CN113704031A - System pressure testing method, device, medium and equipment - Google Patents
System pressure testing method, device, medium and equipment Download PDFInfo
- Publication number
- CN113704031A CN113704031A CN202110904238.7A CN202110904238A CN113704031A CN 113704031 A CN113704031 A CN 113704031A CN 202110904238 A CN202110904238 A CN 202110904238A CN 113704031 A CN113704031 A CN 113704031A
- Authority
- CN
- China
- Prior art keywords
- concurrency
- function
- performance index
- index data
- current
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000012360 testing method Methods 0.000 title claims abstract description 58
- 230000004044 response Effects 0.000 claims abstract description 81
- 238000000034 method Methods 0.000 claims abstract description 51
- 230000006870 function Effects 0.000 claims description 118
- 230000002159 abnormal effect Effects 0.000 claims description 22
- 238000013507 mapping Methods 0.000 claims description 19
- 238000012545 processing Methods 0.000 claims description 10
- 238000012935 Averaging Methods 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 8
- 238000001514 detection method Methods 0.000 claims description 7
- 238000000611 regression analysis Methods 0.000 claims description 7
- 238000013450 outlier detection Methods 0.000 claims description 5
- 238000009662 stress testing Methods 0.000 claims description 4
- 238000010998 test method Methods 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 8
- 230000009471 action Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 230000007423 decrease Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/22—Detection or location of defective computer hardware by testing during standby operation or during idle time, e.g. start-up testing
- G06F11/2273—Test methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computational Mathematics (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Quality & Reliability (AREA)
- Educational Administration (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Pure & Applied Mathematics (AREA)
- Strategic Management (AREA)
- Mathematical Physics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Algebra (AREA)
- Probability & Statistics with Applications (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Computer Hardware Design (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Testing And Monitoring For Control Systems (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The disclosure relates to a system pressure test method, device, medium and equipment. The method comprises the following steps: acquiring first performance index data of a system under the current concurrency number; determining a first function of requests per second versus concurrency and a second function of response time versus concurrency based on the first performance metric data; determining a next concurrency number for the system pressure test based on the current concurrency number, the first function and the second function; and taking the next concurrency number as the current concurrency number, and triggering and acquiring first performance index data of the system under the current concurrency number until the maximum request number per second and the corresponding response time of the system are determined. According to the technical scheme, the concurrency number of the system is automatically adjusted through the first performance index data acquired in real time, and the efficiency of system pressure testing is improved.
Description
Technical Field
The present disclosure relates to the field of computer network technologies, and in particular, to a method, an apparatus, a medium, and a device for testing system pressure.
Background
Some performance indicators of the service system, such as the number of requests per second and response time, can be used to characterize the amount of stress that the service system can withstand. The service system is oriented to access of thousands of users, and if the number of users requesting access to the service system at the same time is too large, the service system is halted. If the performance of the service system does not reach the standard and the service system is operated online, the loss is brought to developers. Therefore, the service system needs to be pressure tested before the service system is on line.
In the traditional pressure test, a tester needs to manually trigger the concurrency number of the system, then the concurrency number is continuously manually adjusted by observing the change condition of the performance index of the system, and the iteration is circulated until the optimal solution of the system is found. Therefore, the existing pressure testing method not only consumes a lot of time, but also needs manual regulation and control of all pressure testing processes, consumes a lot of manpower, and in addition, the existing pressure testing method is influenced by subjective factors of people and cannot accurately position the optimal solution of the system.
Disclosure of Invention
To solve the above technical problem or at least partially solve the above technical problem, the present disclosure provides a system pressure testing method, apparatus, medium, and device.
The present disclosure provides a system pressure testing method, including:
acquiring first performance index data of a system under a current concurrency number, wherein the first performance index data comprises request number per second and response time;
determining a first function of the number of requests per second versus concurrency and a second function of the response time versus concurrency based on the first performance metric data;
determining a next concurrency number for a system stress test based on the current concurrency number, the first function and the second function;
and taking the next concurrency number as the current concurrency number, and triggering and acquiring first performance index data of the system under the current concurrency number until the maximum request number per second and the corresponding response time of the system are determined.
In some embodiments, prior to obtaining the first performance indicator data for the system at the current concurrency, the method further comprises:
acquiring second performance index data of the system under the current concurrency number;
judging whether a preset constraint condition is met or not based on the second performance index data;
acquiring first performance index data of a system under the current concurrency number, wherein the first performance index data comprises the following steps:
and when the preset constraint condition is met, acquiring first performance index data of the system under the current concurrency.
In some embodiments, the second performance indicator data comprises at least one of a central processor occupancy, a memory occupancy, and an interface request error rate;
the preset constraint condition comprises at least one of the following:
the occupancy rate of the central processing unit is less than a first occupancy rate threshold value;
the memory occupancy rate is less than a second occupancy rate threshold;
the interface request error rate is less than a request error rate threshold.
In some embodiments, the method further comprises:
and when the constraint condition is not met, acquiring first performance index data of the system under the current concurrency number, and taking the number of requests per second in the first performance index data as the maximum number of requests per second of the system.
In some embodiments, determining the first function of the number of requests per second versus concurrency and the second function of the response time versus concurrency based on the first performance metric data comprises:
respectively averaging the request number per second and the response time, and obtaining a first mapping relation between the request number per second and the concurrency number and a second mapping relation between the response time and the concurrency number based on the average values;
and respectively performing polynomial fitting on the request number per second and the response time by adopting nonlinear regression analysis based on the first mapping relation and the second mapping relation to obtain a first function and a second function.
