Performance test method, device and cluster

Abstract

The invention provides a performance testing method and device and a cluster. The method comprises the following steps: receiving configuration information input by a user corresponding to a service system, wherein the configuration information comprises a success rate threshold; in the first test stage, the N service request ends are instructed to send service requests to the service system uninterruptedly; wherein N is an integer greater than or equal to 1, and the service system is used for receiving and processing service requests sent by N service request ends by using resources to obtain a processing result of the service requests; when the ratio of the number of the successful processing results obtained by the service system in the first unit time length to the total number of the processing results obtained in the first unit time length is greater than or equal to a success rate threshold value, obtaining a performance test result of the service system based on the total number of the processing results obtained by the service system in the first unit time length; wherein the successful processing result is a processing result indicating that the service request is successfully processed. The method can improve the accuracy of the performance test result.

Description

Technical Field

[0001] This application relates to the field of computer technology, and particularly to a performance testing method, system and cluster. Background Art

[0002] The performance testing of business systems is of great significance. The performance testing of business systems can help determine the maximum load that a business system can handle, providing theoretical support for planning the resources, capacity and expansion of the business system. The performance testing of business systems can also determine the performance bottlenecks of business systems, helping to optimize and improve the business systems targeted.

[0003] Currently, the operation of the performance testing scheme for business systems is cumbersome and requires high requirements for testers. Moreover, the accuracy of the performance testing results obtained by the current performance testing scheme for business systems is low, and there is a large difference from the true performance of the business system. Summary of the Invention

[0004] This application provides a performance testing method, device and cluster, which can improve the accuracy of performance testing results.

[0005] In a first aspect, a performance testing method for a business system is provided, and the business system corresponds to preset resources; the method includes: receiving configuration information input by a user corresponding to the business system, where the configuration information includes a success rate threshold; in a first testing stage, instructing N business request terminals to continuously send business requests to the business system; where N is an integer greater than or equal to 1, and the business system is used to receive and process the business requests sent by the N business request terminals using the resources to obtain processing results of the business requests; when the ratio of the number of successfully processed results obtained by the business system within a first unit time period to the total number of processing results obtained within the first unit time period is greater than or equal to the success rate threshold, based on the total number of processing results obtained by the business system within the first unit time period, obtaining a performance testing result of the business system; where a successfully processed result is a processing result indicating that the business request is processed successfully, and the first unit time period belongs to the first testing stage.

[0006] In this method, when the success rate of the processing results of the business requests by the business system meets the success rate threshold expected by the user, the number of processing results of the business requests by the business system is used to obtain the performance testing result. That is to say, the obtained performance testing result is the result obtained by performing performance testing when the business system meets the user's requirements for the business success rate. The performance testing result obtained in this way can truly reflect the capabilities of the business system, that is, the performance testing result obtained in this way has high accuracy.

[0007] In a possible implementation, the configuration information further includes: a usage rate threshold of a first resource; the method further includes: identifying a security processing result from the processing results obtained by the service system within a first unit time period; wherein, the usage rate of the first resource when the service system processes a service request corresponding to the security processing result is less than the usage rate threshold; when the ratio of the number of successfully processed results obtained by the service system within the first unit time period to the total number of processed results obtained within the first unit time period is greater than or equal to a success rate threshold, based on the total number of processed results obtained by the service system within the first unit time period, including: when the ratio of the number of securely successfully processed results obtained by the service system within the first unit time period to the total number of security processing results obtained within the first unit time period is greater than or equal to the success rate threshold, obtaining a performance test result of the service system based on the total number of security processing results obtained by the service system within the first unit time period; wherein, a securely successfully processed result is a security processing result indicating that the service request is processed successfully.

[0008] If the resource usage rate when the service system processes the service request is less than the resource usage rate threshold, it indicates that the service system is within a safe range when processing the service request and the risk of downtime is low. Based on the number of processed results of the service system within the unit time period at this time, a performance test of the service system is obtained, so that the performance test result can reflect the performance of the service system within the safe range. Based on this performance test result, when the user sets the service capacity of the service system, the service system can be ensured to be within the safe range, thereby ensuring the stable and persistent operation of the service.

[0009] In a possible implementation, the method further includes: in a second test phase, instructing M service request terminals to continuously send service requests to the service system; wherein, M is an integer greater than N; the service system is used to receive and process the service requests sent by the M service request terminals by using resources to obtain processing results of the service requests; the second test phase is the next test phase after the first test phase; when the ratio of the number of successfully processed results obtained by the service system within a second unit time period to the total number of processed results obtained within the second unit time period is greater than or equal to the success rate threshold, obtaining a performance test result of the service system based on the total number of processed results obtained by the service system within the second unit time period and the total number of processed results obtained within the first unit time period; the second unit time period belongs to the second test phase.

[0010] The service system can be tested in phases. Among them, the number of service request terminals can be gradually increased stage by stage, thereby increasing the speed of sending service requests to the service system to detect the limit capacity of the service system.

[0011] In a possible implementation, the method further includes: after the change range of the speed at which the service system receives and processes service requests in the first test phase is less than a preset range threshold, starting the second test phase.

[0012] In this implementation, the change range of the speed at which the service system processes service requests in the current test phase is less than the range threshold, indicating that the speed at which the service system processes service requests in the current test phase has entered a stable state. At this time, the performance of the service system in the current service phase has been accurately tested. At this time, the current test phase can be ended and the test of the next phase can be started.

[0013] In a possible implementation, the method further includes: obtaining the usage rate of the second resource of the service system in the first test phase; obtaining M based on the usage rate of the second resource and N; where the difference between M and N is negatively correlated with the usage rate of the second resource.

[0014] Specifically, if the usage rate of the second resource of the service system in the current test phase is relatively low, it means that the load of the service system in the current test phase is relatively low, that is, when N service request terminals continuously send service requests to the service system, the load of the service system is relatively low. At this time, in the next test phase of the current test phase, the number of service request terminals used to send service requests to the service system can be increased by a large margin. If the usage rate of the second resource of the service system in the current test phase is relatively high, it means that the load of the service system in the current test phase is relatively high. At this time, the number of service request terminals used to send service requests to the service system is increased by a small margin. Thus, the test pressure on the service system is adaptively adjusted.

[0015] In a possible implementation, the type of the second resource includes a preset resource type and / or a user-input resource type.

[0016] In a possible implementation, based on the total number of processing results obtained by the service system in the second unit time period and the total number of processing results obtained in the first unit time period, the performance test result of the service system is obtained, including: when the total number of processing results obtained in the second unit time period is less than the total number of processing results obtained in the first unit time period, determining that the total number of processing results obtained in the first unit time period is the limit capacity of the service system.

