011] For each database parameter in the database to be configured, determine the value range of the database parameter; according to the value range of the database parameter, determine the preset coding rule corresponding to the database parameter; according to the preset coding rule, feature encode the value range of the database parameter to obtain the value space corresponding to the database parameter.

[0012] In one embodiment, determining the performance indicator function for the database to be configured according to the multiple query tasks includes:

[0013] Receive multiple performance indicator information for the database to be configured; obtain initial functions corresponding to the multiple performance indicator information, wherein the initial function includes function items corresponding to each performance indicator information; and assign respective weight coefficients to each function item according to the multiple query tasks to obtain a performance indicator function for the database to be configured.

[0014] In one embodiment, the execution index score of the performance index function includes the execution index score of each function item in the performance index function; and determining the target value point in the target value space according to the execution index score of the performance index function under the database parameter represented by each value point in the target value space includes:

[0015] Obtain an execution index score threshold for each function item in the performance index function; compare the execution index score of each function item in the performance index function under the database parameters represented by each value point in the targeted value space with the execution index score threshold, and determine candidate value points in which the execution index score of each function item is greater than the execution index score threshold; determine the target value point in the targeted value space according to the execution index score of each function item in the performance index function under the database parameters represented by each candidate value point.

[0016] In one embodiment, determining a target value point in the targeted value space according to the execution index score of each function item in the performance index function under the database parameter represented by each candidate value point includes:

[0017] Obtain a respective custom proportional coefficient for each function item in the multiple performance indicator information; perform weighted summation of the respective execution indicator scores of each function item in the performance indicator function under the database parameters represented by each value point in the targeted value space according to the respective custom proportional coefficient for each function item in the multiple performance indicator information, and obtain a target execution indicator score of the performance indicator function under the database parameters represented by each value point in the targeted value space; use the value point represented by the database parameter corresponding to the maximum target execution indicator score as the target value point.

[0018] In one embodiment, executing the multiple query tasks according to the database parameters represented by the traversed value points to obtain the execution index scores of the performance index functions under the database parameters represented by the traversed value points includes:

[0019] Determine the value space where the traversed value point is located, and convert the traversed value point into a candidate database parameter according to a preset coding rule corresponding to the value space where the traversed value point is located; execute the multiple query tasks according to the candidate database parameters to obtain the execution index score of the performance index function under the candidate database parameters.

[0020] In a second aspect, the present application also provides a parameter configuration device in a multi-computing cluster environment, including:

[0021] A first determination module is used to determine the value space of each database parameter in the database to be configured;

[0022] A second determination module is used to obtain a plurality of query tasks in a preset database task processing cluster, and determine a performance indicator function for the database to be configured according to the plurality of query tasks;

[0023] An execution module is used to traverse each value point in the value space for each of the value spaces, and execute the multiple query tasks according to the database parameters represented by the traversed value points to obtain the execution index score of the performance index function under the database parameters represented by the traversed value points;

[0024] A configuration module is used to determine the target value point in the value space after the traversal is completed, according to the execution index score of the performance index function under the database parameters represented by each value point in the value space, and perform parameter configuration on the database to be configured according to the database parameters represented by the target value point.

[0025] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0026] Determine the value space of each database parameter in the database to be configured;

[0027] Acquire multiple query tasks in a preset database task processing cluster, and determine a performance indicator function for the database to be configured according to the multiple query tasks;

[0028] For each of the value spaces, each value point in the value space is traversed, and the multiple query tasks are executed according to the database parameters represented by the traversed value points to obtain the execution index scores of the performance index functions under the database parameters represented by the traversed value points;

[0029] When the traversal is completed, the target value point is determined in the target value space according to the execution index score of the performance index function under the database parameters represented by each value point in the target value space, and the parameters of the database to be configured are configured according to the database parameters represented by the target value point.

[0030] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0031] Determine the value space of each database parameter in the database to be configured;

[0032] Acquire multiple query tasks in a preset database task processing cluster, and determine a performance indicator function for the database to be configured according to the multiple query tasks;

[0033] For each of the value spaces, each value point in the value space is traversed, and the multiple query tasks are executed according to the database parameters represented by the traversed value points to obtain the execution index scores of the performance index functions under the database parameters represented by the traversed value points;

[0034] When the traversal is completed, the target value point is determined in the target value space according to the execution index score of the performance index function under the database parameters represented by each value point in the target value space, and the parameters of the database to be configured are configured according to the database parameters represented by the target value point.

[0035] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0036] Determine the value space of each database parameter in the database to be configured;

[0037] Acquire multiple query tasks in a preset database task processing cluster, and determine a performance indicator function for the database to be configured according to the multiple query tasks;

[0038] For each of the value spaces, each value point in the value space is traversed, and the multiple query tasks are executed according to the database parameters represented by the traversed value points to obtain the execution index scores of the performance index functions under the database parameters represented by the traversed value points;

[0039] When the traversal is completed, the target value point is determined in the target value space according to the execution index score of the performance index function under the database parameters represented by each value point in the target value space, and the parameters of the database to be configured are configured according to the database parameters represented by the target value point.

[0040] The parameter configuration method, device, computer equipment, computer-readable storage medium and computer program product in the multi-computing cluster environment determine the value space of each database parameter in the database to be configured; set a reasonable value space for different database parameters, which helps to improve the pertinence and effectiveness of subsequent optimization. And by clarifying the value range of each parameter, the comprehensiveness of the search process is ensured, and no possible optimization opportunities are missed.