In some embodiments, determining a next concurrency number for a system stress test based on the current concurrency number, the first function, and the second function comprises:
determining a first derivative of the first function at the current concurrency based on the current concurrency and the first function;
determining a second derivative of the second function at the current concurrency based on the current concurrency and the second function;
taking a ratio of the first derivative to the second derivative as a gradient of a concurrent iteration;
determining the next concurrency number based on the current concurrency number and the gradient.
In some embodiments, determining a maximum number of requests per second for the system comprises:
and when the number of requests per second of the system under the current concurrency number is less than or equal to the number of requests per second of the system under the last concurrency number, determining the number of requests per second of the system under the last concurrency number to be the maximum number of requests per second.
In some embodiments, prior to determining the first function of requests per second versus concurrency and the second function of response time versus concurrency based on the first performance indicator data, the method further comprises:
and preprocessing the first performance index data to eliminate invalid first performance index data.
In some embodiments, pre-processing the first performance indicator data comprises:
calculating a first standard deviation of the requests per second and a second standard deviation of the response time, respectively, based on the first performance indicator data;
performing outlier detection on the first performance indicator data when any one of the first standard deviation and the second standard deviation is less than or equal to a preset standard deviation;
when the first standard deviation and the second standard deviation are both larger than a preset standard deviation, triggering and executing to acquire first performance index data of the system under the current concurrency, and when any one of the first standard deviation and the second standard deviation is smaller than or equal to the preset standard deviation, carrying out abnormal value detection on the first performance index data.
In some embodiments, after outlier detection of the first performance indicator data, the method further comprises:
averaging the detected abnormal values;
determining a first function of the number of requests per second versus concurrency and a second function of the response time versus concurrency based on the first performance metric data, comprising:
determining a first function of the number of requests per second with respect to concurrency and a second function of the response time with respect to concurrency based on normal values and equalized abnormal values in the first performance index data.
In some embodiments, the method further comprises:
when the number of times of triggering execution of acquiring the first performance index data of the system under the current concurrency number reaches a preset number, if the first standard deviation and the second standard deviation are both larger than a preset standard deviation, acquiring the first performance index data of the system under the current concurrency number at the last time of triggering execution, and taking the request number per second in the first performance index data as the maximum request number per second of the system.
The present disclosure provides a system pressure test device, comprising:
the system comprises a first performance index data acquisition module, a second performance index data acquisition module and a first performance index data processing module, wherein the first performance index data acquisition module is used for acquiring first performance index data of a system under a current concurrence number, and the first performance index data comprises request number per second and response time;
a concurrency number function determination module for determining a first function of the number of requests per second with respect to concurrency number and a second function of the response time with respect to concurrency number based on the first performance index data;
a next concurrency number determination module, configured to determine a next concurrency number for a system stress test based on the current concurrency number, the first function, and the second function;
and the repeated execution module is used for taking the next concurrency number as the current concurrency number, and triggering execution and acquisition of first performance index data of the system under the current concurrency number until the maximum request number per second and the corresponding response time of the system are determined.
The present disclosure also provides a computer-readable storage medium storing a program or instructions for causing a computer to perform the steps of any one of the methods described above.
The present disclosure also provides a system pressure test apparatus, including: a processor and a memory;
the processor is configured to perform the steps of any of the above methods by calling a program or instructions stored in the memory.
Compared with the prior art, the technical scheme provided by the embodiment of the disclosure has the following advantages:
the technical scheme provided by the embodiment of the disclosure determines a first function of the request number per second with respect to the concurrency number and a second function of the response time with respect to the concurrency number based on the request number per second and the response time under the current concurrency number of the system, and determines the next concurrency number for the system pressure test based on the current concurrency number, the first function and the second function, so as to perform the pressure test on the system under the next concurrency number, and thus, the concurrency number is continuously and automatically adjusted until the optimal solution of the system is obtained, namely, the limit performance index value which can be borne by the system is obtained. Therefore, the technical scheme provided by the embodiment of the disclosure can automatically adjust the concurrency number of the system through the request number per second and the response time acquired in real time without human participation, and can quickly find the optimal solution of the system, thereby improving the efficiency of the system pressure test and reducing the time and labor cost.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure.
In order to more clearly illustrate the embodiments or technical solutions in the prior art of the present disclosure, the drawings used in the description of the embodiments or prior art will be briefly described below, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without inventive exercise.
Fig. 1 is a flowchart of a system pressure testing method according to an embodiment of the present disclosure;
fig. 2 is a block diagram of a system pressure testing apparatus provided in the embodiment of the present disclosure;
fig. 3 is a schematic structural diagram of a system pressure testing device provided in an embodiment of the present disclosure.
Detailed Description
In order that the above objects, features and advantages of the present disclosure may be more clearly understood, aspects of the present disclosure will be further described below. It should be noted that the embodiments and features of the embodiments of the present disclosure may be combined with each other without conflict.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present disclosure, but the present disclosure may be practiced in other ways than those described herein; it is to be understood that the embodiments disclosed in the specification are only a few embodiments of the present disclosure, and not all embodiments.
Currently, the process of performing pressure testing is more often performed with a fixed gradient over a period of time. For example, an initial concurrency number is manually set to be 3, then a stress test is performed on the system with 3 as the concurrency number and the system is continuously operated for 30s, a request Per Second (QPS) timing diagram and a Response Time (RT) timing diagram within 30s Time can be obtained by using an existing tool (e.g. a jmeter tool), then a gradient +3 is added, the execution Time of 30s is continued with 6 as the concurrency number, a QPS timing diagram and an RT timing diagram are obtained, and the like, the maximum QPS and the RT under the corresponding concurrency number of the system are obtained until the preset maximum concurrency number is obtained, for example, 30, and finally the QPS timing diagram and the RT timing diagram are observed. However, the pressure testing method not only consumes a lot of time, but also all pressure testing processes need to be regulated and controlled manually, which consumes a lot of manpower.