[0017] Second aspect, a performance testing device for a service system is provided, where the service system corresponds to preset resources; the device includes: a receiving module, configured to receive configuration information input by a user corresponding to the service system, where the configuration information includes a success rate threshold; an indicating module, configured to, in a first testing stage, instruct N service request terminals to continuously send service requests to the service system; where N is an integer greater than or equal to 1, and the service system is configured to receive and process service requests sent by the N service request terminals by using resources to obtain processing results of the service requests; a obtaining module, configured to, when the ratio of the number of successfully processed results obtained by the service system within a first unit time period to the total number of processed results obtained within the first unit time period is greater than or equal to the success rate threshold, obtain a performance testing result of the service system based on the total number of processed results obtained by the service system within the first unit time period; where a successfully processed result is a processing result indicating that the service request is processed successfully, and the first unit time period belongs to the first testing stage.

[0018] In a possible implementation manner, the configuration information further includes: a usage rate threshold of a first resource; the device further includes an identifying module; where the identifying module is configured to: in the processing results obtained by the service system within a first unit time period, identify security processing results; where the usage rate of the first resource when the service system processes service requests corresponding to the security processing results is less than the usage rate threshold; the obtaining module is configured to: when the ratio of the number of securely successfully processed results obtained by the service system within a first unit time period to the total number of security processing results obtained within the first unit time period is greater than or equal to the success rate threshold, obtain a performance testing result of the service system based on the total number of security processing results obtained by the service system within the first unit time period; where a securely successfully processed result is a security processing result indicating that the service request is processed successfully.

[0019] In a possible implementation manner, the indicating module is further configured to: in a second testing stage, instruct M service request terminals to continuously send service requests to the service system; where M is an integer greater than N; the service system is configured to receive and process service requests sent by the M service request terminals by using resources to obtain processing results of the service requests; the second testing stage is the next testing stage after the first testing stage; the obtaining module is configured to: when the ratio of the number of successfully processed results obtained by the service system within a second unit time period to the total number of processed results obtained within the second unit time period is greater than or equal to the success rate threshold, obtain a performance testing result of the service system based on the total number of processed results obtained by the service system within the second unit time period and the total number of processed results obtained within the first unit time period; the second unit time period belongs to the second testing stage.

[0020] In a possible implementation, the apparatus further includes: an enabling module, configured to enable a second test phase after the change range of the speed at which the service system receives and processes service requests in the first test phase is less than a preset range threshold.

[0021] In a possible implementation, the apparatus further includes: an obtaining module; the obtaining module is configured to: obtain the usage rate of a second resource of the service system in the first test phase; a obtaining module is configured to: obtain M based on the usage rate of the second resource and N; where the difference between M and N is negatively correlated with the usage rate of the second resource.

[0022] In a possible implementation, the type of the second resource includes a preset resource type and / or a resource type input by a user.

[0023] In a possible implementation, the obtaining module is configured to: when the total number of processing results obtained in the second unit time duration is less than the total number of processing results obtained in the first unit time duration, determine the total number of processing results obtained in the first unit time duration as the limit capacity of the service system.

[0024] In a third aspect, a computing device cluster is provided, including at least one computing device, and each computing device includes a processor and a memory; the processor of at least one computing device is configured to execute instructions stored in the memory of at least one computing device, so that the computing device cluster executes the method provided in the first aspect.

[0025] In a fourth aspect, a computer-readable storage medium is provided, including computer program instructions, and when the computer program instructions are executed by the computing device cluster, the computing device cluster executes the method provided in the first aspect.

[0026] In a fifth aspect, a computer program product including instructions is provided, and when the instructions are run by a computer device cluster, the computer device cluster is caused to execute the method provided in the first aspect.

[0027] For the beneficial effects of the second aspect to the fifth aspect, reference may be made to the introduction of the beneficial effects of the first aspect above, which will not be elaborated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 It is a schematic diagram of a system architecture provided by an embodiment of the present application;

[0029] Figure 2 It is a schematic structural diagram of a test apparatus provided by an embodiment of the present application;

[0030] Figure 3 It is a flowchart of a performance test method provided by an embodiment of the present application;

[0031] Figure 4A schematic diagram of the switching during the test phase provided by an embodiment of the present application;

[0032] Figure 5 A schematic diagram of the ultimate capacity provided by an embodiment of the present application;

[0033] Figure 6 A schematic diagram of the structure of a performance testing device provided by an embodiment of the present application;

[0034] Figure 7 A schematic diagram of the structure of a computing device provided by an embodiment of the present application;

[0035] Figure 8 A schematic diagram of the structure of a computing device cluster provided by an embodiment of the present application;

[0036] Figure 9 A schematic diagram of the structure of a computing device cluster connected through a network provided by an embodiment of the present application. Detailed implementation manners

[0037] The solutions provided by the embodiments of the present application will be described below in conjunction with the accompanying drawings. Among them, in the embodiments of the present application, "a plurality of" means two or more, and "a variety of" means two or more. "First", "second", etc. are only used to distinguish similar objects and do not necessarily need to describe a specific order or the number of objects.

[0038] To facilitate the understanding of the solutions provided by the embodiments of the present application, the technical terms that may be involved in the embodiments of the present application will be introduced first.

[0039] Touch height: It refers to applying pressure to the business system in stages under limited resource conditions to obtain the best performance indicators under such conditions, such as the maximum throughput.

[0040] Inflection point: Also known as the ultimate capacity, it is a description of a phenomenon that appears during the performance stress testing process. After applying pressure to any system to a certain limit value, various indicators such as throughput deteriorate sharply, and this point becomes the stress testing inflection point.

[0041] Pressure testing: It is a software testing method, usually used to test the performance and stability of a business system under high load and high pressure. Pressure testing is to simulate a large number of users accessing the business system at the same time, or perform a large number of data processing or calculation operations on the business system, to test indicators such as the load capacity, performance bottleneck, and stability of the business system. Through pressure testing, the bottlenecks and weaknesses of the business system can be found, and then the business system can be optimized to improve the performance and stability of the business system.

[0042] Business system: It refers to a system that corresponds to certain resources and uses the corresponding resources to process business requests and obtain processing results. The business system can be a software system, an application system, etc. The business system runs on one or more computing devices, and the one or more computing devices provide the resources corresponding to the business system.

[0043] Business request end: It refers to a device, equipment, platform, etc. that sends business requests to the business system.

[0044] Latency: Also known as response time (RT), it refers to the time consumed by the business request end from sending a business request to receiving the feedback of the business request. Latency includes the time for the business system to process the business request, the time for the business request to be transmitted in the network, and the time for the feedback to be transmitted in the network. Among them, the unit of latency can be milliseconds (ms).

[0045] Concurrency: It refers to multiple business request ends sending business requests to the business system under test simultaneously to test the performance of the business system under test in processing business requests.

[0046] Concurrency number: It refers to the number of business request ends that send business requests to the business system under test simultaneously.