[0041] Acquire multiple query tasks in a preset database task processing cluster, and determine the performance indicator function for the database to be configured based on the multiple query tasks; by comprehensively considering the performance of multiple query tasks, a multi-dimensional evaluation of database performance can be achieved, avoiding the side effects of single indicator optimization.

[0042] For each of the value spaces, each value point in the value space is traversed, and the multiple query tasks are executed according to the database parameters represented by the traversed value points to obtain the execution index scores of the performance index functions under the database parameters represented by the traversed value points; by traversing all possible parameter combinations, the thoroughness and accuracy of the search process are ensured, which is conducive to finding the optimal parameter configuration. The actual query task is executed each time the traversal is performed, which not only verifies the effect of the parameter configuration, but also provides a reliable basis for the final selection.

[0043] When the traversal is completed, the target value point is determined in the target value space according to the execution index score of the performance index function under the database parameters represented by each value point in the target value space, and the parameters of the database to be configured are configured according to the database parameters represented by the target value point. By comparing the performance index scores under different parameter configurations, the optimal parameter configuration is finally selected, which directly improves the performance and resource utilization of the database. Through the above steps, the problems of unbalanced resource utilization and low query efficiency of the storage and computing separation cloud analytical database in a multi-computing cluster environment can be effectively solved, the overall performance of the database can be improved, and at the same time, it is ensured that the computing clusters under different hardware configurations can perform at their best. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0045] Figure 1 An application environment diagram of a parameter configuration method in a multi-computing cluster environment in one embodiment;

[0046] Figure 2 A schematic diagram of a flow chart of a parameter configuration method in a multi-computing cluster environment in one embodiment;

[0047] Figure 3 A framework diagram of a parameter configuration method in a multi-computing cluster environment in one embodiment;

[0048] Figure 4 A flow chart of a parameter configuration method in a multi-computing cluster environment in another embodiment;

[0049] Figure 5 A structural block diagram of a parameter configuration device in a multi-computing cluster environment in one embodiment;

[0050] Figure 6 An internal structural diagram of a computer device in one embodiment. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0052] The parameter configuration method in a multi-computing cluster environment provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. The terminal 102 is used to generate a parameter configuration request in a multi-computing cluster environment, and send the parameter configuration request in the multi-computing cluster environment to the server 104, so that the server 104 determines the target value point in the targeted value space, and performs parameter configuration on the database to be configured according to the database parameter represented by the target value point. Among them, the terminal 102 can be, but is not limited to, various personal computers, laptops, smart phones, tablets, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car devices, projection devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. Head-mounted devices can be virtual reality (VR) devices, augmented reality (AR) devices, smart glasses, etc. Server 104 is a database parameter configuration cluster. As an auxiliary computing cluster, the database parameter configuration cluster mainly explores and tests different database parameter configurations to find the best configuration solution without affecting the production environment. This cluster usually has the same hardware specifications and software environment as the main computing cluster, i.e., the database task processing cluster (the cluster that undertakes actual business operations), to ensure the validity and reliability of the test results.

[0053] In an exemplary embodiment, Figure 2 As shown in the figure, a parameter configuration method in a multi-computing cluster environment is provided. Figure 1 The server 104 in the example is used as an example to illustrate, including the following steps 202 to 208. Among them:

[0054] Step 202: determine the value space of each database parameter in the database to be configured.

[0055] The database to be configured refers to a database that needs to be optimized. In this application, the database to be configured is a storage-computing separation cloud analysis database. This type of database separates data storage and data processing functions, allowing independent expansion of storage and computing capabilities to meet different business needs.

[0056] Database parameters refer to the settings that control the behavior of the database, affecting the performance, security, reliability, etc. of the database. Database parameters include, but are not limited to: buffer pool size (memory size for caching database pages), connection pool size (maximum number of database connections), query cache parameters (memory size for caching query results), memory usage (maximum amount of memory available for a database instance), sort and aggregation memory allocation (memory allocation for sort and aggregation operations).

[0057] The value space refers to the set of all possible values ​​that each database parameter can accept. During the parameter optimization process, the value space of each parameter will be defined so that the algorithm can search for the best configuration among these possible values. In this application, for each database parameter, it is necessary to determine its reasonable value range, and then search for the best parameter value in this value space. This process involves traversing each value point (i.e. parameter value), executing the predetermined query task, evaluating the performance indicators, and finally determining an optimal parameter configuration.

[0058] Specifically, first identify the database to be configured that needs parameter optimization. In this application, the database to be configured is a storage-computing separated cloud analytical database. This database separates data storage and data processing functions, allowing independent expansion of storage and computing capabilities to meet different business needs.

[0059] Then determine the list of database parameters that need to be optimized. These parameters are usually key settings that affect database performance, including but not limited to: buffer pool size, connection pool size, query cache parameters, memory usage, sorting and aggregation memory allocation, and other related configuration items.

[0060] Next, define a reasonable range for each parameter to be optimized. Understandably, this range should be based on actual hardware resources and business requirements. For example, the buffer pool size is 16MB to 128MB.

[0061] Finally, the value range of each parameter is mapped to a continuous search space, i.e., the value space. This step is to facilitate the subsequent optimization algorithm (such as the particle swarm algorithm) to process. For example, the buffer pool size from 16MB to 128MB is mapped to the interval [0, 1]. It can be understood that the values ​​at both ends and in the middle of the value range are linearly mapped in proportion.