In view of the above technical problems, the embodiments of the present disclosure provide a system pressure testing method. Specifically, fig. 1 is a flowchart of a system pressure testing method according to an embodiment of the present disclosure. The method can be executed by a system pressure testing device, can be realized in a software and/or hardware mode, and can be applied to system pressure testing equipment. As shown in fig. 1, the method comprises the steps of:
s110, acquiring first performance index data of the system under the current concurrency number.
Wherein the first performance indicator data comprises a number of requests per second and a response time.
In some embodiments, when the system initially runs, the current concurrency number may be manually set by a tester or may be a default value of the system. The method and the device for acquiring the request number and the response time of the system running under the current concurrency number can be used for acquiring the request number and the response time of the system running under the current concurrency number in real time by using a jmeter tool, wherein the running time of the system under the current concurrency number can be set according to actual conditions, and is not limited here.
S120, determining a first function of the number of requests per second and a second function of the response time and the number of concurrencies based on the first performance index data.
In the embodiment of the present disclosure, the first function and the second function are both continuous nonlinear functions. In practical application, when the system does not reach a saturation state, a first curve corresponding to the first function and a second curve corresponding to the second function both increase with the increase of the concurrency number, wherein the slope of the first curve gradually decreases with the increase of the concurrency number, and the slope of the second curve gradually increases with the increase of the concurrency number. After the system reaches the saturation state, the first curve keeps unchanged or decreases along with the increase of the concurrency number, and the second curve continuously increases along with the increase of the concurrency number, and the increase degree is obviously larger than the increase degree when the system does not reach the saturation state.
Since the first performance indicator data is only obtained at the current concurrency number, in order to obtain a first function of the number of requests per second with respect to the concurrency number and a second function of the response time with respect to the concurrency number, the disclosed embodiments fit the first function and the second function using nonlinear regression analysis. In some embodiments, the request number per second and the response time are respectively averaged, and a first mapping relation between the request number per second and the concurrency number and a second mapping relation between the response time and the concurrency number are obtained based on the average values;
and respectively performing polynomial fitting on the request number per second and the response time by adopting nonlinear regression analysis based on the first mapping relation and the second mapping relation to obtain a first function and a second function.
In the disclosed embodiment, the first function is fqps(x)＝a1*x2+b1X; the second function being frt(x)＝a2*x3+b2*x2+ c x; wherein x is the number of concurrencies, a1、b1、a2、b2And c are constants and are obtained by polynomial fitting through nonlinear regression analysis.
And S130, determining the next concurrency number for the system pressure test based on the current concurrency number, the first function and the second function.
Based on the change rule of the corresponding curves of the first function and the second function mentioned in S120, a gradient descent algorithm may be used to find the inflection point of the system. The first function and the second function have different changing trends corresponding to curves, the slope of the curve is different in a geometric figure, and the derivative of the function is different in a mathematical formula. In some embodiments, based on the current concurrency and the first function, determining a first derivative of the first function at the current concurrency; determining a second derivative of the second function at the current concurrency number based on the current concurrency number and the second function; taking the ratio of the first derivative to the second derivative as the gradient of the concurrent iteration; based on the current concurrency number and the gradient, a next concurrency number is determined.
Specifically, the following formula is adopted to calculate the next concurrency number:
wherein x isi+1Is the next concurrency number, xiIs the current concurrency number, alpha is the learning rate, f'q′ps(xi) At x as a first functioniThe derivative of (a), i.e. the first derivative, f'r′t(xi) At x for the second functioniThe derivative at (a), i.e. the second derivative described above.
In some embodiments, the learning rate determines how fast the algorithm converges to some extent, and according to the relationship that the first performance index data varies with the concurrency number, firstly, it is expected that the early stage of the concurrency number may vary faster, and when the system approaches a saturation state, the change of the requested number per second is less obvious along with the variation of the concurrency number, and at this time, it is expected that the concurrency number may vary slower, so that the corresponding saturation point may be found more accurately, and the value of the saturation point may not be missed because the concurrency number varies too fast, and therefore, an AdaDelta algorithm (an optimization algorithm with adaptive learning rate adjustment) may be used to adaptively adjust the value of the learning rate. The concrete formula is as follows:
wherein:
beta is the global learning rate and the value range is [0.1, 1%]Rho is exponential decay rate and generally takes 0.9 gtIs the gradient of the t-th iteration, E (g)2)tRepresents the mean value of the gradient for the t iterations and epsilon represents a minimum value, such as 0.000001, to avoid a denominator of 0.
And S140, taking the next concurrency number as the current concurrency number, and triggering and executing to acquire the first performance index data of the system under the current concurrency number until the maximum request number per second and the corresponding response time of the system are determined.
The step is a concurrency number adjusted by loop iteration, that is, the next concurrency number is taken as a current concurrency number, and S110 to S140 are executed until the maximum request number per second and the response time under the corresponding concurrency number of the system are determined, and the maximum request number per second and the response time under the corresponding concurrency number are the optimal solution of the system.
In some embodiments, determining the maximum number of requests per second for the system comprises:
and when the number of requests per second of the system under the current concurrency number is less than or equal to the number of requests per second of the system under the last concurrency number, determining the number of requests per second of the system under the last concurrency number to be the maximum number of requests per second.
The system pressure testing method provided by the embodiment of the disclosure determines a first function of the request number per second with respect to the concurrency number and a second function of the response time with respect to the concurrency number based on the request number per second and the response time under the current concurrency number of the system, and determines the next concurrency number for the system pressure testing based on the current concurrency number, the first function and the second function, so that the system is subjected to the pressure testing under the next concurrency number, and thus, the concurrency number is continuously and automatically adjusted until the optimal solution of the system, namely the ultimate performance index value which can be borne by the system, is obtained. Therefore, the technical scheme provided by the embodiment of the disclosure can automatically adjust the concurrency number of the system through the request number per second and the response time acquired in real time without human participation, and can quickly find the optimal solution of the system, thereby improving the efficiency of the system pressure test and reducing the time and labor cost.