[0047] Throughput: It refers to the total number of business requests received and processed by the business system per unit time. Throughput is negatively correlated with latency. Common throughputs include requests per second (RPS). Among them, the unit of RPS is hit / s.

[0048] In related technologies, for the performance testing of a business system, testers need to design multiple load models. Then, the business system under test executes various load models, and during the execution of the load models by the business system under test, performance data such as response time, central processing unit (CPU) utilization rate, memory occupancy, etc. are collected. After that, based on the performance data collected in multiple rounds, the performance of the system under different load conditions is analyzed to determine the performance of the business system, such as the limit capacity.

[0049] Among them, designing load models requires research and cumbersome configuration work, and has high requirements for the experience and professional capabilities of personnel. Moreover, it is necessary to manually conduct multiple rounds of different load tests on business scenarios, collect data, calculate the limit capacity, etc., and the operation is cumbersome. When there are many business scenarios to be tested, the efficiency of this solution is very low.

[0050] An embodiment of the present application provides a performance testing method for a business system, which is used to test the user's business system. Through this method, performance testing of the user's business system can be performed based on the configuration information input by the user, and high-accuracy performance test results that meet the user's requirements can be obtained without the user designing a load model.

[0051] Next, the performance testing method provided by the embodiment of the present application will be introduced.

[0052] Figure 1 The system architecture that can be used to implement the performance testing method provided by the embodiment of the present application is shown. As Figure 1 shown, the system architecture includes a business system 100 and a testing device 200.

[0053] The business system 100 can also be referred to as a test case and is the object of performance testing. The business system 100 can process related services, such as online shopping, image rendering, data forwarding services, etc. The business system 100 corresponds to a preset resource A, and the business system 200 uses this resource A to receive and process service requests and send the processing results of the service requests. Among them, the resource A includes computing resources, storage resources, and network resources, etc. Among them, the computing resources refer to processor resources, etc., the storage resources refer to resources such as memory and disks, and the network resources refer to resources such as network cards and bandwidth.

[0054] In one example, the business system 100 can be implemented as an interface platform, such as an application programming interface (API) platform. This platform includes multiple interfaces for processing data forwarding services.

[0055] The business system 100 belongs to user B, and the resource A is a resource built or purchased by the user for the business system 100. Specifically, the business system 100 can be deployed locally by user B. User B can build the resource A locally and deploy the business system 100 using the resource A. The business system 100 can also be deployed in the cloud. User B can purchase or lease the resource A in the cloud and deploy the business system 100 using the resource A.

[0056] In some embodiments, as Figure 1 shown, the business system 100 can be deployed in a computing cluster. The computing cluster can include one or more servers. The business system 100 is specifically deployed in at least one of the servers in the computing cluster, and the at least one server provides the resource A for the business system 100.

[0057] The test device 200 can be any state, device, platform or cluster with data processing capabilities. The test device 200 is used to perform performance testing on the business system 100. Among them, the test device 200 can create a business request end and instruct the business request end to continuously send business requests to the business system 100 to perform performance testing on the business system 100. Among them, continuously sending business requests means that whenever the processing result of a business request is received, the next business request is immediately sent. Specifically, the business request end sends a business request to the business system 100. When the business request end receives the processing result of the business request from the business system 100, it sends another business request to the business system.

[0058] User B corresponding to the business system 100 can request or trigger the test device 200 to perform performance testing on the business system 100. User B can input a test request to the test device 200, and this test request can trigger the test device 200 to perform performance testing on the business system 100.

[0059] Among them, the test request can include the identifier of the business system 100, so that the test device 200 can identify the business system 100 based on the identifier of the business system 100 and perform testing on the business system 100. In one example, the identifier of the business system 100 can be the address of the business interface of the business system 100. The business interface refers to the interface through which the business system 100 receives business requests. Through the address of the business interface, the test device 200 can send business requests to the business system 100. Among them, the address of the business interface can be the Internet Protocol (IP) address of the business interface.

[0060] User B can input configuration information to the test device 200, and this configuration information includes the configuration of performance testing by User B. After receiving the configuration information, the test device 200 can perform performance testing on the business system 100 according to the configuration of User B based on the configuration information. Exemplarily, the configuration information can be included in the test request. Exemplarily, User B can send the configuration information to the test device 200 before sending the test request to the test device 200.

[0061] The configuration information can include at least one business request logic. Among them, the business request logic corresponds to the business processing logic of the business system 100. Taking the business of online shopping as an example, the business processing logic includes the logic of providing a product display page in response to a product display request, the logic of selecting a product based on a product selection request, the logic of making a payment based on a payment request, etc. Correspondingly, the business request logic includes the logic for generating a product display request, the logic for generating a product selection request, the logic for generating a payment request, etc.

[0062] When the configuration information includes multiple service request logics, the configuration information includes the orchestration result of the multiple service request logics. Among them, the orchestration result of the multiple service request logics refers to the execution order among the multiple service request logics. Taking the logic for generating a product display request, the logic for generating a product selection request, and the logic for generating a payment request as an example, their execution order is successively: the logic for generating a product display request, the logic for generating a product selection request, and the logic for generating a payment request.

[0063] In some embodiments, the service request logic can be implemented by a script. The orchestration result of the service request logic can also be referred to as the script orchestration logic.

[0064] The test device 200 can generate a service request based on the service request logic, and then send the service request to the service system 100 to test the performance of the service system 100.

[0065] The configuration information can include a success rate threshold. The processing result of the service system 100 for processing a service request may be successful or failed. The service success rate refers to the ratio of the number of successful processing results in the processing results obtained by the service system 100 for processing service requests within a unit time period to the total number of processing results obtained by the service system 100 for processing service requests within the unit time period. If the ratio (i.e., the service success rate) is greater than or equal to the success rate threshold, it indicates that the service system 100 can effectively process service requests.

[0066] The test device 200 can receive the processing result of the service system 100 for processing a service request from the service system 100 and calculate the service success rate. Then, based on the service processing results within the unit time period when the service success rate is greater than the threshold, the performance test result of the service system 100 is obtained.

[0067] In some embodiments, the configuration information may further include a resource utilization rate threshold. Among them, the resource utilization rate can be one or more of the computing resource utilization rate, the storage resource utilization rate, and the network resource utilization rate. The resource utilization rate refers to the ratio of the resources used by the service system 100 when processing a service request to the maximum resources that the service system 100 can use. If the ratio is greater than or equal to the resource utilization rate threshold, it indicates that the load of the service system 100 when processing this service request is too high, which is unsafe and there is a risk of downtime. Correspondingly, if the resource utilization rate of the service system 100 when processing this service request is greater than or equal to the resource utilization rate threshold, the processing result of processing this service request is unsafe. If the resource utilization rate of the service system 100 when processing this service request is less than the resource utilization rate threshold, the processing result of processing this service request is safe.