[0062] Step 204: Acquire multiple query tasks in a preset database task processing cluster, and determine a performance indicator function for the database to be configured based on the multiple query tasks.

[0063] The database task processing cluster refers to a computing cluster used to execute database query tasks. In this application, the database task processing cluster is the user's main database operation cluster, responsible for processing the user's actual business needs and executing various database query tasks.

[0064] A query task refers to an SQL query statement executed in a database. These query tasks can be various types of queries, including but not limited to: single-table query, multi-table association query, aggregation query, and high-concurrency query. In this application, query tasks are collected from the database task processing cluster. These query tasks reflect typical operations in actual business scenarios and are used to evaluate database performance under different parameter configurations.

[0065] The performance indicator function is a mathematical function used to evaluate the performance of the database under a given parameter configuration. It can be understood that the performance indicator function is constructed based on multiple performance indicators, which may include but are not limited to: query response time (the time required to execute a query task), throughput (the number of queries that can be processed per unit time), resource utilization (the usage of resources such as CPU, memory, disk I / O), concurrency (the ability of the system to process multiple queries simultaneously), etc. In this application, the goal of the performance indicator function is to combine these performance indicators and give a numerical score to reflect the overall performance of the database under the current parameter configuration.

[0066] Specifically, first determine the database task processing cluster used to perform actual business query tasks. This cluster is the user's main database operation cluster, responsible for processing the user's actual business needs. Collect SQL query statements in actual business scenarios from the database task processing cluster. These query tasks may include but are not limited to: single-table query, multi-table association query, aggregation query, and high-concurrency query. Sort and classify the collected query tasks to ensure that they can fully reflect the typical operations in actual business scenarios. This helps to make subsequent performance evaluation more accurate.

[0067] Then determine the key indicators for evaluating database performance. Optional, including but not limited to: query response time, throughput, resource utilization, concurrency, etc. Based on the selected performance indicators, build a performance indicator function. The performance indicator function is a mathematical function used to comprehensively evaluate the performance of the database under a given parameter configuration. In this application, the performance indicator function converts each performance indicator into a numerical score that reflects the overall performance of the database. For example, performance indicator function = (1 / average query response time) + (throughput / maximum throughput) + (resource utilization / 100).

[0068] Finally, the performance indicator function can be adjusted and optimized according to actual needs. For example, if query response time is the most important indicator, it can be given a higher weight:

[0069] Performance indicator function = w1×(1 / average query response time)+w2×(throughput / maximum throughput)+w3×(resource utilization / 100).

[0070] Among them, w1, w2, and w3 are the weights of each indicator, which can be set according to actual business needs.

[0071] Step 206, for each value space, traverse each value point in the value space, and execute multiple query tasks according to the database parameters represented by the traversed value point to obtain the execution index score of the performance index function under the database parameters represented by the traversed value point.

[0072] Among them, a value point refers to a specific parameter value combination in the value space of the database parameter. The value space is the set of all possible values ​​of each parameter, and the value point is a specific value in this set. The execution index score refers to the score calculated by the performance index function after executing multiple query tasks under a given parameter configuration (value point). This score reflects the performance of the database under the current parameter configuration.

[0073] Specifically, the first step is to initialize the particle swarm, including determining the database parameters that need to be optimized and their value ranges. For example, the value range of the buffer pool size is 16MB to 128MB. Map the value range of each database parameter to a continuous value space. For example, map the buffer pool size from 16MB to 128MB to the interval [0, 1]. Initialize a swarm containing multiple particles, each particle represents a possible parameter configuration. Optionally, randomly generate the position of each particle to ensure that different areas of the entire search space are covered. Initialize the velocity vector for each particle, and the velocity is also randomly set within a smaller range.

[0074] Then, the initial particle performance is evaluated, including configuring the cluster using database parameters, and executing multiple query tasks collected from the database task processing cluster according to the position of each particle (i.e., parameter configuration). Based on the execution results, the performance indicator function value of each particle, i.e., the execution indicator score, is calculated. For example, the following performance indicator function is used:

[0075] Performance indicator function = performance indicator function = 0.5×(1 / average query response time)+0.3×(throughput / maximum throughput)+0.2×(resource utilization / 100).

[0076] Step 208, when the traversal is completed, the target value point is determined in the target value space according to the execution index score of the performance index function under the database parameters represented by each value point in the target value space, and the parameters of the database to be configured are configured according to the database parameters represented by the target value point.

[0077] The target value point refers to the optimal parameter configuration finally determined according to the execution index score of the performance index function after traversing all the value points in the value space. Specifically, the target value point is the value point with the highest performance index function value, i.e., the execution index score, among all the tested parameter configurations.

[0078] Specifically, first update the individual extreme values, including recording the best parameter configuration (i.e., execution index score) found by each particle. Update the global extreme value, including determining the configuration with the highest execution index score among all particles as the global best. Apply the PSO formula to update the speed and position, including using the PSO speed update formula and position update formula to adjust the speed and position of each particle, as follows:

[0079] v i (t+1)=v i (t)+c1r1(p best，i -x i (t))+c2r2(g best -x i (t)

[0080] x i (t+1)=x i (t)+v i (t+1)

[0081] Among them, v i (t) is the velocity of particle i at the tth iteration, x i (t) is the position of particle i at the tth iteration, p best，i is the individual extreme value of particle i, g best is the global extremum, c1 and c2 are learning factors, and r1 and r2 are random numbers.