Based on the above technical solution, in some embodiments, before obtaining the first performance index data of the system under the current concurrency number, the method further includes:
a. and acquiring second performance index data of the system under the current concurrency number.
In some embodiments, the second performance indicator data includes at least one of central processor occupancy, memory occupancy, and interface request error rate.
b. And judging whether the preset constraint condition is met or not based on the second performance index data.
In the embodiment of the present disclosure, the preset constraint condition is used to constrain whether to execute the step of the system pressure testing method provided by the embodiment of the present disclosure, and when the second performance index data does not satisfy the preset constraint condition, it indicates that the system has reached a saturation state, that is, the number of requests per second of the system reaches the maximum value, so that only when the second performance index data satisfies the preset constraint condition, the step of the system pressure testing method is executed. In some embodiments, when the constraint is not satisfied, first performance indicator data for the system at the current concurrency number is obtained, and the number of requests per second in the first performance indicator data is taken as the maximum number of requests per second for the system.
The preset constraint condition comprises at least one of the following: the occupancy rate of the central processing unit is less than a first occupancy rate threshold value; the memory occupancy rate is less than a second occupancy rate threshold value; the interface request error rate is less than the request error rate threshold. The first occupancy rate threshold, the second occupancy rate threshold and the error rate threshold are set according to actual conditions.
Correspondingly, acquiring first performance index data of the system under the current concurrency number comprises the following steps: and when the preset constraint condition is met, acquiring first performance index data of the system under the current concurrency.
In some embodiments, prior to determining a first function of number of requests per second versus number of concurrencies and a second function of response time versus number of concurrencies based on the first performance metric data, the method further comprises:
the first performance index data is preprocessed to remove invalid first performance index data. Therefore, performance index fluctuation caused by external environmental factors such as a network and the like is avoided to the maximum extent.
Because the performance index of the system is influenced by external factors such as network state and the like, after the first performance index data is obtained, the first performance index data needs to be preprocessed, after the first performance index data is judged to be effective, a first function of the request number per second and a second function of the response time and the concurrency number are determined based on the first performance index data, otherwise, the obtained result cannot represent the real performance of the system. When the external conditions such as the network and the like are unstable, the requests per second and the response time of the system generate large fluctuation, namely, the difference between most requests per second in a period of time and the average value of the requests per second in the period of time is large, and the difference between most response time and the average value of the response time in the period of time is large. Considering that the standard deviation is a measure of the degree of dispersion of the mean values of a set of data, a larger standard deviation represents a larger difference between the majority of the values and their mean values, and a smaller standard deviation represents values closer to the mean value. Therefore, the current stability of the system can be measured by calculating the standard deviation of the request number per second and the response time, and the smaller the standard deviation is, the more stable the system is, the less the system is influenced by external environment factors.
In some embodiments, pre-processing the first performance indicator data comprises:
respectively calculating a first standard deviation of the request number per second and a second standard deviation of the response time based on the first performance index data; when any one of the first standard deviation and the second standard deviation is smaller than or equal to a preset standard deviation, abnormal value detection is carried out on the first performance index data; when the first standard deviation and the second standard deviation are both larger than the preset standard deviation, triggering execution to acquire first performance index data of the system under the current concurrency number, and detecting abnormal values of the first performance index data when any one of the first standard deviation and the second standard deviation is smaller than or equal to the preset standard deviation.
In the above embodiment, when both the first standard deviation and the second standard deviation are greater than the preset standard deviation, it is described that the fluctuation of the number of requests per second and the response time is large, at this time, the system is unstable, the obtained number of requests per second and the response time cannot reflect the real performance of the system, the number of requests per second and the response time of the system under the current concurrency number need to be obtained again, the first standard deviation of the number of requests per second and the second standard deviation of the response time obtained again are continuously calculated and compared with the preset standard deviation, the stability of the system is determined, and if the system is unstable, the number of requests per second and the response time of the system under the current concurrency number are obtained again. And circulating the steps until the system is judged to be stable. In addition, when any one of the first standard deviation and the second standard deviation is less than or equal to the preset standard deviation, it is indicated that the fluctuation of the number of requests per second and the response time is large, and at this time, the system is unstable, but there may still be a large difference between the individual number of requests per second or the response time and the average value, and these large differences from the average value are called abnormal values. To eliminate the effect of these outliers on subsequent calculations, the outliers may be removed or averaged.
For example, the preset standard deviation may include a first preset standard deviation σ corresponding to the first standard deviation1Second predetermined standard deviation sigma corresponding to the second standard deviation2. The system running time is T under the current concurrency, and the request number per second and the response time are monitored in real time during the time T, so that a data set of the request number per second in the time T can be obtained, such as Dqps：{dqps1,dqps2,dqps3,……，dqpsn1And a data set of response times within time T, e.g. Drt：{drt1,drt2,drt3,……，drtn2}; then, based on the data set DqpsCalculating a first standard deviation sigma of requests per secondqpsBased on the data set DrtCalculating a second standard deviation sigma of the response timert(ii) a The first standard deviation sigma is compared respectivelyqpsAnd a first predetermined standard deviation sigma1And a second standard deviation σrtAnd a second predetermined standard deviation sigma2When the first standard deviation σqpsLess than or equal to the first preset standard deviation sigma1Or second standard deviation σrtLess than or equal to a second preset standard deviation sigma2Then, carrying out abnormal value detection on the first performance index data; when the first standard deviation σqpsGreater than a first predetermined standard deviation sigma1And a second standard deviation σrtGreater than a second predetermined standard deviation sigma2And triggering execution to acquire first performance index data of the system under the current concurrency number.