[0068] The test device 200 can receive the resource utilization rate of the service system 100 when the service system 100 processes a service request, and determine whether the processing result of the service request is a secure processing result based on the resource utilization rate. Then, based on the secure processing result, the performance test result of the service system 100 is obtained.

[0069] The test device 200 can be used to obtain the limit capacity of the service system 100. Among them, the limit capacity of the service system 100 refers to the performance limit of the service system 100.

[0070] Among them, the test device 200 can test the service system 100 in stages to obtain the limit capacity. Refer to Figure 2 , the test device 200 includes a configurator 210, an executor 220, a state machine 230, and a scheduler 240. Among them, the configurator 210 is used to receive the configuration information sent by the user, and based on the configuration information, instruct the executor 220 to send a service request to the service system 100, and based on the configuration information, instruct the state machine 230 to calculate the performance test results of each stage, and obtain the limit capacity based on the performance test results of each stage. In addition, the state machine 230 is also used to provide a performance test report when the limit capacity is obtained. The performance test includes visual performance metric information (such as throughput, latency, etc.). The scheduler 240 is used to instruct the executor 220 to increase or decrease the speed of sending service requests to the service system 100, so as to adjust the service pressure of the service system 100, and test the limit capacity of the service system 100.

[0071] The above example introduces the system architecture provided by the embodiments of the present application. Next, combined with this system architecture, the performance test method provided by the embodiments of the present application is introduced. Among them, this method is executed by the test device 200. As Figure 3 shown, this method includes the following steps.

[0072] Step 301, the test device 200 receives the configuration information input by user B corresponding to the service system 100, and the configuration information includes a success rate threshold.

[0073] In some embodiments, the test device 200 can be located at the remote end of user B. User B can input the configuration information on the terminal device local to user B and send the configuration information to the test device 200 through the terminal device. In some embodiments, the test device 200 is located locally to user B, and user B can input the configuration information on the test device 200.

[0074] Step 302, in test phase C1, the test device 200 instructs N service request terminals to continuously send service requests to the service system 100; where N is an integer greater than or equal to 1, and the service system 100 is configured to receive and process the service requests sent by the N service request terminals using resource A to obtain the processing results of the service requests.

[0075] Among them, the service request terminals can be created by the test device 200. The service request terminals can generate service requests based on the service request logic in the configuration information. For example, if the service request logic is the logic for generating a product display request, the generated service request is a product display request. Another example is that if the service request logic is the logic for generating a product selection request, the generated service request is a product selection request. And so on, which will not be elaborated here one by one.

[0076] And send service requests to the service system 100. Whenever a service request terminal receives the processing result of a service request from the service system 100, it immediately sends another service request to the service system 100, thus continuously sending service requests to the service system 100.

[0077] The larger the value of N, the more service requests are sent to the service system 100 per unit time, and thus the larger the number of service requests that the service system 100 needs to process per unit time.

[0078] In some embodiments, the test device 200 can perform performance testing on the service system 100 in stages. Among them, the number of service request terminals used to send service requests to the service system 100 can be increased gradually by stage to gradually increase the test pressure on the service system 100 and test the limit capacity of the service system 100.

[0079] In some embodiments, test phase C1 can be the initial phase, that is, the first phase. N can be a preset value, such as 1, 2, or 3, etc. In some embodiments, test phase C2 can be the next phase after test phase C1, and the value of N is determined by the number of service request terminals in test phase C1 and the performance test results. Specific details will be introduced below and will not be elaborated here.

[0080] The service system 100 receives and processes service requests sent to the service system 100 by using the resource A corresponding to the service system, and obtains the processing results of the service requests. Among them, the processing results can be divided into successful processing results and failed processing results. For example, if the service request is a product display request, its successful processing result is to send a product display page to the service request end that sends the service request, and its failed processing result is to send a failure indication to the service request end that sends the service request. Another example is that if the service request is a product selection request, its successful processing result is to send a product selection success indication to the service request end that sends the service request, and its failed processing result is to send a selection failure indication to the service request end that sends the service request. And so on, which will not be enumerated one by one here.

[0081] Step 303, when the ratio of the number of successful processing results obtained by the service system 100 within the unit time period T1 to the total number of processing results obtained within the unit time period T1 is greater than or equal to the success rate threshold, the testing device 200 obtains the performance test result of the service system 100 based on the total number of processing results obtained by the service system 100 within the unit time period T1; where the successful processing result is a processing result indicating that the service request is successfully processed, and the unit time period T1 belongs to the test phase C1.

[0082] Among them, the unit time period T1 is preset, such as 1 second or 1 millisecond, etc. In some embodiments, the unit time period T1 is 1 second, and the total number of processing results obtained within the unit time period T1 can be the number of responses per second (RPS).

[0083] The ratio of the number of successful processing results obtained within the unit time period T1 to the total number of processing results obtained within the unit time period T1 being greater than or equal to the success rate threshold indicates that the service system 100 effectively processes service requests within this unit time period. The performance test result obtained based on the total number of processing results obtained within this unit time period can reflect the true performance of the service system 100 in processing service requests. Specifically, when the number of service requests is so large that the performance of the service system 100 is difficult to handle, most of the processing results of the service system 100 in processing service requests are failed processing results. In this case, although a large number of processing results can be received within the unit time period, most of these processing results are failed processing results. Therefore, the performance test result obtained based on the number of processing results received within this unit time period is seriously distorted and far from the true performance of the service system.

[0084] In the performance testing method provided in the embodiments of the present application, user B sets the success rate threshold, that is, the success rate threshold reflects the business success rate expected by user B. The ratio of the number of successfully processed results obtained within the unit time period T1 to the total number of processed results obtained within the unit time period T1 is greater than or equal to the success rate threshold, indicating that the success rate of the business system 100 in processing the business within the unit time period T1 meets the success rate expected by the user. In this case, the total number of processed results obtained within the unit time period T1 is used to obtain the performance test result of the business system 100, which can truly reflect the performance of the business system 100, and the reflected performance is the performance that can meet the success rate expected by user B.

[0085] Among them, the test phase C1 consists of multiple unit time periods T1. Among them, the total number of processed results of all unit time periods T1 whose ratio of the total number of processed results is greater than or equal to the success rate threshold is used to obtain the performance test result of the business system 100. For example, the average value of the total number of processed results of all unit time periods T1 whose ratio of the total number of processed results is greater than or equal to the success rate threshold is used as the performance test result of the business system 100 in the test phase C1.