[0082] Then, if the updated position is outside the valid range, use boundary processing techniques such as reflection, wrapping, or shrinking to ensure that the position is within the valid range. Repeat the above steps until the stop condition is met. Optionally, the stop condition is the maximum number of iterations or the maximum execution index score.

[0083] Finally, after all iterations are completed, the parameter configuration represented by the global best particle is determined and used as the optimal parameter setting of the database.

[0084] In one of the embodiments, for each database parameter in the database to be configured, the value range of the database parameter is determined; based on the value range of the database parameter, the preset encoding rule corresponding to the database parameter is determined; based on the preset encoding rule, the value range of the database parameter is feature-encoded to obtain the value space corresponding to the database parameter.

[0085] The value range refers to the set of all possible values ​​that each database parameter can accept. These ranges are usually determined based on actual hardware resources and business requirements. The definition of the value range helps to limit the search space of the parameter, i.e. the value space, during the optimization process, thereby improving the efficiency and accuracy of the optimization.

[0086] The preset encoding rule refers to a method of mapping the value range of the database parameter to a continuous search space, i.e., the value space (e.g., the interval [0, 1]). It can be understood that the preset encoding rule enables the optimization algorithm (e.g., the particle swarm optimization algorithm) to more conveniently process and search for parameter values.

[0087] Specifically, first determine the storage-computing separation cloud analytical database that needs to optimize parameters, that is, the database to be configured. List the database parameters that need to be optimized. For example, buffer pool size, connection pool size, query cache parameters, etc. And determine the value range of each parameter based on actual business needs and hardware resources. For example, the value range of the buffer pool size is 16MB to 128MB.

[0088] Then select a suitable encoding rule, i.e., a preset encoding rule. Optionally, the preset encoding rule is a linear mapping, a logarithmic mapping, a piecewise linear mapping, a nonlinear mapping, and a normalized mapping, etc., which can be set according to actual needs. According to the preset encoding rule, the value range of each database parameter is encoded to obtain a corresponding value space. For example, the buffer pool size is mapped from 16MB to 128MB to the interval [0, 1]. It can be understood that the values ​​at both ends and in the middle of the value range are feature encoded according to the preset encoding rule.

[0089] By clarifying the value range of each database parameter, the search space of the optimization algorithm can be limited to avoid invalid or unreasonable parameter values. This helps to improve the efficiency and accuracy of optimization. Further, through feature encoding, the parameter value range is converted into a format that can be directly processed by the optimization algorithm, which can significantly improve the efficiency of the optimization algorithm. For example, the particle swarm optimization (PSO) algorithm can more effectively search for the optimal solution in a continuous search space.

[0090] In one of the embodiments, multiple performance indicator information for a database to be configured is received; an initial function corresponding to the multiple performance indicator information is obtained, the initial function including a function item corresponding to each performance indicator information; and a weight coefficient is assigned to each function item according to multiple query tasks to obtain a performance indicator function for the database to be configured.

[0091] The performance indicator information refers to the key indicators used to evaluate database performance. These indicators usually reflect the performance of the database to be configured in different aspects, including but not limited to: query response time, throughput, resource utilization, and concurrency.

[0092] The initial function is a preliminary mathematical function used to comprehensively evaluate the performance of the database under different performance indicators. The initial function consists of multiple function items, each of which corresponds to a performance indicator.

[0093] A function term refers to each part of the initial function, and each function term corresponds to a performance indicator. A function term is usually a mathematical expression used to quantify the performance of a specific performance indicator. For example:

[0094] The function term of query response time = 1 / average query response time.

[0095] The weight coefficient refers to the weight assigned to each function item, which is used to adjust the importance of different performance indicators in the comprehensive evaluation. The weight coefficient is usually a value between 0 and 1, indicating the relative importance of the performance indicator in the overall performance evaluation. For example: the query response time is the most important indicator, and it is assigned a higher weight coefficient, 0.5.

[0096] Specifically, firstly, a plurality of key indicators for evaluating database performance, namely, performance indicator information, is received, for example, query response time, throughput, resource utilization, and concurrency.

[0097] Then define the initial function, including building a preliminary mathematical function to comprehensively evaluate the performance of the database under different performance indicators. The initial function consists of multiple function items, each of which corresponds to a performance indicator. For example:

[0098] Initial function = f1 (query response time) + f2 (throughput) + f3 (resource utilization) + f4 (concurrency)

[0099] Define function terms, including defining a function term for each performance indicator. A function term is usually a mathematical expression that quantifies the performance of a specific performance indicator. For example:

[0100] The function term of query response time is: f1 (query response time) = 1 / average query response time

[0101] The function term of throughput is: f2 (throughput) = throughput / maximum throughput

[0102] The function term of resource utilization is: f3 (resource utilization) = resource utilization / 100

[0103] The function item of concurrency is: f4 (concurrency) = concurrency / maximum concurrency

[0104] Finally, according to the actual business needs and the characteristics of the query task, a weight coefficient is assigned to each function item. The weight coefficient is usually a value between 0 and 1, indicating the relative importance of the performance indicator in the overall performance evaluation. For example, the weight coefficient of query response time is 0.5, the weight coefficient of throughput is 0.3, the weight coefficient of resource utilization is 0.2, and the weight coefficient of concurrency is 0.1. Multiply each function item by its corresponding weight coefficient to obtain the final performance indicator function. For example:

[0105] Performance indicator function = 0.5×(1 / average query response time) + 0.3×(throughput / maximum throughput) + 0.2×(resource utilization / 100) + 0.1×(concurrency / maximum concurrency).