In the above embodiment, the abnormal value detection may be performed by the method of the box chart.
In some embodiments, after the outlier detection of the first performance indicator data, the method further comprises: and carrying out averaging processing on the detected abnormal values so as to eliminate fluctuation caused by the abnormal values. Accordingly, determining a first function of requests per second versus concurrency and a second function of response time versus concurrency based on the first performance metric data, comprises: a first function of the number of requests per second with respect to the number of concurrencies and a second function of the response time with respect to the number of concurrencies are determined based on the normal value (first performance index data other than the abnormal value) in the first performance index data and the abnormal value after the averaging process. Based on the above embodiment, the normal value and the abnormal value after the averaging process in the first performance index data may be averaged to obtain a mapping relationship between the number of requests per second and the number of concurrencies and a mapping relationship between the response time and the number of concurrencies, and then the first function and the second function may be fitted by a nonlinear regression analysis based on the mapping relationship.
In some embodiments, the method further comprises:
when the number of times of triggering execution of acquiring the first performance index data of the system under the current concurrency number reaches a preset number, if the first standard deviation and the second standard deviation are both larger than the preset standard deviation, acquiring the first performance index data of the system under the current concurrency number at the last time of triggering execution, and taking the request number per second in the first performance index data as the maximum request number per second of the system. Therefore, in order to prevent the unlimited circulation of the operation of triggering the execution of acquiring the first performance index data of the system under the current concurrency number due to the long-term instability of the external factors, the present embodiment sets the upper limit value of the number of times of the triggering operation, that is, the preset number of times, to end the circulation operation, and meanwhile, when the number of times of triggering the execution of acquiring the first performance index data of the system under the current concurrency number reaches the preset number of times, we consider that the system has reached the maximum number of requests per second, so the last acquired number of requests per second is taken as the maximum number of requests per second under the current environment.
Corresponding to the system pressure testing method provided by the embodiment of the disclosure, the embodiment of the disclosure also provides a system pressure testing device. Fig. 2 is a block diagram of a system pressure testing apparatus according to an embodiment of the present disclosure, and as shown in fig. 2, the system pressure testing apparatus includes:
a first performance index data obtaining module 21, configured to obtain first performance index data of the system under the current concurrency number, where the first performance index data includes a request number per second and response time;
a concurrency number function determining module 22 for determining a first function of number of requests per second with respect to concurrency number and a second function of response time with respect to concurrency number based on the first performance index data;
a next concurrency number determining module 23, configured to determine a next concurrency number for the system pressure test based on the current concurrency number, the first function, and the second function;
and the repeated execution module 24 is configured to use the next concurrency number as the current concurrency number, and trigger execution to acquire the first performance index data of the system under the current concurrency number until the maximum request number per second and the corresponding response time of the system are determined.
In some embodiments, the system pressure testing apparatus further comprises:
the second performance index data acquisition module is used for acquiring second performance index data of the system under the current concurrency number before acquiring the first performance index data of the system under the current concurrency number;
the constraint condition judging module is used for judging whether a preset constraint condition is met or not based on the second performance index data;
the first performance indicator data acquisition is for:
and when the preset constraint condition is met, acquiring first performance index data of the system under the current concurrency.
In some embodiments, the second performance indicator data comprises at least one of central processor occupancy, memory occupancy, and interface request error rate;
the preset constraint condition comprises at least one of the following:
the occupancy rate of the central processing unit is less than a first occupancy rate threshold value;
the memory occupancy rate is less than a second occupancy rate threshold value;
the interface request error rate is less than the request error rate threshold.
In some embodiments, the system pressure testing apparatus further comprises:
and the optimal solution determining module is used for acquiring first performance index data of the system under the current concurrency number when the constraint condition is not met, and taking the request number per second in the first performance index data as the maximum request number per second of the system.
In some embodiments, the concurrency function determination module 22 is configured to:
respectively averaging the request number per second and the response time, and obtaining a first mapping relation between the request number per second and the concurrency number and a second mapping relation between the response time and the concurrency number based on the average values;
and respectively performing polynomial fitting on the request number per second and the response time by adopting nonlinear regression analysis based on the first mapping relation and the second mapping relation to obtain a first function and a second function.
In some embodiments, the next concurrency number determination module 23 is configured to:
determining a first derivative of the first function at the current concurrency based on the current concurrency and the first function;
determining a second derivative of the second function at the current concurrency number based on the current concurrency number and the second function;
taking the ratio of the first derivative to the second derivative as the gradient of the concurrent iteration;
based on the current concurrency number and the gradient, a next concurrency number is determined.
In some embodiments, the optimal solution determination module is further configured to:
and when the number of requests per second of the system under the current concurrency number is less than or equal to the number of requests per second of the system under the last concurrency number, determining the number of requests per second of the system under the last concurrency number to be the maximum number of requests per second.
In some embodiments, the system pressure testing apparatus further comprises:
and the data preprocessing module is used for preprocessing the first performance index data to eliminate invalid first performance index data before determining a first function of the request number per second and a second function of the response time and the concurrency number based on the first performance index data.
In some embodiments, the data pre-processing module is to:
respectively calculating a first standard deviation of the request number per second and a second standard deviation of the response time based on the first performance index data;
when any one of the first standard deviation and the second standard deviation is smaller than or equal to a preset standard deviation, abnormal value detection is carried out on the first performance index data;
when the first standard deviation and the second standard deviation are both larger than the preset standard deviation, triggering execution to acquire first performance index data of the system under the current concurrency number, and detecting abnormal values of the first performance index data when any one of the first standard deviation and the second standard deviation is smaller than or equal to the preset standard deviation.