[0086] In some embodiments, the configuration information further includes: the usage rate threshold of the first resource. Among them, the first resource may be at least one of computing resources, storage resources, and network resources. The performance testing method provided in the embodiments of the present application further includes: identifying security processed results among the processed results obtained by the business system 100 within the unit time period T1; wherein, the usage rate of the first resource when the business system 100 processes the service request corresponding to the security processed result is less than the usage rate threshold. Among them, step 303 includes: when the ratio of the number of security successfully processed results obtained by the business system within the unit time period T1 to the total number of security processed results obtained within the unit time period T1 is greater than or equal to the success rate threshold, based on the total number of security processed results obtained by the business system 100 within the unit time period T1, obtaining the performance test result of the business system 100; wherein, the security successfully processed result is a security processed result indicating that the service request is processed successfully.

[0087] Specifically, when the resource utilization rate of the service system 100 is too high during the processing of a service request, the processing of the service request by the service system 100 is unsafe and there are risks such as system crashes. For the convenience of description, if the resource utilization rate of the service system 100 is too high when processing a certain service request, the processing result obtained by processing this service request is called an unsafe processing result. If the resource utilization rate of the service system 100 is not too high when processing a certain service request, it means that the service system is safe during the processing of the service request and the risk of system crashes is low. Then the processing result obtained by processing this service request is called a safe processing result. By determining whether it is greater than the utilization rate threshold of the first resource in the configuration information, it is judged whether the utilization rate of the first resource of the service system 100 is too high when processing a certain service request. That is to say, if the utilization rate of the first resource of the service system 100 is less than the utilization rate threshold of the first resource when processing a certain service request, the processing result obtained by the service system 100 for processing this service request is a safe processing result. If the utilization rate of the first resource of the service system 100 is greater than or equal to the utilization rate threshold of the first resource when processing a certain service request, the processing result obtained by the service system 100 for processing this service request is an unsafe processing result.

[0088] Among them, if the processing result is both a safe processing result and a successful processing result, then this processing result can be called a safe and successful processing result. That is, when the utilization rate of the first resource of the service system 100 is less than the utilization rate threshold of the first resource and the processing result of this service request is a successful processing result, the processing result of this service request is a safe and successful processing result.

[0089] In this embodiment, the testing device 200 can obtain the utilization rate of the first resource of the service system 100 when processing a service request, and judge whether the obtained utilization rate is less than the utilization rate threshold of the first resource, so as to identify whether the processing result of this service request is a safe processing result. And when the processing result of this service request is a successful processing result, it is confirmed that the processing result of this service request is a safe and successful processing result.

[0090] When determining the performance test result, consider the number of safe and successful processing results and the proportion of the number of safe and successful processing results in the total number of safe processing results, so that the obtained performance test result reflects the performance of the service system when processing services safely. Based on this performance test result, set the service capacity of the service system, which can ensure that the service system processes service requests safely and avoid or reduce problems such as system crashes.

[0091] In some embodiments, refer to Figure 3, in step 304, during test phase C2, the test device 200 instructs M service request terminals to continuously send service requests to the service system 100; where M is an integer greater than N; the service system 100 receives and processes the service requests sent by the M service request terminals using resource A; test phase C2 is the next test phase after the above-mentioned test phase C1.

[0092] As described above, the test device 200 performs performance testing on the service system 100 in stages. After test phase C1 ends, the test device 200 can enter the next test phase of test phase C1 (i.e., test phase C2).

[0093] In an example of this embodiment, when the change amplitude of the speed at which the service system 100 receives and processes service requests during test phase C1 is less than a preset amplitude threshold, the test device 200 activates test phase C2. That is, when N service request terminals continuously send service requests to the service system 100, when the speed at which the service system 100 receives and processes service requests enters a stable state, the next test phase, i.e., test phase C2, can be activated.

[0094] In one example, it can be set that the speed at which the service system 100 processes service requests is characterized by RT and RPS. The multi-stage testing of the service system 100 can be as Figure 4 shown. When during test phase C1, the RPS and / or RT at which the service system 100 processes service requests are in a stable state, test phase C2 is activated. That is, the testing of the service system 100 enters test phase C2 from test phase C1.

[0095] In some embodiments, the size of M is determined by the size of N and the usage rate of the second resource of the service system 100 during test phase C1. Where the second resource can be at least one of computing resources, storage resources, and network resources. In one example, the second resource can be a pre-set resource type. In another example, the second resource can be a resource type input by user B.

[0096] In this embodiment, the test device 200 may obtain the usage rate of the second resource of the service system 100 in the test phase C1. Then, based on the usage rate of the second resource of the service system 100 in the test phase C1 and N, M is obtained. The difference between M and N is negatively correlated with the usage rate of the second resource of the service system 100 in the test phase C1. The difference between M and N is the difference obtained by subtracting N from M. Specifically, if the usage rate of the second resource of the service system 100 in the test phase C1 is relatively low, it indicates that the load of the service system 100 in the test phase C1 is relatively low. That is, when N service request terminals continuously send service requests to the service system 100, the load of the service system 100 is relatively low. At this time, in the next test phase after the test phase C1, that is, the test phase C2, the number of service request terminals used to send service requests to the service system 100 can be increased by a large margin, that is, the concurrency can be increased by a large margin. If the usage rate of the second resource of the service system 100 in the test phase C1 is relatively high, it indicates that the load of the service system 100 in the test phase C1 is relatively high. At this time, the number of service request terminals used to send service requests to the service system 100 is increased by a small margin. Thus, the test pressure on the service system 100 is adaptively adjusted.

[0097] In some embodiments, the configuration information further includes the test duration. The difference between M and N is negatively correlated with the test duration. The difference between M and N is the difference obtained by subtracting N from M. That is to say, the longer the test duration, the smaller the difference in the number of service request terminals between two adjacent test phases. Thus, when entering the next test phase, the service request terminals increase incrementally with fine granularity, so that the limit capacity of the service system 100 can be tested with finer granularity, and a more accurate limit capacity can be obtained.

[0098] Step 305, when the ratio of the number of successfully processed results obtained by the service system 100 within the unit time period T2 to the total number of processed results obtained within the unit time period T2 is greater than or equal to the success rate threshold, based on the total number of processed results obtained by the service system 100 within the unit time period T2 and the total number of processed results obtained within the above-mentioned unit time period T1, the performance test result of the service system 100 is obtained; the unit time period T2 belongs to the test phase C2.

[0099] The unit time period T2 is preset, such as 1 second or 1 millisecond, etc. In some embodiments, the unit time period T2 is 1 second, and the total number of processed results obtained within the unit time period T2 can be per RPS.

[0100] The total number of processed results obtained by the service system 100 within the unit time period T2 and the total number of processed results obtained within the above-mentioned unit time period T1 can be compared.

[0101] If the total number of processing results obtained by the service system 100 within the unit time period T2 is greater than the total number of processing results obtained within the above-mentioned unit time period T1, it indicates that the service system 100 has not reached its limit capacity when M service request terminals continuously send service requests to the service system 100. At this time, in the next test phase, the number of service request terminals used to send service requests to the service system 100 can be further increased to detect the limit capacity of the service system 100.