[0106] By defining the initial function, multiple performance indicator information is standardized into a mathematical model. This allows different performance indicators to be processed uniformly, which facilitates the operation and comparison of the optimization algorithm. In addition, each performance indicator corresponds to a function item, which clarifies the specific role and calculation method of each indicator in the evaluation, making the performance evaluation more standardized and scientific. Furthermore, by assigning a weight coefficient to each function item, the importance of different performance indicators can be flexibly adjusted according to actual business needs and the characteristics of the query task. This makes the optimization process more targeted and can better meet business needs.

[0107] In one of the embodiments, an execution index score threshold value of each function item in the performance index function is obtained; the execution index score of each function item in the performance index function under the database parameters represented by each value point in the targeted value space is compared with the execution index score threshold value to determine the candidate value points in which the execution index score of each function item is greater than the execution index score threshold value; based on the execution index score of each function item in the performance index function under the database parameters represented by the candidate value points, the target value point is determined in the targeted value space.

[0108] The execution index score threshold refers to a minimum standard or passing score set for each performance index function item. This threshold is used to filter out parameter configurations that perform well on specific performance indicators. If the execution index score of a performance index function item under a parameter configuration is lower than the threshold, the parameter configuration will be excluded.

[0109] Candidate value points refer to those parameter configurations in the value space whose execution index scores on each performance index function item are greater than or equal to the execution index score threshold among all parameter configurations. These candidate value points are considered to be candidate solutions that meet the basic performance requirements and are further used to determine the final optimal parameter configuration.

[0110] Specifically, first of all, for the performance indicator function that has been constructed. For example:

[0111] Performance indicator function = 0.5×(1 / average query response time) + 0.3×(throughput / maximum throughput) + 0.2×(resource utilization / 100) + 0.1×(concurrency / maximum concurrency).

[0112] Set an execution index score threshold for each function item in the performance index function. For example, the execution index score threshold for query response time is 0.8, the execution index score threshold for throughput is 0.7, the execution index score threshold for resource utilization is 0.6, and the execution index score threshold for concurrency is 0.5.

[0113] Then, we generate value points, including multiple parameter configurations within the value space of each database parameter. For example, the buffer pool size is 0.4. We use the database parameter configuration cluster to execute the collected query tasks according to each parameter configuration. Based on the execution results, we calculate the execution index score of each performance index function item under each parameter configuration.

[0114] For example, the execution index score of each performance index function item under the parameter configuration of the buffer pool size of 0.4 includes: the execution index score of the query response time is 0.9, the execution index score of the throughput is 0.8, the execution index score of the resource utilization is 0.7, and the execution index score of the concurrency is 0.6.

[0115] The execution index scores of each performance index function item under the parameter configuration of the buffer pool size of 0.3 include: the execution index score of query response time is 0.7, the execution index score of throughput is 0.6, the execution index score of resource utilization is 0.5, and the execution index score of concurrency is 0.4.

[0116] Next, the execution index score of each performance index function item under each parameter configuration is compared with the corresponding threshold. Only when the execution index scores of all performance index function items are greater than or equal to the corresponding threshold, the parameter configuration is considered as a candidate value point.

[0117] Then, for all candidate value points, calculate their total scores in the performance indicator function. For example, the total score in the performance indicator function under the parameter configuration of the buffer pool size of 0.4 = 0.5 × 0.9 + 0.3 × 0.8 + 0.2 × 0.7 + 0.1 × 0.6 = 0.45 + 0.24 + 0.14 + 0.06 = 0.89.

[0118] The total score in the performance indicator function under the parameter configuration of the buffer pool size of 0.3 = 0.5×0.85+0.3×0.75+0.2×0.65+0.1×0.55=0.835.

[0119] Finally, the candidate value point with the highest total score is selected as the target value point. For example, the total score of the buffer pool size of 0.4 is 0.89, which is higher than the total score of 0.835 of the buffer pool size of 0.3. The candidate value point with the characterization parameter configuration of the buffer pool size of 0.4 is selected as the target value point.

[0120] By screening out candidate value points that meet all performance indicator thresholds, we can ensure that these configurations have good performance on all key performance indicators. And by setting thresholds and screening candidate value points, we can clearly see which parameter configurations perform well on which performance indicators, which can significantly reduce the number of parameter configurations that need to be further evaluated. This helps to improve the efficiency of the optimization algorithm and reduce unnecessary calculations and tests.

[0121] In one of the embodiments, a custom proportional coefficient of each function item in a plurality of performance indicator information is obtained; based on the custom proportional coefficient of each function item in the plurality of performance indicator information, a weighted sum is performed on the execution indicator score of each function item in the performance indicator function under the database parameter represented by each value point in the target value space to obtain a target execution indicator score of the performance indicator function under the database parameter represented by each value point in the target value space; and the value point represented by the database parameter corresponding to the maximum target execution indicator score is used as the target value point.

[0122] The custom scale factor is a weight factor set for each performance indicator function item, which is used to reflect the relative importance of the performance indicator in the overall performance evaluation. These coefficients can be flexibly adjusted according to actual business needs and scenarios, making the optimization process more targeted.

[0123] The target execution index score is the comprehensive score obtained by weighted summing the execution index scores of each performance index function item at each value point. This comprehensive score reflects the overall performance of the parameter configuration on all performance indicators. Finally, the value point with the highest target execution index score is selected as the optimal parameter configuration.