In some embodiments, the system pressure testing apparatus further comprises:
the abnormal value processing module is used for carrying out averaging processing on the detected abnormal value after the abnormal value detection is carried out on the first performance index data;
the concurrency function determination module 22 is configured to:
a first function of requests per second with respect to concurrency and a second function of response time with respect to concurrency are determined based on the normal values and the equalized abnormal values in the first performance index data.
In some embodiments, the optimal solution determination module is further configured to:
when the number of times of triggering execution of acquiring the first performance index data of the system under the current concurrency number reaches a preset number, if the first standard deviation and the second standard deviation are both larger than the preset standard deviation, acquiring the first performance index data of the system under the current concurrency number at the last time of triggering execution, and taking the request number per second in the first performance index data as the maximum request number per second of the system.
The system pressure testing device disclosed in the above embodiments can perform the system pressure testing method disclosed in each of the above embodiments, has the same or corresponding beneficial effects, and is not described herein again to avoid repetition.
Embodiments of the present disclosure also provide a computer-readable storage medium storing a program or instructions that causes a computer to perform the steps of any one of the methods described above.
Illustratively, the program or instructions cause a computer to perform a system stress testing method comprising:
acquiring first performance index data of a system under the current concurrency number, wherein the first performance index data comprises request number per second and response time;
determining a first function of requests per second versus concurrency and a second function of response time versus concurrency based on the first performance metric data;
determining a next concurrency number for the system pressure test based on the current concurrency number, the first function and the second function;
and taking the next concurrency number as the current concurrency number, and triggering and acquiring first performance index data of the system under the current concurrency number until the maximum request number per second and the corresponding response time of the system are determined.
Optionally, the computer executable instruction, when executed by the computer processor, may be further configured to execute the technical solution of any system pressure testing method provided in the embodiment of the present disclosure, so as to achieve corresponding beneficial effects.
From the above description of the embodiments, it is obvious for those skilled in the art that the embodiments of the present disclosure can be implemented by software and necessary general hardware, and certainly can be implemented by hardware, but the former is a better implementation in many cases. Based on such understanding, the technical solutions of the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a computer-readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, and the like, and includes several instructions to enable a computer device (which may be a personal computer, a server, or a network device, and the like) to execute the methods described in the embodiments of the present disclosure.
On the basis of the foregoing embodiments, an embodiment of the present disclosure further provides a system pressure testing device, including: a processor and a memory; the processor is used for executing the steps of any one of the above methods by calling the program or the instruction stored in the memory, so as to realize the corresponding beneficial effects.
In some embodiments, fig. 3 illustrates a structure of a system pressure testing device provided by an embodiment of the present disclosure. Referring to fig. 3, the system pressure test apparatus may include:
one or more processors 301, one processor 301 being illustrated in FIG. 3;
a memory 302;
the system pressure test apparatus may further include: an input device 303 and an output device 304.
The processor 301, the memory 302, the input device 303 and the output device 304 in the system pressure test apparatus may be connected by a bus or other means, and the connection manner is exemplarily illustrated in fig. 3 by the bus connection.
The memory 302 is a non-transitory computer-readable storage medium, and can be used to store software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the method of the application program in the embodiment of the present disclosure (for example, the first performance index data obtaining module 21, the concurrency function determining module 22, the next concurrency determining module 23, and the repeat executing module 24 shown in fig. 2). The processor 301 executes various functional applications of the server and data processing by executing software programs, instructions and modules stored in the memory 302, namely, implements the method of the above-described method embodiment.
The memory 302 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to use of the electronic device, and the like.
Further, the memory 302 may include high speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device.
In some embodiments, memory 302 optionally includes memory located remotely from processor 301, which may be connected to a terminal device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input device 303 may be used to receive input numeric or character information and generate key signal inputs related to user settings and function control of the electronic apparatus.
The output means 304 may comprise a display device such as a display screen.
It is noted that, in this document, relational terms such as "first" and "second," and the like, may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The foregoing are merely exemplary embodiments of the present disclosure, which enable those skilled in the art to understand or practice the present disclosure. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the disclosure. Thus, the present disclosure is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (14)
1. A system stress testing method, comprising:
acquiring first performance index data of a system under a current concurrency number, wherein the first performance index data comprises request number per second and response time;
determining a first function of the number of requests per second versus concurrency and a second function of the response time versus concurrency based on the first performance metric data;
determining a next concurrency number for a system stress test based on the current concurrency number, the first function and the second function;
and taking the next concurrency number as the current concurrency number, and triggering and acquiring first performance index data of the system under the current concurrency number until the maximum request number per second and the corresponding response time of the system are determined.
2. The method of claim 1, wherein prior to obtaining the first performance indicator data for the system at the current concurrency level, the method further comprises:
acquiring second performance index data of the system under the current concurrency number;
judging whether a preset constraint condition is met or not based on the second performance index data;
acquiring first performance index data of a system under the current concurrency number, wherein the first performance index data comprises the following steps:
and when the preset constraint condition is met, acquiring first performance index data of the system under the current concurrency.
3. The method of claim 2, wherein the second performance indicator data comprises at least one of central processor occupancy, memory occupancy, and interface request error rate;
the preset constraint condition comprises at least one of the following:
the occupancy rate of the central processing unit is less than a first occupancy rate threshold value;
the memory occupancy rate is less than a second occupancy rate threshold;
the interface request error rate is less than a request error rate threshold.
4. The method of claim 2, further comprising:
and when the constraint condition is not met, acquiring first performance index data of the system under the current concurrency number, and taking the number of requests per second in the first performance index data as the maximum number of requests per second of the system.