[0102] In one example, if the total number of processing results obtained by the service system 100 within the unit time period T2 is less than the total number of processing results obtained within the above-mentioned unit time period T1, it indicates that the total number of processing results obtained within the unit time period T1 is the limit capacity of the service system 100, that is, the maximum effective processing capacity of the service system 100 has been reached. At this time, it can be determined that the total number of processing results obtained within the unit time period T1 is the limit capacity of the service system 100.

[0103] In one example, if the total number of processing results obtained by the service system 100 within the unit time period T2 is less than the total number of processing results obtained within the above-mentioned unit time period T1, one or more test phases can be executed again, and the number of service request terminals used to send service requests to the service system 100 in each test phase is greater than the number of service request terminals used to send service requests to the service system 100 in the previous test phase of this test phase. Then, compare the total number of processing results obtained within the unit time in this one or more test phases with the total number of processing results obtained within the above-mentioned unit time period T1. Among them, the total number of processing results obtained within the unit time in this one or more test phases is the total number in the case where the ratio of the number of successfully processed results obtained within the unit time to the total number of processing results obtained within the unit time is greater than or equal to the success rate threshold.

[0104] If the total number of processing results obtained within the unit time in this one or more test phases is less than the total number of processing results obtained within the above-mentioned unit time period T1, it can be determined that the total number of processing results obtained within the unit time period T1 is the limit capacity of the service system 100.

[0105] In an example of this example, refer to Figure 5, it is possible to set that the total number of processing results obtained within a unit time is RPS. The RPS in the test phase when the number of service request terminals for sending service requests to the service system 100 is 116 is less than the RPS in the test phase when the number of service request terminals for sending service requests to the service system 100 is 96. Moreover, the RPS in the test phase when the number of service request terminals for sending service requests to the service system 100 is 138 is less than the RPS in the test phase when the number of service request terminals for sending service requests to the service system 100 is 96. This indicates that the RPS in the test phase when the number of service request terminals for sending service requests to the service system 100 is 96 is the limit capacity of the service system 100.

[0106] Among them, Figure 5 in it, TP90 refers to the 90th percentile of the delay, that is, 90% of the delays are lower than TP90. TP99 refers to the 99th percentile of the delay, that is, 99% of the delays are lower than TP99.

[0107] In some embodiments, after obtaining the limit capacity of the service system 100, the test device 200 can provide a test report to user B. Among them, the test report may include the performance test results (such as RPS, TP) of each test phase, as well as the resource utilization rate, service success rate, etc. of each test phase. Among them, the RPS, TP, resource utilization rate, and service success rate of each test phase in the test report may be the average RPS, average TP, average resource utilization rate, and average service success rate of this test phase respectively. In one example, the test report may be visual.

[0108] In summary, the performance test method provided by the embodiments of the present application can perform performance tests when the service system meets the user's requirements for the service success rate, so that the obtained performance test results are test results that can meet the user's requirements for the service success rate, improving the accuracy of the performance test results.

[0109] Referring to Figure 6 , the embodiments of the present application also provide a performance test device 600 for a service system. Among them, the service system corresponds to preset resources. As Figure 6 shown, the device 600 includes:

[0110] A receiving module 610, configured to receive configuration information input by a user corresponding to the service system, where the configuration information includes a success rate threshold;

[0111] An indication module 620, configured to, in a first test phase, instruct N service request terminals to continuously send service requests to the service system; where N is an integer greater than or equal to 1, and the service system is configured to receive and process the service requests sent by the N service request terminals by using the resources, so as to obtain a processing result of the service request;

[0112] An obtaining module 630, configured to, when a ratio of a quantity of successfully processed results obtained by the service system within a first unit time period to a total quantity of processed results obtained within the first unit time period is greater than or equal to the success rate threshold, obtain a performance test result of the service system based on the total quantity of processed results obtained by the service system within the first unit time period; where the successfully processed result is a processing result indicating that the service request is successfully processed, and the first unit time period belongs to the first test phase.

[0113] In some embodiments, the configuration information further includes: a usage rate threshold of a first resource; the apparatus 600 further includes an identification module; where the identification module is configured to: in the processed results obtained by the service system within the first unit time period, identify secure processed results; where a usage rate of the first resource when the service system processes the service requests corresponding to the secure processed results is less than the usage rate threshold; the obtaining module 630 is configured to: when a ratio of a quantity of securely successfully processed results obtained by the service system within the first unit time period to a total quantity of secure processed results obtained within the first unit time period is greater than or equal to the success rate threshold, obtain a performance test result of the service system based on the total quantity of secure processed results obtained by the service system within the first unit time period; where the securely successfully processed result is a secure processed result indicating that the service request is successfully processed.

[0114] In some embodiments, the indication module 620 is further configured to: in a second test phase, instruct M service request terminals to continuously send service requests to the service system; where M is an integer greater than N; the service system is configured to receive and process the service requests sent by the M service request terminals by using the resources, so as to obtain a processing result of the service request; the second test phase is a next test phase of the first test phase; the obtaining module 630 is configured to: when a ratio of a quantity of successfully processed results obtained by the service system within a second unit time period to a total quantity of processed results obtained within the second unit time period is greater than or equal to the success rate threshold, obtain a performance test result of the service system based on the total quantity of processed results obtained by the service system within the second unit time period and the total quantity of processed results obtained within the first unit time period; the second unit time period belongs to the second test phase.

[0115] In an example of this embodiment, the apparatus 600 further includes: an enabling module, configured to enable the second test phase after the amplitude of the change in the speed at which the service system receives and processes service requests in the first test phase is less than a preset amplitude threshold.

[0116] In another example of this embodiment, the apparatus 600 further includes: an obtaining module; the obtaining module is configured to: obtain the utilization rate of a second resource of the service system in the first test phase; the obtaining module 630 is configured to: obtain the M based on the utilization rate of the second resource and the N; wherein, the difference between the M and the N is negatively correlated with the utilization rate of the second resource.

[0117] In an example of this example, the type of the second resource includes a preset resource type and / or a resource type input by the user.

[0118] In some embodiments, the obtaining module 630 is configured to: when the total number of processing results obtained in the second unit time period is less than the total number of processing results obtained in the first unit time period, determine the total number of processing results obtained in the first unit time period as the limit capacity of the service system.

[0119] Among them, the receiving module 610, the indicating module 620, and the obtaining module 630 can all be implemented by software or by hardware. Exemplarily, next, taking the receiving module 610 as an example, the implementation manner of the receiving module 610 will be introduced. Similarly, the implementation manners of the indicating module 620 and the obtaining module 630 can refer to the implementation manner of the receiving module 610.