[0124] Specifically, first, for the performance indicator function that has been constructed, for example, performance indicator function = f1 (query response time) + f2 (throughput) + f3 (resource utilization) + f4 (concurrency).

[0125] Set a custom scaling factor for each performance indicator function item. These coefficients reflect the relative importance of each performance indicator in the overall performance evaluation. For example, the custom scaling factor for query response time is 0.5, the custom scaling factor for throughput is 0.3, and the custom scaling factor for resource utilization is 0.2.

[0126] The custom scaling factor for concurrency is 0.1.

[0127] Then, we generate value points, including multiple parameter configurations within the value space of each database parameter. For example, the buffer pool size is 0.4. We use the database parameter configuration cluster to execute the collected query tasks according to each parameter configuration. Based on the execution results, we calculate the execution index score of each performance index function item under each parameter configuration.

[0128] For example, the execution index score of each performance index function item under the parameter configuration of the buffer pool size of 0.4 includes: the execution index score of the query response time is 0.9, the execution index score of the throughput is 0.8, the execution index score of the resource utilization is 0.7, and the execution index score of the concurrency is 0.6.

[0129] The execution index scores of each performance index function item under the parameter configuration of the buffer pool size of 0.3 include: the execution index score of query response time is 0.7, the execution index score of throughput is 0.6, the execution index score of resource utilization is 0.5, and the execution index score of concurrency is 0.4.

[0130] Next, the execution index score of each value point is weighted and summed according to the custom scale factor to obtain the target execution index score. For example, for the parameter configuration of the buffer pool size of 0.4, the target execution index score = 0.5 × 0.9 + 0.3 × 0.8 + 0.2 × 0.7 + 0.1 × 0.6 = 0.89; for the parameter configuration of the buffer pool size of 0.3, the target execution index score = 0.5 × 0.7 + 0.3 × 0.6 + 0.2 × 0.5 + 0.1 × 0.4 = 0.67.

[0131] Finally, compare the target execution index scores of each value point (i.e. parameter configuration) and select the value point with the highest score as the target value point. For example, the target execution index score corresponding to the parameter configuration with a buffer pool size of 0.4 is 0.89, which is higher than the target execution index score of 0.67 for the parameter configuration with a buffer pool size of 0.3. Therefore, the value point with a buffer pool size of 0.4 is selected as the target value point.

[0132] Due to the customized proportional coefficient, the importance of different performance indicators can be weighted according to the specific application scenario, so as to obtain a database parameter configuration that better meets specific business needs. And by weighting and summing the execution index scores of each performance indicator, a comprehensive performance index score can be obtained, which can more accurately reflect the impact of different parameter configurations on the overall performance and help find the global optimal or near-optimal parameter configuration.

[0133] In one of the embodiments, the value space of the traversed value point is determined, and the traversed value point is converted into a candidate database parameter according to a preset encoding rule corresponding to the value space of the traversed value point; based on the candidate database parameters, multiple query tasks are executed to obtain the execution index score of the performance index function under the candidate database parameters.

[0134] Among them, candidate database parameters refer to the process of parameter optimization, in which a value point in the search space (i.e., the value space) is converted into a set of specific database parameter configurations through certain encoding rules (i.e., preset encoding rules). These parameter configurations are potential solutions for testing and evaluating performance indicators. In this application, each point (value point) in the value space represents a set of possible parameter configurations. This value point is converted into a set of specific database parameters through preset encoding rules. For example, a point in the value space may correspond to specific parameter settings such as a buffer pool size of 128MB, a connection pool size of 300, and a query cache size of 256MB.

[0135] Specifically, first, each value point in the value space can be represented by a coordinate. For example, in the value space [0, 1] corresponding to the database parameter buffer pool size, a value point A may be (0.5, 0, 0), and the value range corresponding to the buffer pool size is 16MB to 128MB. Then, according to the preset encoding rules, the value point is converted into a specific database parameter configuration. For example, the specific database parameter configuration corresponding to the value point A = 16MB + (128MB-16MB) × 0.5 = 72MB. The specific database parameter configuration of each value point in the calculated value space is used as the candidate database parameter of each value point. Next, the generated candidate database parameters are applied to the database parameter configuration cluster. Collect all query statements of the database task processing cluster to create a performance indicator function. Finally, execute these query tasks in the database parameter configuration cluster, and record the execution indicator score of the performance indicator function for each query task.

[0136] By determining the value space of the traversed value point, the search range of the parameter can be controlled more precisely, avoiding blind search and improving search efficiency. In addition, the preset encoding rules accurately convert the value point into a specific database parameter configuration, ensuring that the parameter configuration of each test is clear and executable.

[0137] In one embodiment, reference Figure 3 ,The framework structure of the parameter configuration method in a multi-computing cluster environment mainly includes a database task processing cluster, a database parameter configuration cluster, an object storage, a parameter optimization module, and a monitoring and feedback loop, among which:

[0138] The database task processing cluster is mainly used for users' daily database operations and undertakes major business needs.

[0139] The database parameter configuration cluster is mainly used for optimization testing of database parameter configuration. It does not directly participate in business operations, but shares the same object storage data with the database task processing cluster. In this application, it has the same number of hosts and specifications as the corresponding database task processing cluster to ensure that the optimization test environment simulates the real production environment as much as possible.