5. The method of claim 1, wherein determining the first function of the number of requests per second versus concurrency and the second function of the response time versus concurrency based on the first performance metric data comprises:
respectively averaging the request number per second and the response time, and obtaining a first mapping relation between the request number per second and the concurrency number and a second mapping relation between the response time and the concurrency number based on the average values;
and respectively performing polynomial fitting on the request number per second and the response time by adopting nonlinear regression analysis based on the first mapping relation and the second mapping relation to obtain a first function and a second function.
6. The method of claim 1, wherein determining a next concurrency number for system stress testing based on the current concurrency number, the first function, and the second function comprises:
determining a first derivative of the first function at the current concurrency based on the current concurrency and the first function;
determining a second derivative of the second function at the current concurrency based on the current concurrency and the second function;
taking a ratio of the first derivative to the second derivative as a gradient of a concurrent iteration;
determining the next concurrency number based on the current concurrency number and the gradient.
7. The method of claim 1, wherein determining a maximum number of requests per second for the system comprises:
and when the number of requests per second of the system under the current concurrency number is less than or equal to the number of requests per second of the system under the last concurrency number, determining the number of requests per second of the system under the last concurrency number to be the maximum number of requests per second.
8. The method of claim 1, wherein prior to determining the first function of the number of requests per second versus concurrency and the second function of the response time versus concurrency based on the first performance metric data, the method further comprises:
and preprocessing the first performance index data to eliminate invalid first performance index data.
9. The method of claim 8, wherein preprocessing the first performance indicator data comprises:
calculating a first standard deviation of the requests per second and a second standard deviation of the response time, respectively, based on the first performance indicator data;
performing outlier detection on the first performance indicator data when any one of the first standard deviation and the second standard deviation is less than or equal to a preset standard deviation;
when the first standard deviation and the second standard deviation are both larger than a preset standard deviation, triggering and executing to acquire first performance index data of the system under the current concurrency, and when any one of the first standard deviation and the second standard deviation is smaller than or equal to the preset standard deviation, carrying out abnormal value detection on the first performance index data.
10. The method of claim 9, wherein after performing outlier detection on the first performance indicator data, the method further comprises:
averaging the detected abnormal values;
determining a first function of the number of requests per second versus concurrency and a second function of the response time versus concurrency based on the first performance metric data, comprising:
determining a first function of the number of requests per second with respect to concurrency and a second function of the response time with respect to concurrency based on normal values and equalized abnormal values in the first performance index data.
11. The method of claim 9, further comprising:
when the number of times of triggering execution of acquiring the first performance index data of the system under the current concurrency number reaches a preset number, if the first standard deviation and the second standard deviation are both larger than a preset standard deviation, acquiring the first performance index data of the system under the current concurrency number at the last time of triggering execution, and taking the request number per second in the first performance index data as the maximum request number per second of the system.
12. A system pressure testing apparatus, comprising:
the system comprises a first performance index data acquisition module, a second performance index data acquisition module and a first performance index data processing module, wherein the first performance index data acquisition module is used for acquiring first performance index data of a system under a current concurrence number, and the first performance index data comprises request number per second and response time;
a concurrency number function determination module for determining a first function of the number of requests per second with respect to concurrency number and a second function of the response time with respect to concurrency number based on the first performance index data;
a next concurrency number determination module, configured to determine a next concurrency number for a system stress test based on the current concurrency number, the first function, and the second function;
and the repeated execution module is used for taking the next concurrency number as the current concurrency number, and triggering execution and acquisition of first performance index data of the system under the current concurrency number until the maximum request number per second and the corresponding response time of the system are determined.
13. A computer-readable storage medium, characterized in that it stores a program or instructions for causing a computer to carry out the steps of the method according to any one of claims 1 to 11.
14. A system stress testing apparatus, comprising: a processor and a memory;
the processor is adapted to perform the steps of the method of any one of claims 1 to 11 by calling a program or instructions stored in the memory.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110904238.7A CN113704031B (en) | 2021-08-06 | 2021-08-06 | System pressure testing method, device, medium and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110904238.7A CN113704031B (en) | 2021-08-06 | 2021-08-06 | System pressure testing method, device, medium and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113704031A true CN113704031A (en) | 2021-11-26 |
| CN113704031B CN113704031B (en) | 2023-10-10 |
Family
ID=78651779
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110904238.7A Active CN113704031B (en) | 2021-08-06 | 2021-08-06 | System pressure testing method, device, medium and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113704031B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114546852A (en) * | 2022-02-21 | 2022-05-27 | 北京百度网讯科技有限公司 | Performance test method and device, electronic equipment and storage medium |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130308457A1 (en) * | 2012-04-28 | 2013-11-21 | International Business Machines Corporation | System detection method and apparatus and flow control method and device |