[0120] As an example of a software functional unit, the receiving module 610 may include code running on a computing instance. Among them, the computing instance may include at least one of a physical host (computing device), a virtual machine, and a container. Further, the above computing instance may be one or more. For example, the receiving module 610 may include code running on multiple hosts / virtual machines / containers. It should be noted that the multiple hosts / virtual machines / containers for running this code may be distributed in the same region or in different regions. Further, the multiple hosts / virtual machines / containers for running this code may be distributed in the same available zone AZ or in different AZs, and each AZ includes one data center or multiple geographically close data centers. Usually, one region may include multiple AZs.

[0121] Similarly, multiple hosts / virtual machines / containers used to run the code can be distributed within the same VPC or across multiple VPCs. Usually, one VPC is set up within one region. For cross-region communication between two VPCs within the same region and between VPCs in different regions, communication gateways need to be set up within each VPC, and the interconnection between VPCs is achieved through the communication gateways.

[0122] As an example of a hardware functional unit, the receiving module 610 may include at least one computing device, such as a server. Alternatively, the receiving module 610 may also be a device implemented using an application-specific integrated circuit (ASIC) or a programmable logic device (PLD). Among them, the above PLD may be implemented by a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.

[0123] The multiple computing devices included in the receiving module 610 can be distributed within the same region or across different regions. The multiple computing devices included in the receiving module 610 can be distributed within the same availability zone (AZ) or across different AZs. Similarly, the multiple computing devices included in the receiving module 610 can be distributed within the same VPC or across multiple VPCs. Among them, the multiple computing devices can be any combination of computing devices such as servers, ASICs, PLDs, CPLDs, FPGAs, and GALs.

[0124] It should be noted that in other embodiments, the receiving module 610 can be used to execute Figure 3 any step in the method shown, the indicating module 620 can be used to execute Figure 3 any step in the method shown, and the obtaining module 630 can be used to execute Figure 3 any step in the method shown. The steps to be implemented by the receiving module 610, the indicating module 620, and the obtaining module 630 can be specified as needed, and all functions of the apparatus 600 are implemented by respectively implementing Figure 3 different steps in the method shown.

[0125] This application also provides a computing device 700. As Figure 7As shown, the computing device 700 includes: a bus 702, a processor 704, a memory 706, and a communication interface 708. The processor 704, the memory 706, and the communication interface 708 communicate with each other via the bus 702. The computing device 700 can be a server or a terminal device. It should be understood that the present application does not limit the number of processors and memories in the computing device 700.

[0126] The bus 702 can be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of simplicity of representation, Figure 7 only one line is used to represent it in the figure, but it does not mean that there is only one bus or one type of bus. The bus 702 can include a path for transmitting information between various components of the computing device 700 (for example, the memory 706, the processor 704, and the communication interface 708).

[0127] The processor 704 can include any one or more of a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP).

[0128] The memory 706 can include volatile memory, such as random access memory (RAM). The memory 706 can also include non-volatile memory, such as read-only memory (ROM), flash memory, a hard disk drive (HDD), or a solid state drive (SSD).

[0129] The memory 706 stores executable program code, and the processor 704 executes the executable program code to respectively implement the functions of the aforementioned receiving module 610, indicating module 620, and obtaining module 630, thereby implementing Figure 3 the method shown. That is, the memory 706 stores instructions for executing Figure 3 the method shown.

[0130] The communication interface 708 uses a transceiver module such as, but not limited to, a network interface card or a transceiver to implement communication between the computing device 700 and other devices or a communication network.

[0131] Embodiments of the present application also provide a cluster of computing devices. The cluster of computing devices includes at least one computing device. The computing device may be a server, such as a central server, an edge server, or a local server in a local data center. In some embodiments, the computing device may also be a terminal device such as a desktop computer, a laptop computer, or a smart phone.

[0132] As Figure 8 shown, the cluster of computing devices includes at least one computing device 700. Instructions for executing the Figure 3 method shown may be stored in the memories 706 of one or more of the computing devices 700 in the cluster of computing devices.

[0133] In some possible implementation manners, instructions for executing the Figure 3 method shown may also be separately stored in the memories 706 of one or more of the computing devices 700 in the cluster of computing devices. In other words, a combination of one or more computing devices 700 may jointly execute the instructions for executing the Figure 3 method shown.

[0134] It should be noted that different memories 706 in different computing devices 700 in the cluster of computing devices may store different instructions for separately executing partial functions of the apparatus 600. That is, the instructions stored in the memories 706 of different computing devices 700 may implement the functions of one or more of the receiving module 610, the indicating module 620, and the obtaining module 630.

[0135] In some possible implementation manners, one or more computing devices in the cluster of computing devices may be connected through a network. Wherein, the network may be a wide area network or a local area network, etc. Figure 9 shows a possible implementation manner. As Figure 9 shown, two computing devices 700A and 700B are connected through a network. Specifically, they are connected to the network through the communication interfaces in each computing device. In this type of possible implementation manner, instructions for executing the function of the receiving module 610 are stored in the memory 706 of the computing device 700A. At the same time, instructions for executing the functions of the indicating module 620 and the obtaining module 630 are stored in the memory 706 of the computing device 700B.

[0136] It should be understood that Figure 9The functions of the computing device 700A shown can also be completed by multiple computing devices 700. Similarly, the functions of the computing device 700B can also be completed by multiple computing devices 700.

[0137] Embodiments of this application also provide another computing device cluster. The connection relationships between the computing devices in this computing device cluster can be similarly referred to Figure 8 and Figure 9 the connection method of the described computing device cluster. The difference is that the same instructions for executing Figure 3 the method shown can be stored in the memory 706 of one or more of the computing devices 700 in this computing device cluster.

[0138] In some possible implementation manners, the memory 706 of one or more of the computing devices 700 in this computing device cluster can also separately store partial instructions for executing Figure 3 the method shown. In other words, the combination of one or more computing devices 700 can jointly execute the instructions for executing Figure 3 the method shown.

[0139] Embodiments of this application also provide a computer program product containing instructions. The computer program product can be software or a program product containing instructions that can run on a computing device or be stored in any available medium. When the computer program product runs on at least one computing device, it causes at least one computing device to execute Figure 3 the method shown.

[0140] Embodiments of this application also provide a computer-readable storage medium. The computer-readable storage medium can be any available medium that a computing device can store or a host migration device such as a data center containing one or more available media. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, a solid-state drive), etc. The computer-readable storage medium includes instructions, and the instructions direct the computing device to execute Figure 3 the method shown.

[0141] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them; although this application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the protection scope of the technical solutions of the embodiments of this application.

Claims

1. A performance testing method for a service system, characterized in that The service system corresponds to preset resources; the method includes: Receiving configuration information input by a user corresponding to the service system, where the configuration information includes a success rate threshold; In a first test phase, instructing N service request terminals to continuously send service requests to the service system; where N is an integer greater than or equal to 1, and the service system is used to receive and process the service requests sent by the N service request terminals by using the resources to obtain processing results of the service requests; When the ratio of the number of successfully processed results obtained by the service system within a first unit time period to the total number of processing results obtained within the first unit time period is greater than or equal to the success rate threshold, obtaining a performance test result of the service system based on the total number of processing results obtained by the service system within the first unit time period; where the successfully processed result is a processing result indicating that the service request is successfully processed, and the first unit time period belongs to the first test phase.

2. The method according to claim 1, wherein The configuration information further includes: a usage rate threshold of a first resource; The method further includes: among the processing results obtained by the service system within the first unit time period, identifying secure processing results; where the usage rate of the first resource when the service system processes the service requests corresponding to the secure processing results is less than the usage rate threshold; The "when the ratio of the number of successfully processed results obtained by the service system within a first unit time period to the total number of processing results obtained within the first unit time period is greater than or equal to the success rate threshold, obtaining a performance test result of the service system based on the total number of processing results obtained by the service system within the first unit time period" includes: when the ratio of the number of secure successfully processed results obtained by the service system within the first unit time period to the total number of secure processing results obtained within the first unit time period is greater than or equal to the success rate threshold, obtaining a performance test result of the service system based on the total number of secure processing results obtained by the service system within the first unit time period; where the secure successfully processed result is a secure processing result indicating that the service request is successfully processed.

3. The method according to claim 1 or 2, characterized in that, The method further includes: In a second test phase, instructing M service request terminals to continuously send service requests to the service system; where M is an integer greater than N; the service system is used to receive and process the service requests sent by the M service request terminals by using the resources to obtain processing results of the service requests; the second test phase is the next test phase after the first test phase; When the ratio of the number of successfully processed results obtained by the service system within a second unit time period to the total number of processing results obtained within the second unit time period is greater than or equal to the success rate threshold, obtaining a performance test result of the service system based on the total number of processing results obtained by the service system within the second unit time period and the total number of processing results obtained within the first unit time period; the second unit time period belongs to the second test phase.

4. The method according to claim 3, wherein The method further includes: after the change range of the speed at which the service system receives and processes service requests in the first test phase is less than a preset amplitude threshold, starting the second test phase.

5. The method according to claim 3 or 4, characterized in that, The method further includes: obtaining the utilization rate of a second resource of the service system in the first test phase; obtaining the M based on the utilization rate of the second resource and the N; wherein, the difference between the M and the N is negatively correlated with the utilization rate of the second resource.

6. The method according to claim 5, characterized in that, The type of the second resource includes a preset resource type and / or a resource type input by the user.

7. The method according to any one of claims 3-6, characterized in that, Obtaining the performance test result of the service system based on the total number of processing results obtained by the service system in the second unit time period and the total number of processing results obtained in the first unit time period includes: when the total number of processing results obtained in the second unit time period is less than the total number of processing results obtained in the first unit time period, determining the total number of processing results obtained in the first unit time period as the limit capacity of the service system.

8. A performance testing device for a service system, characterized in that, The service system corresponds to a preset resource; the device includes: a receiving module, configured to receive configuration information input by a user corresponding to the service system, where the configuration information includes a success rate threshold; an indicating module, configured to, in a first test phase, instruct N service request terminals to continuously send service requests to the service system; where N is an integer greater than or equal to 1, and the service system is configured to use the resource to receive and process service requests sent by the N service request terminals to obtain processing results of the service requests; a obtaining module, configured to, when the ratio of the number of successfully processed results obtained by the service system in the first unit time period to the total number of processing results obtained in the first unit time period is greater than or equal to the success rate threshold, obtain the performance test result of the service system based on the total number of processing results obtained by the service system in the first unit time period; wherein, the successfully processed result is a processing result indicating that the service request is successfully processed, and the first unit time period belongs to the first test phase.

9. The device according to claim 8, characterized in that, The configuration information further includes: a utilization rate threshold of a first resource; the device further includes an identification module; wherein, the identification module is configured to: in the processing results obtained by the service system in the first unit time period, identify security processing results; wherein, the utilization rate of the first resource when the service system processes service requests corresponding to the security processing results is less than the utilization rate threshold; the obtaining module is configured to: when the ratio of the number of securely successfully processed results obtained by the service system in the first unit time period to the total number of security processing results obtained in the first unit time period is greater than or equal to the success rate threshold, obtain the performance test result of the service system based on the total number of security processing results obtained by the service system in the first unit time period; wherein, the securely successfully processed result is a security processing result indicating that the service request is successfully processed.

10. The device according to claim 8 or 9, wherein The indication module is further configured to: in the second test phase, instruct M service request terminals to continuously send service requests to the service system; where M is an integer greater than N; the service system is configured to receive and process the service requests sent by the M service request terminals by using the resources, to obtain processing results of the service requests; the second test phase is the next test phase after the first test phase; The obtaining module is configured to: when a ratio of a quantity of successfully processed results obtained by the service system in a second unit time period to a total quantity of processed results obtained in the second unit time period is greater than or equal to the success rate threshold, obtain a performance test result of the service system based on the total quantity of processed results obtained by the service system in the second unit time period and the total quantity of processed results obtained in the first unit time period; the second unit time period belongs to the second test phase.

11. The device according to claim 10, wherein The apparatus further includes: An enabling module, configured to enable the second test phase after a change amplitude of a speed at which the service system receives and processes service requests in the first test phase is less than a preset amplitude threshold.

12. The device according to claim 10 or 11, characterized in that, The apparatus further includes: an obtaining module; The obtaining module is configured to: obtain a usage rate of a second resource of the service system in the first test phase. The obtaining module is configured to: obtain the M based on the usage rate of the second resource and the N; where a difference between the M and the N is negatively correlated with the usage rate of the second resource.

13. The device according to claim 12, wherein The type of the second resource includes a preset resource type and / or a resource type input by the user.

14. The device according to any one of claims 10-13, characterized in that, The obtaining module is configured to: when the total quantity of processed results obtained in the second unit time period is less than the total quantity of processed results obtained in the first unit time period, determine the total quantity of processed results obtained in the first unit time period as a limit capacity of the service system.

15. A cluster of computing devices, characterized in that, including at least one computing device, each computing device including a processor and a memory; The processor of the at least one computing device is configured to execute instructions stored in the memory of the at least one computing device, so that the computing device cluster executes the method according to any one of claims 1-7.

16. A computer-readable storage medium, characterized in that, including computer program instructions, when the computer program instructions are executed by a computing device cluster, the computing device cluster executes the method according to any one of claims 1-7.

17. A computer program product comprising instructions, characterized in that, When the instructions are run by a computing device cluster, the computing device cluster is caused to execute the method according to any one of claims 1-7.

Images