[0140] Object storage, as the data sharing layer between the database task processing cluster and the database parameter configuration cluster, ensures that the data inserted in the database task processing cluster can also be accessed and operated by the database parameter configuration cluster to achieve data consistency.

[0141] The parameter optimization module is responsible for optimizing the database parameters of the database parameter configuration cluster using the particle swarm optimization (PSO) algorithm. It includes the following submodules:

[0142] Parameter space definition module: Determine the database parameters that need to be optimized and their value ranges.

[0143] Parameter encoding module: maps the parameter value range to the value space to facilitate the operation of the particle swarm algorithm.

[0144] Particle swarm initialization module: Create a particle swarm, each particle represents a possible parameter configuration, that is, one of the value points in the value space.

[0145] Fitness function creation module: Builds a performance indicator function based on the actual query statements of the database task processing cluster to evaluate the performance of parameter configuration.

[0146] Particle performance evaluation module: Tests the parameter configuration represented by each particle and calculates its execution index score.

[0147] Particle swarm evolution module: Use the PSO algorithm to update the speed and position of particles and find a better parameter configuration.

[0148] Boundary processing module: When the particle position exceeds the valid value range of the parameter, measures are taken to ensure the legitimacy of the particle position.

[0149] Optimal configuration selection module: selects the parameter configuration with the best performance from all particles, that is, the parameter configuration represented by the target value point.

[0150] Verification and deployment module: Verifies the validity of the optimal parameter configuration on the database parameter configuration cluster and synchronizes the configuration to the database task processing cluster.

[0151] The monitoring and feedback loop is used to monitor the actual operation of the database task processing cluster, and continuously adjust the parameter optimization strategy of the database parameter configuration cluster according to changes in business needs, forming a dynamic optimization closed loop.

[0152] In an exemplary embodiment, Figure 4 As shown, it includes steps 402 to 408. Among them:

[0153] Step 402: for each database parameter in the database to be configured, determine the value range of the database parameter; according to the value range of the database parameter, determine the preset coding rule corresponding to the database parameter; according to the preset coding rule, feature code the value range of the database parameter to obtain the value space corresponding to the database parameter;

[0154] Step 404, obtaining multiple query tasks in a preset database task processing cluster, and receiving multiple performance indicator information for the database to be configured; obtaining initial functions corresponding to the multiple performance indicator information, the initial function including function items corresponding to each performance indicator information; according to the multiple query tasks, respectively assigning respective weight coefficients to each function item, and obtaining a performance indicator function for the database to be configured;

[0155] Step 406: for each value space, traverse each value point in the value space, determine the value space where the traversed value point is located, and convert the traversed value point into a candidate database parameter according to a preset coding rule corresponding to the value space where the traversed value point is located; execute multiple query tasks according to the candidate database parameters to obtain the execution index score of the performance index function under the candidate database parameters;

[0156] Step 408, when the traversal is completed, obtain the execution index score threshold of each function item in the performance index function; compare the execution index score of each function item in the performance index function under the database parameter represented by each value point in the target value space with the execution index score threshold, and determine the candidate value points whose execution index scores of each function item are greater than the execution index score threshold; obtain the custom proportional coefficient of each function item in the multiple performance index information; according to the custom proportional coefficient of each function item in the multiple performance index information, perform weighted summation of the execution index score of each function item in the performance index function under the database parameter represented by each value point in the target value space, and obtain the target execution index score of the performance index function under the database parameter represented by each value point in the target value space; take the value point represented by the database parameter corresponding to the maximum target execution index score as the target value point.

[0157] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0158] Based on the same inventive concept, the embodiment of the present application also provides a parameter configuration device in a multi-computing cluster environment for implementing the parameter configuration method in the multi-computing cluster environment involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations of the embodiments of the parameter configuration device in one or more multi-computing cluster environments provided below can refer to the limitations of the parameter configuration method in the multi-computing cluster environment above, and will not be repeated here.

[0159] In an exemplary embodiment, Figure 5 As shown, a parameter configuration device in a multi-computing cluster environment is provided, including: a first determination module 502, a second determination module 504, an execution module 506 and a configuration module 508, wherein:

[0160] A first determination module 502 is used to determine the value space of each database parameter in the database to be configured;

[0161] The second determination module 504 is used to obtain multiple query tasks in a preset database task processing cluster, and determine a performance indicator function for the database to be configured according to the multiple query tasks;

[0162] An execution module 506 is used to traverse each value point in each value space, and execute multiple query tasks according to the database parameters represented by the traversed value points to obtain the execution index score of the performance index function under the database parameters represented by the traversed value points;

[0163] Configuration module 508 is used to determine the target value point in the value space after the traversal is completed according to the execution index score of the performance index function under the database parameters represented by each value point in the value space, and perform parameter configuration on the database to be configured according to the database parameters represented by the target value point.

[0164] In one of the embodiments, the first determination module 502 is used to determine the value range of the database parameter for each database parameter in the database to be configured; determine the preset encoding rule corresponding to the database parameter based on the value range of the database parameter; and perform feature encoding on the value range of the database parameter according to the preset encoding rule to obtain the value space corresponding to the database parameter.

[0165] In one embodiment, the second determination module 504 is used to receive multiple performance indicator information for the database to be configured; obtain an initial function corresponding to the multiple performance indicator information, the initial function including a function item corresponding to each performance indicator information; and assign a respective weight coefficient to each function item according to multiple query tasks to obtain a performance indicator function for the database to be configured.

[0166] In one embodiment, the configuration module 508 is used to obtain the execution index score threshold of each function item in the performance index function; compare the execution index score of each function item in the performance index function under the database parameters represented by each value point in the targeted value space with the execution index score threshold, and determine the candidate value points where the execution index score of each function item is greater than the execution index score threshold; determine the target value point in the targeted value space based on the execution index score of each function item in the performance index function under the database parameters represented by the candidate value points.

[0167] In one embodiment, the configuration module 508 is used to obtain a custom proportional coefficient for each function item in a plurality of performance indicator information; based on the custom proportional coefficient for each function item in the plurality of performance indicator information, a weighted sum is performed on the execution indicator score of each function item in the performance indicator function under the database parameter represented by each value point in the target value space to obtain a target execution indicator score of the performance indicator function under the database parameter represented by each value point in the target value space; and the value point represented by the database parameter corresponding to the maximum target execution indicator score is used as the target value point.

[0168] In one of the embodiments, the execution module 506 is used to determine the value space where the traversed value point is located, and convert the traversed value point into a candidate database parameter according to a preset encoding rule corresponding to the value space where the traversed value point is located; based on the candidate database parameters, multiple query tasks are executed to obtain the execution index score of the performance index function under the candidate database parameters.

[0169] Each module in the parameter configuration device in the multi-computing cluster environment can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0170] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 6 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data related to parameter configuration in a multi-computing cluster environment. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a parameter configuration method in a multi-computing cluster environment is implemented.

[0171] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0172] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0173] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0174] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0175] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0176] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0177] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0178] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A parameter configuration method in a multi-computing cluster environment, characterized in that: The method comprises: Determine the value space of each database parameter in the database to be configured; Acquire multiple query tasks in a preset database task processing cluster, and determine a performance indicator function for the database to be configured according to the multiple query tasks; For each of the value spaces, each value point in the value space is traversed, and the multiple query tasks are executed according to the database parameters represented by the traversed value points to obtain the execution index scores of the performance index functions under the database parameters represented by the traversed value points; When the traversal is completed, the target value point is determined in the target value space according to the execution index score of the performance index function under the database parameters represented by each value point in the target value space, and the parameters of the database to be configured are configured according to the database parameters represented by the target value point.

2. The method according to claim 1, characterized in that The determining of the value space of each database parameter in the database to be configured includes: For each database parameter in the database to be configured, determining a value range of the database parameter; Determine the preset encoding rule corresponding to the database parameter according to the value range of the database parameter; According to the preset encoding rule, the value range of the targeted database parameter is feature-encoded to obtain the value space corresponding to the targeted database parameter.

3. The method according to claim 1, characterized in that The step of determining a performance indicator function for the database to be configured according to the multiple query tasks includes: Receiving a plurality of performance indicator information for the database to be configured; Acquire initial functions corresponding to the plurality of performance indicator information, wherein the initial function includes function items corresponding to each performance indicator information; According to the multiple query tasks, a respective weight coefficient is assigned to each function item to obtain a performance indicator function for the database to be configured.

4. The method according to claim 3, characterized in that The execution index score of the performance index function includes the execution index score of each function item in the performance index function; Determining a target value point in the targeted value space according to the execution index score of the performance index function under the database parameter represented by each value point in the targeted value space includes: Obtaining the execution index score threshold of each function item in the performance index function; Compare the execution index score of each function item in the performance index function under the database parameter represented by each value point in the value space with the execution index score threshold, and determine the candidate value points where the execution index score of each function item is greater than the execution index score threshold; According to the execution index score of each function item in the performance index function under the database parameters represented by each candidate value point, a target value point is determined in the targeted value space.

5. The method according to claim 4, characterized in that The step of determining a target value point in the target value space according to the execution index score of each function item in the performance index function under the database parameter represented by each candidate value point includes: Obtaining a custom proportional coefficient for each function item in the plurality of performance indicator information; According to the respective custom proportional coefficients of each function item in the multiple performance indicator information, weighted summation is performed on the respective execution indicator scores of each function item in the performance indicator function under the database parameters represented by each value point in the target value space, so as to obtain the target execution indicator score of the performance indicator function under the database parameters represented by each value point in the target value space; The value point represented by the database parameter corresponding to the maximum target execution index score is taken as the target value point.

6. The method according to claim 1, characterized in that The executing the plurality of query tasks according to the database parameters represented by the traversed value points to obtain the execution index scores of the performance index functions under the database parameters represented by the traversed value points includes: Determine the value space where the traversed value point is located, and convert the traversed value point into a candidate database parameter according to a preset encoding rule corresponding to the value space where the traversed value point is located; The multiple query tasks are executed according to the candidate database parameters to obtain execution index scores of the performance index function under the candidate database parameters.

7. A parameter configuration device in a multi-computing cluster environment, characterized in that: The device comprises: A first determination module is used to determine the value space of each database parameter in the database to be configured; A second determination module is used to obtain a plurality of query tasks in a preset database task processing cluster, and determine a performance indicator function for the database to be configured according to the plurality of query tasks; An execution module is used to traverse each value point in the value space for each of the value spaces, and execute the multiple query tasks according to the database parameters represented by the traversed value points to obtain the execution index score of the performance index function under the database parameters represented by the traversed value points; A configuration module is used to determine the target value point in the value space after the traversal is completed, according to the execution index score of the performance index function under the database parameters represented by each value point in the value space, and perform parameter configuration on the database to be configured according to the database parameters represented by the target value point.

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

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

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

Images