| CN106533750A (en) * | 2016-10-28 | 2017-03-22 | 东北大学 | System and method for predicting non-steady application user concurrency in cloud environment |
| US9647919B1 (en) * | 2014-12-04 | 2017-05-09 | Amazon Technologies | Automated determination of maximum service throughput |
| US20170132058A1 (en) * | 2015-11-11 | 2017-05-11 | International Business Machines Corporation | System resource component utilization |
| US20170255505A1 (en) * | 2016-03-04 | 2017-09-07 | International Business Machines Corporation | Application abnormality detection |
| CN107329881A (en) * | 2017-06-02 | 2017-11-07 | 腾讯科技（深圳）有限公司 | Application system performance method of testing and device, computer equipment and storage medium |
| CN108540349A (en) * | 2018-04-18 | 2018-09-14 | 武汉极意网络科技有限公司 | A kind of automated performance testing method and system based on Jmeter |
| CN109284229A (en) * | 2018-10-17 | 2019-01-29 | 武汉斗鱼网络科技有限公司 | A kind of dynamic adjusting method and relevant device based on QPS |
| CN109426593A (en) * | 2017-08-24 | 2019-03-05 | 北京京东尚科信息技术有限公司 | The method and apparatus of automatic evaluation system performance |
| CN110635961A (en) * | 2018-06-22 | 2019-12-31 | 北京京东尚科信息技术有限公司 | Pressure measurement method, device and system of server |
| CN110780990A (en) * | 2019-09-12 | 2020-02-11 | 中移（杭州）信息技术有限公司 | Performance detection method, performance detection device, server and storage medium |
| CN111563014A (en) * | 2019-02-13 | 2020-08-21 | 北京京东尚科信息技术有限公司 | Interface service performance test method, device, equipment and storage medium |
| WO2020238345A1 (en) * | 2019-05-31 | 2020-12-03 | 深圳前海微众银行股份有限公司 | Pressure test method, device, system, apparatus, and computer readable storage medium |
| CN112765019A (en) * | 2021-01-13 | 2021-05-07 | 北京鼎事兴教育咨询有限公司 | Pressure measurement method and device, storage medium and electronic equipment |
-
2021
- 2021-08-06 CN CN202110904238.7A patent/CN113704031B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130308457A1 (en) * | 2012-04-28 | 2013-11-21 | International Business Machines Corporation | System detection method and apparatus and flow control method and device |
| US9647919B1 (en) * | 2014-12-04 | 2017-05-09 | Amazon Technologies | Automated determination of maximum service throughput |
| US20170132058A1 (en) * | 2015-11-11 | 2017-05-11 | International Business Machines Corporation | System resource component utilization |
| US20170255505A1 (en) * | 2016-03-04 | 2017-09-07 | International Business Machines Corporation | Application abnormality detection |
| CN106533750A (en) * | 2016-10-28 | 2017-03-22 | 东北大学 | System and method for predicting non-steady application user concurrency in cloud environment |
| CN107329881A (en) * | 2017-06-02 | 2017-11-07 | 腾讯科技（深圳）有限公司 | Application system performance method of testing and device, computer equipment and storage medium |
| CN109426593A (en) * | 2017-08-24 | 2019-03-05 | 北京京东尚科信息技术有限公司 | The method and apparatus of automatic evaluation system performance |
| CN108540349A (en) * | 2018-04-18 | 2018-09-14 | 武汉极意网络科技有限公司 | A kind of automated performance testing method and system based on Jmeter |
| CN110635961A (en) * | 2018-06-22 | 2019-12-31 | 北京京东尚科信息技术有限公司 | Pressure measurement method, device and system of server |
| CN109284229A (en) * | 2018-10-17 | 2019-01-29 | 武汉斗鱼网络科技有限公司 | A kind of dynamic adjusting method and relevant device based on QPS |
| CN111563014A (en) * | 2019-02-13 | 2020-08-21 | 北京京东尚科信息技术有限公司 | Interface service performance test method, device, equipment and storage medium |
| WO2020238345A1 (en) * | 2019-05-31 | 2020-12-03 | 深圳前海微众银行股份有限公司 | Pressure test method, device, system, apparatus, and computer readable storage medium |
| CN110780990A (en) * | 2019-09-12 | 2020-02-11 | 中移（杭州）信息技术有限公司 | Performance detection method, performance detection device, server and storage medium |
| CN112765019A (en) * | 2021-01-13 | 2021-05-07 | 北京鼎事兴教育咨询有限公司 | Pressure measurement method and device, storage medium and electronic equipment |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114546852A (en) * | 2022-02-21 | 2022-05-27 | 北京百度网讯科技有限公司 | Performance test method and device, electronic equipment and storage medium |
| CN114546852B (en) * | 2022-02-21 | 2024-04-09 | 北京百度网讯科技有限公司 | Performance test method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113704031B (en) | 2023-10-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP2021532502A (en) | Neural network model training methods, equipment, computer equipment and storage media | |
| JP4659850B2 (en) | Network monitoring program, network monitoring method, and network monitoring apparatus | |
| CN110572297B (en) | Network performance evaluation method, server and storage medium | |
| WO2019223443A1 (en) | Method and apparatus for processing database configuration parameter, and computer device and storage medium | |
| CN112921589B (en) | Method and device for analyzing drying and cooling time | |
| CN110890998A (en) | Method and device for determining threshold | |
| CN109857528B (en) | Data migration speed adjusting method and device, storage medium and mobile terminal | |
| CA2650531A1 (en) | Method, program and apparatus for optimizing configuration parameter set of system | |
| CN113704031B (en) | System pressure testing method, device, medium and equipment | |
| WO2020093502A1 (en) | Nominal bandwidth adjusting method and device | |
| CN113868953B (en) | Multi-unit operation optimization method, device and system in industrial system and storage medium | |
| CN113342588B (en) | Method and device for carrying out pressure test on server based on dynamic adjustment load | |
| WO2020010629A1 (en) | Method and apparatus for adjusting process control prediction model, and process controller | |
| US9188968B2 (en) | Run-time characterization of on-demand analytical model accuracy | |
| CN110380982B (en) | Flow control method and related device | |
| CN110245019B (en) | Thread concurrency method and device for self-adaptive system resources | |
| US20190089795A1 (en) | Communication analysis device, communication analysis method, and program recording medium | |
| CN113204411A (en) | Data processing method, intermediate processing equipment and storage medium | |
| JP2008165412A (en) | Performance-computing device | |
| CN110727518B (en) | Data processing method and related equipment | |
| CN112731150A (en) | Voltage sag state estimation method and device, computer equipment and storage medium | |
| CN112766657A (en) | Single equipment quality evaluation method based on fault probability and equipment state | |
| KR20200068076A (en) | Method and apparatus for reinforcement learning based on state correction | |
| CN116908603B (en) | Reliability detection method and system based on connector | |
| CN113030558B (en) | Method, device and equipment for identifying data abnormity and readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |